Title :
The obstacle detection on the railway crossing based on optical flow and clustering
Author :
Silar, Zdenek ; Dobrovolny, M.
Abstract :
This article deals with the obstacle detection on a railway crossing (clearance detection). The presented detection is based on the optical flow estimation and classification of the flow vectors by K-means clustering algorithm. The optical flow is based on a modified Lucas-Kanade method. For testing of the developed methods a model was created and the results were verified on a real data.
Keywords :
image classification; image sequences; object detection; pattern clustering; K-means clustering algorithm; clearance detection; flow vector classification; modified Lucas-Kanade method; obstacle detection; optical flow estimation; railway crossing; Adaptive optics; Clustering algorithms; Computer vision; Estimation; Image motion analysis; Optical imaging; Vectors; Background Estimation; K-means Clustering; Matlab; Objects Detection; Optical Flow; Railway Crossing Monitoring; Velocity Vectors;
Conference_Titel :
Telecommunications and Signal Processing (TSP), 2013 36th International Conference on
Conference_Location :
Rome
Print_ISBN :
978-1-4799-0402-0
DOI :
10.1109/TSP.2013.6614039
