A study on obstacle detection method of the frontal view using a camera on highway

International Conference on Functional Materials and Chemical Engineering 2017

材料科学;化学工业

Nguyen, Van-Quang^1 ; Park, Jeonghyeon^2 ; Seo, Changjun^2 ; Kim, Heungseob^1 ; Boo, Kwangsuck^1

Department of Mechanical and Automotive Engineering, Inje University, Gimhae, Gyeongnam, Korea, Republic of^1

Department of Electronic Engineering, Inje University, Gimhae, Gyeongnam, Korea, Republic of^2

关键词: Driver assistance;    Driver assistance system;    Horizontal edge;    Line detection;    Obstacle detection;    Vanishing point estimations;    Vehicle detection;    Vertical Edge detections;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/323/1/012026/pdf
DOI  :  10.1088/1757-899X/323/1/012026

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

In this work, we introduce an approach to detect vehicles for driver assistance, or warning system. For driver assistance system, it must detect both lanes (left and right side lane), and discover vehicles ahead of the test vehicle. Therefore, in this study, we use a camera, it is installed on the windscreen of the test vehicle. Images from the camera are used to detect three lanes, and detect multiple vehicles. In lane detection, line detection and vanishing point estimation are used. For the vehicle detection, we combine the horizontal and vertical edge detection, the horizontal edge is used to detect the vehicle candidates, and then the vertical edge detection is used to verify the vehicle candidates. The proposed algorithm works with of 480 × 640 image frame resolution. The system was tested on the highway in Korea.