An Improved YOLO for Road and Vehicle Target Detection Model
DOI:
https://doi.org/10.13052/jicts2245-800X.1125Keywords:
Target detection, convolutional neural network (CNN), small targets, occluded targets, feature fusionAbstract
The yolo series is the prevalent algorithm for target identification at now. Nevertheless, due to the high real-time, mixed target parity, and obscured target features of vehicle target recognition, missed detection and incorrect detection are common. It enhances the yolo algorithm in order to enhance the network performance of this method while identifying vehicle targets. To properly portray the improvement impact, the yolov4 method is used as the improvement baseline. First, the structure of the DarkNet backbone network is modified, and a more efficient backbone network, FBR-DarkNet, is presented to enhance the effect of feature extraction. In order to better detect obstructed cars, a thin feature layer for focused detection of tiny objects is added to the Neck module to increase the recognition impact. The attention mechanism module CBAM is included to increase the model’s precision and speed of convergence. The lightweight network replaces the MISH function with the H-SWISH function, and the improved algorithm improves by 4.76 percentage points over the original network on the BDD100K data set, with the mAP metrics improving by 8 points, 8 points, and 7 points, respectively, for the car, truck, and bus categories. Compared to other newer and better algorithms, it nevertheless maintains a pretty decent performance. It satisfies the criteria for real-time detection and significantly improves the detection accuracy.
Downloads
References
Girshick. R. Fast r-cnn[C] Proceedings of the IEEE international conference on computer vision. 2015:1440–1448.
Yang S, Wang J, Hu L, et al. Research on improved Retina-Net’s occlusion target detection algorithm[J]. Computer Engineering and Applications, 2022, 58(11): 209–214.
Jia K C, Ma Z H, Zhu R, et al. Attention mechanism to improve lightweight SSD model for sea surface small target detection[J]. Chinese Journal of Image Graphics, 2022, 27(04):1161–1175.
Gu Yongli, Zong Xinxin. A review of deep learning-based target detection research[J]. Modern Information Technology 2022, 6(11):76–81. DOI: 10.19850/j.cnki.2096-4706.2022.011.020.
Hou Xueliang, Shan Tengfei, Xue Jingguo. Analysis of typical algorithms for target detection with deep learning and its application status[J]. Foreign Electronic Measurement, 2022, 41(06):165–174.
Zheng Hao, Liu Jianfang, Ren Xiaogang. Dim Target Detection Method Based on Deep Learning in Complex Traffic Environment [J]. Journal of Grid Computing, 2022, 20(1).
Bochkovskiy Alexey, Wang C Y, Liao H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv preprint, 2020, arXiv:2004.10934.
Wenhao Cao, Zhuoyu Feng, Dongyao Zhang, et al. Facial Expression Recognition via a CBAM Embedded Network[J]. Procedia Computer Science, 2020, 174.
Huang Shan, He Ye, Chen Xiao-an. M-YOLO: A Nighttime Vehicle Detection Method Combining Mobilenet v2 and YOLO v3[J]. Journal of Physics: Conference Series, 2021, 1883.
Wang C Y, Liao H Y M, Wu Y H, et al. CSPNet: A new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 2020: 390–391.
He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9).
Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8759–8768.
Ju Zhiyong, Li Yuming, Xue Yongjie, et al. Pedestrian detection algorithm based on improved YOLOv4 model[J/OL]. Control Engineering:1–13 [2022-10-26]. DOI: 10.14107//j.cnki.kzgc.20220053.
Mahto P., Garg P., Seth P, et al. Refining Yolov4 for vehicle detection[J]. International Journal of Advanced Research in Engineering and Technology, 2020, 11(5).
Chen Zhixiong, Tian Shengwei, Yu Long, et al. An object detection network based on YOLOv4 and improved spatial attention mechanism[J]. Journal of Intelligent & Fuzzy Systems, 2022, 42(3).
Ren, Feng Yi, Pei, Xinbiao, Qiao, Zheng, et al. A lightweight detection method for YOLOv4 incorporating CBAM[J/OL]. Small Microcomputer Systems:1–8 [2022-10-26]. http://kns.cnki.net/kcms/detail/21.1106.tp.20220301.0935.002.html
Zhao Qi. Mobile Net-V3-based fatigue driving detection algorithm [D]. Hangzhou University of Electronic Science and Technology, 2022. DOI: 10.27075/d.cnki.ghzdc.2022.000209.
Evan, Wulandari Meirista, Syamsudin Eko. Recognition of Pedestrian Traffic Light using Tensorflow And SSD MobileNet V2[J]. IOP Conference Series: Materials Science and Engineering, 2020, 1007 (1).
Deng T M, Liu X H, Wang L et al. A vehicle detection algorithm combining cascaded attention mechanism[J/OL]. Computer Engineering and Applications:1–12 [2022-11-11]. http://kns.cnki.net/kcms/detail/11.2127.TP.20220926.2015.020.htm.
Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. arXiv preprint arXiv:1503.02531,2015.
