{"id":77,"date":"2022-12-27T19:28:32","date_gmt":"2022-12-27T11:28:32","guid":{"rendered":"http:\/\/106.52.213.145:21080\/?p=77"},"modified":"2023-02-16T02:54:11","modified_gmt":"2023-02-15T18:54:11","slug":"ydbjgxygtxmbjcsfzs2","status":"publish","type":"post","link":"https:\/\/apifj.com\/index.php\/2022\/12\/27\/ydbjgxygtxmbjcsfzs2\/","title":{"rendered":"[\u9605\u8bfb\u7b14\u8bb0] \u5149\u5b66\u9065\u611f\u56fe\u50cf\u76ee\u6807\u68c0\u6d4b\u7b97\u6cd5\u7efc\u8ff0\uff08\u4e8c\uff09"},"content":{"rendered":"

\u5149\u5b66\u9065\u611f\u56fe\u50cf\u76ee\u6807\u68c0\u6d4b\u7b97\u6cd5\u7efc\u8ff0\uff08\u4e8c\uff09<\/h1>\n

\u539f\u6587pdf\u4e0b\u8f7d\uff1a\u4e0b\u8f7d\u94fe\u63a5<\/a><\/p>\n

2.3\u5206\u7c7b\u5668\u8bbe\u8ba1<\/h3>\n

\u6709\u4e3b\u6d41\u7684\u76ee\u6807\u5206\u7c7b\u8bc6\u522b\u4efb\u52a1\u5747\u91c7\u7528\u6709\u76d1\u7763\u7684\u673a\u5668\u5b66\u4e60\u65b9\u5f0f\uff0c\u9700\u8981\u8bbe\u8ba1\u5408\u9002\u7684\u5206\u7c7b\u5668\u3002<\/p>\n

\u5206\u7c7b\uff1a\u903b\u8f91\u56de\u5f52\u3001\u652f\u6301\u5411\u91cf\u673a (SVM) \u3001\u8d1d\u53f6\u65af\u5206\u7c7b\u5668<\/p>\n

2.3.1 \u903b\u8f91\u56de\u5f52<\/h4>\n

\u5b9a\u4e49\uff1a\u5c06\u63d0\u53d6\u7684\u7279\u5f81\u6620\u5c04\u5230\u7ebf\u6027\u53ef\u5206\u7684\u7a7a\u95f4, \u4e4b\u540e\u91c7\u7528\u7ebf\u6027\u5224\u522b\u5668\u5b8c\u6210\u5206 \u7c7b\u8fc7\u7a0b.<\/p>\n\n\n\n\n\n
\u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
[50]Corbane C, Najman L, Pecoul E, Demagistri L, Petit M. A complete processing chain for ship detection using optical satel- lite imagery. International Journal of Remote Sensing, 2010, 31<\/strong>(22): 5837\u22125854<\/td>\n\u63d0\u53d6\u5019\u9009\u533a\u57df\u5185\u7684 Radon \u53d8 \u6362\u3001\u5c0f\u6ce2\u53d8\u6362\u7b49\u591a\u4e2a\u89c6\u89c9\u7279\u5f81, \u5e76\u5c06\u7279\u5f81\u8fdb\u884c\u7ea7\u8054, \u5229\u7528\u903b\u8f91\u56de\u5f52\u5b8c\u6210\u76ee\u6807\u5206\u7c7b\u548c\u8bc6\u522b.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

2.3.2 SVM<\/h4>\n

\u5b9a\u4e49\uff1a\u652f\u6301\u5411\u91cf\u673a\u5c06\u5f85\u5206\u7c7b\u6837\u672c\u901a\u8fc7\u6838\u51fd\u6570\u6620\u5c04\u5230\u7ebf\u6027\u53ef\u5206\u7684\u9ad8\u7ef4\u7a7a\u95f4, \u5e76\u627e\u5230\u6700\u4f18\u7684\u5206\u7c7b\u8d85\u5e73\u9762\u4f7f\u5f97\u652f\u6301\u5411\u91cf\u5728\u7279\u5f81\u7a7a\u95f4\u4e0a\u7684\u95f4\u9694\u6700\u5927<\/p>\n\n\n\n\n\n\n\n
\u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
[40]GongC,HanJW,GuoL,QianXL,ZhouPC,YaoXW, et al. Object detection in remote sensing imagery using a dis- criminatively trained mixture model. ISPRS Journal of Photo- grammetry and Remote Sensing, 2013, 85<\/strong>: 32\u221243<\/td>\n\u8bbe\u8ba1\u4e86\u4e00\u4e2a\u5224\u522b\u5f0f\u7684\u53ef\u89c1\u90e8\u4ef6\u6a21\u578b, \u5229 \u7528\u9690\u652f\u6301\u5411\u91cf\u673a\u8bad\u7ec3\u6a21\u578b\u53c2\u6570, \u7f13\u89e3\u4e86\u9065\u611f\u76ee\u6807\u591a \u5c3a\u5ea6\u95ee\u9898\u548c\u65cb\u8f6c\u95ee\u9898<\/td>\n<\/tr>\n
[51]Zhu X F, Ma C W. The study of combined invariants optimiz- ation method on aircraft recognition. In: Proceedings of the 2011 Symposium on Photonics and Optoelectronics (SOPO). Wuhan, China: IEEE, 2011. 1\u22124<\/td>\n\u63d0\u53d6\u4e0d\u53d8\u77e9\u591a\u7ef4\u7279 \u5f81, \u5bf9\u591a\u4e2a\u77e9\u7279\u5f81\u8fdb\u884c\u7ec4\u5408\u4f18\u5316, \u5229\u7528 SVM \u5206\u7c7b\u5668 \u8fdb\u884c\u5206\u7c7b\u8bc6\u522b, \u6709\u6548\u514b\u670d\u4e86\u5355\u4e00\u7279\u5f81\u9c81\u68d2\u6027\u4e0d\u5f3a\u7684 \u7f3a\u70b9.<\/td>\n<\/tr>\n
[52]Wang D H, He X, Wei Z H, Yu H L. A method of aircraft im- age target recognition based on modified PCA features and SVM. In: Proceedings of the 9th International Conference on Electronic Measurement and Instruments. Beijing, China: IEEE, 2009. 4-177\u22124-181<\/td>\n\u5229\u7528 SVM \u5206\u7c7b\u5668\u5bf9\u63d0\u53d6\u5230\u7684\u7279\u5f81\u8fdb\u884c\u5206\u7c7b\u548c\u8bc6\u522b<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

2.3.3 \u8d1d\u53f6\u65af\u5206\u7c7b\u5668<\/h4>\n

\u5b9a\u4e49\uff1a\u91c7\u7528\u540e\u9a8c\u6982\u7387\u6765\u8fdb\u884c\u5224\u65ad, \u786e\u5b9a\u6982\u7387\u6700\u9ad8\u7684\u7c7b\u522b\u4e3a\u68c0\u6d4b\u7ed3\u679c<\/p>\n

3. \u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u76ee\u6807\u68c0\u6d4b<\/h2>\n

\u4e0e\u624b\u5de5\u8bbe\u8ba1\u7684\u533a\u522b\uff1a\u76f4\u63a5\u5c06\u5019\u9009\u533a\u57df\u63d0\u53d6\u3001\u7279\u5f81\u5b66\u4e60\u548c\u5206\u7c7b\u5668\u6574\u5408\u5728\u4e00\u8d77\uff0c\u5b9e\u73b0\u7aef\u5230\u7aef\u7684\u68c0\u6d4b\u3002<\/p>\n

3.1 \u5178\u578b\u76ee\u6807\u68c0\u6d4b\u6a21\u578b<\/h3>\n

\"\"
\n\u611f\u5174\u8da3\u533a\u57df\uff1a\u5355\u9636\u6bb5\u7684\u901f\u5ea6\u5feb\uff0c\u4f46\u662f\u7cbe\u5ea6\u6bd4\u8f83\u4f4e\u3002\u591a\u9636\u6bb5\u901f\u5ea6\u6162\uff0c\u4f46\u662f\u7cbe\u5ea6\u9ad8\u3002<\/p>\n

\u9884\u8bbe\u951a\u70b9\u6846\u662f\u4e3a\u521d\u59cb\u951a\u70b9\u6846\u540e\u9762\u518d\u8fdb\u4e00\u6b65\u5fae\u8c03\uff1a\u4f18\u52bf\u662f\u8f93\u51fa\u7684\u90fd\u662f\u5728\u951a\u70b9\u6846\u57fa\u7840\u4e0a\u7684\u76f8\u5bf9\u503c\u3002\u503c\u57df\u5c0f\uff0c\u5bb9\u6613\u6536\u655b\uff0c\u4f46\u662f\u9700\u8981\u5927\u91cf\u7684\u4eba\u5de5\u4ee5\u53ca\u5148\u9a8c\uff0c\u6240\u4ee5\u8fc7\u7a0b\u7e41\u7410\uff0c\u800c\u4e14\u5728\u4e00\u4e9b\u957f\u5bbd\u6bd4\u7f55\u89c1\u7684\u76ee\u6807\u4e0a\u4f1a\u6f0f\u68c0\u3002<\/p>\n

\u5173\u952e\u70b9\u68c0\u6d4b\u6700\u8fd1\u5f88\u6d41\u884c\uff1a\u57fa\u4e8e\u50cf\u7d20\u5c42\u9762\u8fdb\u884c\u5206\u7c7b\u548c\u56de\u5f52\uff0c\u4e0d\u9700\u8981\u8fdb\u884c\u8ba1\u7b97IoU\u6765\u6dd8\u6c70\u68c0\u6d4b\u6846\u3002<\/p>\n

\u666e\u901a\u7684\u76ee\u6807\u68c0\u6d4b\u6027\u80fd\u4e0d\u9519\uff0c\u7531\u4e8e\u9065\u611f\u56fe\u50cf\u68c0\u6d4b\u7684\u7279\u6b8a\u6027\uff0c\u65e0\u6cd5\u76f4\u63a5\u5e94\u7528\uff0c\u9700\u8981\u4e00\u4e9b\u6539\u8fdb\u3002<\/p>\n

3.2 \u9065\u611f\u76ee\u6807\u68c0\u6d4b\u6a21\u5757\u6539\u8fdb<\/h3>\n

\"\"<\/p>\n

3.2.1 \u9488\u5bf9\u8d85\u5927\u56fe\u50cf\u5c3a\u5bf8\u7684\u6539\u8fdb<\/h4>\n

\u9065\u611f\u56fe\u50cf\u5177\u6709\u8d85\u5927\u7684\u56fe\u50cf\u5c3a\u5bf8\uff0c\u76f4\u63a5\u8fdb\u884c\u76ee\u6807\u68c0\u6d4b\u9700\u8981\u8fc7\u5927\u7684\u5185\u5b58\u7a7a\u95f4, \u540c\u65f6\u8ba1\u7b97\u91cf\u8fc7\u5927, \u73b0\u6709\u786c\u4ef6\u8fd8\u4e0d\u8db3\u4ee5\u652f\u6301\u3002\u4f46\u662f\u53c8\u4e0d\u80fd\u76f4\u63a5\u7f29\u5c0f\uff0c\u4f1a\u5bfc\u81f4\u76ee\u6807\u5c0f\u65f6\u3002<\/p>\n

\u96be\u70b9\u5728\u4e8e\u5f88\u96be\u4fdd\u8bc1\u68c0\u6d4b\u8d28\u91cf\u7684\u540c\u65f6\u901f\u5ea6\u8fd8\u5feb\u3002<\/p>\n

