50results about How to "Improve subjective and objective quality" patented technology

The invention discloses a learning-based low bit rate compressed image super-resolution reconstruction method, and the algorithm is divided into an offline part and an online part. In the offline part, the low-resolution image is first compressed with different compression quality parameter values; then the compressed image is filtered, and then the quantized distortion degree of the filtered compressed image is used as a feature, and the filtered LR image is classified according to its degree of distortion. Establish a classification sample library for multiple classes, and then use each type of sample to train the super-resolution model. In the online part, the input image is firstly filtered, and then its compression distortion category is determined. Then, according to the determination result, the sample library and super-resolution model of the corresponding category are selected to realize super-resolution restoration based on learning. Compared with other algorithms, the method of the present invention can adaptively adjust the matching sample library for input LR images with different degrees of distortion, and can effectively solve the impact of block effect distortion on image super-resolution, and directly solve the problem of low bit rate Compared with the super-resolution restoration of the distorted image, the image reconstructed by the method of the present invention has higher subjective and objective quality.

The invention discloses a stereoscopic video macroblock loss error concealment method. The stereoscopic video macroblock loss error concealment method includes firstly determining the lost macroblocks belong to a left boundary shielding area, a right boundary shielding area or a non-boundary shielding area; then classifying the lost macroblocks belonging to the non-boundary shielding area as motion macroblocks or static macroblocks according to motion and static features of the macroblocks; utilizing a human sight sensitivity feature of the macroblocks to classify the motion macroblocks as sensitive macroblocks and insensitive macroblocks; then utilizing texture and smooth features of the macroblocks to classify the sensitive macroblocks as texture macroblocks and smooth macroblocks; and utilizing manners of time domain compensation prediction, time domain frame copy, parallax compensation prediction, multi-direction interpolation and linear interpolation to restore the lost macroblocks, the static macroblocks, the insensitive macroblocks, the texture macroblocks and the smooth macroblocks. Since adaptive restoration strategies are adopted according to macroblocks with different features, subjective and objective quality of restored macroblocks are effectively improved.

Aiming at an HEVC video coding standard, the invention provides a high-definition video code rate control algorithm based on the Sobel operator and linear regression. The method mainly comprises the steps: finding an optimal initial QP (quantization parameter) for a coded first frame through a learned linear regression model, thereby enabling a coding process to quickly adapt to a set bandwidth; generating the intra-frame and inter-frame first-order gradient information through employing the Sobel operator, and then adaptively selecting optimal gradient information to replace coding complexity to serve as the weight of LCU layer bit distribution. The method enables the bit rate error to be lower, enables the output code rate to be more stable, and is better in subjective and objective quality of a video. An experiment result indicates that the method, compared with an HEVC standard code rate control scheme K0103, reduces the bit rate error by about 0.67%, and improves the peak SNR by about 0.44dB.