SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network
Change Detection in heterogeneous remote sensing images plays an increasingly essential role in many real-world applications, e.g., urban growth tracking, land use monitoring, disaster evaluation and damage assessment. The objective of change detection is to identify changes of geo-graphical entitie...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/18/3750 |
| _version_ | 1797517339361542144 |
|---|---|
| author | Ruizhe Shao Chun Du Hao Chen Jun Li |
| author_facet | Ruizhe Shao Chun Du Hao Chen Jun Li |
| author_sort | Ruizhe Shao |
| collection | DOAJ |
| description | Change Detection in heterogeneous remote sensing images plays an increasingly essential role in many real-world applications, e.g., urban growth tracking, land use monitoring, disaster evaluation and damage assessment. The objective of change detection is to identify changes of geo-graphical entities or phenomena through two or more bitemporal images. Researchers have invested a lot in the homologous change detection and yielded fruitful results. However, change detection between heterogenous remote sensing images is still a great challenge, especially for change detection of heterogenous remote sensing images obtained from satellites and Unmanned Aerial Vehicles (UAV). The main challenges in satellite-UAV change detection tasks lie in the intensive difference of color for the same ground objects, various resolutions, the parallax effect and image distortion caused by different shooting angles and platform altitudes. To address these issues, we propose a novel method based on dual-channel fully convolution network. First, in order to alleviate the influence of differences between heterogeneous images, we employ two different channels to map heterogeneous remote sensing images from satellite and UAV, respectively, to a mutual high dimension latent space for the downstream change detection task. Second, we adopt Hough method to extract the edge of ground objects as auxiliary information to help the change detection model to pay more attention to shapes and contours, instead of colors. Then, IoU-WCE loss is designed to deal with the problem of imbalanced samples in change detection task. Finally, we conduct extensive experiments to verify the proposed method using a new Satellite-UAV heterogeneous image data set, named HTCD, which is annotated by us and has been open to public. The experimental results show that our method significantly outperforms the state-of-the-art change detection methods. |
| first_indexed | 2024-03-10T07:14:20Z |
| format | Article |
| id | doaj.art-4a3aab491b294347be40effc231ebb4a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T07:14:20Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4a3aab491b294347be40effc231ebb4a2023-11-22T15:07:46ZengMDPI AGRemote Sensing2072-42922021-09-011318375010.3390/rs13183750SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution NetworkRuizhe Shao0Chun Du1Hao Chen2Jun Li3Department of Cognitive Communication, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410000, ChinaDepartment of Cognitive Communication, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410000, ChinaDepartment of Cognitive Communication, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410000, ChinaDepartment of Cognitive Communication, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410000, ChinaChange Detection in heterogeneous remote sensing images plays an increasingly essential role in many real-world applications, e.g., urban growth tracking, land use monitoring, disaster evaluation and damage assessment. The objective of change detection is to identify changes of geo-graphical entities or phenomena through two or more bitemporal images. Researchers have invested a lot in the homologous change detection and yielded fruitful results. However, change detection between heterogenous remote sensing images is still a great challenge, especially for change detection of heterogenous remote sensing images obtained from satellites and Unmanned Aerial Vehicles (UAV). The main challenges in satellite-UAV change detection tasks lie in the intensive difference of color for the same ground objects, various resolutions, the parallax effect and image distortion caused by different shooting angles and platform altitudes. To address these issues, we propose a novel method based on dual-channel fully convolution network. First, in order to alleviate the influence of differences between heterogeneous images, we employ two different channels to map heterogeneous remote sensing images from satellite and UAV, respectively, to a mutual high dimension latent space for the downstream change detection task. Second, we adopt Hough method to extract the edge of ground objects as auxiliary information to help the change detection model to pay more attention to shapes and contours, instead of colors. Then, IoU-WCE loss is designed to deal with the problem of imbalanced samples in change detection task. Finally, we conduct extensive experiments to verify the proposed method using a new Satellite-UAV heterogeneous image data set, named HTCD, which is annotated by us and has been open to public. The experimental results show that our method significantly outperforms the state-of-the-art change detection methods.https://www.mdpi.com/2072-4292/13/18/3750change detectionremote sensingheterogeneous imagesdeep learningfully convolution network |
| spellingShingle | Ruizhe Shao Chun Du Hao Chen Jun Li SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network Remote Sensing change detection remote sensing heterogeneous images deep learning fully convolution network |
| title | SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network |
| title_full | SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network |
| title_fullStr | SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network |
| title_full_unstemmed | SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network |
| title_short | SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network |
| title_sort | sunet change detection for heterogeneous remote sensing images from satellite and uav using a dual channel fully convolution network |
| topic | change detection remote sensing heterogeneous images deep learning fully convolution network |
| url | https://www.mdpi.com/2072-4292/13/18/3750 |
| work_keys_str_mv | AT ruizheshao sunetchangedetectionforheterogeneousremotesensingimagesfromsatelliteanduavusingadualchannelfullyconvolutionnetwork AT chundu sunetchangedetectionforheterogeneousremotesensingimagesfromsatelliteanduavusingadualchannelfullyconvolutionnetwork AT haochen sunetchangedetectionforheterogeneousremotesensingimagesfromsatelliteanduavusingadualchannelfullyconvolutionnetwork AT junli sunetchangedetectionforheterogeneousremotesensingimagesfromsatelliteanduavusingadualchannelfullyconvolutionnetwork |