Title :
Utilization of Directional Properties of Optical Flow for Railway Crossing Occupancy Monitoring
Author :
Silar, Zdenek ; Dobrovolny, M.
Author_Institution :
Dept. of Inf. Technol., Univ. of Pardubice, Pardubice, Czech Republic
Abstract :
This article deals with the obstacle detection on a railway crossing (clearance detection). Detection is based on the optical flow estimation and classification of the flow vectors by K means clustering algorithm. For classification of passing vehicles is used optical flow direction determination. The optical flow estimation is based on a modified Lucas-Kanade method.
Keywords :
image classification; image sequences; matrix algebra; object detection; pattern clustering; rail traffic; railways; traffic engineering computing; background matrix; clearance detection; directional property utilization; flow vector classification; k-means clustering algorithm; modified Lucas-Kanade method; obstacle detection; optical flow direction determination; optical flow estimation; passing vehicle classification; railway crossing occupancy monitoring; Adaptive optics; Clustering algorithms; Computer vision; Estimation; Image motion analysis; Optical imaging; Vectors;
Conference_Titel :
IT Convergence and Security (ICITCS), 2013 International Conference on
Conference_Location :
Macao
DOI :
10.1109/ICITCS.2013.6717896
