Journal of System Simulation
Abstract
Abstract: Aiming at the low detection accuracy in foggy weather, a new defogging target detection method based on DeblurGANv2 and YOLOv4 is proposed. In the method, image enhancement algorithm DeblurGANv2 in the generation countermeasure network is added to the preprocessing module of YOLOv4 to preprocess the foggy image and retain the high-quality texture and color information of the image, lightweight neural network ShuffleNet V2 is used to replace the CSPDarkNet53 network used for backbone feature extraction in YOLOv4 to improve the speed of model mark detection. Attention mechanism is added to the feature extraction network of YOLOv4 to enhance the recognition effect of small targets. The experimental results show that the proposed method can reduce the large color difference and fog residue, and the mAP value in the rest data set reaches 86.56%. The result of practiced defogging target test is good.
Recommended Citation
Liu, Shugang; Zhang, Linkun; Du, Haodong; and Wang, Hongtao
(2023)
"Improved Object Detection of YOLOv4 in Foggy Conditions,"
Journal of System Simulation: Vol. 35:
Iss.
8, Article 5.
DOI: 10.16182/j.issn1004731x.joss.22-0423
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol35/iss8/5
First Page
1681
Last Page
1691
CLC
TP183
Recommended Citation
Liu Shugang, Zhang Linkun, Du Haodong, et al. Improved Object Detection of YOLOv4 in Foggy Conditions[J]. Journal of System Simulation, 2023, 35(8): 1681-1691.
DOI
10.16182/j.issn1004731x.joss.22-0423
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons