Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature Optimization
To improve the accuracy of material identification under low contrast conditions, this paper proposes an improved YOLOv4-tiny target detection method based on an adaptive self-order piecewise enhancement and multiscale feature optimization. The model first constructs an adaptive self-rank piecewise...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/14/8177 |
| _version_ | 1797590468199972864 |
|---|---|
| author | Dengsheng Cai Zhigang Lu Xiangsuo Fan Wentao Ding Bing Li |
| author_facet | Dengsheng Cai Zhigang Lu Xiangsuo Fan Wentao Ding Bing Li |
| author_sort | Dengsheng Cai |
| collection | DOAJ |
| description | To improve the accuracy of material identification under low contrast conditions, this paper proposes an improved YOLOv4-tiny target detection method based on an adaptive self-order piecewise enhancement and multiscale feature optimization. The model first constructs an adaptive self-rank piecewise enhancement algorithm to enhance low-contrast images and then considers the fast detection ability of the YOLOv4-tiny network. To make the detection network have a higher accuracy, this paper adds an SE channel attention mechanism and an SPP module to this lightweight backbone network to increase the receptive field of the model and enrich the expression ability of the feature map. The network can pay more attention to salient information, suppress edge information, and effectively improve the training accuracy of the model. At the same time, to better fuse the features of different scales, the FPN multiscale feature fusion structure is redesigned to strengthen the fusion of semantic information at all levels of the network, enhance the ability of network feature extraction, and improve the overall detection accuracy of the model. The experimental results show that compared with the mainstream network framework, the improved YOLOv4-tiny network in this paper effectively improves the running speed and target detection accuracy of the model, and its <i>mAP</i> index reaches 98.85%, achieving better detection results. |
| first_indexed | 2024-03-11T01:20:55Z |
| format | Article |
| id | doaj.art-b601ea7315464379a4d098ecdf52e5f1 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T01:20:55Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b601ea7315464379a4d098ecdf52e5f12023-11-18T18:09:24ZengMDPI AGApplied Sciences2076-34172023-07-011314817710.3390/app13148177Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature OptimizationDengsheng Cai0Zhigang Lu1Xiangsuo Fan2Wentao Ding3Bing Li4School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Electrical Engineering, Yanshan University, Qinhuangdao 066004, ChinaIntelligent Technology Research Institute of Global Research and Development Center, Guangxi LiuGong Machinery Company Limited, Liuzhou 545007, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou 545006, ChinaGuangxi Collaborative Innovation Centre for Earthmoving Machinery, Guangxi University of Science and Technology, Liuzhou 545006, ChinaTo improve the accuracy of material identification under low contrast conditions, this paper proposes an improved YOLOv4-tiny target detection method based on an adaptive self-order piecewise enhancement and multiscale feature optimization. The model first constructs an adaptive self-rank piecewise enhancement algorithm to enhance low-contrast images and then considers the fast detection ability of the YOLOv4-tiny network. To make the detection network have a higher accuracy, this paper adds an SE channel attention mechanism and an SPP module to this lightweight backbone network to increase the receptive field of the model and enrich the expression ability of the feature map. The network can pay more attention to salient information, suppress edge information, and effectively improve the training accuracy of the model. At the same time, to better fuse the features of different scales, the FPN multiscale feature fusion structure is redesigned to strengthen the fusion of semantic information at all levels of the network, enhance the ability of network feature extraction, and improve the overall detection accuracy of the model. The experimental results show that compared with the mainstream network framework, the improved YOLOv4-tiny network in this paper effectively improves the running speed and target detection accuracy of the model, and its <i>mAP</i> index reaches 98.85%, achieving better detection results.https://www.mdpi.com/2076-3417/13/14/8177deep learningtarget detectionadaptive self-order piecewise enhancementmultiscale feature optimization |
| spellingShingle | Dengsheng Cai Zhigang Lu Xiangsuo Fan Wentao Ding Bing Li Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature Optimization Applied Sciences deep learning target detection adaptive self-order piecewise enhancement multiscale feature optimization |
| title | Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature Optimization |
| title_full | Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature Optimization |
| title_fullStr | Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature Optimization |
| title_full_unstemmed | Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature Optimization |
| title_short | Improved YOLOv4-Tiny Target Detection Method Based on Adaptive Self-Order Piecewise Enhancement and Multiscale Feature Optimization |
| title_sort | improved yolov4 tiny target detection method based on adaptive self order piecewise enhancement and multiscale feature optimization |
| topic | deep learning target detection adaptive self-order piecewise enhancement multiscale feature optimization |
| url | https://www.mdpi.com/2076-3417/13/14/8177 |
| work_keys_str_mv | AT dengshengcai improvedyolov4tinytargetdetectionmethodbasedonadaptiveselforderpiecewiseenhancementandmultiscalefeatureoptimization AT zhiganglu improvedyolov4tinytargetdetectionmethodbasedonadaptiveselforderpiecewiseenhancementandmultiscalefeatureoptimization AT xiangsuofan improvedyolov4tinytargetdetectionmethodbasedonadaptiveselforderpiecewiseenhancementandmultiscalefeatureoptimization AT wentaoding improvedyolov4tinytargetdetectionmethodbasedonadaptiveselforderpiecewiseenhancementandmultiscalefeatureoptimization AT bingli improvedyolov4tinytargetdetectionmethodbasedonadaptiveselforderpiecewiseenhancementandmultiscalefeatureoptimization |