基于CNN的高分遥感影像深度语义特征提取研究综述

鎽樿/Abstract

鎽樿锛� 杩戝勾鏉ワ紝娣卞害瀛︿範浣滀负璁＄畻鏈鸿瑙夌殑鐮旂┒鐑偣锛屽湪璇稿鏂归潰寰椾互鍙戝睍涓庡簲鐢ㄣ�傜壒寰佹彁鍙栨槸鐞嗚В鍜屽垎鏋愰珮鍒嗛仴鎰熷奖鍍忕殑鍏抽敭鍩虹銆備负淇冭繘楂樺垎閬ユ劅褰卞儚鐗瑰緛鎻愬彇鎶�鏈殑鍙戝睍锛屾�荤粨浜嗘繁搴﹀涔犳ā鍨嬪湪楂樺垎閬ユ劅褰卞儚鐗瑰緛鎻愬彇鎶�鏈殑鐮旂┒涓庡彂灞曪紝濡傦細AlexNet锛孷GG-缃戝拰GoogleNet绛夊嵎绉綉缁滄ā鍨嬪湪娣卞害璇箟鐗瑰緛鎻愬彇涓殑搴旂敤銆傛澶栵紝閲嶇偣鍒嗘瀽鍜岃璁轰簡浠ュ嵎绉缁忕綉缁滄ā鍨嬩负鍩虹鐨勫悇绫绘繁搴﹀涔犳ā鍨嬪湪楂樺垎閬ユ劅褰卞儚鐗瑰緛鎻愬彇鏂归潰鐨勫簲鐢ㄤ笌鍒涙柊锛屽锛氳縼绉诲涔犵殑搴旂敤锛涘嵎绉缁忕綉缁�(Convolutional Neural Network锛孋NN)妯″瀷缁撴瀯鐨勬敼鍙橈紱CNN妯″瀷涓庡叾浠栨ā鍨嬬粨鏋勭殑缁撳悎绛夋柟寮忥紝鍧囨彁鍗囦簡娣卞害璇箟鐗瑰緛鎻愬彇鑳藉姏銆傛渶鍚庯紝瀵瑰嵎绉缁忕綉缁滄ā鍨嬪湪楂樺垎閬ユ劅褰卞儚娣卞害璇箟鐗瑰緛鎻愬彇鏂归潰瀛樺湪鐨勯棶棰樹互鍙婂悗缁彲鑳界殑鐮旂┒瓒嬪娍杩涜浜嗗垎鏋愩��

鍏抽敭璇�: High-resolution remote sensing image, Depth semantic feature, Deep learning, Convolutional neural network

Abstract: In recent years锛宒eep learning has been developed and applied in many aspects as a research hotspot of computer vision.Feature extraction is the key basis for understanding and analyzing high-resolution remote sensing images.In order to promote the development of high-resolution remote sensing image feature extraction technology锛宼he research and development of deep learning model in high-resolution remote sensing image feature extraction technology锛宻uch as锛欰lexNet锛孷GG-net锛宎nd GoogleNet convolutional network models锛宧ave been summarized in depth semantic features.In addition锛宼he application of extraction is also focused on the application and innovation of various deep learning models based on convolutional neural network models in high-resolution remote sensing image feature extraction锛宻uch as锛歛pplication of migration learning锛汿he combination of the CNN model and other model structures enhances the ability to extract deep semantic features.Finally锛宼he problems of the convolutional neural network model in the extraction of deep semantic features of high-resolution remote sensing images and the possible research trends are analyzed.

Key words: 楂樺垎杈ㄧ巼閬ユ劅褰卞儚, 娣卞害璇箟鐗瑰緛, 娣卞害瀛︿範, 鍗风Н绁炵粡缃戠粶妯″瀷

涓浘鍒嗙被鍙�:

TP751

钁ｈ暣闆�, 寮犲��. 鍩轰簬CNN鐨勯珮鍒嗛仴鎰熷奖鍍忔繁搴﹁涔夌壒寰佹彁鍙栫爺绌剁患杩癧J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(1): 1-11.