\u6700\u5e38\u7528\u7684\u65b9\u6cd5\uff1a\u5206\u5757\u5207\u5272\uff0c\u4f46\u662f\u8fb9\u7f18\u5c31\u5f88\u5bb9\u6613\u88ab\u4e00\u5206\u4e3a\u4e8c\u3002<\/p>\n

\u603b\u7ed3\uff1a\u56fe\u50cf\u5206\u5757\u7ed3\u5408\u5feb\u901f\u8fc7\u6ee4\u7684\u65b9\u5f0f\u662f\u5f53\u524d\u4ece\u901f\u5ea6\u4e0a\u548c\u7cbe\u5ea6\u4e0a\u6700\u4f18\u7684\u5904\u7406\u65b9\u5f0f.<\/p>\n\n\n\n\n\n\n\n\n
\u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
[66]Wang C, Bai X, Wang S, Zhou J, Ren P. Multiscale visual at- tention networks for object detection in VHR remote sensing images. IEEE Geoscience and Remote Sensing Letters, 2019, 16<\/strong>(2): 310\u2212314<\/td>\n\u4ee5\u4e00\u5b9a\u7684\u91cd\u53e0\u7387\u5bf9\u539f\u56fe\u8fdb\u884c\u5207\u5272, \u4ece\u800c\u589e\u52a0\u4e86\u5206\u5757\u5c0f\u56fe\u8fb9\u7f18\u76ee\u6807\u5b8c\u6574\u6027 \u7684\u53ef\u80fd, \u4f46\u662f\u5374\u589e\u52a0\u4e86\u5b50\u56fe\u50cf\u7684\u6570\u91cf, \u4f7f\u5f97\u5927\u56fe\u7684 \u5904\u7406\u65f6\u95f4\u53d8\u5f97\u5197\u4f59, \u540c\u65f6\u4f9d\u7136\u65e0\u6cd5\u907f\u514d\u76ee\u6807\u68c0\u6d4b\u7ed3 \u679c\u4e00\u5206\u4e3a\u4e8c\u7684\u95ee\u9898<\/td>\n<\/tr>\n
[67]PangJM,LiC,ShiJP,XuZH,FengHJ.R2-CNN:Fast tiny object detection in large-scale remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57<\/strong>(8): 5512\u22125524<\/td>\nR^2-CNN:\u8f7b\u91cf\u7ea7\u4e3b\u5e72 Tiny-Net \u6765\u8fdb\u884c\u7279\u5f81\u63d0\u53d6, \u5e76\u91c7\u7528\u5148\u5224\u65ad\u3001\u540e\u5b9a\u4f4d\u7684\u65b9\u5f0f, \u5c06\u4e0d\u542b\u76ee\u6807\u7684\u5b50\u56fe\u50cf\u5757\u8fdb\u884c\u6ee4\u9664, \u4ece\u800c\u51cf\u5c0f\u540e\u7eed\u68c0\u6d4b\u8bc6\u522b\u8fc7\u7a0b\u7684\u8ba1\u7b97\u8d1f\u62c5, \u8be5\u65b9\u6cd5\u4fdd\u8bc1\u4e86\u68c0\u6d4b\u6548\u679c, \u540c\u65f6\u63d0\u9ad8\u4e86\u68c0\u6d4b\u6548\u7387, \u4f46\u662f\u4f9d\u7136\u4f1a\u5bf9\u91cd\u53e0\u533a\u57df\u8fdb\u884c\u591a\u6b21\u68c0\u6d4b\uff0c\u6709\u91cd\u590d\u8ba1\u7b97\u3002<\/td>\n<\/tr>\n
[68]Van Etten A. You only look twice: Rapid multi-scale object de- tection in satellite imagery. arXiv preprint arXiv: 1805.09512, 2018<\/td>\nYOLT\uff1a\u5bf9\u5207\u5272\u540e\u7684\u5b50\u56fe, \u91c7\u7528\u591a\u4e2a\u8f7b\u91cf\u7ea7\u6a21\u578b\u8fdb\u884c\u68c0\u6d4b, \u5e76\u5c06\u68c0\u6d4b\u7ed3\u679c\u8fdb\u884c\u878d\u5408, \u4fdd\u6301\u68c0\u6d4b\u7cbe\u5ea6\u7684\u540c\u65f6, \u4e00\u5b9a\u7a0b\u5ea6\u4e0a\u63d0\u5347 \u4e86\u68c0\u6d4b\u7684\u901f\u5ea6.<\/td>\n<\/tr>\n
[69]Zhang F, Du B, Zhang L P, Xu M Z. Weakly supervised learn- ing based on coupled convolutional neural networks for air- craft detection. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54<\/strong>(9): 5553\u22125563<\/td>\n\u8be5\u65b9\u6cd5\u5c06\u6574\u5f20\u539f\u56fe\u4f5c\u4e3a\u8f93\u5165=>\u50cf\u7d20\u7ea7\u5206\u7c7b=>\u9ad8\u7f6e\u4fe1\u63d0\u53d6\u540e\u9009\u53d6=>\u975e\u6700\u5927\u503c\u6291\u5236=>\u5355\u72ec\u68c0\u6d4b\u3002<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

3.2.2 \u9488\u5bf9\u76ee\u6807\u65b9\u5411\u591a\u6837\u5316\u7684\u6539\u8fdb<\/h4>\n

\u9065\u611f\u56fe\u50cf\u5747\u662f\u4fef\u89c6\u89c6\u89d2\u62cd\u6444\u5f97\u5230\u7684, \u65b9\u5411\u6027\u95ee\u9898\u7a81\u51fa\uff0c\u800c\u7ecf\u5178\u7684\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u4e0d\u5177\u5907\u65cb\u8f6c\u4e0d\u53d8\u6027\u3002<\/p>\n

\u6539\u8fdb\u601d\u8def\uff1a\u6570\u636e\u6269\u5145\u3001\u589e\u52a0\u65cb\u8f6c\u4e0d\u53d8\u5b50\u6a21\u5757<\/p>\n

\u6570\u636e\u6269\u5145\uff08\u6570\u636e\u589e\u5f3a\uff09\uff1a\u5bf9\u539f\u6709\u8bad\u7ec3\u6570\u636e, \u5206\u522b\u65cb\u8f6c\u591a\u4e2a\u4e0d\u540c\u7684\u89d2\u5ea6\u3002\u4e00\u5b9a\u7a0b\u5ea6\u63d0\u5347\u4e86\u6837\u672c\u7684\u591a\u6837\u6027\uff0c\u4f46\u662f\u4f5c\u7528\u6709\u9650\uff0c\u4e0d\u80fd\u4ece\u6839\u672c\u4e0a\u89e3\u51b3\u95ee\u9898\u3002<\/p>\n\n\n\n\n\n\n\n
\u8bba\u6587<\/th>\n<\/th>\n<\/tr>\n<\/thead>\n
[62]Fu Y M, Wu F G, Zhao J S. Context-aware and depthwise- based detection on orbit for remote sensing image. In: Proceed- ings of the 24th International Conference on Pattern Recogni- tion (ICPR). Beijing, China: IEEE, 2018. 1725\u22121730<\/td>\n<\/td>\n<\/tr>\n
[63]Li M J, Guo W W, Zhang Z H, Yu W X, Zhang T. Rotated re- gion based fully convolutional network for ship detection. In: Proceedings of the 2018 IEEE International Geoscience and Re- mote Sensing Symposium (IGARSS 2018). Valencia, Spain: IEEE, 2018. 673\u2212676<\/td>\n<\/td>\n<\/tr>\n
[64]Schilling H, Bulatov D, Niessner R, Middelmann W, Soergel U. Detection of vehicles in multisensor data via multibranch con- volutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11<\/strong>(11): 4299\u22124316<\/td>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\u5176\u4e2d\uff0c\u76f4\u63a5\u5c06\u6269\u5145\u591a\u4e2a\u89d2\u5ea6\u540e\u7684\u56fe\u50cf\u6570\u636e\u5408\u6210\u4e00\u4e2a\u66f4\u5927\u7684\u6570\u636e\u96c6\u8fdb\u884c\u8bad\u7ec3\u3001\u76f4\u63a5\u5728\u8bad\u7ec3\u8fc7\u7a0b\u4e2d\u5bf9\u5355\u5e45\u56fe\u50cf\u91c7\u7528\u968f\u673a\u65cb\u8f6c\u5904\u7406\u3002<\/p>\n\n\n\n\n\n\n\n
\u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
[25]Cheng G, Zhou P C, Han J W. Learning rotation-invariant convolutional neural networks for object detection in VHR op- tical remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54<\/strong>(12): 7405\u22127415<\/td>\nRICNN:\u4f18\u5316\u4e00\u4e2a\u65b0\u7684\u76ee\u6807\u51fd\u6570, \u901a\u8fc7\u5f15\u5165\u6b63\u5219\u5316\u7ea6\u675f, \u4f7f\u6837\u672c\u7684\u7279\u5f81\u8868\u793a\u5728\u65cb\u8f6c\u524d\u540e\u76f8\u4e92 \u63a5\u8fd1, \u5b9e\u73b0\u65cb\u8f6c\u4e0d\u53d8\u6027.<\/td>\n<\/tr>\n
[70]Cheng G, Han J W, Zhou P C, Xu D. Learning rotation-invari- ant and fisher discriminative convolutional neural networks for object detection. IEEE Transactions on Image Processing, 2019, 28<\/strong>(1): 265\u2212278<\/td>\n\u4f18\u5316\u4e00\u4e2a \u65b0\u7684\u76ee\u6807\u51fd\u6570\u663e\u5f0f\u5730\u5728 CNN \u7279\u5f81\u4e0a\u6dfb\u52a0\u4e86\u4e00\u4e2a\u65cb\u8f6c\u4e0d\u53d8\u6b63\u5219\u5316\u5668, \u5f3a\u5236\u65cb\u8f6c\u524d\u540e\u8bad\u7ec3\u6837\u672c\u7684\u7279\u5f81\u8868 \u793a\u7d27\u5bc6\u6620\u5c04, \u4ee5\u5b9e\u73b0\u65cb\u8f6c\u4e0d\u53d8\u6027<\/td>\n<\/tr>\n
[71]Wu X, Hong D F, Tian J J, Chanussot J, Li W, Tao R. OR- SIm detector: A novel object detection framework in optical re- mote sensing imagery using spatial-frequency channel features. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57<\/strong>(7): 5146\u22125158<\/td>\nORSIm:\u68c0\u6d4b\u5668\u91c7\u7528\u4e86\u4e00\u79cd\u65b0\u9896\u7684\u7a7a\u9891\u4fe1\u9053\u7279\u5f81 (SFCF), \u7efc\u5408\u8003\u8651\u4e86\u9891\u57df\u5185\u6784\u9020\u7684\u65cb\u8f6c\u4e0d\u53d8\u4fe1\u9053\u7279\u5f81\u548c\u539f\u59cb\u7684\u7a7a\u95f4\u4fe1\u9053\u7279\u5f81\u6765\u5e94\u5bf9\u65cb\u8f6c\u95ee\u9898<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

3.2.3 \u9488\u5bf9\u76ee\u6807\u5c3a\u5ea6\u8fc7\u5c0f\u7684\u6539\u8fdb<\/h4>\n

\u9065\u611f\u56fe\u50cf\u4e2d\u5c0f\u76ee\u6807\u7684\u6570\u91cf\u89c4\u6a21\u66f4\u5927\uff0c\u5c0f\u76ee\u6807\u7684\u50cf\u7d20\u5f88\u5c0f\uff08\u53ea\u6709\u51e0\u5341\u5230\u51e0\u767e\uff09\uff0c\u4f46\u662f\u5377\u8bb0\u5f97\u65f6\u5019\u4f1a\u4e0b\u91c7\u6837\uff0cfeature map \u4e0d\u65ad\u7f29\u5c0f\uff0c\u4ece\u800c\u5728\u6df1\u5c42map\u4e2d\u6d88\u5931\uff0c\u6240\u4ee5\u5c0f\u76ee\u6807\u68c0\u6d4b\u662f\u96be\u70b9\u3002<\/p>\n

