Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement
Change detection is an important task in identifying land cover change in different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects the performance of change detection. To improve the accuracy of change detection, a novel...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/18/3697 |
| _version_ | 1797517337710034944 |
|---|---|
| author | Liangliang Li Hongbing Ma Zhenhong Jia |
| author_facet | Liangliang Li Hongbing Ma Zhenhong Jia |
| author_sort | Liangliang Li |
| collection | DOAJ |
| description | Change detection is an important task in identifying land cover change in different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects the performance of change detection. To improve the accuracy of change detection, a novel automatic SAR image change detection algorithm based on saliency detection and convolutional-wavelet neural networks is proposed. The log-ratio operator is adopted to generate the difference image, and the speckle reducing anisotropic diffusion is used to enhance the original multitemporal SAR images and the difference image. To reduce the influence of speckle noise, the salient area that probably belongs to the changed object is obtained from the difference image. The saliency analysis step can remove small noise regions by thresholding the saliency map, and interest regions can be preserved. Then an enhanced difference image is generated by combing the binarized saliency map and two input images. A hierarchical fuzzy c-means model is applied to the enhanced difference image to classify pixels into the changed, unchanged, and intermediate regions. The convolutional-wavelet neural networks are used to generate the final change map. Experimental results on five SAR data sets indicated the proposed approach provided good performance in change detection compared to state-of-the-art relative techniques, and the values of the metrics computed by the proposed method caused significant improvement. |
| first_indexed | 2024-03-10T07:15:15Z |
| format | Article |
| id | doaj.art-40e751e011ea4b30a9216bfc6485f857 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T07:15:15Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-40e751e011ea4b30a9216bfc6485f8572023-11-22T15:06:59ZengMDPI AGRemote Sensing2072-42922021-09-011318369710.3390/rs13183697Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency EnhancementLiangliang Li0Hongbing Ma1Zhenhong Jia2Department of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaChange detection is an important task in identifying land cover change in different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects the performance of change detection. To improve the accuracy of change detection, a novel automatic SAR image change detection algorithm based on saliency detection and convolutional-wavelet neural networks is proposed. The log-ratio operator is adopted to generate the difference image, and the speckle reducing anisotropic diffusion is used to enhance the original multitemporal SAR images and the difference image. To reduce the influence of speckle noise, the salient area that probably belongs to the changed object is obtained from the difference image. The saliency analysis step can remove small noise regions by thresholding the saliency map, and interest regions can be preserved. Then an enhanced difference image is generated by combing the binarized saliency map and two input images. A hierarchical fuzzy c-means model is applied to the enhanced difference image to classify pixels into the changed, unchanged, and intermediate regions. The convolutional-wavelet neural networks are used to generate the final change map. Experimental results on five SAR data sets indicated the proposed approach provided good performance in change detection compared to state-of-the-art relative techniques, and the values of the metrics computed by the proposed method caused significant improvement.https://www.mdpi.com/2072-4292/13/18/3697synthetic aperture radar imagechange detectionsaliency detectionconvolutional-wavelet neural networkshierarchical fuzzy c-means |
| spellingShingle | Liangliang Li Hongbing Ma Zhenhong Jia Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement Remote Sensing synthetic aperture radar image change detection saliency detection convolutional-wavelet neural networks hierarchical fuzzy c-means |
| title | Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement |
| title_full | Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement |
| title_fullStr | Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement |
| title_full_unstemmed | Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement |
| title_short | Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement |
| title_sort | change detection from sar images based on convolutional neural networks guided by saliency enhancement |
| topic | synthetic aperture radar image change detection saliency detection convolutional-wavelet neural networks hierarchical fuzzy c-means |
| url | https://www.mdpi.com/2072-4292/13/18/3697 |
| work_keys_str_mv | AT liangliangli changedetectionfromsarimagesbasedonconvolutionalneuralnetworksguidedbysaliencyenhancement AT hongbingma changedetectionfromsarimagesbasedonconvolutionalneuralnetworksguidedbysaliencyenhancement AT zhenhongjia changedetectionfromsarimagesbasedonconvolutionalneuralnetworksguidedbysaliencyenhancement |