Yong-Deok Kim

Error Concealment of H.264/AVC Video Frames for Mobile Video Broadcasting

An efficient frame error concealment (EC) algorithm for H.264 video is proposed in this work. The proposed algorithm temporally conceals a lost frame by combining several pixels or several motion vectors using an overlapping window. The proposed algorithm requires a low computational complexity, but provides better performance than the conventional frame error concealment methods. Therefore, the proposed algorithm is suitable for mobile video broadcasting applications.

Big/little deep neural network for ultra low power inference

Deep neural networks (DNNs) have recently proved their effectiveness in complex data analyses such as object/speech recognition. As their applications are being expanded to mobile devices, their energy efficiencies are becoming critical. In this paper, we propose a novel concept called big/LITTLE DNN (BL-DNN) which significantly reduces energy consumption required for DNN execution at a negligible loss of inference accuracy. The BL-DNN consists of a little DNN (consuming low energy) and a full-fledged big DNN. In order to reduce energy consumption, the BL-DNN aims at avoiding the execution of the big DNN whenever possible. The key idea for this goal is to execute the little DNN first for inference (without big DNN execution) and simply use its result as the final inference result as long as the result is estimated to be accurate. On the other hand, if the result from the little DNN is not considered to be accurate, the big DNN is executed to give the final inference result. This approach reduces the total energy consumption by obtaining the inference result only with the little, energy-efficient DNN in most cases, while maintaining the similar level of inference accuracy through selectively utilizing the big DNN execution. We present design-time and runtime methods to control the execution of big DNN under a trade-off between energy consumption and inference accuracy. Experiments with state-of-the-art DNNs for ImageNet and MNIST show that our proposed BL-DNN can offer up to 53.7% (ImageNet) and 94.1% (MNIST) reductions in energy consumption at a loss of 0.90% (ImageNet) and 0.12% (MNIST) in inference accuracy, respectively.

Efficient Multi-Hypothesis Error Concealment Technique for H.264

An efficient multi-hypothesis error concealment algorithm for H.264 video is proposed in this work. The proposed algorithm temporally conceals a lost block by combining several hypothesis blocks in the previous frame. We investigate the error recovery performance according to the number of hypotheses and the weighting coefficients. Simulation results demonstrate that the proposed algorithm provides better performance than the conventional error concealment algorithm, although the additional complexity requirement is negligible.