Compressed Video Acquisition and Reconstruction System Based on Structured Sparse Dictionary Learning

Abstract

The invention provides a compressed video acquisition and reconstruction system based on structured sparse dictionary learning, including: a structured sparse dictionary learning module, a video signal sensing module and a reconstruction processing module, wherein: the structured sparse dictionary learning module first The training set is obtained by using subspace clustering method, and then the dictionary is obtained by using the linear subspace learning method and the block sparse dictionary learning method that minimizes block correlation. The sensing module projects the video signal in the form of image blocks, and the obtained data is finally It is decoded and reconstructed in the reconstruction processing module. The present invention provides compressed sampling while also conforming to the distributed progressive structure of the video sampling process, and the special construction of the structured sparse dictionary matrix also improves the accuracy and efficiency of reconstruction, and the present invention greatly improves the sampling of video signals Compared with other methods, it has achieved reconstruction gains under different sampling compression rates, and it also has good scalability.

Description

technical field [0001] The invention relates to a video signal acquisition scheme, in particular to a compressed video acquisition and reconstruction system based on structured sparse dictionary learning. Background technique [0002] The acquisition and encoding (compression) of video signals is crucial for applications such as storage and transmission of video. The traditional signal processing system adopts the mode of sampling first and then compressing: in order to completely preserve all information of the signal, the video should be sampled at a sampling frequency not less than twice the signal bandwidth; the collected original signal is removed after a series of encoding techniques For the purpose of redundancy, the bottleneck of related technologies is that a large amount of sensors and computing resources are spent to obtain a small amount of signal compression data after processing, and the demand for resources at the sampling end is too high. In order to further...

AI Technical Summary

Problems solved by technology

[0003] After searching the literature of the prior art, it was found that Yue M.Lu and Minh N.Do proposed in the article "A Theory for Sampling Signals From a Union of Subspaces" published in the journal "IEEE Transactions on Signal Processing" (TSP) in 2008 The theory of signal sampling based on subspace set is given. This theory gives the conditions of uniqueness and stability to be satisfied for the sampling of signals in the subspace set. However, the subspace set assumed by the theory is composed of a fixed basis As a result, it cannot provide more effective sparsity and adaptability

In the article "Union of Data-driven Subspaces via Subspace Clustering for Compressive VideoSampling" published at the "IEEE Data Compression Conference" (IEEE DCC) conference in 2014, Y.Li and H.Xiong proposed a data-driven subspace set model based on Applying compressed sensing to video sampling, this method directly compresses and samples the video signal at the sampling encoding end, and uses the UoDS base as the sparse base to reconstruct the signal at the decoding end. This method can flexibly and effectively sparse the signal In order to ensure the subjective quality of the video obtained by reconstruction, but the UoDS base used in this method does not consider the overlap between each subspace, which is manifested in the high correlation between blocks so that a compact block sparsity cannot be obtained. thereby reducing the effectiveness of

Images