Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism
With the rapid advancement of technology, satellite and drone technologies have had significant impacts on various fields, creating both opportunities and challenges. In areas like the military, urban planning, and environmental monitoring, the application of remote sensing technology is paramount....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/4/644 |
| _version_ | 1797297059836985344 |
|---|---|
| author | Yuanyuan Li Zhengguo Zhou Guanqiu Qi Gang Hu Zhiqin Zhu Xin Huang |
| author_facet | Yuanyuan Li Zhengguo Zhou Guanqiu Qi Gang Hu Zhiqin Zhu Xin Huang |
| author_sort | Yuanyuan Li |
| collection | DOAJ |
| description | With the rapid advancement of technology, satellite and drone technologies have had significant impacts on various fields, creating both opportunities and challenges. In areas like the military, urban planning, and environmental monitoring, the application of remote sensing technology is paramount. However, due to the unique characteristics of remote sensing images, such as high resolution, large-scale scenes, and small, densely packed targets, remote sensing object detection faces numerous technical challenges. Traditional detection methods are inadequate for effectively detecting small targets, rendering the accurate and efficient detection of objects in complex remote sensing images a pressing issue. Current detection techniques fall short in accurately detecting small targets compared to medium and large ones, primarily due to limited feature information, insufficient contextual data, and poor localization capabilities for small targets. In response, we propose an innovative detection method. Unlike previous approaches that often focused solely on either local or contextual information, we introduce a novel Global and Local Attention Mechanism (GAL), providing an in-depth modeling method for input images. Our method integrates fine-grained local feature analysis with global contextual information processing. The local attention concentrates on details and spatial relationships within local windows, enabling the model to recognize intricate details in complex images. Meanwhile, the global attention addresses the entire image’s global information, capturing overarching patterns and structures, thus enhancing the model’s high-level semantic understanding. Ultimately, a specific mechanism fuses local details with global context, allowing the model to consider both aspects for a more precise and comprehensive interpretation of images. Furthermore, we have developed a multi-head prediction module that leverages semantic information at various scales to capture the multi-scale characteristics of remote sensing targets. Adding decoupled prediction heads aims to improve the accuracy and robustness of target detection. Additionally, we have innovatively designed the Ziou loss function, an advanced loss calculation, to enhance the model’s precision in small target localization, thereby boosting its overall performance in small target detection. Experimental results on the Visdrone2019 and DOTA datasets demonstrate that our method significantly surpasses traditional methods in detecting small targets in remote sensing imagery. |
| first_indexed | 2024-03-07T22:15:46Z |
| format | Article |
| id | doaj.art-3a4a8802a61d4668a2e1c940f7fd93ca |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-07T22:15:46Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3a4a8802a61d4668a2e1c940f7fd93ca2024-02-23T15:32:58ZengMDPI AGRemote Sensing2072-42922024-02-0116464410.3390/rs16040644Remote Sensing Micro-Object Detection under Global and Local Attention MechanismYuanyuan Li0Zhengguo Zhou1Guanqiu Qi2Gang Hu3Zhiqin Zhu4Xin Huang5College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaComputer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USAComputer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USACollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaWith the rapid advancement of technology, satellite and drone technologies have had significant impacts on various fields, creating both opportunities and challenges. In areas like the military, urban planning, and environmental monitoring, the application of remote sensing technology is paramount. However, due to the unique characteristics of remote sensing images, such as high resolution, large-scale scenes, and small, densely packed targets, remote sensing object detection faces numerous technical challenges. Traditional detection methods are inadequate for effectively detecting small targets, rendering the accurate and efficient detection of objects in complex remote sensing images a pressing issue. Current detection techniques fall short in accurately detecting small targets compared to medium and large ones, primarily due to limited feature information, insufficient contextual data, and poor localization capabilities for small targets. In response, we propose an innovative detection method. Unlike previous approaches that often focused solely on either local or contextual information, we introduce a novel Global and Local Attention Mechanism (GAL), providing an in-depth modeling method for input images. Our method integrates fine-grained local feature analysis with global contextual information processing. The local attention concentrates on details and spatial relationships within local windows, enabling the model to recognize intricate details in complex images. Meanwhile, the global attention addresses the entire image’s global information, capturing overarching patterns and structures, thus enhancing the model’s high-level semantic understanding. Ultimately, a specific mechanism fuses local details with global context, allowing the model to consider both aspects for a more precise and comprehensive interpretation of images. Furthermore, we have developed a multi-head prediction module that leverages semantic information at various scales to capture the multi-scale characteristics of remote sensing targets. Adding decoupled prediction heads aims to improve the accuracy and robustness of target detection. Additionally, we have innovatively designed the Ziou loss function, an advanced loss calculation, to enhance the model’s precision in small target localization, thereby boosting its overall performance in small target detection. Experimental results on the Visdrone2019 and DOTA datasets demonstrate that our method significantly surpasses traditional methods in detecting small targets in remote sensing imagery.https://www.mdpi.com/2072-4292/16/4/644remote-sensing detectionmulti scale feature fusionattention mechanismloss function |
| spellingShingle | Yuanyuan Li Zhengguo Zhou Guanqiu Qi Gang Hu Zhiqin Zhu Xin Huang Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism Remote Sensing remote-sensing detection multi scale feature fusion attention mechanism loss function |
| title | Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism |
| title_full | Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism |
| title_fullStr | Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism |
| title_full_unstemmed | Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism |
| title_short | Remote Sensing Micro-Object Detection under Global and Local Attention Mechanism |
| title_sort | remote sensing micro object detection under global and local attention mechanism |
| topic | remote-sensing detection multi scale feature fusion attention mechanism loss function |
| url | https://www.mdpi.com/2072-4292/16/4/644 |
| work_keys_str_mv | AT yuanyuanli remotesensingmicroobjectdetectionunderglobalandlocalattentionmechanism AT zhengguozhou remotesensingmicroobjectdetectionunderglobalandlocalattentionmechanism AT guanqiuqi remotesensingmicroobjectdetectionunderglobalandlocalattentionmechanism AT ganghu remotesensingmicroobjectdetectionunderglobalandlocalattentionmechanism AT zhiqinzhu remotesensingmicroobjectdetectionunderglobalandlocalattentionmechanism AT xinhuang remotesensingmicroobjectdetectionunderglobalandlocalattentionmechanism |