\u89e3\u51b3\u65b9\u6cd5\uff1a\u5f15\u5165\u6d45\u5c42\u7279\u5f81\u3001\u6df1\u5c42\u7279\u5f81\u4e0a\u91c7\u6837<\/p>\n

1.\u9488\u5bf9\u6d45\u5c42\u7279\u5f81\u5f15\u5165<\/em><\/strong>\u7684\u6539\u8fdb<\/p>\n

\u5f15\u5165\u6d45\u5c42\u7279\u5f81\u7684\u65b9\u5f0f, \u5bf9\u4e8e\u5c0f\u76ee\u6807\u4f1a\u5f15\u5165\u8fc7\u591a\u7684\u80cc\u666f\u566a\u58f0<\/p>\n\n\n\n\n\n\n\n\n\n\n
\u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
[60]Yang X, Sun H, Sun X, Yan M L, Guo Z, Fu K. Position de- tection and direction prediction for arbitrary-oriented ships via multitask rotation region convolutional neural network. IEEE Access, 2018, 6<\/strong>: 50839\u221250849<\/td>\n\u589e\u52a0\u6d45\u5c42\u7279\u5f81\u91d1\u5b57\u5854\u7684\u6570\u91cf \u548c \u89c4\u6a21\u6765\u63d0\u5347\u5c0f\u76ee\u6807\u7684\u68c0\u6d4b\u7cbe\u5ea6, \u5e76\u91c7\u7528\u7a20\u5bc6\u8fde\u63a5\u7684\u7ed3\u6784\u589e\u5f3a\u5c0f\u76ee\u6807\u7684\u7279\u5f81\u8868\u8fbe\u80fd\u529b<\/td>\n<\/tr>\n
[68]Van Etten A. You only look twice: Rapid multi-scale object de- tection in satellite imagery. arXiv preprint arXiv: 1805.09512, 2018<\/td>\nYOLT: \u589e\u52a0\u4e0a\u91c7\u6837, \u5e76\u901a\u8fc7\u6052\u7b49\u6620\u5c04\u5c06\u4e2d\u95f4\u6d45\u5c42\u7279\u5f81\u4e0e\u8f93\u51fa\u7279\u5f81\u8fdb\u884c\u62fc\u63a5, \u540c\u65f6\u589e\u52a0\u9884\u6d4b\u7f51\u683c\u7684\u4e2a\u6570, \u4ece\u800c\u63d0\u9ad8\u5c0f\u76ee\u6807\u7684\u9002\u5e94\u6027, \u5e76\u878d\u5408\u591a\u4e2a\u5c3a\u5ea6\u6765\u5bfb\u627e\u66f4\u5c0f\u7684\u76ee\u6807<\/td>\n<\/tr>\n
[72]Chen S Q, Zhan R H, Zhang J. Geospatial object detection in remote sensing imagery based on multiscale single-shot detect- or with activated semantics. Remote Sensing, 2018, 10<\/strong>(6): Art- icle No. 820<\/td>\n\u5728\u6700\u6d45\u5c42\u7279\u5f81\u4e0a\u7ed3\u5408\u8bed\u4e49\u4fe1\u606f\u8fdb\u884c\u589e\u5f3a, \u5e76\u4e0e\u6df1\u5c42\u7279\u5f81\u8fdb\u884c \u878d\u5408, \u63d0\u9ad8\u5c0f\u76ee\u6807\u68c0\u6d4b\u7387<\/td>\n<\/tr>\n
[73]Wang P J, Sun X, Diao W H, Fu K. FMSSD: Feature-merged single-shot detection for multiscale objects in large-scale re- mote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58<\/strong>(5): 3377\u22123390<\/td>\n\u5728\u7ed3\u5408\u6d45\u5c42\u4fe1\u606f\u540e, \u540c\u65f6\u6539\u8fdb\u635f\u5931\u51fd\u6570\u6765\u589e\u52a0\u5c0f\u76ee\u6807\u7684\u8bad\u7ec3\u6743\u91cd.<\/td>\n<\/tr>\n
[63]Li M J, Guo W W, Zhang Z H, Yu W X, Zhang T. Rotated re- gion based fully convolutional network for ship detection. In: Proceedings of the 2018 IEEE International Geoscience and Re- mote Sensing Symposium (IGARSS 2018). Valencia, Spain: IEEE, 2018. 673\u2212676<\/td>\n\u5229\u7528\u53cd\u5377\u79ef\u5c42\u8fdb\u884c\u6d45\u5c42\u7279\u5f81\u548c\u6df1\u5c42\u7279\u5f81\u7684\u878d\u5408, \u5728\u5df2\u6709\u68c0\u6d4b\u7cbe\u5ea6\u4e0b, \u8fdb\u4e00\u6b65\u589e\u5f3a\u5c0f\u76ee\u6807\u7684\u68c0\u6d4b\u80fd\u529b\u3002<\/td>\n<\/tr>\n
[62]Fu Y M, Wu F G, Zhao J S. Context-aware and depthwise- based detection on orbit for remote sensing image. In: Proceed- ings of the 24th International Conference on Pattern Recogni- tion (ICPR). Beijing, China: IEEE, 2018. 1725\u22121730<\/td>\n\u5728\u8fdb\u884c\u6d45\u5c42\u7279\u5f81\u548c\u6df1\u5c42\u7279\u5f81\u878d\u5408\u65f6, \u91c7\u7528\u4e00\u4e2a\u5e73\u8861\u56e0\u5b50\u6765\u5e73\u8861\u7279\u5f81\u878d\u5408\u7684\u6743\u91cd, \u4f46\u662f\u5bf9\u4e8e\u56e0\u5b50\u7684 \u53d6\u503c\u53ea\u80fd\u51ed\u501f\u68c0\u6d4b\u4efb\u52a1\u7684\u5148\u9a8c, \u9762\u5bf9\u4e0d\u540c\u4efb\u52a1\u9c81\u68d2\u6027\u8f83\u5dee.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

2.\u9488\u5bf9\u6df1\u5c42\u7279\u5f81\u4e0a\u91c7\u6837<\/p>\n

\u4e3b\u8981\u4ee5\u53cd\u5377\u79ef\u7684\u5f62\u5f0f\u5b9e\u73b0<\/p>\n\n\n\n\n\n\n\n\n\n
\u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
[74]Zhang W, Wang S H, Thachan S, Chen J Z, Qian Y T. De- conv R-CNN for small object detection on remote sensing im- ages. In: Proceedings of the 2018 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2018). Valencia, Spain: IEEE, 2018. 2483\u22122486<\/td>\n\u5728\u4e24\u9636\u6bb5 Faster RCNN \u57fa\u7840\u4e0a, \u5bf9\u524d \u4e00\u9636\u6bb5\u63d0\u53d6\u7684\u6bcf\u4e2a\u5019\u9009\u533a\u57df\u901a\u8fc7\u53cd\u5377\u79ef\u8fdb\u884c\u4e0a\u91c7\u6837, \u653e\u5927\u7279\u5f81\u56fe\u5c3a\u5bf8, \u6539\u5584\u5c0f\u76ee\u6807\u68c0\u6d4b\u6548\u679c<\/td>\n<\/tr>\n
[64]Schilling H, Bulatov D, Niessner R, Middelmann W, Soergel U. Detection of vehicles in multisensor data via multibranch con- volutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11<\/strong>(11): 4299\u22124316<\/td>\n1.\u5229\u7528\u53cd\u5377\u79ef\u5c42\u6269\u5927\u6df1\u5c42\u7279\u5f81\u7684\u5c3a\u5ea6, \u878d\u5408\u6d45\u5c42 \u7279\u5f81\u5171\u540c\u5b8c\u6210\u68c0\u6d4b\u8fc7\u7a0b\u30022.\u76ee\u7684\u662f\u4e3a\u4e86\u89e3\u51b3 \u56e0\u4e3a\u964d\u91c7\u6837\u800c \u201c\u4e22\u5931\u201d\u4e86\u7684\u4fe1\u606f\u7279\u5f81\u7684\u95ee\u9898\u3002\u65b9\u5f0f\u662f\u540c\u65f6\u7ed3\u5408\u5f15\u5165\u6d45\u5c42\u7279\u5f81\u4ee5\u53ca\u6df1\u5c42\u7279\u5f81\u4e0a\u91c7\u6837\u8fc7\u7a0b, \u5b9e\u73b0\u4f18\u52bf\u4e92\u8865, \u4f46\u662f\u968f\u7740\u7279\u5f81\u56fe\u5c3a\u5ea6\u7684\u589e\u52a0, \u8ba1\u7b97\u590d\u6742\u5ea6\u4e5f\u6709\u4e86\u4e00\u5b9a\u7a0b\u5ea6\u7684\u589e\u52a0\u3002<\/td>\n<\/tr>\n
[75]Liu W C, Ma L, Wang J, Chen H. Detection of multiclass ob- jects in optical remote sensing images. IEEE Geoscience and Remote Sensing Letters, 2019, 16<\/strong>(5): 791\u2212795<\/td>\n\u91c7\u7528\u81a8\u80c0\u5377\u79ef\u64cd\u4f5c\u6765\u4ee3\u66ff\u5377\u79ef, \u5728\u76f8\u540c\u611f\u53d7\u91ce\u7684\u524d\u63d0\u4e0b, \u51cf\u5c11\u4e86\u53c2\u6570, \u7136\u800c\u81a8\u80c0\u5377\u79ef\u4f1a\u9020\u6210\u5c40\u90e8\u4fe1\u606f\u7684\u4e22\u5931<\/td>\n<\/tr>\n
[76]YingX,WangQ,LiXW,YuM,JiangH,GaoJ,etal.Multi- attention object detection model in remote sensing images based on multi-scale. IEEE Access, 2019, 7<\/strong>: 94508\u221294519<\/td>\n\u4f7f\u7528\u50cf\u7d20\u6ce8\u610f\u529b\u673a\u5236\u6765\u8fdb\u884c\u5c40\u90e8\u4fe1\u606f\u7684\u878d\u5408, \u5f25\u8865\u4e86\u81a8\u80c0\u5377\u79ef\u7684\u4e0d\u8db3, \u6539\u5584\u4e86\u5c0f\u76ee\u6807\u68c0\u6d4b\u95ee\u9898<\/td>\n<\/tr>\n
<\/td>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

3.2.4 \u9488\u5bf9\u76ee\u6807\u5bc6\u96c6\u5206\u5e03\u7684\u6539\u8fdb<\/h4>\n

\u9065\u611f\u56fe\u50cf\u5728\u4e00\u4e9b\u7279\u5b9a\u573a\u5408\u4e0b\u76ee\u6807\u5206\u5e03\u8fc7\u4e8e\u5bc6\u96c6\uff0c\u5982\u505c\u8f66\u573a\u3001\u6e2f\u53e3\u7b49\u3002\u4f46\u662f\u5728\u9065\u611f\u4e2d\u6bd4\u8f83\u5bb9\u6613\u7684\u662f\u4e00\u822c\u60c5\u51b5\u4e0b\u4e0d\u4f1a\u6709\u540c\u7c7b\u76ee\u6807\u76f8\u4e92\u906e\u6321\u7684\u60c5\u51b5\u3002<\/p>\n

