Publications

Classification Based Inter-Frame Prediction in Video Compression

Published in 5^th International Conference on Advance in Electrical Engineering (ICAEE), 2019

Abstract— Video compression is the technique of reducing the original size or storage of the video content. Traditional video coding uses the block-based translation motion model for this purpose. This approach often fails for preserving the good quality of compression, if the motion discontinuities exist in the video frames. A Block that contains the boundary of moving object need more bit for better prediction of the current frame. In the presence of complex motion model the traditional method catastrophically fails to predict the objects having the multiple motion. In this paper, we present a technique for the classification of blocks either it contains the single motion or multiple motion. Experimental result shows that the average accuracy for classification of HD sequences is 85.76% and the achieved bit rebate is up to 1.083% over standalone HEVC.

Recommended citation: Md. Zahirul Islam, Md. Eimran Hossain Eimon, Boshir Ahmed, Md. Al Mehedi Hasan. "Classification Based Inter-Frame Prediction in Video Compression", 5^th International Conference on Advance in Electrical Engineering (ICAEE) https://ieeexplore.ieee.org/document/8975416

Superpixel Based Inter-Frame Prediction for Video Coding

Published in 5^th International Conference on Advance in Electrical Engineering (ICAEE), 2019

Abstract —Traditional video codec uses the block-based approach for motion estimation and compensation, which is unable to capture the true underlying motion. Blocks consisting the boundary of moving object need more bit for better prediction of the current frame because real-world objects are not block-based and their motion is not translational. One of the main goal of the current standard (HEVC) is to minimize the prediction error energy by using quad-tree splitting method. But if motion discontinuity exits, quad-tree based splitting method uses a large amount of motion bit-rate and also introduces a potential coding overhead in the video encoder and decoder. In this paper, we propose a segmentation-based method of using arbitrary shape superpixel and affine motion registration technique for reducing the prediction error energy between the current and reference frame. This method uses the already encoded reference frame for predicting the current frame. The experimental result shows that good subjective quality with PSNR up to 27.71dB can be obtained using this approach.

Recommended citation: Md. Eimran Hossain Eimon, Md. Zahirul Islam, Md. Shahid Uz Zaman, Md. Al Mehedi Hasan, Boshir Ahmed. "Superpixel Based Inter-Frame Prediction for Video Coding", 5^th International Conference on Advance in Electrical Engineering (ICAEE) https://ieeexplore.ieee.org/document/8975508