Share Email Print

Optical Engineering

Unsupervised video-based lane detection using location-enhanced topic models
Author(s): Hao Sun; Cheng Wang; Boliang Wang; Naser El-Sheimy
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An unsupervised learning algorithm based on topic models is presented for lane detection in video sequences observed by uncalibrated moving cameras. Our contributions are twofold. First, we introduce the maximally stable extremal region (MSER) detector for lane-marking feature extraction and derive a novel shape descriptor in an affine invariant manner to describe region shapes and a modified scale-invariant feature transform descriptor to capture feature appearance characteristics. MSER features are more stable compared to edge points or line pairs and hence provide robustness to lane-marking variations in scale, lighting, viewpoint, and shadows. Second, we proposed a novel location-enhanced probabilistic latent semantic analysis (pLSA) topic model for simultaneous lane recognition and localization. The proposed model overcomes the limitation of a pLSA model for effective topic localization. Experimental results on traffic sequences in various scenarios demonstrate the effectiveness and robustness of the proposed method.

Paper Details

Date Published: 1 October 2010
PDF: 9 pages
Opt. Eng. 49(10) 107201 doi: 10.1117/1.3490422
Published in: Optical Engineering Volume 49, Issue 10
Show Author Affiliations
Hao Sun, National Univ. of Defense Technology (China)
Cheng Wang, Xiamen Univ. (China)
Boliang Wang, Xiamen Univ. (China)
Naser El-Sheimy, Univ. of Calgary (Canada)

© SPIE. Terms of Use
Back to Top