Title: An algorithm to estimate speed by colour-based object detection

Authors: Aghil Shavalipour; Sallehuddin Mohamed Haris

Addresses: Department of Mechanical and Materials Engineering, Faculty of Engineering and the Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia ' Department of Mechanical and Materials Engineering, Faculty of Engineering and the Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia

Abstract: This paper describes a method to determine the travelling speed of a moving object from a sequence of captured video image frames. Using a new method for the detection of objects in colour images, the target moving object is identified and located in each video frame. The object detection process is performed by a colour segmentation method and a labelling algorithm. By defining a rectangular bounding box around it in every frame, the detected object image is isolated from other moving objects in the video, and tracked. The velocity can then be determined by calculating the distance through which the bounding box centroid moves over a sequence of frames with respect to the frame rate of the video recording.

Keywords: object colour detection; moving centre; bounding box; speed estimation; object detection; travelling speed; moving objects; video images; video frames; colour images; object tracking; colour segmentation; labelling algorithm.

DOI: 10.1504/IJSISE.2014.066599

International Journal of Signal and Imaging Systems Engineering, 2014 Vol.7 No.4, pp.203 - 210

Accepted: 30 May 2013
Published online: 29 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article