Real-time temporal texture characterisation using block based motion co-occurrence statistics

Contemporary temporal texture classification methods use pixel based features thus making the process slow for time sensitive applications like video indexing and surveillance. In this paper, a real-time classification technique is presented by using readily available block based motion vectors. Experimental results demonstrate the ability of the proposed technique to classify a large set of temporal textures in realtime with high accuracy.

• Type: Conference
• Year: 2004
• Where: ICIP
• Authors: Ashfaqur Rahman, M. Manzur Murshed
• Keywords: Block Based Motion, ICIP 2004, Image Processing, Pixel Based Features, Real-time Classification Technique, Temporal Texture Classification, Temporal Textures