Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2013, Vol. 14 Issue (11): 822-834    DOI: 10.1631/jzus.C1300090
    
Road model prediction based unstructured road detection
Wen-hui Zuo, Tuo-zhong Yao
Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China; Ningbo Institute of Materials Technology & Engineering, Chinese Academy of Sciences, Ningbo 315201, China
Road model prediction based unstructured road detection
Wen-hui Zuo, Tuo-zhong Yao
Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China; Ningbo Institute of Materials Technology & Engineering, Chinese Academy of Sciences, Ningbo 315201, China
 全文: PDF 
摘要: Vision-based road detection is an important research topic in different areas of computer vision such as the autonomous navigation of mobile robots. In outdoor unstructured environments such as villages and deserts, the roads are usually not well-paved and have variant colors or texture distributions. Traditional region- or edge-based approaches, however, are effective only in specific environments, and most of them have weak adaptability to varying road types and appearances. In this paper we describe a novel top-down based hybrid algorithm which properly combines both region and edge cues from the images. The main difference between our proposed algorithm and previous ones is that, before road detection, an off-line scene classifier is efficiently learned by both low- and high-level image cues to predict the unstructured road model. This scene classification can be considered a decision process which guides the selection of the optimal solution from region- or edge-based approaches to detect the road. Moreover, a temporal smoothing mechanism is incorporated, which further makes both model prediction and region classification more stable. Experimental results demonstrate that compared with traditional region- and edge-based algorithms, our algorithm is more robust in detecting the road areas with diverse road types and varying appearances in unstructured conditions.
关键词: Road detectionSurface layoutRoad model predictionTemporal smoothing    
Abstract: Vision-based road detection is an important research topic in different areas of computer vision such as the autonomous navigation of mobile robots. In outdoor unstructured environments such as villages and deserts, the roads are usually not well-paved and have variant colors or texture distributions. Traditional region- or edge-based approaches, however, are effective only in specific environments, and most of them have weak adaptability to varying road types and appearances. In this paper we describe a novel top-down based hybrid algorithm which properly combines both region and edge cues from the images. The main difference between our proposed algorithm and previous ones is that, before road detection, an off-line scene classifier is efficiently learned by both low- and high-level image cues to predict the unstructured road model. This scene classification can be considered a decision process which guides the selection of the optimal solution from region- or edge-based approaches to detect the road. Moreover, a temporal smoothing mechanism is incorporated, which further makes both model prediction and region classification more stable. Experimental results demonstrate that compared with traditional region- and edge-based algorithms, our algorithm is more robust in detecting the road areas with diverse road types and varying appearances in unstructured conditions.
Key words: Road detection    Surface layout    Road model prediction    Temporal smoothing
收稿日期: 2013-04-14 出版日期: 2013-11-06
CLC:  TP317.4  
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
Wen-hui Zuo
Tuo-zhong Yao

引用本文:

Wen-hui Zuo, Tuo-zhong Yao. Road model prediction based unstructured road detection. Front. Inform. Technol. Electron. Eng., 2013, 14(11): 822-834.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/jzus.C1300090        http://www.zjujournals.com/xueshu/fitee/CN/Y2013/V14/I11/822

[1] Li-wei Liu, Yang Li, Ming Zhang, Liang-hao Wang, Dong-xiao Li. 基于K-最近邻域搜寻的ToF深度摄像机和被动立体深度获取的融合技术研究[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(3): 174-186.
[2] Shi-yan Wang, Hui-min Yu. Convex relaxation for a 3D spatiotemporal segmentation model using the primal-dual method[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(6): 428-439.
[3] Qiao-song Chen, Choon-woo Kim. Contrast evaluation methods for natural color images in display systems: within- and cross-content evaluations[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(11): 897-909.
[4] Lei Zhang, Xin Du, Ji-lin Liu. Using concurrent lines in central catadioptric camera calibration[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(3): 239-249.
[5] Hua-jun Feng, Yong-pan Wang, Zhi-hai Xu, Qi Li, Hua Lei, Ju-feng Zhao. Real-time motion deblurring algorithm with robust noise suppression[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(5): 375-380.
[6] Chang-cheng WU, Chun-yu ZHAO, Da-yue CHEN. Improved switching based filter for protecting thin lines of color images[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(1): 36-44.