YOLOv5-Fog: A Multiobjective Visual Detection Algorithm for Fog Driving Scenes Based on Improved YOLOv5

作     者：Wang, Hai Xu, Yansong He, Youguo Cai, Yingfeng Chen, Long Li, Yicheng Sotelo, Miguel Angel Li, Zhixiong 

作者机构：Jiangsu Univ Sch Automot & Traff Engn Zhenjiang 212013 Jiangsu Peoples R China Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Jiangsu Peoples R China Univ Alcal Dept Comp Engn Alcal Henares Madrid 28801 Spain Yonsei Univ Yonsei Frontier Lab Seoul 03722 South Korea Opole Univ Technol Fac Mech Engn PL-45758 Opole Poland 

出 版 物：《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》 (IEEE Trans. Instrum. Meas.)

年 卷 期：2022年第71卷

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0804[工学-仪器科学与技术] 

基　　金：National Natural Science Foundation of China [U20A20333, 52072160, 51875255] Key Research and Development Program of Jiangsu Province [BE2019010-2, BE2020083-3] Jiangsu Province's Six Talent Peaks [TD-GDZB-022] Zhenjiang Key Research and Development Program [GY2020006] Narodowego Centrum Nauki Poland [2020/37/K/ST8/02748] 

主　　题：Feature extraction Detection algorithms Atmospheric modeling Autonomous vehicles Training Meteorology Object detection 2-D object detection autonomous driving complex traffic conditions fog 

摘      要：With the rapid development of deep learning in recent years, the level of automatic driving perception has also increased substantially. However, automatic driving perception under adverse conditions, such as fog, remains a significant obstacle. The existing fog-oriented detection algorithms are unable to simultaneously address the detection accuracy and detection speed. Based on improved YOLOv5, this work provides a multiobject detection network for fog driving scenes. We construct a synthetic fog dataset by using the dataset of a virtual scene and the depth information of the image. Second, we present a detection network for driving in fog based on improved YOLOv5. The ResNeXt model, which has been modified by structural re-parameterization, serves as the model s backbone. We build a new feature enhancement module (FEM) in response to the lack of features in fog scene images and use the attention mechanism to help the detection network pay more attention to the more useful features in the fog scenes. The test results show that the proposed fog multitarget detection network outperforms the original YOLOv5 in terms of detection accuracy and speed. The accuracy of the Real-world Task-driven Testing Set (RTTS) public dataset is 77.8%, and the detection speed is 31 frames/s, which is 14 frames faster as compared with the original YOLOv5.