\u96be\u70b9\uff1a\u9065\u611f\u56fe\u50cf\u4e2d\u76ee\u6807\u5c3a\u5ea6\u8fc7\u5c0f\u3002\u5bb9\u6613\u51fa\u73b0\u8fb9\u754c\u6a21\u7cca\u3001\u9ad8\u5bc6\u5ea6\u76ee\u6807\u7279\u5f81\u805a\u96c6\u3002<\/p>\n

\u73b0\u6709\u7814\u7a76\u5927\u591a\u901a\u8fc7 \u7279\u5f81\u589e\u5f3a<\/em><\/strong> \u65b9\u5f0f\u6765\u63d0\u5347\u5355\u4e2a\u76ee\u6807\u7684\u533a\u5206\u5ea6.<\/p>\n\n\n\n\n\n\n\n\n\n\n
\u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
[77]Long H, Chung Y, Liu Z B, Bu S H. Object detection in aerial images using feature fusion deep networks. IEEE Access, 2019, 7<\/strong>: 30980\u221230990<\/td>\n\u5c06\u591a\u79cd\u4f20\u7edf\u65b9\u6cd5\u548c\u6df1\u5ea6\u5b66\u4e60\u65b9\u6cd5\u8fdb\u884c\u7ec4\u5408, \u53ef\u4ee5\u6709\u6548\u5904\u7406\u9ad8\u5bc6\u5ea6, \u5c0f\u5c3a\u5bf8\u7684\u7269\u4f53\u5728 \u6742\u80cc\u666f\u4e0b\u7684\u68c0\u6d4b, \u4f46\u662f\u6d41\u7a0b\u6781\u5176\u590d\u6742\u3002<\/td>\n<\/tr>\n
[78]Cheng L, Liu X, Li L L, Jiao L C, Tang X. Deep adaptive pro- posal network for object detection in optical remote sensing im- ages. arXiv preprint arXiv: 1807.07327, 2018<\/td>\nDAPNet\uff1a\u901a\u8fc7\u5224\u65ad\u56fe\u50cf\u4e2d\u76ee\u6807\u7684\u5206\u5e03\u5bc6\u5ea6, \u6765\u8fdb\u884c\u81ea\u9002\u5e94\u7684\u533a\u57df\u751f\u6210\u7b56\u7565<\/td>\n<\/tr>\n
[79]Long Y, Gong Y P, Xiao Z F, Liu Q. Accurate object localiza- tion in remote sensing images based on convolutional neural networks. IEEE Transactions on Geoscience and Remote Sens- ing, 2017, 55<\/strong>(5): 2486\u22122498<\/td>\n\u63d0\u51fa\u4e86\u4e00\u79cd\u57fa\u4e8e\u65e0\u76d1\u7763 \u5206\u6570\u7684\u8fb9\u754c\u76d2\u56de\u5f52 (USB-BBR) \u7b97\u6cd5\uff0c\u5e76\u7ed3\u5408\u975e\u6700\u5927\u6291\u5236\u7b97\u6cd5\u5bf9\u68c0\u6d4b\u5230\u7684\u76ee\u6807\u533a\u57df\u7684\u8fb9\u754c\u76d2\u8fdb\u884c\u4f18 \u5316, \u63d0\u9ad8\u5bc6\u96c6\u5206\u5e03\u76ee\u6807\u7684\u5b9a\u4f4d\u7cbe\u5ea6.<\/td>\n<\/tr>\n
[80]YangX,YangJR,YanJC,ZhangY,ZhangTF,GuoZ,etal. SCRDet: Towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the 2019 IEEE\/CVF In- ternational Conference on Computer Vision (ICCV). Seoul, Korea: IEEE, 2019. 8232\u22128241<\/td>\nSCRDet\uff1a\u589e\u52a0\u4e86\u50cf\u7d20\u6ce8\u610f\u529b\u673a\u5236\u548c\u901a\u9053\u6ce8\u610f\u529b\u673a\u5236\u6765\u540c\u65f6\u5b9e\u73b0\u5c0f\u76ee\u6807\u548c\u5bc6\u96c6\u76ee\u6807\u7684\u7279\u5f81\u589e\u5f3a.<\/td>\n<\/tr>\n
[81]Yang X, Liu Q Q, Yan J C, Li A. R3Det: Refined single-stage detector with feature refinement for rotating object. In: Pro- ceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021.<\/td>\nR3Det\uff1a\u901a\u8fc7\u589e\u52a0\u4e00 \u4e2a\u7279\u5f81\u56fe\u5fae\u8c03\u6a21\u5757, \u5c3d\u91cf\u4fdd\u8bc1\u76ee\u6807\u7684\u7279\u5f81\u548c\u76ee\u6807\u7684 \u4e2d\u5fc3\u5bf9\u9f50, \u63d0\u9ad8\u5bc6\u96c6\u76ee\u6807\u7684\u5b9a\u4f4d\u7cbe\u5ea6<\/td>\n<\/tr>\n
[82]YangX,YanJC,YangXK,TangJ,LiaoWL,HeT. SCRDet++: Detecting small, cluttered and rotated objects via instance-level feature denoising and rotation loss smoothing. arXiv preprint arXiv: 2004.13316, 2020<\/td>\nSCRDet++\uff1a\u501f\u52a9\u8bed\u4e49\u5206\u5272\u7f51\u7edc\u7684\u4e2d\u95f4\u7279\u5f81\u6765\u6307\u5bfc\u68c0\u6d4b\u8bc6\u522b\u7684\u7279\u5f81\u63d0\u53d6\u8fc7\u7a0b, \u95f4\u63a5\u4f7f\u7528\u6ce8\u610f\u529b\u673a\u5236\u6765\u8fdb\u884c\u5bc6\u96c6\u76ee\u6807\u7684\u7279\u5f81\u589e\u5f3a, \u4ece\u800c\u63d0\u5347\u5bc6\u96c6\u76ee\u6807\u7684\u8fb9\u754c\u533a\u5206\u7a0b\u5ea6.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\u8fd9\u4e9b\u65b9\u6cd5\u5728\u727a\u7272\u7b97\u6cd5\u6548\u7387\u7684\u57fa\u7840\u4e0a, \u63d0\u9ad8\u4e86\u5bf9\u4e8e\u5bc6\u96c6\u76ee\u6807\u68c0\u6d4b\u548c\u5b9a\u4f4d\u7684\u7cbe\u5ea6.<\/p>\n

3.2.5 \u9488\u5bf9\u76ee\u6807\u5f62\u72b6\u5dee\u5f02\u5927\u7684\u6539\u8fdb<\/h4>\n

\u96be\u70b9\uff1a\u4e0d\u540c\u7c7b\u4e4b\u95f4\u7684\u76ee\u6807\u5f62\u72b6\u5dee\u5f02\u8fc7\u5927\uff0c\u5bb9\u6613\u56e0\u4e3a\u951a\u70b9\u6846\u9884\u8bbe\u4e0d\u5408\u9002, \u9020\u6210\u6f0f\u5339\u914d\u95ee\u9898\u3002<\/p>\n

\u89e3\u51b3\u65b9\u6cd5\uff1a\u68c0\u6d4b\u9636\u6bb5\u63d0\u9ad8\u951a\u70b9\u6846\u7684\u79cd\u7c7b\u548c\u6570\u91cf\u3001\u91c7\u7528\u53ef\u53d8\u5f62\u5377\u79ef\u7f51\u7edc\u3001\u6ce8\u610f\u529b\u6a21\u5757\u3001\u57fa\u4e8e\u5173\u952e\u70b9\u7684\u68c0\u6d4b\u6a21\u578b<\/p>\n

    \n
  1. \n

    \u68c0\u6d4b\u9636\u6bb5\u63d0\u9ad8\u951a\u70b9\u6846\u7684\u79cd\u7c7b\u548c\u6570\u91cf<\/p>\n

    \u589e\u52a0\u4e0d\u540c\u7684\u5c3a\u5ea6\u3001\u4e0d\u540c\u7684\u957f\u5bbd\u6bd4\u3001\u751a\u81f3\u589e\u52a0\u4e0d\u540c\u89d2\u5ea6\u7684\u951a\u70b9\u6846\u6765\u7c97\u66b4\u5730\u63d0\u5347\u7b97\u6cd5\u5bf9\u76ee\u6807\u5f62\u72b6\u7684\u6cdb\u5316 \u80fd\u529b\u3002\u5c3d\u7ba1\u53d6\u5f97\u4e86\u660e\u663e\u7684\u6548\u679c, \u4f46\u662f\u5bf9\u4e8e\u5f62\u72b6\u8fc7\u4e8e\u72ed\u957f\u7684\u76ee\u6807, \u5f88\u5c0f\u7684\u89d2\u5ea6\u504f\u5dee\u5c31\u4f1a\u5bfc\u81f4\u91cd\u5408\u5ea6\u7684\u5927\u5e45\u5ea6\u4e0b\u964d, \u6781\u5bb9\u6613\u5bfc\u81f4\u6f0f\u5339\u914d, \u4f9d\u7136\u96be\u4ee5\u4ece\u6839\u672c\u4e0a\u89e3\u51b3\u5f62\u72b6\u5dee\u5f02\u7684\u95ee\u9898\u3002<\/p>\n

    \u4ee5\u727a\u7272\u6548\u7387\u4e3a\u4ee3\u4ef7\u6362 \u53d6\u5bf9\u4e0d\u540c\u76ee\u6807\u5f62\u72b6\u7684\u9002\u5e94\u6027<\/p>\n\n\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n<\/th>\n<\/tr>\n<\/thead>\n
    [77]Long H, Chung Y, Liu Z B, Bu S H. Object detection in aerial images using feature fusion deep networks. IEEE Access, 2019, 7<\/strong>: 30980\u221230990<\/td>\n<\/td>\n<\/tr>\n
    [81]Yang X, Liu Q Q, Yan J C, Li A. R3Det: Refined single-stage detector with feature refinement for rotating object. In: Pro- ceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021.<\/td>\n<\/td>\n<\/tr>\n
    [83]Yang X, Sun H, Fu K, Yang J R, Su X, Yan M L, et al. Auto- matic ship detection in remote sensing images from Google earth of complex scenes based on multiscale rotation dense fea- ture pyramid networks. Remote Sensing, 2018, 10<\/strong>(1): Article No. 132<\/td>\n<\/td>\n<\/tr>\n
    [84]Azimi S M, Vig E, Bahmanyar R, K\u00f6rner M, Reinartz P. To- wards multi-class object detection in unconstrained remote sensing imagery. In: Proceedings of the 14th Asian Conference on Computer Vision (ACCV 2018). Perth, Australia: Springer, 2018. 150\u2212165<\/td>\n<\/td>\n<\/tr>\n
    [85]Wang X B, Jiang Y Y, Luo Z B, Liu C L, Choi H, Kim S. Ar- bitrary shape scene text detection with adaptive text region representation. In: Proceedings of the 2019 IEEE\/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 6449\u22126458<\/td>\n<\/td>\n<\/tr>\n
    [86]Ding J, Xue N, Long Y, Xia G S, Lu Q K. Learning RoI trans- former for oriented object detection in aerial images. In: Pro- ceedings of the 2019 IEEE\/CVF Conference on Computer Vis- ion and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 2844\u22122853<\/td>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/li>\n
  2. \n

    \u91c7\u7528\u53ef\u53d8\u5f62\u5377\u79ef\u7f51\u7edc(Deformable convolution)<\/p>\n<\/li>\n<\/ol>\n

    \u76ee\u7684\uff1a\u81ea\u52a8\u9002\u914d\u4e0d\u540c\u7684\u76ee\u6807\u5f62\u72b6<\/p>\n

