REAL-TIME TEMPORAL TEXTURE CHARACTERISATION USING BLOCK-BASED MOTION CO-OCCURRENCE STATISTICS (TA-P6)

Author(s) : Ashfaqur Rahman (Monash University, Australia) Manzur Murshed (Monash University, Australia)

Abstract : 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 real-time with high accuracy.

Menu