Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel Convolution
Remote sensing image change detection method plays a great role in land cover research, disaster assessment, medical diagnosis, video surveillance, and other fields, so it has attracted wide attention. Based on a small sample dataset from SZTAKI AirChange Benchmark Set, in order to solve the problem...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9291461/ |
| _version_ | 1818643694353383424 |
|---|---|
| author | Xin Luo Xiaoxi Li Yuxuan Wu Weimin Hou Meng Wang Yuwei Jin Wenbo Xu |
| author_facet | Xin Luo Xiaoxi Li Yuxuan Wu Weimin Hou Meng Wang Yuwei Jin Wenbo Xu |
| author_sort | Xin Luo |
| collection | DOAJ |
| description | Remote sensing image change detection method plays a great role in land cover research, disaster assessment, medical diagnosis, video surveillance, and other fields, so it has attracted wide attention. Based on a small sample dataset from SZTAKI AirChange Benchmark Set, in order to solve the problem that the deep learning network needs a large number of samples, this work first uses nongenerative sample augmentation method and generative sample augmentation method based on deep convolutional generative adversarial networks, and then, constructs a remote sensing image change detection model based on an improved DeepLabv3+ network. This model can realize end-to-end training and prediction of remote sensing image change detection with subpixel convolution. Finally, Landsat 8, Google Earth, and Onera satellite change detection datasets are used to verify the generalization performance of this network. The experimental results show that the improved network accuracy is 95.1% and the generalization performance is acceptable. |
| first_indexed | 2024-12-17T00:03:01Z |
| format | Article |
| id | doaj.art-904adabfb97a4a1abb09f796c815be67 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-17T00:03:01Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-904adabfb97a4a1abb09f796c815be672022-12-21T22:11:02ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01141447145710.1109/JSTARS.2020.30440609291461Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel ConvolutionXin Luo0https://orcid.org/0000-0002-9534-592XXiaoxi Li1https://orcid.org/0000-0002-7062-8747Yuxuan Wu2https://orcid.org/0000-0002-2705-1663Weimin Hou3https://orcid.org/0000-0003-0956-7057Meng Wang4Yuwei Jin5Wenbo Xu6School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaRemote sensing image change detection method plays a great role in land cover research, disaster assessment, medical diagnosis, video surveillance, and other fields, so it has attracted wide attention. Based on a small sample dataset from SZTAKI AirChange Benchmark Set, in order to solve the problem that the deep learning network needs a large number of samples, this work first uses nongenerative sample augmentation method and generative sample augmentation method based on deep convolutional generative adversarial networks, and then, constructs a remote sensing image change detection model based on an improved DeepLabv3+ network. This model can realize end-to-end training and prediction of remote sensing image change detection with subpixel convolution. Finally, Landsat 8, Google Earth, and Onera satellite change detection datasets are used to verify the generalization performance of this network. The experimental results show that the improved network accuracy is 95.1% and the generalization performance is acceptable.https://ieeexplore.ieee.org/document/9291461/Change detectionDeepLabv3+deep convolutional generative adversarial networks (DCGAN)deep learningsubpixel convolution |
| spellingShingle | Xin Luo Xiaoxi Li Yuxuan Wu Weimin Hou Meng Wang Yuwei Jin Wenbo Xu Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel Convolution IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection DeepLabv3+ deep convolutional generative adversarial networks (DCGAN) deep learning subpixel convolution |
| title | Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel Convolution |
| title_full | Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel Convolution |
| title_fullStr | Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel Convolution |
| title_full_unstemmed | Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel Convolution |
| title_short | Research on Change Detection Method of High-Resolution Remote Sensing Images Based on Subpixel Convolution |
| title_sort | research on change detection method of high resolution remote sensing images based on subpixel convolution |
| topic | Change detection DeepLabv3+ deep convolutional generative adversarial networks (DCGAN) deep learning subpixel convolution |
| url | https://ieeexplore.ieee.org/document/9291461/ |
| work_keys_str_mv | AT xinluo researchonchangedetectionmethodofhighresolutionremotesensingimagesbasedonsubpixelconvolution AT xiaoxili researchonchangedetectionmethodofhighresolutionremotesensingimagesbasedonsubpixelconvolution AT yuxuanwu researchonchangedetectionmethodofhighresolutionremotesensingimagesbasedonsubpixelconvolution AT weiminhou researchonchangedetectionmethodofhighresolutionremotesensingimagesbasedonsubpixelconvolution AT mengwang researchonchangedetectionmethodofhighresolutionremotesensingimagesbasedonsubpixelconvolution AT yuweijin researchonchangedetectionmethodofhighresolutionremotesensingimagesbasedonsubpixelconvolution AT wenboxu researchonchangedetectionmethodofhighresolutionremotesensingimagesbasedonsubpixelconvolution |