OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGES
In this paper a novel object-oriented change detection approach in multitemporal remote-sensing images is proposed. In order to improve post classification comparison (PCC) performance, we propose to exploit spatiotemporal relationship between two images acquired at two different times. The probabil...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2015-04-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-7-W3/1241/2015/isprsarchives-XL-7-W3-1241-2015.pdf |
| _version_ | 1817981489149640704 |
|---|---|
| author | L. Liang G. Ying X. Wen Y. Zhang |
| author_facet | L. Liang G. Ying X. Wen Y. Zhang |
| author_sort | L. Liang |
| collection | DOAJ |
| description | In this paper a novel object-oriented change detection approach in multitemporal remote-sensing images is proposed. In order to improve post classification comparison (PCC) performance, we propose to exploit spatiotemporal relationship between two images acquired at two different times. The probabilities of class transitions are used to describe the temporal dependence information, while the Markov Random Field (MRF) model is utilized to represent the spatial-contextual information. Training sets are required to get initial classification results b maximum likelihood method (ML). Then an estimation procedure: iterated conditional mode (ICM) is present to revise the classification results. Change detection (change/no change) and change type recognitions (from-to types of change) are achieved by compare classification maps acquired at two different times. Experimental results on two QuickBird images confirm that the proposee method can provide higher accuracy than the PCC method, which ignores spatiotemporal relationship between two images. |
| first_indexed | 2024-04-13T23:07:47Z |
| format | Article |
| id | doaj.art-d65277c733eb44308b4f75b81662b202 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-04-13T23:07:47Z |
| publishDate | 2015-04-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-d65277c733eb44308b4f75b81662b2022022-12-22T02:25:39ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342015-04-01XL-7/W31241124810.5194/isprsarchives-XL-7-W3-1241-2015OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGESL. Liang0G. Ying1X. Wen2Y. Zhang3The Third Academy of Engineering of Surveying and Mapping, 2 Xinjun Road, 610500 Chengdu, ChinaGeographic National Condition Monitoring Engineering Research Center of Sichuan Province, 2 Xinjun Road, 610500 Chengdu, ChinaGeographic National Condition Monitoring Engineering Research Center of Sichuan Province, 2 Xinjun Road, 610500 Chengdu, ChinaGeographic National Condition Monitoring Engineering Research Center of Sichuan Province, 2 Xinjun Road, 610500 Chengdu, ChinaIn this paper a novel object-oriented change detection approach in multitemporal remote-sensing images is proposed. In order to improve post classification comparison (PCC) performance, we propose to exploit spatiotemporal relationship between two images acquired at two different times. The probabilities of class transitions are used to describe the temporal dependence information, while the Markov Random Field (MRF) model is utilized to represent the spatial-contextual information. Training sets are required to get initial classification results b maximum likelihood method (ML). Then an estimation procedure: iterated conditional mode (ICM) is present to revise the classification results. Change detection (change/no change) and change type recognitions (from-to types of change) are achieved by compare classification maps acquired at two different times. Experimental results on two QuickBird images confirm that the proposee method can provide higher accuracy than the PCC method, which ignores spatiotemporal relationship between two images.http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-7-W3/1241/2015/isprsarchives-XL-7-W3-1241-2015.pdf |
| spellingShingle | L. Liang G. Ying X. Wen Y. Zhang OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGES The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGES |
| title_full | OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGES |
| title_fullStr | OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGES |
| title_full_unstemmed | OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGES |
| title_short | OBJECT-ORIENTED CHANGE DETECTION BASED ON SPATIOTEMPORAL RELATIONSHIP IN MULTITEMPORAL REMOTE-SENSING IMAGES |
| title_sort | object oriented change detection based on spatiotemporal relationship in multitemporal remote sensing images |
| url | http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-7-W3/1241/2015/isprsarchives-XL-7-W3-1241-2015.pdf |
| work_keys_str_mv | AT lliang objectorientedchangedetectionbasedonspatiotemporalrelationshipinmultitemporalremotesensingimages AT gying objectorientedchangedetectionbasedonspatiotemporalrelationshipinmultitemporalremotesensingimages AT xwen objectorientedchangedetectionbasedonspatiotemporalrelationshipinmultitemporalremotesensingimages AT yzhang objectorientedchangedetectionbasedonspatiotemporalrelationshipinmultitemporalremotesensingimages |