基于机器视觉的汽车前照近光灯检测算法实现  

Realization of an Algorithm for Vehicle Low-beam Headlamp Detection Based on Computer Vision

作　　者：胥钧 曾德斌 林大超[1] 王文鑫 XU Jun;Zeng Debin;LIN Dachao;WANG Wenxin(North China Institute of Science and Technology, Sanhe 065201, China;Mirong (Beijing) Transportation Technology Co, Ltd, Beijing 100086, China)

机构地区：[1]华北科技学院,河北三河065201 [2]弥荣(北京)交通科技有限公司,北京100086

出　　处：《照明工程学报》2021年第2期88-92,112,共6页China Illuminating Engineering Journal

基　　金：中央高校基本科研业务费(3142020046)。

摘　　要：近光灯明暗截止线及拐点检测是汽车前照灯检测中极为重要的技术项目。本文依据热点、水平明暗截止线及倾斜明暗截止线三者之间的相对位置关系,提出了一种基于热点的自适应感兴趣区域定位算法,并对其进行了较为详细的阐述。最后,通过使用标准光源,从视觉和检测偏转角两个方面对算法进行验证。验证结果表明,本文的算法具有较好的鲁棒性、稳定性及实用性。Detection of the cut-off line and corner of low-beam is an important item in the examination of vehicle headlamps.This paper proposes an adaptive localization algorithm of the region of interest that is realized on the basis of the relationship among the hotspot,the horizontal cut-off line and the inclined cut-off line,and presents an analysis and discussion of the algorithm in detail.The algorithm is then examined from two aspects of the vision and deflection angle measurements,by using the standard low-beam source.The result shows that the proposed algorithm has good robustness,stability and possibility for practice.

关 键 词：前照灯检测 明暗截止线检测 拐点检测 感兴趣区域 

分 类 号：U461.99[机械工程—车辆工程]