基于目标HSV(色调-饱和度-亮度)空间图像自适应分割的直线检测算法  

Straight Line Detection Algorithm Based on Adaptive Segmentation of Target HSV Space Images

作　　者：尉金强 杜文正 孙晓艳 聂婷 唐圣金 WEI Jinqiang;DU Wenzheng;SUN Xiaoyan;NIE Ting;TANG Shengjin(Rocket Force University of Engineering,Xi’an 710025,Shaanxi)

机构地区：[1]火箭军工程大学,陕西西安710025

出　　处：《火箭军工程大学学报》2024年第5期59-68,共10页Journal of Rocket Force University of Engineering

摘　　要：针对现阶段利用数字图像进行半挂车倒车辅助过程中,存在辅助地标线检测效果鲁棒性差和实时性不高等问题,提出了一种基于目标色调-饱和度-亮度(Hue-SaturationValue,HSV)空间图像自适应分割的直线检测算法。首先,对不同场景下的直线目标进行分割提取,通过统计不同场景下目标HSV空间图像直方图确定图像分割的初始阈值,并基于初始阈值提出一种基于目标HSV空间的图像自适应分割算法。然后,对图像进行预处理及边缘检测,提取目标边缘点。最后,采用基于中位数绝对偏差的最小二乘直线检测方法剔除边缘点中的离群值以提高地标直线目标的检测精度。实验结果表明:该算法能够在不同背景、不同光照条件下对目标进行准确检测,具有良好的鲁棒性;与Hough变换算法相比,该算法的运算速度更快,直线检测的准确率更高,并且对不同颜色地标线的检测也具有良好的适用性。To solve problems in exisiting digital images processing-based semi-trailer revers-ing assistant system development,such as poor robustness and low real-time of landmark line de-tection,a straight line detection algorithm based on adaptive segmentation of target Hue-Satura-tion-Value(HSV)space images was proposed.First,line targets in various scenes were seg-mented and extracted.Simultaneously,histograms of target images in the HSV space across dif-ferent scenes were used to determine the initial threshold for image segmentation,based on which an image adaptive segmentation algorithm according to target HSV space images was proposed.Subsequently,the preprocessing and edge detection of images were conducted to extract edge points of targets.Finally,outliers of edge points were eliminated by using a median absolute de-viation-based least squares straight line detection method to improve the detection accuracy of landmark line targets.Experimental results showed that the proposed algorithm is able to accu-rately detect targets under different backgrounds and lighting conditions with good robustness.Compared to the Hough transform algorithm,the algorithm has faster operation speed,higher ac-curacy of straight line detection,and good applicability to the detection of landmark lines of dif-ferent colors.

关 键 词：数字图像处理 目标自适应分割 HSV颜色空间 最小二乘法 中位数绝对偏差 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]