Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images
In recent years, object counting has been investigated and has made significant progress under a surveillance-view. However, there exists only a few works focusing on the remote sensing object density estimation, and the performance of existing methods is not promising. On the one hand, due to the i...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/16/4026 |
| _version_ | 1797442215955398656 |
|---|---|
| author | Junyu Gao Maoguo Gong Xuelong Li |
| author_facet | Junyu Gao Maoguo Gong Xuelong Li |
| author_sort | Junyu Gao |
| collection | DOAJ |
| description | In recent years, object counting has been investigated and has made significant progress under a surveillance-view. However, there exists only a few works focusing on the remote sensing object density estimation, and the performance of existing methods is not promising. On the one hand, due to the imbalance distribution of targets in remote sensing images, the model might collapse, leading a severe degradation. On the other hand, the scale of targets in remote sensing images actually varies in real scenarios, which remains a challenge for counting objects accurately. To remedy the above problems, we propose an approach named “SwinCounter” for object counting in remote sensing. Moreover, we introduce a Balanced MSE Loss to pay more attention to the fewer samples, which alleviates the problem of imbalanced object labels. In addition, the attention mechanism in our SwinCounter can precisely capture multi-scale information. Thus, the model is aware of different scales of objects, which capture small and dense targetes more precisely. We build experiments on the RSOC dataset, achieving MAEs of 7.2, 151.5, 14.38, and 52.88 and MSEs of 10.1, 436.0, 22.7, and 74.82 on the Building, Small-Vehicle, Large-Vehicle, and Ship sub-datasets, which demonstrates the competitiveness and superiority of the proposed method. |
| first_indexed | 2024-03-09T12:39:36Z |
| format | Article |
| id | doaj.art-2787c0f113cc49cf9fa015479f282b0e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:39:36Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2787c0f113cc49cf9fa015479f282b0e2023-11-30T22:20:09ZengMDPI AGRemote Sensing2072-42922022-08-011416402610.3390/rs14164026Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing ImagesJunyu Gao0Maoguo Gong1Xuelong Li2Academy of Advanced Interdisciplinary Research, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Xidian University, Xi’an 710071, ChinaSchool of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, ChinaIn recent years, object counting has been investigated and has made significant progress under a surveillance-view. However, there exists only a few works focusing on the remote sensing object density estimation, and the performance of existing methods is not promising. On the one hand, due to the imbalance distribution of targets in remote sensing images, the model might collapse, leading a severe degradation. On the other hand, the scale of targets in remote sensing images actually varies in real scenarios, which remains a challenge for counting objects accurately. To remedy the above problems, we propose an approach named “SwinCounter” for object counting in remote sensing. Moreover, we introduce a Balanced MSE Loss to pay more attention to the fewer samples, which alleviates the problem of imbalanced object labels. In addition, the attention mechanism in our SwinCounter can precisely capture multi-scale information. Thus, the model is aware of different scales of objects, which capture small and dense targetes more precisely. We build experiments on the RSOC dataset, achieving MAEs of 7.2, 151.5, 14.38, and 52.88 and MSEs of 10.1, 436.0, 22.7, and 74.82 on the Building, Small-Vehicle, Large-Vehicle, and Ship sub-datasets, which demonstrates the competitiveness and superiority of the proposed method.https://www.mdpi.com/2072-4292/14/16/4026coutingremote countingtransformerremote sensing image |
| spellingShingle | Junyu Gao Maoguo Gong Xuelong Li Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images Remote Sensing couting remote counting transformer remote sensing image |
| title | Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images |
| title_full | Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images |
| title_fullStr | Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images |
| title_full_unstemmed | Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images |
| title_short | Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images |
| title_sort | global multi scale information fusion for multi class object counting in remote sensing images |
| topic | couting remote counting transformer remote sensing image |
| url | https://www.mdpi.com/2072-4292/14/16/4026 |
| work_keys_str_mv | AT junyugao globalmultiscaleinformationfusionformulticlassobjectcountinginremotesensingimages AT maoguogong globalmultiscaleinformationfusionformulticlassobjectcountinginremotesensingimages AT xuelongli globalmultiscaleinformationfusionformulticlassobjectcountinginremotesensingimages |