A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images
The very high spatial resolution (VHR) remote sensing images have been an extremely valuable source for monitoring changes occurring on the Earth’s surface. However, precisely detecting relevant changes in VHR images still remains a challenge, due to the complexity of the relationships among ground...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/694 |
| _version_ | 1797623322822836224 |
|---|---|
| author | Junzheng Wu Ruigang Fu Qiang Liu Weiping Ni Kenan Cheng Biao Li Yuli Sun |
| author_facet | Junzheng Wu Ruigang Fu Qiang Liu Weiping Ni Kenan Cheng Biao Li Yuli Sun |
| author_sort | Junzheng Wu |
| collection | DOAJ |
| description | The very high spatial resolution (VHR) remote sensing images have been an extremely valuable source for monitoring changes occurring on the Earth’s surface. However, precisely detecting relevant changes in VHR images still remains a challenge, due to the complexity of the relationships among ground objects. To address this limitation, a dual neighborhood hypergraph neural network is proposed in this article, which combines multiscale superpixel segmentation and hypergraph convolution to model and exploit the complex relationships. First, the bi-temporal image pairs are segmented under two scales and fed to a pre-trained U-net to obtain node features by treating each object under the fine scale as a node. The dual neighborhood is then defined using the father-child and adjacent relationships of the segmented objects to construct the hypergraph, which permits models to represent higher-order structured information far more complex than the conventional pairwise relationships. The hypergraph convolutions are conducted on the constructed hypergraph to propagate the label information from a small amount of labeled nodes to the other unlabeled ones by the node-edge-node transformation. Moreover, to alleviate the problem of imbalanced sampling, the focal loss function is adopted to train the hypergraph neural network. The experimental results on optical, SAR and heterogeneous optical/SAR data sets demonstrate that the proposed method offersbetter effectiveness and robustness compared to many state-of-the-art methods. |
| first_indexed | 2024-03-11T09:27:08Z |
| format | Article |
| id | doaj.art-4ed9c92228a140379b9be152cbca09f1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:08Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4ed9c92228a140379b9be152cbca09f12023-11-16T17:52:54ZengMDPI AGRemote Sensing2072-42922023-01-0115369410.3390/rs15030694A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing ImagesJunzheng Wu0Ruigang Fu1Qiang Liu2Weiping Ni3Kenan Cheng4Biao Li5Yuli Sun6College of Electronic Science, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science, National University of Defense Technology, Changsha 410073, ChinaNorthwest Institute of Nuclear Technology, Xi’an 710024, ChinaNorthwest Institute of Nuclear Technology, Xi’an 710024, ChinaNorthwest Institute of Nuclear Technology, Xi’an 710024, ChinaCollege of Electronic Science, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science, National University of Defense Technology, Changsha 410073, ChinaThe very high spatial resolution (VHR) remote sensing images have been an extremely valuable source for monitoring changes occurring on the Earth’s surface. However, precisely detecting relevant changes in VHR images still remains a challenge, due to the complexity of the relationships among ground objects. To address this limitation, a dual neighborhood hypergraph neural network is proposed in this article, which combines multiscale superpixel segmentation and hypergraph convolution to model and exploit the complex relationships. First, the bi-temporal image pairs are segmented under two scales and fed to a pre-trained U-net to obtain node features by treating each object under the fine scale as a node. The dual neighborhood is then defined using the father-child and adjacent relationships of the segmented objects to construct the hypergraph, which permits models to represent higher-order structured information far more complex than the conventional pairwise relationships. The hypergraph convolutions are conducted on the constructed hypergraph to propagate the label information from a small amount of labeled nodes to the other unlabeled ones by the node-edge-node transformation. Moreover, to alleviate the problem of imbalanced sampling, the focal loss function is adopted to train the hypergraph neural network. The experimental results on optical, SAR and heterogeneous optical/SAR data sets demonstrate that the proposed method offersbetter effectiveness and robustness compared to many state-of-the-art methods.https://www.mdpi.com/2072-4292/15/3/694change detectionhypergraph neural networkdual neighborhoodsemisupervisedremote sensing images |
| spellingShingle | Junzheng Wu Ruigang Fu Qiang Liu Weiping Ni Kenan Cheng Biao Li Yuli Sun A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images Remote Sensing change detection hypergraph neural network dual neighborhood semisupervised remote sensing images |
| title | A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images |
| title_full | A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images |
| title_fullStr | A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images |
| title_full_unstemmed | A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images |
| title_short | A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images |
| title_sort | dual neighborhood hypergraph neural network for change detection in vhr remote sensing images |
| topic | change detection hypergraph neural network dual neighborhood semisupervised remote sensing images |
| url | https://www.mdpi.com/2072-4292/15/3/694 |
| work_keys_str_mv | AT junzhengwu adualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT ruigangfu adualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT qiangliu adualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT weipingni adualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT kenancheng adualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT biaoli adualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT yulisun adualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT junzhengwu dualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT ruigangfu dualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT qiangliu dualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT weipingni dualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT kenancheng dualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT biaoli dualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages AT yulisun dualneighborhoodhypergraphneuralnetworkforchangedetectioninvhrremotesensingimages |