Driver distraction detection based on lightweight networks and tiny object detection
-
Published:2023
Issue:10
Volume:20
Page:18248-18266
-
ISSN:1551-0018
-
Container-title:Mathematical Biosciences and Engineering
-
language:
-
Short-container-title:MBE
Author:
Zhu Zhiqin1, Wang Shaowen1, Gu Shuangshuang1, Li Yuanyuan1, Li Jiahan1, Shuai Linhong2, Qi Guanqiu3
Affiliation:
1. College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China 2. Intelligent Interaction R & D Department, Chongqing Lilong Zhongbao Intelligent Technology Co., Chongqing 400065, China 3. Computer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USA
Abstract
<abstract><p>Real-time and efficient driver distraction detection is of great importance for road traffic safety and assisted driving. The design of a real-time lightweight model is crucial for in-vehicle edge devices that have limited computational resources. However, most existing approaches focus on lighter and more efficient architectures, ignoring the cost of losing tiny target detection performance that comes with lightweighting. In this paper, we present MTNet, a lightweight detector for driver distraction detection scenarios. MTNet consists of a multidimensional adaptive feature extraction block, a lightweight feature fusion block and utilizes the IoU-NWD weighted loss function, all while considering the accuracy gain of tiny target detection. In the feature extraction component, a lightweight backbone network is employed in conjunction with four attention mechanisms strategically integrated across the kernel space. This approach enhances the performance limits of the lightweight network. The lightweight feature fusion module is designed to reduce computational complexity and memory access. The interaction of channel information is improved through the use of lightweight arithmetic techniques. Additionally, CFSM module and EPIEM module are employed to minimize redundant feature map computations and strike a better balance between model weights and accuracy. Finally, the IoU-NWD weighted loss function is formulated to enable more effective detection of tiny targets. We assess the performance of the proposed method on the LDDB benchmark. The experimental results demonstrate that our proposed method outperforms multiple advanced detection models.</p></abstract>
Publisher
American Institute of Mathematical Sciences (AIMS)
Subject
Applied Mathematics,Computational Mathematics,General Agricultural and Biological Sciences,Modeling and Simulation,General Medicine
Reference39 articles.
1. A. Krizhevsky, I. Sutskever, G. E. Hinton, Imagenet classification with deep convolutional neural networks, Adv. Neural Inform. Process. Syst., 6 (2017), 84–90. https://doi.org/10.1145/3065386 2. K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90 3. J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You only look once: Unified, real-time object detection, preprint, arXiv: 1506.02640. 4. J. Redmon, A. Farhadi, Yolov3: An incremental improvement, preprint, arXiv: 1804.02767. 5. Ultralytics, Yolov5, 2021. Available from: https://github.com/ultralytics/yolov5.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|