Zhu Xiuchang

Compressed video super-resolution reconstruction based on regularized algorithm

Estimating high-resolution (HR) video from a sequence of low-resolution (LR) compressed observations is the focus of this paper. Based on the theory of regularization, this paper proposes a new form of regularized cost function to control the within-channel balance between received data and prior information, and a channel weight coefficient to control the cross-channel fidelity. The LR frames are adaptively weighted according to their reliability and the regularization parameter is simultaneously estimated for each channel with ameliorating artifacts in compressed video. An iterative gradient descent algorithm is utilized to reconstruction the HR video. Experimental results demonstrate that the proposed algorithm has an improvement in terms of both objective and subjective quality

Distributed adaptive compressed video sensing using smoothed projected landweber reconstruction

A novel Compressed-Sensing-based (CS-based) Distributed Video Coding (DVC) system, called Distributed Adaptive Compressed Video Sensing (DISACOS), is proposed in this paper. In this system, the input frames are divided into key frames and non-key frames, which are encoded by block CS sampling. The key frames are encoded as CS measurements at substantially higher rates than the non-key frames and decoded by the Smoothed Projected Landweber (SPL) algorithm using multi-hypothesis predictions. For the non-key frames, a small number of CS measurements are first transmitted to detect blocks having low-quality Side Information (SI) generated by the conventional interpolation or extrapolation at the decoder; then, another group of CS measurements are sampled again upon the decoders request. To fully utilise the CS measurements, we adaptively allocate these measurements to each block in terms of different edge features. Finally, the residual frame is reconstructed using the SPL algorithm and the decoded non-key frame is simply determined as the sum of the residual frame and the SI. Experimental results have revealed that our CS-based DVC system yields better rate-distortion performance when compared with other schemes.

RESEARCH ON TWO-DIMENSIONAL LDA FOR FACE RECOGNITION

The letter presents an improved two-dimensional linear discriminant analysis method for feature extraction. Compared with the current two-dimensional methods for feature extraction, the improved two-dimensional linear discriminant analysis method makes full use of not only the row and the column direction information of face images but also the discriminant information among different classes. The method is evaluated using the Nanjing University of Science and Technology (NUST) 603 face database and the Aleix Martinez and Robert Benavente (AR) face database. Experimental results show that the method in the letter is feasible and effective.

Multi-view Synthesis Using the Relative Affine Structure from Video Sequences

This paper proposes an approach for Multi-view synthesis, the process of view synthesis based on the relative affine structure. We specifying the virtual camera position in an uncalibrated setting, based on the interpolation of the motion among the reference views. Novel images can be rendered from virtual cameras moving on parametric trajectories. Synthetic and real experiments illustrate the approach.

Fuzzy reasoning based intra frame error concealment for block based images

A new technique of information-restoration for the block-based images is proposed. This scheme is based on fuzzy reasoning and aims at intra frame error concealment for gray level images. Fuzzy reasoning is applied to classify the results of pixel matching and then the pixel correction is managed to modify the pixel values of the blocks with low RED (recover exactness degree). The experiment results show the effectiveness of our proposed method.