    \u7f3a\u70b9\uff1a\u589e\u52a0\u4e86\u8bad\u7ec3\u96be\u5ea6, \u56e0\u6b64\u76ee\u524d\u5e76\u6ca1\u6709\u660e\u663e\u7684\u6548\u679c\u63d0\u5347<\/p>\n

    3.\u6ce8\u610f\u529b\u6a21\u5757<\/p>\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n<\/tr>\n<\/thead>\n
    [89]LiCZ,XuCY,CuiZ,WangD,ZhangT,YangJ.Feature- attentioned object detection in remote sensing imagery. In: Proceedings of the 2019 IEEE International Conference on Im- age Processing (ICIP). Taipei, China: IEEE, 2019. 3886\u22123890<\/td>\n<\/tr>\n
    [90]QiuHQ,LiHL,WuQB,MengFM,NganKN,ShiHC. A2RMNet: Adaptively aspect ratio multi-scale network for ob- ject detection in remote sensing images. Remote Sensing, 2019, 11<\/strong>(13): Article No. 1594<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    4.\u57fa\u4e8e\u5173\u952e\u70b9\u7684\u68c0\u6d4b\u65b9\u5f0f<\/p>\n

    \u5174\u8d77\u7684\u6709\u6f5c\u529b\u7684\u89e3\u51b3\u65b9\u5f0f<\/em><\/strong> \uff1a\u76f4\u63a5\u7701\u53bb\u4e86\u951a\u70b9\u6846\u4e0e\u76ee\u6807\u5339\u914d\u7684\u8fc7\u7a0b, \u800c\u662f\u57fa\u4e8e\u50cf\u7d20\u76f4\u63a5\u5bf9\u5f62\u72b6\u8fdb\u884c\u9884\u6d4b, \u4ece\u800c\u89e3\u51b3\u4e86\u5f62\u72b6\u5dee\u5f02\u5927\u7684\u95ee\u9898\u3002<\/p>\n

    \u4ece\u7cbe\u5ea6\u6765\u770b, \u57fa\u672c\u548c\u57fa\u4e8e\u951a\u70b9\u6846\u68c0\u6d4b\u5668\u7684\u7cbe\u5ea6\u6301\u5e73, \u8fd8\u6709\u8f83\u5927\u7684\u6f5c\u5728\u4f18\u5316\u7a7a\u95f4\u3002<\/p>\n\n\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n<\/tr>\n<\/thead>\n
    [91]Lin Y T, Feng P M, Guan J, Wang W W, Chambers J. IENet: Interacting embranchment one stage anchor free detector for orientation aerial object detection. arXiv preprint arXiv: 1912.00969, 2019<\/td>\n<\/tr>\n
    [92]ZhouL,WeiHR,LiH,ZhangY,SunX,ZhaoWZ.Objects detection for remote sensing images based on polar coordinates. arXiv preprint arXiv: 2001.02988, 2020<\/td>\n<\/tr>\n
    [93]Wei H R, Zhang Y, Chang Z H, Li H, Wang H Q, Sun X. Ori- ented objects as pairs of middle lines. ISPRS Journal of Photo- grammetry and Remote Sensing, 2020, 169<\/strong>: 268\u2212279<\/td>\n<\/tr>\n
    [94]Zhu Y X, Du J, Wu X Q. Adaptive period embedding for rep- resenting oriented objects in aerial images. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58<\/strong>(10): 7247\u22127257<\/td>\n<\/tr>\n
    [95]Zhu Y X, Du J, Wu X Q. Adaptive period embedding for rep- resenting oriented objects in aerial images. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58<\/strong>(10): 7247\u22127257XiaoZF,QianLJ,ShaoWP,TianXW,WangK.Axis learning for orientated objects detection in aerial images. Re- mote Sensing, 2020, 12<\/strong>(6): Article No. 908<\/td>\n<\/tr>\n
    [96]FengPM,LinYT,GuanJJ,HeGJ,ShiHF,ChambersJ. TOSO: Student’s-T distribution aided one-stage orientation target detection in remote sensing images. In: Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020). Barcelona, Spain: IEEE, 2020. 4057\u22124061<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
    [97]PanXJ,RenYQ,ShengKK,DongWM,YuanHL,GuoX W, et al. Dynamic refinement network for oriented and densely packed object detection. In: Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Re- cognition (CVPR). Seattle, USA: IEEE, 2020. 11207\u221211216<\/td>\n\u5728\u57fa\u4e8e\u5173\u952e\u70b9\u68c0\u6d4b\u7684\u57fa\u7840\u4e0a, \u589e\u52a0\u4e86\u7279\u5f81\u9009\u62e9 \u6a21\u5757\u548c\u52a8\u6001\u589e\u5f3a\u68c0\u6d4b\u5934, \u4f7f\u5f97\u68c0\u6d4b\u80fd\u591f\u8fdb\u4e00\u6b65\u5bf9\u76ee\u6807\u5f62\u72b6\u8fdb\u884c\u81ea\u9002\u5e94\u8c03\u6574, \u4f46\u662f\u7cbe\u5ea6\u7684\u63d0\u5347\u4f9d\u7136\u5f88\u5c0f, \u4e0d\u80fd\u4ece\u6839\u672c\u4e0a\u89e3\u51b3\u5f62\u72b6\u5dee\u5f02\u5e26\u6765\u7684\u5f71\u54cd.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    3.2.6 \u9488\u5bf9\u76ee\u6807\u5c3a\u5ea6\u53d8\u5316\u5927\u7684\u6539\u8fdb<\/h4>\n

    \u9065\u611f\u56fe\u50cf\u76ee\u6807\u5c3a\u5bf8\u53d8\u5316\u8303\u56f4\u66f4\u5927<\/p>\n

    \u89e3\u51b3\u65b9\u6cd5\uff1a\u5f15\u5165\u591a\u5c3a\u5ea6\u4fe1\u606f<\/p>\n

    \u591a\u5c3a\u5ea6\u4fe1\u606f\u7684\u5f15\u5165\u6709\u6548\u89e3\u51b3\u4e86\u4e0d\u540c\u5c3a\u5ea6\u76ee\u6807\u7684 \u6cdb\u5316\u80fd\u529b, \u4f46\u662f\u5bf9\u4e8e\u6781\u7aef\u5c3a\u5ea6\u7684\u76ee\u6807<\/p>\n

