Please wait a minute...
工程设计学报
Chinese Journal of Engineering Design  2013, Vol. 20 Issue (2): 157-162    DOI:
    
Unstructured road-detection algorithm based on multiple models and optimization
 LIU  Yuan, SONG  Xiao-Lin, ZHANG  Wei-Wei
State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body， Hunan University， Changsha 410082， China
Download: HTML     PDF(891KB)
Export: BibTeX | EndNote (RIS)      

Abstract  Unstructured road-detection has been a difficulty in the road-detection algorithms. An unstructured road-detection approach based on color Gaussian mixture model and parabolic model was presented. First we took the full-resolution color image and produced a low-resolution color image by a combination of averaging filtering and sub-sampling， and had illumination compensation. Then we formulated Gaussian mixture model based on K-means algorithm， which was optimized clustering center for the road area and the other areas. Next we solved these parameters of right and left road parabolic models by the least square method. Lastly， we fitted the boundary of the road and achieved the extraction of it. The experimental results show that this approach has robustness against uneven illumination， shadows and reliability improving the processing speed．

Key words： unstructured road-detection      illumination compensation      color Gaussian mixture model      K-means algorithm      parabolic model     
Published: 28 April 2013
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LIU Yuan
SONG Xiao-Lin
ZHANG Wei-Wei
Cite this article:

LIU Yuan, SONG Xiao-Lin, ZHANG Wei-Wei. Unstructured road-detection algorithm based on multiple models and optimization. Chinese Journal of Engineering Design, 2013, 20(2): 157-162.

URL:

https://www.zjujournals.com/gcsjxb/     OR     https://www.zjujournals.com/gcsjxb/Y2013/V20/I2/157


基于多模型结合优化的非结构化道路检测算法

非结构化道路检测一直是道路检测算法中的难点．提出一种基于彩色混合高斯模型与抛物线模型相结合的优化的非结构化道路检测算法．首先采用中值滤波和二次采样法将待处理彩色图像由高分辨率变为低分辨率图像， 并对图像进行光照补偿；然后建立基于优化聚类中心的Kmeans算法的混合高斯模型，通过最小二乘法求解左右道路抛物线模型参数；最后完成对道路边界线的拟合，实现其提取．实验结果表明，该算法对光照不均、阴影等影响的图像处理具有较强的抗干扰性，提高了运算速度，具有一定的鲁棒性和实时性．

关键词： 非结构化道路检测,  光照补偿,  彩色混合高斯模型,  K-means算法,  抛物线道路模型 
[1] YE Jian， GAO Jin-liang， DIAO Mei-ling， LI Dong-ping， WANG Jing-hui. Application study on urban water supply network planning based on fractal theory[J]. Chinese Journal of Engineering Design, 2014, 21(6): 562-565.