Adaptive spatial-temporal error concealment with embedded side information

Error concealment (EC) is an important technique to recover the lost/damaged video data in transmitting video over error prone networks such as the Internet or wireless networks. Different EC strategies have their strength and weakness for different scenarios. Therefore an adaptive EC approach is desired. However, it is generally difficult for the decoder to figure out which strategy works the best for a specific case. This paper proposes to use data embedding to convey the necessary high level side information in a standard compliant way to help improve the decoder's EC performance. We show that the EC “mode” information (i.e., whether spatial EC or temporal EC should be used) is critical for a lightweight adaptive spatial-temporal EC approach. Experiments show that with such side information embedded in the standard compressed bitstream, significant quality improvement can be achieved in recovering the lost video packets.