1 October 2010 Unsupervised video-based lane detection using location-enhanced topic models
Author Affiliations +
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.
© (2010) Society of Photo-Optical Instrumentation Engineers (SPIE)
Hao Sun, Hao Sun, Cheng Wang, Cheng Wang, Boliang Wang, Boliang Wang, Naser El-Sheimy, Naser El-Sheimy, } "Unsupervised video-based lane detection using location-enhanced topic models," Optical Engineering 49(10), 107201 (1 October 2010). https://doi.org/10.1117/1.3490422 . Submission:
JOURNAL ARTICLE
9 PAGES


SHARE
RELATED CONTENT

Automatic selection of visual features and classifiers
Proceedings of SPIE (December 22 1999)
Context-enhanced video understanding
Proceedings of SPIE (January 09 2003)

Back to Top