Object Geometry Based Error Resilient Video Coding

Abstract

We present an object geometry based error resilience method. We extract object geometry through analyzing motion vector field at the encoder using the iterative self-organizing data analysis technique algorithm. The extracted object geometry, in the form of an index map, is then embedded in the bitstream. At the decoder side, this information is exploited to recover motion vectors of corrupted macroblocks. The proposed method has been validated in MPEG2 codec in a standard-compliant way. Experimental results carried out on several sequences have shown that the proposed method outperforms two conventional temporal error concealment methods by an average PSNR gain of 0.9 dB and 1.5 dB, respectively.