Dong Yunya, Zhang Qian. A Survey of Depth Semantic Feature Extraction of High-Resolution Remote Sensing Images based on CNN [J]. Remote Sensing Technology and Application, 2019, 34(1): 1-11.

鍙傝�冩枃鐚�

[1锛絏ie Jiali锛孡i Yongshu锛孡i Hechao锛宔t al.Method for Recognizing Damaged Buildings in Hollow Village Using the Texture Feature of Gray Level Co-occurrence Matrix[J].Bulletin of Surveying and Mapping锛�2017锛�12锛�90-93.[璋㈠槈涓斤紝鏉庢案鏍戯紝鏉庝綍瓒咃紝绛�.鍒╃敤鐏板害鍏辩敓鐭╅樀绾圭悊鐗瑰緛璇嗗埆绌哄績鏉戞崯姣佸缓绛戠墿鐨勬柟娉昜J].娴嬬粯閫氭姤锛�2017锛�12锛�90-93.[2]Jia Hongguo锛孡iu Luyao锛學ei Bowen锛宔t al.Automatic Extraction of Bridge Targets based on Shape and Texture Features for High Resolution SAR Imagery[J].Bulletin of Surveying and Mapping锛�2017锛�12锛�82-85.[璐炬椽鏋滐紝鍒樿矾閬ワ紝闊﹀崥鏂囷紝绛�.鍩轰簬褰㈢姸涓庣汗鐞嗙壒寰佺殑楂樺垎杈ㄧ巼SAR褰卞儚妗ユ鐩爣鑷姩鎻愬彇鏂规硶[J].娴嬬粯閫氭姤锛�2017锛�12锛�82-85.]顎� [3]Yang Tao锛孒uang Farong锛孡i Qian.Spatiotemporal Changes of NDVI in the Growing Season of Northern Xinjiang and Its Relationship with Winter Snowfall[J].Remote Sensing Technology and Application.2017锛�32(6)锛�1132-1140.[鏉ㄦ稕锛岄粍娉曡瀺锛屾潕鍊�.鏂扮枂鍖楅儴妞嶈鐢熼暱瀛DVI鏃剁┖鍙樺寲鍙婂叾涓庡啲瀛ｉ檷闆殑鍏崇郴[J].閬ユ劅鎶�鏈笌搴旂敤锛�2017锛�32(6)锛�1132-1140.] [4]Hou Qunqun锛學ang Fei锛孻an Li.Texture Feature Extraction of Color Remote Sensing Images based on Gray Level Co-occurrence Matrix[J].Remote Sensing for Land and Resources锛�2013锛�25(4)锛�26-32.[渚兢缇わ紝鐜嬮锛屼弗涓�.鍩轰簬鐏板害鍏辩敓鐭╅樀鐨勫僵鑹查仴鎰熷浘鍍忕汗鐞嗙壒寰佹彁鍙朳J].鍥藉湡璧勬簮閬ユ劅锛�2013锛�25(4)锛�26-32.] [5]Hu Hualong锛學u Bing锛孒uang Shaomei.Urban Road Extraction Method based on Gabor Texture and Geometric Features in High Resolution Remote Sensing Images[J].Journal of Surveying and Mapping Science and Technology锛�2015锛�32(4)锛�395-400.[鑳″崕榫欙紝鍚村啺锛岄粍閭电編.缁撳悎Gabor绾圭悊涓庡嚑浣曠壒寰佺殑楂樺垎杈ㄧ巼閬ユ劅褰卞儚鍩庡尯閬撹矾鎻愬彇鏂规硶[J].娴嬬粯绉戝鎶�鏈鎶ワ紝2015锛�32(4)锛�395-400.]顎� [6]Pesaresi M锛孏erhardinger A锛孠ayitakire F.A Robust Built-up Area Presence Index by Anisotropic Rotation-invariant Textural Measure[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing锛�2009锛�1(3)锛�180-192. [7]Pesaresi M锛孏erhardinger A.Improved Textural Built-up Presence[JP] Index for Automatic Recognition of Human Settlements in Arid Regions with Scattered Vegetation[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing锛�2011锛�4(1)锛�16-26.顎� [8]Lowe D G.Object Recognition from Local Scale-Invariant Features[C]鈭he Proceedings of the Seventh IEEE International Conference on Computer Vision锛�2002锛�1150.