    \u73b0\u6709\u5927\u591a\u6570\u7b97\u6cd5\u5728\u8bad\u7ec3\u65b9\u5f0f\u4e0a, \u91c7\u7528\u56fe\u50cf\u91d1\u5b57\u5854\u8fdb\u884c\u591a\u5c3a\u5ea6\u8bad\u7ec3\u548c\u591a\u5c3a\u5ea6\u6d4b\u8bd5, \u8fdb\u4e00\u6b65\u964d\u4f4e\u6f0f\u68c0\u7387, \u63d0\u9ad8\u68c0\u6d4b\u7cbe\u5ea6, \u4f46\u662f\u589e\u52a0\u4e86\u5927\u91cf\u7684\u8ba1\u7b97\u5f00\u9500\u3002<\/p>\n\n\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
    [98]Guo W, Yang W, Zhang H J, Hua G. Geospatial object detec- tion in high resolution satellite images based on multi-scale convolutional neural network. Remote Sensing, 2018, 10<\/strong>(1): Article No. 131<\/td>\n\u76f4\u63a5\u91c7\u7528\u591a\u5c3a\u5ea6\u7684\u5019\u9009\u533a\u57df\u7f51\u7edc\u548c\u591a\u5c3a\u5ea6\u7684\u68c0\u6d4b\u5668\u6765\u68c0\u6d4b\u4e0d\u540c\u5c3a\u5ea6\u7684\u76ee\u6807.<\/td>\n<\/tr>\n
    [99]ZhangXD,ZhuK,ChenGZ,TanXL,ZhangLF,DaiF, et al. Geospatial object detection on high resolution remote sensing imagery based on double multi-scale feature pyramid network. Remote Sensing, 2019, 11<\/strong>(7): Article No. 755<\/td>\n\u76f4\u63a5\u91c7\u7528\u591a\u5c3a\u5ea6\u7684\u5019\u9009\u533a\u57df\u7f51\u7edc\u548c\u591a\u5c3a\u5ea6\u7684\u68c0\u6d4b\u5668\u6765\u68c0\u6d4b\u4e0d\u540c\u5c3a\u5ea6\u7684\u76ee\u6807.<\/td>\n<\/tr>\n
    [69]Zhang F, Du B, Zhang L P, Xu M Z. Weakly supervised learn- ing based on coupled convolutional neural networks for air- craft detection. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54<\/strong>(9): 5553\u22125563<\/td>\n\u5c06\u7b2c\u4e00\u9636\u6bb5\u63d0\u53d6\u7684\u5019\u9009\u533a\u57df\u8c03\u6574\u4e3a\u4e09\u4e2a\u4e0d\u540c\u5c3a\u5bf8\u56fe, \u5e76\u5206\u522b\u4f7f\u7528\u4e09\u4e2a\u7f51\u7edc\u8fdb\u884c\u5e76\u884c\u9884\u6d4b, \u6700\u7ec8\u901a\u8fc7\u6295\u7968\u673a\u5236\u786e\u5b9a\u7c7b\u522b, \u589e\u5f3a\u4e86\u4e0d\u540c\u5c3a\u5ea6\u7684\u9002\u5e94\u80fd\u529b<\/td>\n<\/tr>\n
    [100]Zhang S, He G H, Chen H B, Jing N F, Wang Q. Scale adapt- ive proposal network for object detection in remote sensing im- ages. IEEE Geoscience and Remote Sensing Letters, 2019, 16<\/strong>(6): 864\u2212868<\/td>\n\u5728\u5df2\u6709 Faster R-CNN \u57fa\u7840\u4e0a, \u5728\u4e0d\u540c\u7684\u7279\u5f81\u56fe\u4e0a\u5e76\u884c\u5f15\u5165\u4e0d\u540c\u7684\u5019\u9009\u533a\u57df\u63d0\u53d6\u7f51\u7edc, \u6765\u72ec\u7acb\u5bf9\u4e0d\u540c\u5c3a\u5ea6\u76ee\u6807\u8fdb\u884c\u68c0\u6d4b<\/td>\n<\/tr>\n
    [66]Wang C, Bai X, Wang S, Zhou J, Ren P. Multiscale visual at- tention networks for object detection in VHR remote sensing images. IEEE Geoscience and Remote Sensing Letters, 2019, 16<\/strong>(2): 310\u2212314<\/td>\n\u4f7f\u7528\u6b8b\u5dee\u8fde\u63a5\u7684\u81ea\u7f16\u7801\u5668\u591a\u5c3a\u5ea6\u7ed3\u6784\u6765\u9002\u5e94\u4e0d\u540c\u5c3a\u5ea6\u7684\u53d8\u5316<\/td>\n<\/tr>\n
    [101]Hou J Y, Ma H B, Wang S J. Parallel cascade R-CNN for ob- ject detection in remote sensing imagery. Journal of Physics: Conference Series, 2020, 1544<\/strong>: Article No. 012124<\/td>\n\u91c7\u7528\u591a\u4e2a\u5e76\u884c\u7684 ROI Pooling \u6a21\u5757\u5c06\u7279\u5f81\u6620\u5c04\u5230\u4e0d\u540c\u7684\u5c3a\u5ea6, \u5e76\u91c7\u7528\u591a \u9636\u6bb5\u7ea7\u8054\u7684\u65b9\u5f0f\u8fdb\u884c\u68c0\u6d4b.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    \u591a\u5c3a\u5ea6\u4fe1\u606f\u7279\u5f81\u878d\u5408<\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
    [102]Lin T Y, Doll\u00e1r P, Girshick R, He K M, Hariharan B, Be- longie S. Feature pyramid networks for object detection. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 2117\u22122125<\/td>\n\u901a\u8fc7\u878d\u5408\u5e95\u5c42\u89c6\u89c9\u7279\u5f81\u548c\u9ad8\u5c42\u8bed\u4e49\u4fe1\u606f, \u5e76\u5728\u4e0d\u540c\u5c3a\u5ea6\u7279\u5f81\u4e0a\u5206\u522b \u8fdb\u884c\u9884\u6d4b, \u5728\u5e38\u89c4\u56fe\u50cf\u4e2d\u83b7\u5f97\u4e86\u5e7f\u6cdb\u7684\u5e94\u7528<\/td>\n<\/tr>\n
    [60]Yang X, Sun H, Sun X, Yan M L, Guo Z, Fu K. Position de- tection and direction prediction for arbitrary-oriented ships via multitask rotation region convolutional neural network. IEEE Access, 2018, 6<\/strong>: 50839\u221250849<\/td>\n\u57fa\u4e8e FPN \u91c7\u7528\u7a20\u5bc6\u7279\u5f81\u91d1\u5b57\u5854\u7f51\u7edc\u8fdb\u4e00\u6b65\u52a0\u5f3a\u4e0d\u540c\u5c3a\u5ea6\u7279\u5f81\u4e4b\u95f4\u7684\u8054\u7cfb<\/td>\n<\/tr>\n
    [83]Yang X, Sun H, Fu K, Yang J R, Su X, Yan M L, et al. Auto- matic ship detection in remote sensing images from Google earth of complex scenes based on multiscale rotation dense fea- ture pyramid networks. Remote Sensing, 2018, 10<\/strong>(1): Article No. 132<\/td>\n\u57fa\u4e8e FPN \u91c7\u7528\u7a20\u5bc6\u7279\u5f81\u91d1\u5b57\u5854\u7f51\u7edc\u8fdb\u4e00\u6b65\u52a0\u5f3a\u4e0d\u540c\u5c3a\u5ea6\u7279\u5f81\u4e4b\u95f4\u7684\u8054\u7cfb<\/td>\n<\/tr>\n
    [103]ZouFH,XiaoW,JiWT,HeKK,YangZX,SongJK,etal. Arbitrary-oriented object detection via dense feature fusion and attention model for remote sensing super-resolution image. Neu- ral Computing and Applications, 2020, 32<\/strong>(18): 14549\u221214562<\/td>\n\u57fa\u4e8e FPN \u91c7\u7528\u7a20\u5bc6\u7279\u5f81\u91d1\u5b57\u5854\u7f51\u7edc\u8fdb\u4e00\u6b65\u52a0\u5f3a\u4e0d\u540c\u5c3a\u5ea6\u7279\u5f81\u4e4b\u95f4\u7684\u8054\u7cfb<\/td>\n<\/tr>\n
    [104]Fu K, Chang Z H, Zhang Y, Xu G L, Zhang K S, Sun X. Rota- tion-aware and multi-scale convolutional neural network for ob- ject detection in remote sensing images. ISPRS Journal of Pho- togrammetry and Remote Sensing, 2020, 161<\/strong>: 294\u2212308<\/td>\n\u5728 FPN \u81ea\u9876\u5411\u4e0b\u540e\u989d\u5916\u53c8\u52a0\u5165\u81ea\u5e95\u5411\u4e0a\u7684\u8fde\u63a5, \u5c06\u5e95\u5c42\u7279\u5f81\u4fe1\u606f\u548c\u9ad8\u5c42\u89c6\u89c9\u4fe1\u606f\u8fdb\u884c\u4e86\u4e8c\u6b21\u878d \u5408, \u4ece\u800c\u8fdb\u4e00\u6b65\u589e\u5f3a\u7279\u5f81\u8868\u8fbe\u80fd\u529b<\/td>\n<\/tr>\n
    [84]Azimi S M, Vig E, Bahmanyar R, K\u00f6rner M, Reinartz P. To- wards multi-class object detection in unconstrained remote sensing imagery. In: Proceedings of the 14th Asian Conference on Computer Vision (ACCV 2018). Perth, Australia: Springer, 2018. 150\u2212165<\/td>\n\u76f4\u63a5\u5bf9\u7279\u5f81\u878d\u5408\u6a21\u5757\u7684\u7f51\u7edc\u7ed3\u6784\u8fdb\u884c\u6539\u8fdb, \u4ece\u800c\u589e\u5f3a\u7279\u5f81\u8868\u793a<\/td>\n<\/tr>\n
    [89]LiCZ,XuCY,CuiZ,WangD,ZhangT,YangJ.Feature- attentioned object detection in remote sensing imagery. In: Proceedings of the 2019 IEEE International Conference on Im- age Processing (ICIP). Taipei, China: IEEE, 2019. 3886\u22123890<\/td>\n\u76f4\u63a5\u5bf9\u7279\u5f81\u878d\u5408\u6a21\u5757\u7684\u7f51\u7edc\u7ed3\u6784\u8fdb\u884c\u6539\u8fdb, \u4ece\u800c\u589e\u5f3a\u7279\u5f81\u8868\u793a<\/td>\n<\/tr>\n
    [105]WangJW,DingJ,GuoHW,ChengWS,PanT,YangW. Mask OBB: A semantic attention-based mask oriented bound- ing box representation for multi-category object detection in aerial images. Remote Sensing, 2019, 11<\/strong>(24): Article No. 2930<\/td>\n\u76f4\u63a5\u5bf9\u7279\u5f81\u878d\u5408\u6a21\u5757\u7684\u7f51\u7edc\u7ed3\u6784\u8fdb\u884c\u6539\u8fdb, \u4ece\u800c\u589e\u5f3a\u7279\u5f81\u8868\u793a<\/td>\n<\/tr>\n
    [106]Fu K, Chen Z, Zhang Y, Sun X. Enhanced feature representa- tion in detection for optical remote sensing images. Remote Sensing, 2019, 11<\/strong>(18): Article No. 2095<\/td>\n\u76f4\u63a5\u5bf9\u7279\u5f81\u878d\u5408\u6a21\u5757\u7684\u7f51\u7edc\u7ed3\u6784\u8fdb\u884c\u6539\u8fdb, \u4ece\u800c\u589e\u5f3a\u7279\u5f81\u8868\u793a<\/td>\n<\/tr>\n
    [107]Li Y Y, Huang Q, Pei X, Jiao L C, Shang R H. RADet: Refine feature pyramid network and multi-layer attention network for arbitrary-oriented object detection of remote sensing images. Remote Sensing, 2020, 12<\/strong>(3): Article No. 389<\/td>\n\u76f4\u63a5\u5bf9\u7279\u5f81\u878d\u5408\u6a21\u5757\u7684\u7f51\u7edc\u7ed3\u6784\u8fdb\u884c\u6539\u8fdb, \u4ece\u800c\u589e\u5f3a\u7279\u5f81\u8868\u793a<\/td>\n<\/tr>\n
    [108]Zhang G J, Lu S J, Zhang W. CAD-Net: A context-aware de- tection network for objects in remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57<\/strong>(12): 10015\u221210024<\/td>\n\u76f4\u63a5\u5bf9\u7279\u5f81\u878d\u5408\u6a21\u5757\u7684\u7f51\u7edc\u7ed3\u6784\u8fdb\u884c\u6539\u8fdb, \u4ece\u800c\u589e\u5f3a\u7279\u5f81\u8868\u793a<\/td>\n<\/tr>\n
    [109]Xu C Y, Li C Z, Cui Z, Zhang T, Yang J. Hierarchical semant- ic propagation for object detection in remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58<\/strong>(6): 4353\u22124364<\/td>\n\u76f4\u63a5\u5bf9\u7279\u5f81\u878d\u5408\u6a21\u5757\u7684\u7f51\u7edc\u7ed3\u6784\u8fdb\u884c\u6539\u8fdb, \u4ece\u800c\u589e\u5f3a\u7279\u5f81\u8868\u793a<\/td>\n<\/tr>\n
    [110]YanJQ,WangHQ,YanML,DiaoWH,SunX,LiH.IoU- adaptive deformable R-CNN: Make full use of IoU for multi-class object detection in remote sensing imagery. Remote Sens- ing, 2019, 11<\/strong>(3): Article No. 286<\/td>\n\u5728\u591a\u5c3a\u5ea6\u68c0\u6d4b \u57fa\u7840\u4e0a, \u5e73\u8861\u4e0d\u540c\u5c3a\u5ea6\u76ee\u6807\u5bf9\u4e8e\u635f\u5931\u51fd\u6570\u7684\u8bad\u7ec3\u6743 \u91cd, \u52a0\u5f3a\u7b97\u6cd5\u5bf9\u4e0d\u540c\u5c3a\u5ea6\u7684\u9c81\u68d2\u6027.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    3.2.7 \u9488\u5bf9\u76ee\u6807\u5916\u89c2\u6a21\u7cca\u7684\u6539\u8fdb<\/h4>\n

    \u9065\u611f\u56fe\u50cf\u53ef\u4ee5\u6709\u4e91\u3001\u96fe\u6216\u8005\u96e8\u96ea\u5e72\u6270\uff0c\u8d28\u91cf\u4f4e\uff0c\u65e0\u6cd5\u8fdb\u884c\u68c0\u6d4b\u3002<\/p>\n

    \u89e3\u51b3\u65b9\u6cd5\uff1a\u7ed3\u5408\u533a\u57df\u4e0a\u4e0b\u6587\u4fe1\u606f\u6765\u8fdb\u4e00\u6b65\u5f3a\u5316\u7279\u5f81, \u63d0\u9ad8\u5206\u7c7b\u51c6\u786e\u7387.<\/p>\n

    \u7f3a\u70b9\uff1a\u53ea\u80fd\u5904\u7406\u4e0e\u5468\u8fb9\u73af\u5883\u6709\u4e00\u5b9a\u5171\u751f\u5173\u7cfb\u7684\u76ee\u6807, \u76f8\u5bf9\u72ec\u7acb\u7684\u76ee\u6807\u8f83\u96be\u5904\u7406, \u4e14\u63d0\u5347\u7684\u5e45\u5ea6\u6709\u9650.<\/p>\n

