Vehicle Kinematics-Based Image Augmentation against Motion Blur for Object Detectors

Author:

Zhang Zhuang,Zhang Lijun,Meng Dejian,Huang Luying,Xiao Wei,Tian Wei

Abstract

<div class="section abstract"><div class="htmlview paragraph">High-speed vehicles in low illumination environments severely blur the images used in object detectors, which poses a potential threat to object detector-based advanced driver assistance systems (ADAS) and autonomous driving systems. Augmenting the training images for object detectors is an efficient way to mitigate the threat from motion blur. However, little attention has been paid to the motion of the vehicle and the position of objects in the traffic scene, which limits the consistence between the resulting augmented images and traffic scenes. In this paper, we present a vehicle kinematics-based image augmentation algorithm by modeling and analyzing the traffic scenes to generate more realistic augmented images and achieve higher robustness improvement on object detectors against motion blur. Firstly, we propose a traffic scene model considering vehicle motion and the relationship between the vehicle and the object in the traffic scene. Simulations based on typical ADAS test scenes show that the high vehicle speed and near object position is the key factor in generating motion blur. Second, we propose the vehicle-motion-based image augmentation algorithm. The proposed method applies the motion blur on the clear object based on the vehicle's speed and the relative position of the object. Subjective evaluation and multiple objective evaluation indexes including structural similarity index measure (SSIM), perceptual hash, normalized mutual information, and cosine similarity demonstrates that the proposed image augmentation can produce images more consistent with the traffic scenes. Thirdly, we apply the proposed method to the training of object detectors. Experiments on the KITTI dataset as well as real-world driving tests show that the proposed image augmentation achieves a higher robustness improvement than existing image augmentation algorithms on multiple object detectors including CenterNet, YOLOv3, and Faster R-CNN.</div></div>

Publisher

SAE International

Reference34 articles.

1. Grigorescu , S. , Trasnea , B. , Cocias , T. , and Macesanu , G. A Survey of Deep Learning Techniques for Autonomous Driving Journal of Field Robotics 37 3 2020 362 386 10.1002/rob.21918

2. Hacohen , S. , Medina , O. , and Shoval , S. Autonomous Driving: A Survey of Technological Gaps Using Google Scholar and Web of Science Trend Analysis IEEE Transactions on Intelligent Transportation Systems 10.1109/TITS.2022.3172442

3. Wozniak , D. , Shahini , F. , Nasr , V. , and Zahabi , M. Analysis of Advanced Driver Assistance Systems in Police Vehicles: A Survey Study Transportation Research Part F-Traffic Psychology and Behaviour 83 2021 1 11 10.1016/j.trf.2021.09.017

4. Li , X.R. , Lin , K.Y. , Meng , M. , Li , X.X. et al. A Survey of ADAS Perceptions with Development in China IEEE Transactions on Intelligent Transportation Systems 10.1109/TITS.2022.3149763

5. PANTHATI , J. Traffic Object Detection and Distance Estimation Using Yolov3 SAE Technical Paper 2022-28-0120 2022 https://doi.org/10.4271/2022-28-0120

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3