顎� [9]Huang X锛孼hang L.A Multidirectional and Multiscale Morphological Index for Automatic Building Extraction from Multispectral GeoEye-1 Imagery[J].Photogrammetric Engineering and Remote Sensing锛�2015锛�77(7)锛�721-732.顎� [10]Tian Feng锛孋hen Donghua锛孒uang Xinli锛宔t al.Building Height Estimation based on Morphological Shadow Index and High Scores No.2 Image[J].Remote Sensing Technology and Application锛�2017锛�32(5)锛�844-850.[鐢板嘲锛岄檲鍐姳锛岄粍鏂板埄锛岀瓑.鍩轰簬褰㈡�佸闃村奖鎸囨暟鐨勯珮鍒嗕簩鍙峰奖鍍忓缓绛戠墿楂樺害浼拌[J].閬ユ劅鎶�鏈笌搴旂敤锛�2017锛�32(5)锛�844-850.]顎� [11]Wang Ma.Cheng Bo锛孡iu Yueming.Research on the Extraction of High-resolution Remote Sensing Image based on Multi-source Feature Fusion in the Offshore Culture Area[J].Remote Sensing Technology and Application锛�2018锛�33(2)锛�296-304.[鐜嬮┈.绋嬪崥锛屽垬宀虫槑.鍩轰簬澶氭簮鐗瑰緛铻嶅悎鐨勯珮鍒嗚鲸鐜囬仴鎰熷浘鍍忚繎娴峰吇娈栧尯鎻愬彇鏂规硶鐮旂┒[J].閬ユ劅鎶�鏈笌搴旂敤锛�2018锛�33(2)锛�296-304.]顎� [12]Zhu Q锛孼hong Y锛孼hao B锛宔t al.Bag-of-Visual-Words Scene Classifier with Local and Global Features for High Spatial Resolution Remote Sensing Imagery[J].IEEE Geoscience and Remote Sensing Letters锛�2017锛�13(6)锛�747-751.顎� [13]Olshausen B A锛孎ield D J.Sparse Coding with an Overcomplete Basis Set锛欰 Strategy Employed by V1?[J].Vision Research锛�1997锛�37(23)锛�3311-3325.顎� [14]L眉 Qi锛孌ou Yong锛孨iu Xin锛宔t al.Classification of Remote Sensing Image based on DBN Model[J].Journal of Computer Research and Development锛�2014锛�51(9)锛�1911-1918.[鍚曞惎锛岀鍕囷紝鐗涙柊锛岀瓑.鍩轰簬DBN妯″瀷鐨勯仴鎰熷浘鍍忓垎绫籟J].璁＄畻鏈虹爺绌朵笌鍙戝睍锛�2014锛�51(9)锛�1911-1918.]顎� [15]Liu Xingwang锛學ang Jiangqing锛孹u Ke.A Hybrid Algorithm Combining Auto Encoder and CNN for Image Feature Extraction[J].Application Research of Computers锛�2017锛�34(12)锛�3839-3843.[鍒樺叴鏃猴紝鐜嬫睙鏅达紝寰愮.涓�绉嶈瀺鍚圓uto Encoder涓嶤NN鐨勬贩鍚堢畻娉曠敤浜庡浘鍍忕壒寰佹彁鍙朳J].璁＄畻鏈哄簲鐢ㄧ爺绌讹紝2017锛�34(12)锛�3839-3843.]顎� [16]Hu Yong锛孼hang Xiaocheng锛孧a Zezhong锛宔t al.Rapid Extraction of Rural Housing Information from Remote Sensing Images of UAVs[J].Remote Sensing of Land Resources锛�2016锛�28(3)锛�96-101.[鑳″媷锛屽紶瀛濇垚锛岄┈娉藉繝锛岀瓑.鏃犱汉鏈洪仴鎰熷奖鍍忎腑鍐滄潙鎴垮眿淇℃伅蹇�熸彁鍙朳J].鍥藉湡璧勬簮閬ユ劅锛�2016锛�28(3)锛�96-101.] [17]Cheng Yuan鈥檈锛孼hou Shaoguang锛孻uan Chunqi锛宔t al.Hyperspectral Image Classification based on Active Deep Learning[J].Computer Engineering and Applications锛�2017锛�53(17)锛�192-196.[绋嬪渾濞ワ紝鍛ㄧ粛鍏夛紝琚佹槬鐞︼紝绛�.鍩轰簬涓诲姩娣卞害瀛︿範鐨勯珮鍏夎氨褰卞儚鍒嗙被[J].璁＄畻鏈哄伐绋嬩笌搴旂敤锛�2017锛�53(17)锛�192-196.]