    \u6700\u6709\u6548\u7684\u65b9\u6cd5\uff1a\u63d0\u5347\u56fe\u50cf\u8d28\u91cf<\/p>\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
    [111]Li K, Cheng G, Bu S H, You X. Rotation-insensitive and con- text-augmented object detection in remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56<\/strong>(4): 2337\u22122348<\/td>\n\u63d0\u51fa\u4e86\u4e00\u79cd\u53cc\u901a\u9053\u7279\u5f81\u878d\u5408\u7f51\u7edc, \u53ef\u4ee5\u6cbf\u7740\u4e24\u4e2a\u72ec\u7acb\u7684\u8def\u5f84\u5b66\u4e60\u5c40\u90e8\u5c5e\u6027\u548c\u4e0a\u4e0b\u6587\u5c5e\u6027, \u5e76\u5c06\u7279\u5f81\u8fdb\u884c\u878d\u5408\u589e\u5f3a\u5224\u522b\u529b.<\/td>\n<\/tr>\n
    [112]Chen C Y, Gong W G, Chen Y L, Li W H. Object detection in remote sensing images based on a scene-contextual feature pyr- amid network. Remote Sensing, 2019, 11<\/strong>(3): Article No. 339<\/td>\n\u4ee5 FPN \u4e3a\u57fa\u7840\u63d0\u53d6 ROI \u7279\u5f81\u56fe, \u7136\u540e \u5c06\u6574\u5e45\u56fe\u7684\u7279\u5f81\u56fe\u548c ROI \u7684\u7279\u5f81\u56fe\u878d\u5408, \u5f97\u5230\u4e0a\u4e0b\u6587\u4fe1\u606f\u5b8c\u6210\u68c0\u6d4b<\/td>\n<\/tr>\n
    [113]MaWP,GuoQQ,WuY,ZhaoW,ZhangXR,JiaoLC.A novel multi-model decision fusion network for object detection in remote sensing images. Remote Sensing, 2019, 11<\/strong>(7): Article No. 737<\/td>\n\u8bbe\u8ba1\u4e86\u4e00\u79cd\u878d\u5408\u5c40\u90e8\u4e0a\u4e0b\u6587\u7279\u5f81\u548c\u76ee\u6807\u2212\u76ee\u6807\u5173\u7cfb\u4e0a\u4e0b\u6587\u7279\u5f81\u7684\u4e0a\u4e0b\u6587\u4fe1\u606f\u878d\u5408\u5b50\u7f51\u7edc, \u6765\u5904\u7406\u76ee\u6807\u5bf9\u8c61\u5916\u89c2\u7684\u590d\u6742\u6027.<\/td>\n<\/tr>\n
    [108]Zhang G J, Lu S J, Zhang W. CAD-Net: A context-aware de- tection network for objects in remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57<\/strong>(12): 10015\u221210024<\/td>\n\u901a\u8fc7\u5b66\u4e60\u76ee\u6807\u7684\u5168\u5c40\u4e0a\u4e0b\u6587\u7279\u5f81\u548c\u5c40\u90e8\u4e0a\u4e0b\u6587\u7279\u5f81\u6765\u589e\u5f3a\u76ee\u6807\u7684\u7279\u5f81\u8868\u8fbe, \u540c\u65f6\u5f15\u5165\u6ce8\u610f\u529b\u673a\u5236\u6765\u96c6\u4e2d\u68c0\u6d4b\u533a\u57df\u76ee\u6807\u7279\u5f81.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    3.2.8 \u9488\u5bf9\u590d\u6742\u80cc\u666f\u7684\u6539\u8fdb<\/h4>\n

    \u5b9a\u4e49<\/strong> \uff1a\u590d\u6742\u80cc\u666f\u4e2d\u7684\u76ee\u6807\u4f1a\u88ab\u80cc\u666f\u6df7\u6dc6\uff0c\u5bfc\u81f4\u8bef\u5224\u7684\u6982\u7387\u589e\u52a0\u3002<\/p>\n

    \u89e3\u51b3\u65b9\u6cd5\uff1a \u7528\u6ce8\u610f\u529b\u673a\u5236\u6765\u51cf\u5f31\u80cc\u666f\u3001\u589e\u5f3a\u76ee\u6807\u4fe1\u606f\u7279\u5f81\u3002<\/p>\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
    [114]Zhang Y K, You Y N, Wang R, Liu F, Liu J. Nearshore vessel detection based on Scene-mask R-CNN in remote sensing im- age. In: Proceedings of the 2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC). Guiy- ang, China: IEEE, 2018. 76\u221280<\/td>\n\u91c7\u7528\u8bed\u4e49\u5206\u5272\u7684\u601d\u60f3\u5206\u522b\u63d0\u53d6\u8239\u53ea\u3001\u6d77\u6d0b\u548c\u9646\u5730\u7684\u7279\u5f81\u63a9\u819c, \u4e4b\u540e\u91c7\u7528\u50cf\u7d20\u6ce8\u610f\u529b\u673a\u5236\u6765\u5bf9\u5404\u4e2a\u7c7b\u522b\u8fdb\u884c\u52a0\u6743, \u63d0\u5347\u6d77\u9646\u5206\u79bb\u7684\u80fd\u529b<\/td>\n<\/tr>\n
    [115]LiQP,MouLC,JiangKY,LiuQJ,WangYH,ZhuXX. Hierarchical region based convolution neural network for multiscale object detection in remote sensing images. In: Pro- ceedings of the 2018 IEEE International Geoscience and Re- mote Sensing Symposium (IGARSS 2018). Valencia, Spain: IEEE, 2018. 4355\u22124358<\/td>\n\u63d0\u53d6\u591a\u5c3a\u5ea6\u7279\u5f81\u540e, \u5bf9\u6bcf\u4e2a\u7279\u5f81\u56fe\u5355\u72ec\u4f7f\u7528\u6ce8\u610f\u529b\u673a\u5236\u8fdb\u884c\u7279\u5f81\u589e\u5f3a, \u4ece\u800c\u6d88\u9664\u80cc\u666f\u566a\u58f0\u7684\u5f71\u54cd<\/td>\n<\/tr>\n
    [118]Li C Y, Luo B, Hong H L, Su X, Wang Y J, Liu J, et al. Ob- ject detection based on global-local saliency constraint in aeri- al images. Remote Sensing, 2020, 12<\/strong>(9): Article No. 1435<\/td>\n\u5728\u7279\u5f81\u56fe\u878d\u5408\u8fc7\u7a0b\u4e2d \u8bbe\u8ba1\u4e86\u663e\u8457\u6027\u91d1\u5b57\u5854\u878d\u5408\u7b56\u7565\u6765\u5f31\u5316\u80cc\u666f\u5e26\u6765\u7684\u5f71 \u54cd, \u589e\u5f3a\u76ee\u6807\u7279\u5f81\u7684\u8868\u8fbe\u80fd\u529b, \u5e76\u7ed3\u5408\u5168\u5c40\u6ce8\u610f\u529b \u673a\u5236\u589e\u5f3a\u8bed\u4e49\u4fe1\u606f, \u5b8c\u6210\u6700\u7ec8\u7684\u68c0\u6d4b\u8fc7\u7a0b.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    \u878d\u5408\u540e\u7684\u591a\u5c3a\u5ea6\u7279\u5f81\u56fe\u91c7\u7528\u6ce8\u610f\u529b\u673a\u5236<\/strong> <\/p>\n\n\n\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n<\/tr>\n<\/thead>\n
    [80]YangX,YangJR,YanJC,ZhangY,ZhangTF,GuoZ,etal. SCRDet: Towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the 2019 IEEE\/CVF In- ternational Conference on Computer Vision (ICCV). Seoul, Korea: IEEE, 2019. 8232\u22128241<\/td>\n<\/tr>\n
    [82]YangX,YanJC,YangXK,TangJ,LiaoWL,HeT. SCRDet++: Detecting small, cluttered and rotated objects via instance-level feature denoising and rotation loss smoothing. arXiv preprint arXiv: 2004.13316, 2020<\/td>\n<\/tr>\n
    [89]LiCZ,XuCY,CuiZ,WangD,ZhangT,YangJ.Feature- attentioned object detection in remote sensing imagery. In: Proceedings of the 2019 IEEE International Conference on Im- age Processing (ICIP). Taipei, China: IEEE, 2019. 3886\u22123890<\/td>\n<\/tr>\n
    [105]WangJW,DingJ,GuoHW,ChengWS,PanT,YangW. Mask OBB: A semantic attention-based mask oriented bound- ing box representation for multi-category object detection in aerial images. Remote Sensing, 2019, 11<\/strong>(24): Article No. 2930<\/td>\n<\/tr>\n
    [107]Li Y Y, Huang Q, Pei X, Jiao L C, Shang R H. RADet: Refine feature pyramid network and multi-layer attention network for arbitrary-oriented object detection of remote sensing images. Remote Sensing, 2020, 12<\/strong>(3): Article No. 389<\/td>\n<\/tr>\n
    [116]Hou L P, Lu K, Xue J, Hao L. Cascade detector with feature fusion for arbitrary-oriented objects in remote sensing images. In: Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME). London, UK: IEEE, 2020. 1\u22126<\/td>\n<\/tr>\n
    [117]Yang F, Li W T, Hu H W, Li W Y, Wang P. Multi-scale fea- ture integrated attention-based rotation network for object de- tection in VHR aerial images. Sensors, 2020, 20<\/strong>(6): Article No. 1686<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    3.2.9 \u9488\u5bf9\u5e38\u89c4\u6c34\u5e73\u6846\u5b9a\u4f4d\u7c97\u7cd9\u7684\u6539\u8fdb<\/h4>\n

    \u5b9a\u4e49<\/strong>\uff1a\u9065\u611f\u56fe\u50cf\u76ee\u6807\u5177\u6709\u65b9\u5411\u6027, \u4e14\u65b9\u5411\u5177\u6709\u968f\u673a\u6027.\u5e38\u89c4\u7684\u6c34\u5e73\u6846\u65e0\u6cd5\u7d27\u51d1\u3001\u7cbe\u51c6\u7684\u5b9a\u4f4d\u3002<\/p>\n

    \u89e3\u51b3\u65b9\u6cd5\uff1a \u5229\u7528\u65cb\u8f6c\u6846\u66ff\u4ee3\u6c34\u5e73\u6846\u7684\u8868\u793a\u65b9\u6cd5, \u8bbe\u8ba1\u65cb\u8f6c\u6846\u68c0\u6d4b\u6a21\u578b\u3002\u4e00\u822c\u6709\u4e24\u79cd\u65b9\u6cd5\uff1a\uff081\uff09\u4e94\u53c2\u6570\u6cd5 \uff082\uff09\u516b\u53c2\u6570\u6cd5<\/p>\n

    \"\"
    \n\uff081\uff09\u4e94\u53c2\u6570\u6cd5 \uff1a\u53c2\u6570\u5c11\u3001\u7814\u7a76\u591a<\/p>\n

    \u4e2d\u5fc3\u70b9\u5750\u6807\uff08x,y) \uff1b\u76ee\u6807\u5bbd\u5ea6\u3001\u9ad8\u5ea6\uff08w,h\uff09;\u89d2\u5ea6\uff08ang\uff09
    \n$$
    \n(x,y;w,h;ang)
    \n$$
    \n\u5176\u4e2d\uff0cang\u7684\u5468\u671f\u4e00\u822c\u4e3a 180\u00b0\u6216\u800590\u00b0<\/p>\n

    \uff082\uff09\u516b\u53c2\u6570\u6cd5\uff1a\u53c2\u6570\u591a\uff0c\u66f4\u7075\u6d3b<\/p>\n

