Distributed Compressed Video Sensing

Abstract

This paper proposes a novel framework called Distributed Compressed Video Sensing (DISCOS) -a solution for Distributed Video Coding (DVC) based on the recently emerging Compressed Sensing theory. The DISCOS framework compressively samples each video frame independently at the encoder. However, it recovers video frames jointly at the decoder by exploiting an interframe sparsity model and by performing sparse recovery with side information. In particular, along with global frame-based measurements, the DISCOS encoder also acquires local block-based measurements for block prediction at the decoder. Our interframe sparsity model mimics state-of-the-art video codecs: the sparsest representation of a block is a linear combination of a few temporal neighboring blocks that are in previously reconstructed frames or in nearby key frames. This model enables a block to be optimally predicted from its local measurements by l1-minimization. The DISCOS decoder also employs a sparse recovery with side information to jointly reconstruct a frame from its global measurements and its local block-based prediction. Simulation results show that the proposed framework outperforms the baseline compressed sensing-based scheme of intraframecoding and intraframe-decoding by 8 − 10dB. Finally, unlike conventional DVC schemes, our DISCOS framework can perform most encoding operations in the analog domain with very low-complexity, making it be a promising candidate for real-time, practical applications where the analog to digital conversion is expensive, e.g., in Terahertz imaging.Index Terms-distributed video coding, Wyner-Ziv coding, compressed sensing, compressive sensing, sparse recovery with decoder side information, structurally random matrices.

Perceptual Distributed Compressive Video Sensing via Reweighted Sampling and Rate-Distortion Optimized Measurements Allocation

“…The GPSR algorithm [12] and the smoothed projected Landweber (SPL) algorithm [13] are utilized for the CS reconstruction of the key frames and the NK frames, respectively. We compare our DCVS codec with four representative DCVS codecs in the literature: DISCOS [1], DISACOS [2], RDO-DCVS [3], and PA-DCVS [4]. For fair comparison, all the DCVS codecs use the same configuration to sample and reconstruct the key frames.…”

“…Most current efforts in DCVS have been focused on enhancing the objective coding performance [1]- [3]. Since the human visual system (HVS) is the ultimate receiver of visual signals, it is worth investigating the perception-based DCVS codec.…”

A Tutorial on Encoding and Wireless Transmission of Compressively Sampled Videos

“…wavelet, DCT), each CS block is represented using a matrix composed of a dictionary of temporal neighboring blocks. While this is shown in [62] to far outperform other methods, it does require a "motion-vector-like" operation at the source node. Because of the high complexity of motion vector calculations, they cannot be implemented on a simple low-complexity and energy constrained sensor node, and are therefore not appropriate for WMSNs.…”

“…In [62], the authors present Distributed Compressed Video Sensing (DISCOS). DISCOS divides a video into two types of frames; key frames (or I-frames) and non-key frames (called CS-frames).…”

Robust face recognition using locally adaptive sparse representation

“…Let K be the number of classes in the training data and N k be the number of training samples in the kth class. We adopt the inter-frame sparsity model [9] in which a block in a video frame can be sparsely represented by few neighboring blocks in reference frames. Fig.…”