顎� [18]Scott G J锛孍ngland M R锛孲tarms W A锛宔t al.Training Deep Convolutional Neural Networks for Land-cover Classification of High-resolution Imagery[J].IEEE Geoscience and Remote Sensing Letters锛�2017锛�(99)锛�1-5.顎� [19]Ali Sharif Razavian锛孒ossein Azizpour锛孞osephine Sullivan锛宔t al.CNN Features Off-the-Shelf锛欰n Astounding Baseline for Recognition[J].2014锛�512-519.顎� [20]Maggiori E锛孴arabalka Y锛孋harpiat G锛宔t al.Fully Convolutional Neural Networks for Remote Sensing Image Classification[C]鈭EEE Geoscience and Remote Sensing Symposium锛�2016锛�5071-5074.顎� [21]Qu B锛孡i X锛孴ao D锛宔t al.Deep Semantic Understanding of High Resolution Remote Sensing Image[C]鈭EEE International Conference on Computer锛孖nformation and Telecommunication Systems锛�2016锛�1-5.顎� [22]Abdullahi H S锛孲heriff R E锛孧ahieddine F.Convolution Neural Network in Precision Agriculture for Plant Image Recognition and Classification[C]鈭nternational Conference on Innovative Computing Technology锛�2017锛�1-3.顎� [23]Huang X锛孻uan W锛孡i J锛宔t al.A New Building Extraction Postprocessing Framework for High-Spatial-Resolution Remote-Sensing Imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing锛�2017锛�10(2)锛�654-668.顎� [24]Krizhevsky A锛孲utskever I锛孒inton G E.Image Net Classification with Deep Convolutional Neural Networks[C]鈭nternational Conference on Neural Information Processing Systems.Curran Associates Inc锛�2012锛�1097-1105.顎� [25]Simonyan K锛孼isserman A.Very Deep Two-Stream Convolutional Networks for Action Recognition in Videos[C]鈭eural Information Processing Systems锛�2014锛�568-576.顎� [26]Lecun Y锛孊oser B锛孌enker J S锛宔t al.Backpropagation Applied to Handwritten Zip Code Recognition[J].Neural Computation锛�2014锛�1(4)锛�541-551.顎� [27]Cheng G锛孡i Z锛孻ao X锛宔t al.Remote Sensing Image Scene Classification Using Bag of Convolutional Features[J].IEEE Geoscience and Remote Sensing Letters锛�2017锛�14(10)锛�1735-1739. [28]Cheng G锛孒an J锛孡u X.Remote Sensing Image Scene Classification锛欱enchmark and State of the Art[J].Proceedings of the IEEE锛�2017锛�105(10)锛�1865-1883.顎� [29]Cheng G锛孧a C锛孼hou P锛宔t al.Scene Classification of High Resolution Remote Sensing Images Using Convolutional Neural Networks[C]鈭EEE Geoscience and Remote Sensing Symposium锛�2016锛�767-770.顎� [30]Xiao J锛孒ays J锛孍hinger K A锛宔t al.SUN Database锛歀arge-scale Scene Recognition from Abbey to Zoo[C]鈭EEE Computer Vision and Pattern Recognition锛�2010锛�3485-3492.