Research on Improved YOLOv5 for Low-Light Environment Object Detection
Object detection in low-light scenarios has been widely acknowledged as a significant research area in the field of computer vision, presenting a challenging task. Aiming at the low detection accuracy of mainstream single-stage object detection models in low-light scenarios, this paper proposes a de...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/14/3089 |
| _version_ | 1797589521979670528 |
|---|---|
| author | Jing Wang Peng Yang Yuansheng Liu Duo Shang Xin Hui Jinhong Song Xuehui Chen |
| author_facet | Jing Wang Peng Yang Yuansheng Liu Duo Shang Xin Hui Jinhong Song Xuehui Chen |
| author_sort | Jing Wang |
| collection | DOAJ |
| description | Object detection in low-light scenarios has been widely acknowledged as a significant research area in the field of computer vision, presenting a challenging task. Aiming at the low detection accuracy of mainstream single-stage object detection models in low-light scenarios, this paper proposes a detection model called DK_YOLOv5 based on YOLOv5, specifically designed for such scenarios. First, a low-light image enhancement algorithm with better results is selected to generate enhanced images that achieve relatively better visual effects and amplify target features. Second, the SPPF layer is improved to an R-SPPF module with faster inference speed and stronger feature expression ability. Next, we replace the C3 module with the C2f module and incorporate an attention mechanism to develop the C2f_SKA module, enabling richer gradient information flow and reducing the impact of noise features. Finally, the model detection head is replaced with a decoupled head suitable for the object detection task in this scenario to improve model performance. Additionally, we expand the Exdark dataset to include low-light data of underground mine scenario targets, named Mine_Exdark. Experimental results demonstrate that the proposed DK_YOLOv5 model achieves higher detection accuracy than other models in low-light scenarios, with an mAP0.5 of 71.9% on the Mine_Exdark dataset, which is 4.4% higher than that of YOLOv5. |
| first_indexed | 2024-03-11T01:07:40Z |
| format | Article |
| id | doaj.art-588318c65efc4988bc03896b83ffcedc |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T01:07:40Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-588318c65efc4988bc03896b83ffcedc2023-11-18T19:05:38ZengMDPI AGElectronics2079-92922023-07-011214308910.3390/electronics12143089Research on Improved YOLOv5 for Low-Light Environment Object DetectionJing Wang0Peng Yang1Yuansheng Liu2Duo Shang3Xin Hui4Jinhong Song5Xuehui Chen6Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, ChinaBeijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, ChinaBeijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, ChinaChina Academy of Industrial Internet, Beijing 100102, ChinaChina Academy of Industrial Internet, Beijing 100102, ChinaJiaojia Gold Mine of Shandong Gold Mining Co., Ltd., Laizhou 261441, ChinaJiaojia Gold Mine of Shandong Gold Mining Co., Ltd., Laizhou 261441, ChinaObject detection in low-light scenarios has been widely acknowledged as a significant research area in the field of computer vision, presenting a challenging task. Aiming at the low detection accuracy of mainstream single-stage object detection models in low-light scenarios, this paper proposes a detection model called DK_YOLOv5 based on YOLOv5, specifically designed for such scenarios. First, a low-light image enhancement algorithm with better results is selected to generate enhanced images that achieve relatively better visual effects and amplify target features. Second, the SPPF layer is improved to an R-SPPF module with faster inference speed and stronger feature expression ability. Next, we replace the C3 module with the C2f module and incorporate an attention mechanism to develop the C2f_SKA module, enabling richer gradient information flow and reducing the impact of noise features. Finally, the model detection head is replaced with a decoupled head suitable for the object detection task in this scenario to improve model performance. Additionally, we expand the Exdark dataset to include low-light data of underground mine scenario targets, named Mine_Exdark. Experimental results demonstrate that the proposed DK_YOLOv5 model achieves higher detection accuracy than other models in low-light scenarios, with an mAP0.5 of 71.9% on the Mine_Exdark dataset, which is 4.4% higher than that of YOLOv5.https://www.mdpi.com/2079-9292/12/14/3089low-light scenariosobject detectionimage enhancementYOLOv5underground mine scenarios |
| spellingShingle | Jing Wang Peng Yang Yuansheng Liu Duo Shang Xin Hui Jinhong Song Xuehui Chen Research on Improved YOLOv5 for Low-Light Environment Object Detection Electronics low-light scenarios object detection image enhancement YOLOv5 underground mine scenarios |
| title | Research on Improved YOLOv5 for Low-Light Environment Object Detection |
| title_full | Research on Improved YOLOv5 for Low-Light Environment Object Detection |
| title_fullStr | Research on Improved YOLOv5 for Low-Light Environment Object Detection |
| title_full_unstemmed | Research on Improved YOLOv5 for Low-Light Environment Object Detection |
| title_short | Research on Improved YOLOv5 for Low-Light Environment Object Detection |
| title_sort | research on improved yolov5 for low light environment object detection |
| topic | low-light scenarios object detection image enhancement YOLOv5 underground mine scenarios |
| url | https://www.mdpi.com/2079-9292/12/14/3089 |
| work_keys_str_mv | AT jingwang researchonimprovedyolov5forlowlightenvironmentobjectdetection AT pengyang researchonimprovedyolov5forlowlightenvironmentobjectdetection AT yuanshengliu researchonimprovedyolov5forlowlightenvironmentobjectdetection AT duoshang researchonimprovedyolov5forlowlightenvironmentobjectdetection AT xinhui researchonimprovedyolov5forlowlightenvironmentobjectdetection AT jinhongsong researchonimprovedyolov5forlowlightenvironmentobjectdetection AT xuehuichen researchonimprovedyolov5forlowlightenvironmentobjectdetection |