Focused information learning method for change detection based on segmentation with limited annotations
Recent advancements have significantly improved the field of segmentation-based change detection, particularly in the context of remote-sensing images. However, change detection datasets generally lack segmentation annotations, and the required labeling process is resource-intensive. We propose an i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-05-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843224001936 |
| _version_ | 1797203028297646080 |
|---|---|
| author | H. Ahn S. Chung S. Park D. Kim |
| author_facet | H. Ahn S. Chung S. Park D. Kim |
| author_sort | H. Ahn |
| collection | DOAJ |
| description | Recent advancements have significantly improved the field of segmentation-based change detection, particularly in the context of remote-sensing images. However, change detection datasets generally lack segmentation annotations, and the required labeling process is resource-intensive. We propose an improved change detection method based on segmentation to address this challenge. First, change detection annotations are converted to incomplete segmentation annotations through label matching. During segmentation, we utilize the focused information-guided segmentation method (FIGS) and a greenness index to provide prior information during training, guiding the model using accurately labeled regions. Finally, we generate a change map using pretrained features obtained from the segmentation stage. We demonstrate the robustness of our proposed label-matching process by comparing the results to a correctly matched dataset and show that incorporating FIGS and the greenness index improves the segmentation performance. Our method achieves effective change detection results even in scenarios associated with a shortage of annotations. |
| first_indexed | 2024-04-24T08:12:49Z |
| format | Article |
| id | doaj.art-65d6c8a776cd4d8786099e90246dbbc4 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-24T08:12:49Z |
| publishDate | 2024-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-65d6c8a776cd4d8786099e90246dbbc42024-04-17T04:48:56ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-05-01129103839Focused information learning method for change detection based on segmentation with limited annotationsH. Ahn0S. Chung1S. Park2D. Kim3Korea Aerospace Research Institute, 169-84 Gwahakro, Daejeon 34133, Republic of Korea; University of Science and Technology, 217 Gajeong-ro, Yuseong-gu, Daejeon 34113, Republic of Korea; Corresponding author.University of California, Irvine, CA 92697, United StatesDexterous Technology 582, Daedeok-daero, Yuseong-gu, Daejeon 34121, Republic of KoreaDexterous Technology 582, Daedeok-daero, Yuseong-gu, Daejeon 34121, Republic of KoreaRecent advancements have significantly improved the field of segmentation-based change detection, particularly in the context of remote-sensing images. However, change detection datasets generally lack segmentation annotations, and the required labeling process is resource-intensive. We propose an improved change detection method based on segmentation to address this challenge. First, change detection annotations are converted to incomplete segmentation annotations through label matching. During segmentation, we utilize the focused information-guided segmentation method (FIGS) and a greenness index to provide prior information during training, guiding the model using accurately labeled regions. Finally, we generate a change map using pretrained features obtained from the segmentation stage. We demonstrate the robustness of our proposed label-matching process by comparing the results to a correctly matched dataset and show that incorporating FIGS and the greenness index improves the segmentation performance. Our method achieves effective change detection results even in scenarios associated with a shortage of annotations.http://www.sciencedirect.com/science/article/pii/S1569843224001936Building detectionChange detectionData labelingDeep learningRemote sensingSegmentation |
| spellingShingle | H. Ahn S. Chung S. Park D. Kim Focused information learning method for change detection based on segmentation with limited annotations International Journal of Applied Earth Observations and Geoinformation Building detection Change detection Data labeling Deep learning Remote sensing Segmentation |
| title | Focused information learning method for change detection based on segmentation with limited annotations |
| title_full | Focused information learning method for change detection based on segmentation with limited annotations |
| title_fullStr | Focused information learning method for change detection based on segmentation with limited annotations |
| title_full_unstemmed | Focused information learning method for change detection based on segmentation with limited annotations |
| title_short | Focused information learning method for change detection based on segmentation with limited annotations |
| title_sort | focused information learning method for change detection based on segmentation with limited annotations |
| topic | Building detection Change detection Data labeling Deep learning Remote sensing Segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S1569843224001936 |
| work_keys_str_mv | AT hahn focusedinformationlearningmethodforchangedetectionbasedonsegmentationwithlimitedannotations AT schung focusedinformationlearningmethodforchangedetectionbasedonsegmentationwithlimitedannotations AT spark focusedinformationlearningmethodforchangedetectionbasedonsegmentationwithlimitedannotations AT dkim focusedinformationlearningmethodforchangedetectionbasedonsegmentationwithlimitedannotations |