顎� [31]Szegedy C锛孡iu W锛孞ia Y锛宔t al.Going Deeper with Convolutions[C]鈭omputer Vision and Pattern Recognition.IEEE锛�2015锛�1-9.顎� [32]Lin M锛孋hen Q锛孻an S锛宔t al.Network in Network[C]鈭nternational Conference on Learning Representations锛�2014锛�1-10.顎� [33]Xia G S锛孒u J锛孒u F锛宔t al.AID锛欰 Benchmark Data Set for Performance Evaluation of Aerial Scene Classification[J].IEEE Transactions on Geoscience and Remote Sensing锛�2016锛�(99)锛�1-17.顎� [34]Ioffe S锛孲zegedy C.Batch Normalization锛欰ccelerating Deep Network Training by Reducing Internal Covariate Shift[J].2015锛�448-456.顎� [35]Szegedy C锛孷anhoucke V锛孖offe S锛宔t al.Rethinking the Inception Architecture for Computer Vision[C]鈭omputer Vision and Pattern Recognition Computer Science.IEEE锛�2016锛�2818-2826. [36]He K锛孼hang X锛孯en S锛宔t al.Deep Residual Learning for Image Recognition锛籆锛解垾Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition锛�2016锛�770-778. [37]Deng Z锛孡ei L锛孲un H锛宔t al.An Enhanced Deep Convolutional Neural Network for Densely Packed Objects Detection in Remote Sensing Images[C]鈭nternational Workshop on Remote Sensing with Intelligent Processing.IEEE锛�2017锛�1-4.顎� [38]Song X锛孌ai Y锛孮in X.Deep Depth Super-Resolution锛歀earning Depth Super-Resolution Using Deep Convolutional Neural Network[J].Computer Science Computer Vision and Pattern Recognition锛�2016锛�10114锛�360-376.顎� [39]Liu F锛孲hen C锛孡in G.Deep Convolutional Neural Fields for Depth Estimation from a Single Image[C]鈭� Computer Vision and Pattern Recognition.IEEE锛�2015锛�5162-5170.顎� [40]Deng J锛孌ong W锛孲ocher R锛宔t al.ImageNet锛欰 Large-scale Hierarchical Image Database[C]鈭EEE Conference on Computer Vision and Pattern Recognition锛�2009锛�248-255.顎� [41]Cheng G锛孼hou P锛孒an J.Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images[J].IEEE Transactions on Geoscience and Remote Sensing锛�2016锛�54(12)锛�7405-7415.顎� [42]Liu Y锛孼hong Y锛孎ei F锛宔t al.Scene Semantic Classification based on Random-scale Stretched Convolutional Neural Network for High-spatial Resolution Remote Sensing Imagery[C]鈭EEE Geoscience and Remote Sensing Symposium锛�2016锛�763-766.顎� [43]Tao Y锛孹u M锛孼hang F锛宔t al.Unsupervised-restricted Deconvolutional Neural Network for Very High Resolution Remote-Sensing Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing锛�2017锛�(99)锛�1-19.