Distributed Video Adaptive Block Compressive Sensing

TL;DR

This paper introduces two novel algorithms for distributed video adaptive block compressive sensing that leverage neural network components and temporal correlation, significantly improving reconstruction quality and speed in resource-constrained scenarios.

Contribution

The paper proposes two algorithms, VAL-VFI and VAL-IDA-VFI, that use CNNs and temporal correlation to enhance video reconstruction in distributed compressive sensing, diverging from end-to-end neural network training.

Findings

Achieve state-of-the-art video reconstruction quality.

Reduce reconstruction time compared to existing methods.

Effectively utilize temporal correlation for improved performance.

Abstract

Video block compressive sensing has been studied for use in resource constrained scenarios, such as wireless sensor networks, but the approach still suffers from low performance and long reconstruction time. Inspired by classical distributed video coding, we design a lightweight encoder with computationally intensive operations, such as video frame interpolation, performed at the decoder. Straying from recent trends in training end-to-end neural networks, we propose two algorithms that leverage convolutional neural network components to reconstruct video with greatly reduced reconstruction time. At the encoder, we leverage temporal correlation between frames and deploy adaptive techniques based on compressive measurements from previous frames. At the decoder, we exploit temporal correlation by using video frame interpolation and temporal differential pulse code modulation. Simulations show that our two proposed algorithms, VAL-VFI and VAL-IDA-VFI reconstruct higher quality video, achieving state-of-the-art performance.