A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection
Remote sensing object detection (RSOD) plays a crucial role in resource utilization, geological disaster risk assessment and urban planning. Deep learning-based object-detection algorithms have proven effective in remote sensing image studies. However, accurate detection of objects with small size,...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/22/7166 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850266761993125888 |
|---|---|
| author | Bingqi Liu Peijun Mo Shengzhe Wang Yuyong Cui Zhongjian Wu |
| author_facet | Bingqi Liu Peijun Mo Shengzhe Wang Yuyong Cui Zhongjian Wu |
| author_sort | Bingqi Liu |
| collection | DOAJ |
| description | Remote sensing object detection (RSOD) plays a crucial role in resource utilization, geological disaster risk assessment and urban planning. Deep learning-based object-detection algorithms have proven effective in remote sensing image studies. However, accurate detection of objects with small size, dense distribution and complex object arrangement remains a significant challenge in the remote sensing field. To address this, a refined and efficient object-detection algorithm (RE-YOLO) has been proposed in this paper for remote sensing images. Initially, a refined and efficient module (REM) was designed to balance computational complexity and feature-extraction capabilities, which serves as a key component of the RE_CSP block. RE_CSP block efficiently extracts multi-scale information, overcoming challenges posed by complex backgrounds. Moreover, the spatial extracted attention module (SEAM) has been proposed in the bottleneck of backbone to promote representative feature learning and enhance the semantic information capture. In addition, a three-branch path aggregation network (TBPAN) has been constructed as the neck network, which facilitates comprehensive fusion of shallow positional information and deep semantic information across different channels, enabling the network with a robust ability to capture contextual information. Extensive experiments conducted on two large-scale remote sensing datasets, DOTA-v1.0 and SCERL, demonstrate that the proposed RE-YOLO outperforms state-of-the-art other object-detection approaches and exhibits a significant improvement in generalization ability. |
| format | Article |
| id | doaj-art-41e3ff085fcb4e7e99314c54496df9b9 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-41e3ff085fcb4e7e99314c54496df9b92025-08-20T01:54:04ZengMDPI AGSensors1424-82202024-11-012422716610.3390/s24227166A Refined and Efficient CNN Algorithm for Remote Sensing Object DetectionBingqi Liu0Peijun Mo1Shengzhe Wang2Yuyong Cui3Zhongjian Wu4Norla Institute of Technical Physics, Chengdu 610041, ChinaNorla Institute of Technical Physics, Chengdu 610041, ChinaNorla Institute of Technical Physics, Chengdu 610041, ChinaNorla Institute of Technical Physics, Chengdu 610041, ChinaNorla Institute of Technical Physics, Chengdu 610041, ChinaRemote sensing object detection (RSOD) plays a crucial role in resource utilization, geological disaster risk assessment and urban planning. Deep learning-based object-detection algorithms have proven effective in remote sensing image studies. However, accurate detection of objects with small size, dense distribution and complex object arrangement remains a significant challenge in the remote sensing field. To address this, a refined and efficient object-detection algorithm (RE-YOLO) has been proposed in this paper for remote sensing images. Initially, a refined and efficient module (REM) was designed to balance computational complexity and feature-extraction capabilities, which serves as a key component of the RE_CSP block. RE_CSP block efficiently extracts multi-scale information, overcoming challenges posed by complex backgrounds. Moreover, the spatial extracted attention module (SEAM) has been proposed in the bottleneck of backbone to promote representative feature learning and enhance the semantic information capture. In addition, a three-branch path aggregation network (TBPAN) has been constructed as the neck network, which facilitates comprehensive fusion of shallow positional information and deep semantic information across different channels, enabling the network with a robust ability to capture contextual information. Extensive experiments conducted on two large-scale remote sensing datasets, DOTA-v1.0 and SCERL, demonstrate that the proposed RE-YOLO outperforms state-of-the-art other object-detection approaches and exhibits a significant improvement in generalization ability.https://www.mdpi.com/1424-8220/24/22/7166object detectionremote sensing imagesdeep learningRE-YOLO |
| spellingShingle | Bingqi Liu Peijun Mo Shengzhe Wang Yuyong Cui Zhongjian Wu A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection Sensors object detection remote sensing images deep learning RE-YOLO |
| title | A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection |
| title_full | A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection |
| title_fullStr | A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection |
| title_full_unstemmed | A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection |
| title_short | A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection |
| title_sort | refined and efficient cnn algorithm for remote sensing object detection |
| topic | object detection remote sensing images deep learning RE-YOLO |
| url | https://www.mdpi.com/1424-8220/24/22/7166 |
| work_keys_str_mv | AT bingqiliu arefinedandefficientcnnalgorithmforremotesensingobjectdetection AT peijunmo arefinedandefficientcnnalgorithmforremotesensingobjectdetection AT shengzhewang arefinedandefficientcnnalgorithmforremotesensingobjectdetection AT yuyongcui arefinedandefficientcnnalgorithmforremotesensingobjectdetection AT zhongjianwu arefinedandefficientcnnalgorithmforremotesensingobjectdetection AT bingqiliu refinedandefficientcnnalgorithmforremotesensingobjectdetection AT peijunmo refinedandefficientcnnalgorithmforremotesensingobjectdetection AT shengzhewang refinedandefficientcnnalgorithmforremotesensingobjectdetection AT yuyongcui refinedandefficientcnnalgorithmforremotesensingobjectdetection AT zhongjianwu refinedandefficientcnnalgorithmforremotesensingobjectdetection |