Table of Contents Author Guidelines Submit a Manuscript
Mathematical Problems in Engineering
Volume 2016, Article ID 5810910, 13 pages
Research Article

Study on Leading Vehicle Detection at Night Based on Multisensor and Image Enhancement Method

1School of Transportation, Jilin University, Changchun 130022, China
2China-Japan Union Hospital of Jilin University, Changchun 130033, China

Received 2 June 2016; Revised 16 August 2016; Accepted 23 August 2016

Academic Editor: Jinyang Liang

Copyright © 2016 Mei Chen et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Low visibility is one of the reasons for rear accident at night. In this paper, we propose a method to detect the leading vehicle based on multisensor to decrease rear accidents at night. Then, we use image enhancement algorithm to improve the human vision. First, by millimeter wave radar to get the world coordinate of the preceding vehicles and establish the transformation of the relationship between the world coordinate and image pixels coordinate, we can convert the world coordinates of the radar target to image coordinate in order to form the region of interesting image. And then, by using the image processing method, we can reduce interference from the outside environment. Depending on D-S evidence theory, we can achieve a general value of reliability to test vehicles of interest. The experimental results show that the method can effectively eliminate the influence of illumination condition at night, accurately detect leading vehicles, and determine their location and accurate positioning. In order to improve nighttime driving, the driver shortage vision, reduce rear-end accident. Enhancing nighttime color image by three algorithms, a comparative study and evaluation by three algorithms are presented. The evaluation demonstrates that results after image enhancement satisfy the human visual habits.