A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images
Characterizations of up to date information of the Earth’s surface are an important application providing insights to urban planning, resources monitoring and environmental studies. A large number of change detection (CD) methods have been developed to solve them by utilizing remote sensing (RS) ima...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/9/1377 |
| _version_ | 1811277981367140352 |
|---|---|
| author | Bin Hou Yunhong Wang Qingjie Liu |
| author_facet | Bin Hou Yunhong Wang Qingjie Liu |
| author_sort | Bin Hou |
| collection | DOAJ |
| description | Characterizations of up to date information of the Earth’s surface are an important application providing insights to urban planning, resources monitoring and environmental studies. A large number of change detection (CD) methods have been developed to solve them by utilizing remote sensing (RS) images. The advent of high resolution (HR) remote sensing images further provides challenges to traditional CD methods and opportunities to object-based CD methods. While several kinds of geospatial objects are recognized, this manuscript mainly focuses on buildings. Specifically, we propose a novel automatic approach combining pixel-based strategies with object-based ones for detecting building changes with HR remote sensing images. A multiresolution contextual morphological transformation called extended morphological attribute profiles (EMAPs) allows the extraction of geometrical features related to the structures within the scene at different scales. Pixel-based post-classification is executed on EMAPs using hierarchical fuzzy clustering. Subsequently, the hierarchical fuzzy frequency vector histograms are formed based on the image-objects acquired by simple linear iterative clustering (SLIC) segmentation. Then, saliency and morphological building index (MBI) extracted on difference images are used to generate a pseudo training set. Ultimately, object-based semi-supervised classification is implemented on this training set by applying random forest (RF). Most of the important changes are detected by the proposed method in our experiments. This study was checked for effectiveness using visual evaluation and numerical evaluation. |
| first_indexed | 2024-04-13T00:26:33Z |
| format | Article |
| id | doaj.art-425dec31fe4443d0a8016ca4b0dc675b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T00:26:33Z |
| publishDate | 2016-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-425dec31fe4443d0a8016ca4b0dc675b2022-12-22T03:10:35ZengMDPI AGSensors1424-82202016-08-01169137710.3390/s16091377s16091377A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing ImagesBin Hou0Yunhong Wang1Qingjie Liu2State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, ChinaState Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, ChinaState Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, ChinaCharacterizations of up to date information of the Earth’s surface are an important application providing insights to urban planning, resources monitoring and environmental studies. A large number of change detection (CD) methods have been developed to solve them by utilizing remote sensing (RS) images. The advent of high resolution (HR) remote sensing images further provides challenges to traditional CD methods and opportunities to object-based CD methods. While several kinds of geospatial objects are recognized, this manuscript mainly focuses on buildings. Specifically, we propose a novel automatic approach combining pixel-based strategies with object-based ones for detecting building changes with HR remote sensing images. A multiresolution contextual morphological transformation called extended morphological attribute profiles (EMAPs) allows the extraction of geometrical features related to the structures within the scene at different scales. Pixel-based post-classification is executed on EMAPs using hierarchical fuzzy clustering. Subsequently, the hierarchical fuzzy frequency vector histograms are formed based on the image-objects acquired by simple linear iterative clustering (SLIC) segmentation. Then, saliency and morphological building index (MBI) extracted on difference images are used to generate a pseudo training set. Ultimately, object-based semi-supervised classification is implemented on this training set by applying random forest (RF). Most of the important changes are detected by the proposed method in our experiments. This study was checked for effectiveness using visual evaluation and numerical evaluation.http://www.mdpi.com/1424-8220/16/9/1377change detectionremote sensingextended morphological attribute profilessaliencymorphological building index |
| spellingShingle | Bin Hou Yunhong Wang Qingjie Liu A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images Sensors change detection remote sensing extended morphological attribute profiles saliency morphological building index |
| title | A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images |
| title_full | A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images |
| title_fullStr | A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images |
| title_full_unstemmed | A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images |
| title_short | A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images |
| title_sort | saliency guided semi supervised building change detection method for high resolution remote sensing images |
| topic | change detection remote sensing extended morphological attribute profiles saliency morphological building index |
| url | http://www.mdpi.com/1424-8220/16/9/1377 |
| work_keys_str_mv | AT binhou asaliencyguidedsemisupervisedbuildingchangedetectionmethodforhighresolutionremotesensingimages AT yunhongwang asaliencyguidedsemisupervisedbuildingchangedetectionmethodforhighresolutionremotesensingimages AT qingjieliu asaliencyguidedsemisupervisedbuildingchangedetectionmethodforhighresolutionremotesensingimages AT binhou saliencyguidedsemisupervisedbuildingchangedetectionmethodforhighresolutionremotesensingimages AT yunhongwang saliencyguidedsemisupervisedbuildingchangedetectionmethodforhighresolutionremotesensingimages AT qingjieliu saliencyguidedsemisupervisedbuildingchangedetectionmethodforhighresolutionremotesensingimages |