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>
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