DocumentCode :
2277567
Title :
Automatic Traffic Lane Detection for Mobile Mapping Systems
Author :
Sun, Hao ; Wang, Cheng ; El-Sheimy, Naser
Author_Institution :
Sch. of Electr. Sci. & Eng., Nat. Univ. of Defense Technol., Changsha, China
fYear :
2011
fDate :
10-12 Jan. 2011
Firstpage :
1
Lastpage :
5
Abstract :
Land-based mobile mapping systems have yielded an enormous time saving in capturing road networks and their surrounding. However, the manual extraction of the road information from the mobile mapping data is still a time-consuming task. This paper presents a robust algorithm for automatic traffic lane detection in image sequences from mobile mapping systems. There are two innovations in this work. 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 (SIFT) 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 use probabilistic Latent Semantic Analysis (pLSA) topic model for simultaneous lane recognition and localization. Experimental results on traffic sequences in VISAT™ mobile mapping data demonstrate the effectiveness and robustness of the proposed method.
Keywords :
feature extraction; image sequences; mobile computing; traffic engineering computing; MSER detector; SIFT descriptor; automatic traffic lane detection; feature appearance characteristics; image sequences; land based mobile mapping systems; lane marking feature extraction; lane marking variations; manual extraction; maximally stable extremal region; mobile mapping data; pLSA topic model; probabilistic latent semantic analysis; road information; road networks; scale invariant feature transform; simultaneous lane recognition; time saving;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multi-Platform/Multi-Sensor Remote Sensing and Mapping (M2RSM), 2011 International Workshop on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-9402-6
Type :
conf
DOI :
10.1109/M2RSM.2011.5697365
Filename :
5697365
Link To Document :
بازگشت