Distributed compressed sensing encoding and decoding method for video

• Main Authors: KUO YONGHONG, CHEN JIAN, SUN PENGDA
• Format: Patent
• Language: Chinese; English
• Published: 07.08.2020
• Subjects: ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PICTORIAL COMMUNICATION, e.g. TELEVISION

The invention discloses a distributed compressed sensing encoding and decoding method for a video, which solves the problem that a DCVS reconstruction method in the prior art still needs to be improved. The method comprises the following steps of: 1.1, calculating self-adaptive bloc information of a picture; 1.2, performing DCT coding of different sizes according to the obtained block information;2.1, through a large number of experimental tests, creating and calculating optimal scale sample data; 2.2, calculating the texture complexity of a sample picture; 2.3, training the sample data by using a BP neural network to obtain an adaptive scale factor model; 2.4, modifying an original BCS _ SPL algorithm, and adding new input parameters; and 2.5, modifying the whole key frame encoding and decoding process by using an improved BCS _ SPL algorithm. According to the key frame improvement algorithm provided by the invention, the reconstruction time of the image is greatly shortened on the premise of obviously reduc