| 833 | 19 | 142 |
| 下载次数 | 被引频次 | 阅读次数 |
为了同时精确获取变化区域和地物类别的变化信息,提出一种基于Siam-DeepLabv3+网络的遥感影像语义变化检测方法。首先利用孪生化的ResNet50作为编码器分别提取前后时期影像的特征;其次利用ASPP模块提取影像中多尺度特征,对多尺度特征进行相似性度量;然后将编码器中获取的低层特征与多尺度特征、相似性度量特征叠加输入至解码器,获得前后时期遥感影像地物变化类别;最后利用形态学图像处理方法中膨胀及腐蚀操作消除因影像配准精度不高而可能造成的伪变化。实验结果表明,Siam-DeepLabv3+网络的地物分类结果精度高于传统语义分割网络,对地物类别进行对比获得初始变化检测结果,经过形态学后处理,最终得到的变化检测结果精度高于对比方法,且带有地物类别变化信息。
Abstract：In order to accurately detect change area and provide the category information of the ground feature change, a semantic change detection method for remote sensing image based on Siam-DeepLabv3+ network is proposed in the paper. Firstly, Siamese ResNet50 is used as the encoder to extract the features of the images before and after the period. Secondly, the ASPP module is used to extract the multi-scale features in the image, and the similarity measurement of the multi-scale features is carried out. Then, the low-level features obtained from the encoder are superimposed to input to the decoder with the multi-scale features. Finally, the expansion and erosion operations in morphological image processing method are used to eliminate the false changes caused by the low accuracy of image registration. The experimental results show that the accuracy of the classification results of Siam-DeepLabv3+ network is higher than that of traditional semantic segmentation network, and the initial change detection results are obtained by comparing the surface feature categories. After morphological post-processing, the accuracy of the final change detection results are better than that of the comparison method, which contain the change information of surface feature categories.
[1] ZHOU J,YU B,QIN J.Multi-level spatial analysis for change detection of urban vegetation at individual tree scale[J].Remote Sensing,2014,6(9):9086-9103.
[2] MALMIR M,ZARKESH M,MONAVARI S,et al.Urban development change detection based on multi-temporal satellite images as a fast tracking approach:A case study of Ahwaz county,Southwestern Iran[J].Environmental Monitoring and Assessment,2015,187(3):108-117.
[3] 慕春芳.高分辨率图像变化检测及其在应急灾害评估中的应用研究[D].哈尔滨：哈尔滨工业大学，2011:1-76.MU C F.Study on high resolution image change detection and its application in the emergency disaster evaluation[D].Harbin:Harbin Institute of Technology,2011:1-76.
[4] YANG K,XIA G S,LIU Z,et al.Asymmetric siamese networks for semantic change detection[C]// Proceedings of 2020 IEEE Conference on Computer Vision and Pattern Recognition.Seattle,USA,2020:1-15.
[5] 张良培，武辰.多时相遥感影像变化检测的现状与展望[J].测绘学报，2017,46(10):1447-1459.ZHANG L P,WU C.Advance and future development of change detection for multi-temporal remote sensing imagery[J].Acta Geodaetica et Cartographica Sinica,2017,46(10):1447-1459.
[6] 吴瑞娟，何秀凤.高分雷达与光学影像融合的滨海湿地变化检测[J].测绘科学，2020,45(11):93-100.WU R J,HE X F.Coastal wetland change detection using fusion of high resolution radar and optical images[J].Science of Surveying and Mapping,2020,45(11):93-100.
[7] 宋业冲，李英成，耿中元，等.深度学习方法在光伏用地遥感检测中的应用[J].测绘科学，2020,45(11):84-92.SONG Y C,LI Y C,GENG Z Y,et al.Application of deep learning method in remote sensing detection of photovoltaic land[J].Science of Surveying and Mapping,2020,45(11):84-92.
[8] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Cham,Germany,2015:234-241.
[9] ZHOU Z,SIDDIQUEE M,TAJBAKHSH N,et al.UNet++:A nested U-Net architecture for medical image segmentation[C]// 4th Deep Learning in Medical Image Analysis Workshop.Granada,Spain,2018:3-11.
[10] JATURAPITPORNCHAI R,MATSUOKA M,KANEMOTO N,et al.Newly built construction detection in SAR images using deep learning[J].Remote Sensing,2019,11(12):1444.
[11] ZHANG C X,YUE P,DEODATO T,et al.A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,166:183-200.
[12] CHEN J,YUAN Z,PENG J,et al.DASNet:Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,14:1194-1206.
[13] FANG S,LI K,SHAO J,et al.SNUNet-CD:A densely connected siamese network for change detection of VHR images[J].IEEE Geoscience and Remote Sensing Letters,2021(99):1-5.
[14] CHEN H,SHI Z.A spatial-temporal attention-based method and a new dataset for remote sensing image change detection[J].Remote Sensing,2020,12(10):1662.
[15] DAUDT R C,SAUX B L,BOULCH A,et al.Multitask learning for large-scale semantic change detection[J/OL].Computer Vision and Image Understanding,2019.https://arxiv.org/abs/1810.08452.
[16] CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of The European Conference on Computer Vision.Munich,Germany,2018:801-818.
[17] CHOPRA S,HADSELL R,LECUN Y.Learning a similarity metric discriminatively,with application to face verification[C]// 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,USA,2005:539-546.
[18] NAIR V,HINTON G E.Rectified linear units improve restricted boltzmann machines vinod nair[C]// International Conference on International Conference on Machine Learning.Haifa,Israel,2010:807-814.
基本信息:
DOI：
中图分类号:P237
引用信息:
[1]郭海涛,卢俊,袁洲等.Siam-DeepLabv3+网络遥感影像语义变化检测方法[J].测绘科学技术学报,2021,38(06):597-603.
基金信息:
国家自然科学基金项目(4187610;41671410)