    \u56db\u4e2a\u9876\u70b9\u5750\u6807
    \n$$
    \n(x1,y1;x2,y2;x3,y3;x4,y4)
    \n$$<\/p>\n\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
    [119]<\/td>\n\u76f4\u63a5\u5728 Faster R-CNN \u7684 \u57fa\u7840\u4e0a\u57fa\u4e8e\u4e0a\u8ff0\u53c2\u6570\u8868\u793a\u65b9\u6848\u5f15\u5165\u65b0\u7684\u56de\u5f52\u53c2\u6570, \u6765\u8fdb\u884c\u65cb\u8f6c\u6846\u7684\u68c0\u6d4b<\/td>\n<\/tr>\n
    [120]<\/td>\nRRPN: \u4eba\u5de5\u5b9a\u4e49\u4e86\u5927\u91cf\u5e26\u6709\u89d2\u5ea6\u7684\u951a\u70b9\u6846\u6765\u8fdb\u884c\u65cb\u8f6c\u76ee\u6807\u7684\u56de\u5f52, \u540c\u65f6\u5728\u68c0 \u6d4b\u8bc6\u522b\u9636\u6bb5\u63d0\u51fa\u4e86\u65cb\u8f6c\u7279\u5f81\u6c60\u5316\u64cd\u4f5c (RROI pooling) \u6765\u5c06\u7279\u5f81\u8fdb\u884c\u5f52\u4e00\u5316, \u53d6\u5f97\u4e86\u65b9\u5411\u6027\u76ee\u6807\u68c0\u6d4b \u7684\u521d\u6b65\u6548\u679c.<\/td>\n<\/tr>\n
    [121]<\/td>\nRRCNN:\u4f9d\u7136\u9009\u53d6\u6c34\u5e73\u951a\u70b9\u6846\u6765\u8fdb\u884c\u7b2c\u4e00\u9636\u6bb5\u611f\u5174\u8da3\u533a\u57df\u7684\u63d0\u53d6, \u5728 (Region proposal network, RPN) \u9636\u6bb5\u751f\u6210\u65cb\u8f6c\u5019\u9009\u533a\u57df\u5e76\u91c7\u7528\u591a\u5c3a\u5ea6\u6c60\u5316\u64cd\u4f5c\u6765\u589e\u5f3a\u68c0\u6d4b\u8bc6\u522b\u7279\u5f81\u7684\u6cdb\u5316\u80fd\u529b, \u5728\u7b2c\u4e8c\u9636\u6bb5\u57fa\u4e8e\u6c34\u5e73\u5019\u9009\u533a\u57df\u6765\u8fdb\u884c\u65cb\u8f6c\u6846\u7684\u56de\u5f52, \u8fdb\u4e00\u6b65\u63d0\u5347\u4e86\u6027\u80fd\u5e76\u51cf\u5c0f\u4e86\u5185\u5b58\u6d88\u8017.<\/td>\n<\/tr>\n
    [86]<\/td>\nRoI transformer: \u5728 RPN \u548c RCNN \u4e4b\u95f4\u63d2\u5165\u4e86\u4e00\u4e2a\u8f7b\u91cf\u7ea7\u6a21\u5757, \u5c06 RPN \u751f\u6210\u7684\u6c34\u5e73\u533a\u57df\u8f6c\u6362\u6210\u65cb\u8f6c\u533a\u57df, \u5c3d\u53ef\u80fd\u51cf\u5c11\u65cb\u8f6c\u76ee\u6807\u68c0\u6d4b\u5e26\u6765\u7684\u8ba1\u7b97\u590d\u6742\u5ea6. \u4e3a\u4e86\u8fdb\u4e00\u6b65\u589e\u5f3a\u7279\u5f81\u8868\u8fbe\u80fd\u529b<\/td>\n<\/tr>\n
    [122]<\/td>\n\u540c\u65f6\u8fdb\u884c\u6c34\u5e73\u6846\u548c\u65cb\u8f6c\u6846\u7684\u56de\u5f52, \u4e8c\u8005\u76f8\u4e92\u4fc3\u8fdb, \u5171\u540c\u63d0\u5347\u7cbe\u5ea6.( [86\u3001120-122] \u90fd\u6709)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    3.2.10 \u9488\u5bf9\u65cb\u8f6c\u6846\u8fb9\u754c\u7a81\u53d8\u95ee\u9898\u7684\u6539\u8fdb<\/h4>\n

    \u5b9a\u4e49<\/em>\uff1a\u57fa\u4e8e\u5e38\u89c1\u7684\u53c2\u6570\u8868\u793a\u8fdb\u884c\u65cb\u8f6c\u6846\u5750\u6807\u56de\u5f52\u65f6\u5019\u4f1a\u4f34\u968f\u5178\u578b\u7684\u8fb9\u754c\u7a81\u53d8\u95ee\u9898.<\/p>\n

    \u6ce8\uff1a<\/em> 2\u5ea6\u548c178\u5b9e\u9645\u4e0a\u662f\u5dee\u4e0d\u591a\u7684\uff0c\u4f46\u662f\u6570\u503c\u5dee\u522b\u6bd4\u8f83\u5927\u3002<\/p>\n

    \u89e3\u51b3\u65b9\u6cd5\uff1a\u91c7\u7528\u65b0\u7684\u53c2\u6570\u8868\u793a\u65b9\u6848<\/strong>\u548c\u6539\u8fdb\u635f\u5931\u51fd\u6570<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n
    \u8bba\u6587<\/th>\n\u5185\u5bb9<\/th>\n<\/tr>\n<\/thead>\n
    [94]Zhu Y X, Du J, Wu X Q. Adaptive period embedding for rep- resenting oriented objects in aerial images. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58<\/strong>(10): 7247\u22127257<\/td>\nAPE:\u91c7\u7528\u4e00\u5bf9\u5177\u6709\u5468\u671f\u6027\u7684\u4e09\u89d2\u51fd\u6570\u6765\u8868\u5f81\u89d2\u5ea6\u4fe1\u606f, \u907f\u514d\u4e86\u8fb9\u754c\u7a81\u53d8<\/td>\n<\/tr>\n
    [123]XuYC,FuMT,WangQM,WangYK,ChenK,XiaGS, et al. Gliding vertex on the horizontal bounding box for multi- oriented object detection. IEEE Transactions on Pattern Ana- lysis and Machine Intelligence, 2021, 43<\/strong>(4): 1452\u22121459<\/td>\nGliding vertex :\u9996\u5148\u63d0\u53d6\u5916\u63a5\u6c34\u5e73\u6846, \u8fdb\u800c\u5728\u6c34\u5e73\u6846\u7684\u8fb9\u754c\u4e0a\u5f15\u5165\u4e00\u4e2a\u6bd4\u4f8b\u56e0\u5b50\u5bf9\u65cb\u8f6c\u6846\u9876\u70b9\u8fdb\u884c\u5b9a\u4f4d, \u89e3\u51b3\u4e86\u516b\u53c2\u6570\u8868\u793a\u65b9\u6848\u9876\u70b9\u987a\u5e8f\u7684\u95ee\u9898,\u4e3a\u4e86\u7f13\u89e3\u8fb9\u754c\u95ee\u9898\u5f15\u5165\u4e86\u4e00\u4e2a\u63a7\u5236\u56e0\u5b50\u6765\u51b3\u7b56\u662f\u5426<\/strong>\u9700\u8981\u56de\u5f52\u65cb\u8f6c\u6846<\/td>\n<\/tr>\n
    [124] WangYS,ZhangY,ZhangY,ZhaoLJ,SunX,GuoZ. SARD: Towards scale-aware rotated object detection in aerial imagery. IEEE Access, 2019, 7<\/strong>: 173855\u2212173865<\/td>\nSARD: \u76f4\u63a5\u5bf9\u7f51\u7edc\u8f93\u51fa\u7ed3\u679c\u8fdb \u884c\u4e86\u5f3a\u5236\u7684\u6807\u51c6\u5316, \u5c3d\u7ba1\u53d1\u73b0\u4e86\u8fb9\u754c\u95ee\u9898, \u4f46\u662f\u89e3 \u51b3\u65b9\u5f0f\u53ea\u9650\u4e8e\u5f3a\u52a0\u89c4\u5219, \u5e76\u6ca1\u6709\u6709\u6548\u7f13\u89e3\u8be5\u95ee\u9898.<\/td>\n<\/tr>\n
    [105,107]WangJW,DingJ,GuoHW,ChengWS,PanT,YangW. Mask OBB: A semantic attention-based mask oriented bound- ing box representation for multi-category object detection in aerial images. Remote Sensing, 2019, 11<\/strong>(24): Article No. 2930. && Li Y Y, Huang Q, Pei X, Jiao L C, Shang R H. RADet: Refine feature pyramid network and multi-layer attention network for arbitrary-oriented object detection of remote sensing images. Remote Sensing, 2020, 12<\/strong>(3): Article No. 389<\/td>\nMask OBB & RADet : \u501f\u9274\u5b9e\u4f8b\u5206\u5272\u7684\u65b9\u5f0f, \u57fa\u4e8e\u5206\u5272\u4ea7\u751f\u7684\u7c7b\u522b\u63a9\u819c\u6765\u751f\u6210\u6700\u5c0f\u5916\u63a5\u77e9\u5f62, \u907f \u514d\u4e86\u8fb9\u754c\u95ee\u9898, \u4f46\u662f\u5f15\u5165\u4e86\u989d\u5916\u7684\u8bed\u4e49\u5206\u5272\u8ba1\u7b97, \u8ba1\u7b97\u590d\u6742\u5ea6\u8f83\u9ad8<\/td>\n<\/tr>\n
    [125]Yang X, Yan J C. Arbitrary-oriented object detection with cir- cular smooth label. In: Proceedings of the 16th European Con- ference on Computer Vision (ECCV 2020). Glasgow, UK: Springer, 2020. 677\u2212694<\/td>\nCSL: \u91c7\u7528\u89d2\u5ea6\u5206\u7c7b\u7684\u65b9\u5f0f\u6765\u66ff \u4ee3\u56de\u5f52, \u5e76\u9488\u5bf9\u6027\u8bbe\u8ba1\u4e86\u8f6f\u6807\u7b7e\u6765\u5e94\u5bf9\u8fb9\u754c\u95ee\u9898, \u4ece\u6839\u6e90\u4e0a\u89e3\u51b3\u4e86\u8fb9\u754c\u95ee\u9898, \u53d6\u5f97\u4e86\u5f88\u597d\u7684\u6548\u679c, \u4f46 \u662f\u91c7\u7528\u89d2\u5ea6\u5206\u7c7b\u7684\u65b9\u5f0f\u4e5f\u5bfc\u81f4\u4e86\u8f93\u51fa\u53c2\u6570\u91cf\u8fc7\u5927.<\/td>\n<\/tr>\n
    [80,82]Yang X, Yan J C. Arbitrary-oriented object detection with cir- cular smooth label. In: Proceedings of the 16th European Con- ference on Computer Vision (ECCV 2020). Glasgow, UK: Springer, 2020. 677\u2212694<\/td>\n\u8bbe\u8ba1\u4e86 IOU-Smooth \u635f\u5931\u51fd\u6570\u76f4\u63a5\u5f31\u5316\u8bad\u7ec3\u65f6\u5019\u7684\u8fb9\u754c\u6837\u672c<\/td>\n<\/tr>\n
    [126]Qian W, Yang X, Peng S L, Guo Y, Yan J C. Learning modu- lated loss for rotated object detection. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021.<\/td>\nModulated loss: \u5728\u8fb9\u754c\u4e0a\u91c7\u7528\u6240\u6709\u7a81\u53d8\u503c\u8ba1\u7b97\u635f\u5931\u51fd\u6570\u5e76\u9009\u53d6\u635f\u5931\u6700\u5c0f\u503c\u8fdb\u884c\u8bad\u7ec3, \u6765\u7f13\u89e3\u8fb9\u754c\u95ee\u9898\u7684\u5f71\u54cd.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"excerpt":{"rendered":"

    \u5149\u5b66\u9065\u611f\u56fe\u50cf\u76ee\u6807\u68c0\u6d4b\u7b97\u6cd5\u7efc\u8ff0\uff08\u4e8c\uff09 \u539f\u6587pdf\u4e0b\u8f7d\uff1a\u4e0b\u8f7d\u94fe\u63a5 2.3\u5206\u7c7b\u5668\u8bbe\u8ba1 \u6709\u4e3b\u6d41\u7684\u76ee\u6807\u5206\u7c7b\u8bc6\u522b\u4efb\u52a1\u5747\u91c7\u7528… » \u9605\u8bfb\u5168\u6587<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-77","post","type-post","status-publish","format-standard","hentry","category-dl"],"_links":{"self":[{"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/posts\/77","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/comments?post=77"}],"version-history":[{"count":12,"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/posts\/77\/revisions"}],"predecessor-version":[{"id":133,"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/posts\/77\/revisions\/133"}],"wp:attachment":[{"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/media?parent=77"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/categories?post=77"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/apifj.com\/index.php\/wp-json\/wp\/v2\/tags?post=77"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}