Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity Measure
The emergence of very high resolution (VHR) images contributes to big challenges in change detection. It is hard for traditional pixel-level approaches to achieve satisfying performance due to radiometric difference. This work proposes a novel feature descriptor that is based on spectrum-trend and s...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/21/3606 |
| _version_ | 1797548994505736192 |
|---|---|
| author | Yi Tian Ming Hao Hua Zhang |
| author_facet | Yi Tian Ming Hao Hua Zhang |
| author_sort | Yi Tian |
| collection | DOAJ |
| description | The emergence of very high resolution (VHR) images contributes to big challenges in change detection. It is hard for traditional pixel-level approaches to achieve satisfying performance due to radiometric difference. This work proposes a novel feature descriptor that is based on spectrum-trend and shape context for VHR remote sensing images. The proposed method is mainly composed of two aspects. The spectrum-trend graph is generated first, and then the shape context is applied in order to describe the shape of spectrum-trend. By constructing spectrum-trend graph, spatial and spectral information is integrated effectively. The approach is performed and assessed by QuickBird and SPOT-5 satellite images. The quantitative analysis of comparative experiments proves the effectiveness of the proposed technique in dealing with the radiometric difference and improving the accuracy of change detection. The results indicate that the overall accuracy and robustness are both boosted. Moreover, this work provides a novel viewpoint for discriminating changed and unchanged pixels by comparing the shape similarity of local spectrum-trend. |
| first_indexed | 2024-03-10T15:08:34Z |
| format | Article |
| id | doaj.art-ef425db664c948ebb429a6cc03342cf2 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T15:08:34Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ef425db664c948ebb429a6cc03342cf22023-11-20T19:36:56ZengMDPI AGRemote Sensing2072-42922020-11-011221360610.3390/rs12213606Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity MeasureYi Tian0Ming Hao1Hua Zhang2MNR Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, ChinaMNR Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, ChinaMNR Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, ChinaThe emergence of very high resolution (VHR) images contributes to big challenges in change detection. It is hard for traditional pixel-level approaches to achieve satisfying performance due to radiometric difference. This work proposes a novel feature descriptor that is based on spectrum-trend and shape context for VHR remote sensing images. The proposed method is mainly composed of two aspects. The spectrum-trend graph is generated first, and then the shape context is applied in order to describe the shape of spectrum-trend. By constructing spectrum-trend graph, spatial and spectral information is integrated effectively. The approach is performed and assessed by QuickBird and SPOT-5 satellite images. The quantitative analysis of comparative experiments proves the effectiveness of the proposed technique in dealing with the radiometric difference and improving the accuracy of change detection. The results indicate that the overall accuracy and robustness are both boosted. Moreover, this work provides a novel viewpoint for discriminating changed and unchanged pixels by comparing the shape similarity of local spectrum-trend.https://www.mdpi.com/2072-4292/12/21/3606change detectionvery high resolution (VHR)spectrum-trendshape similarity |
| spellingShingle | Yi Tian Ming Hao Hua Zhang Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity Measure Remote Sensing change detection very high resolution (VHR) spectrum-trend shape similarity |
| title | Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity Measure |
| title_full | Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity Measure |
| title_fullStr | Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity Measure |
| title_full_unstemmed | Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity Measure |
| title_short | Unsupervised Change Detection Using Spectrum-Trend and Shape Similarity Measure |
| title_sort | unsupervised change detection using spectrum trend and shape similarity measure |
| topic | change detection very high resolution (VHR) spectrum-trend shape similarity |
| url | https://www.mdpi.com/2072-4292/12/21/3606 |
| work_keys_str_mv | AT yitian unsupervisedchangedetectionusingspectrumtrendandshapesimilaritymeasure AT minghao unsupervisedchangedetectionusingspectrumtrendandshapesimilaritymeasure AT huazhang unsupervisedchangedetectionusingspectrumtrendandshapesimilaritymeasure |