顎� [44]Fang Z锛孡i W锛孼ou J锛宔t al.Using CNN-based High-level Features for Remote Sensing Scene Classification[C]鈭EEE Geoscience and Remote Sensing Symposium锛�2016锛�2610-2613.顎� [45]Hu F锛孹ia G S锛孒u J锛宔t al.Transferring Deep Convolutional Neural Networks for the Scene Classification of High-resolution Remote Sensing Imagery[J].Remote Sensing锛�2015锛岊��7(11)锛氼��14680-14707.顎� [46]Nogueira K锛孭enatti O A B锛孲antos J A D.Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification[J].Pattern Recognition锛�2017锛�61锛�539-556. [47]Lu X锛孼heng X锛孻uan Y.Remote Sensing Scene Classification by Unsupervised Representation Learning[J].IEEE Transactions on Geoscience and Remote Sensing锛�2017锛�55(9)锛�5148-5157.顎� [48]Zeiler M D锛孠rishnan D锛孴aylor G W锛宔t al.Deconvolutional Networks[C]鈭� 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)锛�2010锛�2528-2535.顎� [49]Zeiler M D锛孴aylor G W锛孎ergus R.Adaptive Deconvolutional Networks for Mid and High Level Feature Learning[C]鈭EEE International Conference on Computer Vision锛�2011锛�2018-2025.顎� [50]Zeiler M D锛孎ergus R.Visualizing and Understanding Convolutional Networks[C]鈭uropean Conference on Computer Vision.Springer锛孋ham锛�2014锛�818-833.顎� [51]Long J锛孲helhamer E锛孌arrell T.Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence锛�2017锛�39(4)锛�640-651.顎� [52]Long J锛孲helhamer E锛孌arrell T.Fully Convolutional Networks for Semantic Segmentation[C]鈭EEE Computer Vision and Pattern Recognition锛�2015锛�3431-3440.顎� [53]Girshick R锛孌onahue J锛孌arrell T锛宔t al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]鈭EEE Conference on Computer Vision and Pattern Recognition锛�2014锛�580-587.顎� [53]Girshick R锛孌onahue J锛孌arrell T锛宔t al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]鈭EEE Computer Vision and Pattern Recognition锛�2014锛�580-587.顎� [54]Wang Yannan锛學ang Jianjian锛孏ong Jianxin锛宔t al.Random Forest Method based on the Classification of Land-covered Landforms based on Environmental Satellite Data[J].Remote Sensing Technology and Application锛�2016锛�31(6)锛�1107-1113.[鐜嬭壋妤狅紝鐜嬪仴鍋ワ紝榫氬仴鏂帮紝绛�.鍩轰簬鐜鍗槦鏁版嵁鐨勬部娴锋哗娑傚湴鐗╃被鍨嬪垎绫荤殑闅忔満妫灄鏂规硶[J].閬ユ劅鎶�鏈笌搴旂敤锛�2016锛�31(6)锛�1107-1113.]顎� [55]Yin Wenbin.Application of Convolution Neural Network in Remote Sensing Target Recognition[D].Beijing锛歎niversity of Chinese Academy of Sciences锛�2017.[娈锋枃鏂�.鍗风Н绁炵粡缃戠粶鍦ㄩ仴鎰熺洰鏍囪瘑鍒腑鐨勫簲鐢ㄧ爺绌禰D].鍖椾含锛氫腑鍥界瀛﹂櫌澶у锛�2017.]

