基于颜色空间结合的地面交通标志检测算法  

Ground Traffic Sign Detection Algorithm based on Color Space Combination

作　　者：王晓娅 任锐 文成玉[1] WANG Xiaoya;REN Rui;WEN Chengyu(College of Communicating Engineering,Chengdu University of Information Technology,Chengdu,Chengdu 610225,China)

机构地区：[1]成都信息工程大学通信工程学院,四川成都610225

出　　处：《成都信息工程大学学报》2024年第6期702-711,共10页Journal of Chengdu University of Information Technology

基　　金：四川省科技计划资助项目(2023YFS0422)。

摘　　要：针对传统的检测算法存在过度引入噪声,以及错误地进行边缘定位而导致误检、漏检等现象,提出一种基于HSL和Lab颜色空间结合的地面交通标志检测算法。区别于传统的检测算法利用物体的物理特征对物体进行边缘响应而达到检测目的,该算法高度依赖物体的颜色特征,对带有鲜明颜色特征的物体的检测效果较优。观察发现,路面上的交通标志,车道线、斑马线等往往都是明亮的白色和黄色,因此,该算法可以更好地应用于实际交通场景下的地面交通标志。实验结果表明,该算法针对普通场景和复杂场景下的地面交通标志检测的效果均优于传统检测算法,对噪声的抗干扰能力以及对真实边缘的定位能力更强。A ground traffic sign detection algorithm based on the combination of HSL and Lab color space is proposed to address the excessive introduction of noise in traditional detection algorithms and the occurrence of false or missed detec-tion caused by incorrect edge positioning.Unlike traditional detection algorithms that utilize the physical features of ob-jects in images to perform edge response on objects for detection purposes,this algorithm highly relies on the color fea-tures of objects and has excellent detection performance for objects with distinct color features.Observation shows that traffic signs on the road,such as lane markings and zebra crossings,are often bright white and yellow.Therefore,this algorithm can be well applied to ground traffic signs in actual traffic scenarios.The experimental results show that the al-gorithm performs better than traditional detection algorithms for ground traffic sign detection in both ordinary and complex scenes,with stronger anti-interference ability to noise and positioning ability to real edges.

关 键 词：边缘检测 颜色空间 交通标志 HSL LAB 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]