Adaptive Rate Allocation Algorithm for Transmission of Multiple Embedded Bit Streams over Time-Varying Noisy Channels

Abstract

An efficient rate allocation algorithm for the progressive transmission of multiple images over time-varying noisy channels is proposed. The algorithm is initiated by the distortion optimal solution [1] for the first image and searches for the optimal rate-allocation for each subsequent image in the neighborhood of the solution for the previous image. Given the initial solution, the algorithm is linear-time in the number of transmitted packets per image and its rate allocation solution for each image can achieve a performance equal or very close to the distortion optimal solution for that image. Our simulations for the transmission of images, encoded by embedded source coders, over the binary symmetric channel (BSC) show that with very low complexity the proposed algorithm successfully adapts the channel code rates to the changes of the channel parameter.