基于字典学习与稀疏表示的非结构化道路分割方法

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 384-388.

基于字典学习与稀疏表示的非结构化道路分割方法

肖良, 戴斌, 吴涛, 方宇强

国防科技大学机电工程与自动化学院,长沙 410072

收稿日期:2012-09-30 发布日期:2013-06-01
作者简介:肖良(1988- ),男,博士研究生.研究方向:模式识别与智能系统.E-mail:xiaoliang@nudt.edu.cn
基金资助:
国家自然科学基金项目(61075043).

Unstructured road segmentation method based on dictionary learning and sparse representation

XIAO Liang, DAI Bin, WU Tao, FANG Yu-qiang

College of Mechatronic Engineering and Automation, National University of Defense Technology, Changsha 410072, China

Received:2012-09-30 Published:2013-06-01

摘要/Abstract

摘要：

针对野外环境自主车视觉导航问题,提出了一种新颖的基于字典学习与稀疏表示的道路分割算法。该算法以局部图像小片为处理单元,通过选取典型道路图像学习得到路面图像小片的一组字典,并利用车辆前方的一小块区域作为监督,通过在线字典学习对字典进行实时更新,使路面图像小片可在该字典上精确稀疏表示,而非路面图像小片则不能。因此建立了基于字典学习与稀疏表示的分类框架,利用局部图像小片在字典上的稀疏重构误差进行分类。大量实验结果表明,该算法能够适应多变的非结构化道路环境,且对光照、阴影及水坑等具有较好的鲁棒性。

关键词: 字典学习, 稀疏表示, 道路分割, 非结构化环境

Abstract:

For vision navigation of ALV in complicated environments,a novel dictionary learning and sparse representation based road segmentation algorithm was proposed.The local image patch was used as the processing unit;a dictionary was learned based on man-selected typical road image and the dictionary could be updated in real time by online dictionary learning with the little piece of image right before the vehicle as supervision.With this dictionary,the on-road patches could be sparse represented precisely while the off-road patches could not A dictionary Learning and sparse representation based on classification framework was built and the local image patches could be classified by the reconstruction errors of sparse representation.A variety of experiments show that the proposed algorithm is suitable for various unstructured environments and is robust to illumination,shadow and water stains;unstructured environment.

Key words: dictionary learning, sparse representation, road segmentation, unstructured environment

中图分类号:

TP391

肖良, 戴斌, 吴涛, 方宇强. 基于字典学习与稀疏表示的非结构化道路分割方法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 384-388.

XIAO Liang, DAI Bin, WU Tao, FANG Yu-qiang. Unstructured road segmentation method based on dictionary learning and sparse representation[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 384-388.

参考文献

[1] Hui Kong,Jean-Yves Audibert,Jean Ponce.General road detection from a single image[J].IEEE Trans on Image Processing,2010,9(18):2211-2220.

[2] Alon Y,Ferencz A,Shashua A.Off-road path following using region classification and geometric projection constraints[C]// CVPR,2006.

[3] Patrick Conrad,Mike Foedisch.Performace evaluation of color based road detection using neural nets and support vector machines[C]// Proc.Applied Imagery Patt.Recog.Workshop,2003.

[4] Wright J,Yang A Y,Ganesh A,et al.Robust face recognition via sparse representation [J].IEEE TPAMI,2009,31(2):210-227.

[5] Meng Yang,Lei Zhang,Jian Yang,et al.Robust sparse coding for face recognition[C]// Proc.CVPR.Providence,RI,2011:625-632.

[6] Yang J,Yu K,Gong Y,et al.Linear spatial pyramid matching using sparse coding for image classification[C]// CVPR,2009.

[7] Chen-Kuo Chiang,Chih-Hsueh Duan,Shang-Hong Lai,et al.Learning component-level sparse representation using histogram information for image classification [C]// ICCV,2011.

[8] Gabriel Peyre.Sparse modeling of textures[J].Journal of Mathematical Imaging and Vision,2009,34 (1):17-31.

[9] Bin Zhao,Li Fei-fei,Eric P Xing.Online detection of unusual events in videos via dynamic sparse coding[C]// CVPR,2011.

[10] Tropp J A.Greed is good:Algorithmic results for sparse approximation[J].IEEE Trans.Inform.Theory,2004,50(10):2231-2242.

[11] Allen Y Yang,Sastry S S.Fast l1-minimization algorithms and an application in robust face recognition:a review[C]// ICIP,2010.

[12] Julien Mairal,Francis Bach,Jean Ponce,et al.Online dictionary learning for sparse coding[C]// ICML,2009.

[13] Honglak Lee,Alexis Battle,Rajat Raina,et al.Efcient sparse coding algorithms[C]// Advances Neural Info.Proc.Sys,2006.

[14] Engan K,Aase S O,Hakon-Husoy J H.Method of optimal directions for frame design[C]// Int.Conf.Acoust.,Speech,Signal Process,1999:2443-2446.

[15] Michal Aharon,Michael Elad,Alfred Bruckstein.K-SVD:An algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Trans on Signal Processing,2006,54:4311-4322.

Metrics

Viewed

Full text

404

HTML			PDF

Just accepted	Online first	Issue	Just accepted	Online first	Issue
0	0	0	0	0	404

From	Others	local

Times	82	322
Rate	20%	80%

Abstract

Cited

Shared

Discussed