Video surveillance tracking using colour region adjacency graphs

• Published in: 7th International Conference on Image Processing and its Applications pp. 794 - 798
• Main Authors: Bakowski, A, Jones, G.A
• Format: Conference Proceeding
• Language: English
• Published: London IEE 1999
• Subjects: Applied sciences; Combinatorial mathematics; Exact sciences and technology; Image processing; Image recognition; Information, signal and communications theory; Signal processing; Telecommunications and information theory; Television equipment, systems and applications; Video signal processing; object recognition; colour segmentation; graph theory; optical tracking; automatic tracking system; automatic visual control; matching; image segmentation; colour region adjacency graphs; object tracking; image colour analysis; surveillance; video signal processing; video surveillance tracking; attributed region adjacency graphs; shape; illumination; Hough transform techniques; moving camera; image matching; image motion analysis; 2½ dimensional colour space; motion tracking camera; real-time processing; Hough transforms; video streams; moving objects; image recognition; Light source; Segmentation; Image processing; Hough transformation; Illumination; Real time processing; Automatic tracking; Moving body; Color image; Optimization
• ISBN: 0852967179; 9780852967171
• ISSN: 0537-9989
• DOI: 10.1049/cp:19990433

An automatic tracking system is presented which uses the matching of attributed region adjacency graphs to track moving objects. The problem of object recognition with complex colour images is always made difficult by the changing shape and illumination of objects moving relative to complex light sources. Moreover, a moving camera causes additional complications in distinguishing an object. However, by identifying the colour regions of an object in one frame and looking for these regions in the next frame, object tracking can be achieved. This colour segmentation is efficiently performed within a novel 2½ dimensional colour space drawing on established Hough transform techniques. Automatic visual control of the motion tracking camera demands real-time processing of video streams.