Joint source-channel distortion modeling for image and video communication

Real-time image and video communication is becoming common in commercial wireless systems. Images and videos have high bandwidth and low latency requirements. Therefore, joint source-channel coding (JSCC) has become very important for wireless image and video communication, especially for real-time applications. An important component of practical JSCC schemes is a distortion estimate that can predict the quality of compressed images and videos at various source coding rates and channel bit error rates. The usual approach in the JSCC literature for quantifying the distortion due to quantization and channel errors is to estimate it via simulations or rate-distortion curves. Where these methods are accurate, they are not feasible for real-time applications because of their computational complexity. For real-time applications, distortion should be estimated using low complexity distortion models. In this dissertation, a distortion model for image transmission is proposed. This model predicts the amount of distortion introduced in a set of images due to quantization and channel errors in a joint manner. The effects of important image coding techniques such as differential coding, entropy coding and run-length coding are taken into account by this model. Results show that this model predicts the distortion with high accuracy. Another model for transmission of video sequences is also proposed in this dissertation. This model predicts the amount of distortion in the coded video sequences due to quantization and channel bit errors. The effects of distortion propagation to subsequent frames due to motion estimation and prediction are also modeled by this distortion model. Distortion is predicted with high accuracy by this model. Unequal power allocation for image and video communication is another research area closely related to JSCC. As an application of the distortion models proposed in this dissertation, I also propose an unequal power allocation scheme for transmission of images over multiple-input multiple-output (MIMO) systems. Data streams of unequal importance are transmitted over separate antennas using unequal power such that the distortion is minimized under a power constraint. Results show that this scheme achieves high quality gains as compared to equal power allocation.