MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target Detection
Current target detection methods have achieved high accuracy for detecting large and medium-sized targets. However, due to factors such as the small number of pixels and features available for targets in images, the detection performance for small targets is generally unsatisfactory. In addition, th...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10153099/ |
| _version_ | 1827868512667828224 |
|---|---|
| author | Jun Zhang Yizhen Meng Xiaohui Yu Hongjing Bi Zhipeng Chen Huafeng Li Runtao Yang Jingjun Tian |
| author_facet | Jun Zhang Yizhen Meng Xiaohui Yu Hongjing Bi Zhipeng Chen Huafeng Li Runtao Yang Jingjun Tian |
| author_sort | Jun Zhang |
| collection | DOAJ |
| description | Current target detection methods have achieved high accuracy for detecting large and medium-sized targets. However, due to factors such as the small number of pixels and features available for targets in images, the detection performance for small targets is generally unsatisfactory. In addition, the real-time performance of target detection is also critical. In conclusion, a modified lightweight architecture for real-time small target detection, i.e., MBAB-YOLO, is proposed based on You Only Look Once (YOLO) model by combining channel-wise attention block, space-attention block and multi-branch-ConvNet (Convolutional Neural network) structure. Specifically, our method is more suitable for the rich scale information of small targets through proposed adaptive multi-receptive-field focusing, and then combines proposed blended attention block (BAB) to re-calibrate small target information to make it more prominent and improve the discriminability of small target features. Finally, extensive experiments have been conducted on the open source data set for the proposed real-time small target detection method, i.e., MBAB-YOLO. The results of ablation experiment and contrast experiment show that our method has excellent performance, not only with high detection accuracy, but also with fast detection speed. Compared with the various benchmark methods, it achieves a good trade-off between the two aspects mentioned above. In addition, this paper gives a comprehensive and detailed review of the current work about small target detection from different several perspectives, which can be used as a reference for future researchers. |
| first_indexed | 2024-03-12T15:32:31Z |
| format | Article |
| id | doaj.art-7a479d1beb48400e86274e699d78603e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T15:32:31Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7a479d1beb48400e86274e699d78603e2023-08-09T23:01:10ZengIEEEIEEE Access2169-35362023-01-0111783847840110.1109/ACCESS.2023.328603110153099MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target DetectionJun Zhang0https://orcid.org/0000-0002-9657-5436Yizhen Meng1Xiaohui Yu2Hongjing Bi3Zhipeng Chen4Huafeng Li5Runtao Yang6Jingjun Tian7Computer Science Department, Tangshan Normal University, Tangshan, ChinaComputer Science Department, Tangshan Normal University, Tangshan, ChinaComputer Science Department, Tangshan Normal University, Tangshan, ChinaComputer Science Department, Tangshan Normal University, Tangshan, ChinaComputer Science Department, Tangshan Normal University, Tangshan, ChinaComputer Science Department, Tangshan Normal University, Tangshan, ChinaComputer Science Department, Tangshan Normal University, Tangshan, ChinaComputer Science Department, Tangshan Normal University, Tangshan, ChinaCurrent target detection methods have achieved high accuracy for detecting large and medium-sized targets. However, due to factors such as the small number of pixels and features available for targets in images, the detection performance for small targets is generally unsatisfactory. In addition, the real-time performance of target detection is also critical. In conclusion, a modified lightweight architecture for real-time small target detection, i.e., MBAB-YOLO, is proposed based on You Only Look Once (YOLO) model by combining channel-wise attention block, space-attention block and multi-branch-ConvNet (Convolutional Neural network) structure. Specifically, our method is more suitable for the rich scale information of small targets through proposed adaptive multi-receptive-field focusing, and then combines proposed blended attention block (BAB) to re-calibrate small target information to make it more prominent and improve the discriminability of small target features. Finally, extensive experiments have been conducted on the open source data set for the proposed real-time small target detection method, i.e., MBAB-YOLO. The results of ablation experiment and contrast experiment show that our method has excellent performance, not only with high detection accuracy, but also with fast detection speed. Compared with the various benchmark methods, it achieves a good trade-off between the two aspects mentioned above. In addition, this paper gives a comprehensive and detailed review of the current work about small target detection from different several perspectives, which can be used as a reference for future researchers.https://ieeexplore.ieee.org/document/10153099/Deep learningtarget detectionchannel-wise attentionspace-attentionYOLO |
| spellingShingle | Jun Zhang Yizhen Meng Xiaohui Yu Hongjing Bi Zhipeng Chen Huafeng Li Runtao Yang Jingjun Tian MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target Detection IEEE Access Deep learning target detection channel-wise attention space-attention YOLO |
| title | MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target Detection |
| title_full | MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target Detection |
| title_fullStr | MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target Detection |
| title_full_unstemmed | MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target Detection |
| title_short | MBAB-YOLO: A Modified Lightweight Architecture for Real-Time Small Target Detection |
| title_sort | mbab yolo a modified lightweight architecture for real time small target detection |
| topic | Deep learning target detection channel-wise attention space-attention YOLO |
| url | https://ieeexplore.ieee.org/document/10153099/ |
| work_keys_str_mv | AT junzhang mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection AT yizhenmeng mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection AT xiaohuiyu mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection AT hongjingbi mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection AT zhipengchen mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection AT huafengli mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection AT runtaoyang mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection AT jingjuntian mbabyoloamodifiedlightweightarchitectureforrealtimesmalltargetdetection |