Constrained bit-rate control for very low bit-rate streaming-video applications

We propose a low-complexity frame-layer bit-rate control algorithm for very low bit-rate streaming-video applications with causal one-pass processing. Rate control is achieved by jointly adapting the frame rate and quantization step-size. Constraint coding is introduced, which forces the encoder to operate within a subset of operating points on a 2-D grid. The control parameters are also constrained to change in a gradual fashion, allowing bits to be saved in easy scenes so that more bits can be used for difficult scenes. A simple scene-change detector is used to insert intra frames at scene-change boundaries. The proposed algorithm is implemented in H.263 and is compared with the case of fixed control parameters and a conventional off-line bit-rate control based on adapting the quantization step-size. It is shown that the proposed algorithm codes more frames over a given time interval while achieving average PSNR gains over 1 dB and reducing bit-rate fluctuations. Results are confirmed by subjective tests, which show that our bit-rate control consistently provides improved visual quality.