Abstract: “This article deals with the occupancy 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: railway crossing monitoring, objects detection, background estimation, K-means clustering, Matlab, optical flow, velocity vectors