[1]	鏋楁鎬�, 姹皬閽�, 姹ょ传闇�, 鏉庤挋钂�, 鍚寸憺濮�, 榛勫痉鍗�. 鍩轰簬闈㈠悜瀵硅薄CNN鍜孯F鐨勪笉鍚岀┖闂村垎杈ㄧ巼閬ユ劅褰卞儚鍐滀笟澶ф鎻愬彇鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(2): 315-327.
[2]	浣欓潚浣�, 鎽嗙帀榫�, 鑼冩弧绾�. 铻嶅悎鏀寔鍚戦噺鏈虹畻娉曠殑鏁版嵁椹卞姩鍨嬫暟鎹悓鍖栨柟娉曠爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(2): 381-392.
[3]	闄嗙編, 鏉庝匠鐢�, 鏉庢枃, 鑳℃槑娲�, 鏉ㄤ匠娆�. 铻嶅悎澶氬昂搴︿綆绉╄〃绀轰笌鍙屽悜閫掑綊婊ゆ尝鐨勯珮鍏夎氨鍥惧儚鍒嗙被[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(2): 393-404.
[4]	鑹鹃亽涓�,榛勫崕鍥�,閮,鍒樼偝鏉�,闄堟爲鏂�,鐢版槙. 鍩轰簬瀛敓娈嬪樊绁炵粡缃戠粶鐨凣F-2褰卞儚鏋楀湴鍙樺寲妫�娴�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(1): 24-33.
[5]	涔屽凹涔�,鍖呯帀榫�,甯冧粊鍥鹃泤,鍥惧竷鏂板反闆呭皵,闄惰禌鍠滈泤鎷夊浘,鍖呯帀娴�,閲戦灏斿痉鏈ㄥ悙. 鍩轰簬鏃犱汉鏈洪珮鍏夎氨閬ユ劅鐨勫吀鍨嬭崏鍘熼��鍖栨寚绀虹璇嗗埆[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(1): 248-258.
[6]	鍒樺嚡,鐜嬪瓙浜�,鏇规櫠鏅�. 鍩轰簬Landsat-8 OLI褰卞儚鍜屾寚鏁版硶鐨勭孩鏍戞灄鎻愬彇瀵规瘮鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(1): 55-66.
[7]	鍚磋櫣钃�,鏈卞矚宸�,浣欐亽,鏂藉啲. 鍩轰簬閬ユ劅鐨勬捣鍗楁湰宀涙琚 鐩栧害鏃剁┖鍙樺寲鍙婂叾鍦板舰鏁堝簲鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(5): 1062-1070.
[8]	澶忕背楹�,涓樹徊閿�,鑳℃櫒鎮�,榫欒壋姊�,璧靛啲鑷�,寤栧粨,鍚村埌鎳�. 鍩轰簬鑹插尮閰嶅嚱鏁扮殑鍗槦褰卞儚鐪熷僵鑹插悎鎴愮爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(5): 1092-1106.
[9]	椹畻鏂�,閮濆嚒,瀹嬬惓,楹荤憺. 涓�绉嶅浘鍍忓洖褰掍笌鍏宠仈鍏崇郴鐗瑰緛铻嶅悎鐨勯仴鎰熷奖鍍忓彉鍖栨娴嬫柟娉�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(5): 1215-1225.
[10]	鍞愭檾,鍒樺皬鐕�,宕旇��骞�,鍙插織鏂�,閭撲寒,闄堝噯. 鍩轰簬楂樺垎鍙鍏夐仴鎰熸寚鏁扮殑鍩庡競闃村奖楂樻晥鎻愬彇鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(4): 945-955.
[11]	鏇规枌,閮戞仼璁�,娌堥挧鎴�. 鍩轰簬绁炵粡缃戠粶娉ㄦ剰鍔涙灦鏋勬悳绱㈢殑鍏夊閬ユ劅鍥惧儚鍦烘櫙鍒嗙被[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(4): 913-923.
[12]	鏉庣拹,寮犻涓�,閭佃姼,榄忕鏂�,榛勭划鐞�,鐒﹂泤妤�. 鍩轰簬婊戝姩绐楀彛鐨勯珮鍒嗚鲸鐜嘢AR鍥惧儚鐐圭洰鏍囩Н鍒嗗搷搴旇兘閲忚绠楁柟娉曠爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(1): 182-189.
[13]	闄堝悏鑷�,寮犲悰,钖涗寒. 鍩轰簬澶滈棿鐏厜鏁版嵁鐨勯檿瑗跨渷鍘垮煙鐩稿璐洶姘村钩鏃剁┖宸紓鍒嗘瀽[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(4): 908-918.
[14]	鍚曞紑浜�,渚槶闃�,榫氬惊寮�,鏉ㄧ. 涓�绉嶅熀浜嶢SR鍜孭APCNN鐨凬SCT鍩熼仴鎰熷奖鍍忚瀺鍚堟柟娉�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(4): 829-838.
[15]	闅嬪啺娓�,娈峰織绁�,鍚撮箯娴�,鍚磋壋鍏�. 闈㈠悜浜戣鐩栫殑閬ユ劅褰卞儚鏃剁┖铻嶅悎娣卞害瀛︿範鏂规硶鍙婂叾搴旂敤[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(4): 800-810.

鍩轰簬CNN鐨勯珮鍒嗛仴鎰熷奖鍍忔繁搴﹁涔夌壒寰佹彁鍙栫爺绌剁患杩�

A Survey of Depth Semantic Feature Extraction of High-Resolution Remote Sensing Images based on CNN

PDF (PC)

鍙鍖�

鎽樿/Abstract

寮曠敤鏈枃

浣跨敤鏈枃

鍙傝�冩枃鐚�

鐩稿叧鏂囩珷 15

缂栬緫鎺ㄨ崘

Metrics

鏈枃璇勪环