Distributed compressed video sensing based on convolutional sparse coding using Fourier measurement matrix and L1 fidelity term

This paper investigates Distributed Compressed Video Sensing (DCVS) using Convolutional Sparse Coding (CSC). DCVS is a coding method that combines compressed video sensing and distributed video coding. Although many CSC approaches to DCVS use a random matrix as the measurement matrix, our method employs the Fourier matrix for the measurement matrix to reduce the computational load and memory consumption. In addition, this work addresses a DCVS in the convolutional sparse coding manner, which is more robust against object shift than that in a block-wise manner. The convolutional filters are also designed to improve the fidelity by using the L1 fidelity term. The experiments show that the proposed method outperforms the conventional method in SSIM and PSNR while reducing the execution time and memory usage at both the encoders and the decoder's sides.