Abstract
In response to the impact of driver's violations, such as using a mobile phone, on vehicle safety during the driving process, we propose an improved real-time monitoring algorithm based on YOLOv5s with lightweight optimization. Firstly, we replace the C3 module (CSP Bottleneck with 3 convolutions) in the backbone network of YOLOv5s with a lightweight Ghost Module to reduce the model's parameter count, enhance detection speed, and maintain inference accuracy unaffected, thus meeting the requirements of real-time monitoring. Secondly, we introduce the RepConv (Receptive Field Block) module into the Feature Extraction Network (PANet) structure to increase the neural network's receptive field for input images and further reduce the model's computational load. Experimental results show that the improved network achieves an mAP@0.5 of 95.7%, a detection speed of 140 FPS, and a model size reduction to 10.6MB, meeting the demand for real-time and reliable detection on embedded devices.
Publisher
Darcy & Roy Press Co. Ltd.
Reference28 articles.
1. World Health Organization.Global status report on road safety[R].Geneva:WHO,2018[2019-09-15].
2. H K M B, SKOV M B, THOMASSEN N G.You can touch, but you can’t look: interacting with in-vehicle systems [C]//Conference on Human Factors in Computing Systems. Florence, Italy: CHI, 2008:1139-1148.
3. BEISSEL S, BELYTSCHKO T. Nodal integration of the element-free Galerkin method[J].Computer Methods in Applied Mechanics and Engineering, 1996,139(1-4): 49-74.
4. CHENG Y M, ZHANG Y H, CHEN W S. Wilson non-conforming element in numerical manifold method[J]. Commun. Numer. Meth, 2002, 18(12): 877-884.
5. Hou Yuqingyang, Quan Jicheng, Wang Hongwei. Overview of Deep Learning Development[J]. Journal of Shipborne Electronic Engineering, 2017, 37(4): 5-9.