Low-Complexity Video Coding Based on Two-Dimensional Singular Value Decomposition
In conventional video coding, the complexity of an encoder is generally much higher than that of a decoder because of operations such as motion estimation consume significant computational resources. Such codec architecture is suitable for downlink transmission model of broadcast. However, in the contemporary applications of mobile wireless video uplink transmission, it is desirable to have low complexity video encoder to meet the resource limitations on the mobile devices. Recent advances in distributed video source coding provide potential reverse in computational complexity for encoder and decoder [1, 2]. In the same spirit, we proposed in this paper a syndrome-based light-weight video encoding scheme for mobile wireless applications. This scheme is based on two innovations: (1) adoption of low resolution low quality reference frames for motion estimation at the decoder; (2) introduction of more powerful product accumulate code. Extensive experimental results have confirmed that this syndrome based encoding can reduce computational complexity at the encoder while maintaining good reconstruction quality at the decoder. Therefore, this light weight video coding scheme is suitable for mobile wireless applications.