Title :
Subspace-based preceding vehicle detection
Author :
Mangai, M. Alarmel ; Gounden, N. Ammasai
Author_Institution :
Dept. of Electr. & Electron. Eng., Nat. Inst. of Technol., Tiruchirappalli, India
Abstract :
In this paper, a vision-based preceding vehicle detection scheme using the statistical information of the vehicles and non-vehicles obtained is presented. K clusters are created using the simple K -means clustering algorithm. The partitions are recomputed using the nested subspacing concept. Mahalanobis distance based measure is used for grouping the image patterns and recognizing the vehicles. The performance of the proposed vehicle detection scheme is compared with that of Multi-Clustered Modified Quadratic Discriminant Function (MC-MQDF) method of preceding vehicle detection. Experimental results prove that the proposed scheme is more suitable for a reliable driver assistance system.
Keywords :
computer vision; driver information systems; object detection; object recognition; pattern clustering; road vehicles; statistical analysis; Mahalanobis distance based measure; driver assistance system; k-means clustering algorithm; multiclustered modified quadratic discriminant function; nested subspacing concept; nonvehicle statistical information; subspace-based preceding vehicle detection; vehicle recognition; vision-based preceding vehicle detection scheme; Covariance matrix; Eigenvalues and eigenfunctions; Image color analysis; Space vehicles; Training; Vehicle detection; Mahalanobis distance; driver assistance systems; eigenspace projections; nested subspacing; principal component analysis; vehicle detection;
Conference_Titel :
Recent Advances in Intelligent Computational Systems (RAICS), 2011 IEEE
Conference_Location :
Trivandrum
Print_ISBN :
978-1-4244-9478-1
DOI :
10.1109/RAICS.2011.6069311
