Adaptive Block Compressive Sensing: Toward a Real-Time and Low-Complexity Implementation

• Main Authors: Joseph Zammit, Ian J. Wassell
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Adaptive block compressive imaging; adaptive block compressive sensing; compressed sensing; deterministic sensing matrices; iterative reconstruction
• Online Access: https://ieeexplore.ieee.org/document/9133085/

Adaptive block-based compressive sensing (ABCS) algorithms are studied in the context of the practical realisation of compressive sensing on resource-constrained image and video sensing platforms that use single-pixel cameras, multi-pixel cameras or focal plane processing sensors. In this paper, we introduce two novel ABCS algorithms that are suitable for compressively sensing images or intra-coded video frames. Both use deterministic 2D-DCT dictionaries when sensing the images instead of random dictionaries. The first uses a low number of compressive measurements to compute the block boundary variation (BBV) around each image block, from which it estimates the number of 2D-DCT transform coefficients to measure from each block. The second uses a low number of DCT domain (DD) measurements to estimate the total number of transform coefficients to capture from each block. The two algorithms permit reconstruction in real time, averaging 8 ms and 26 ms for 256 × 256 and 512 × 512 greyscale images, respectively, using a simple inverse 2D-DCT operation without requiring GPU acceleration. Furthermore, we show that an iterative compressive sensing reconstruction algorithm (IDA), inspired by the denoising-based approximate message passing algorithm, can be used as a post-processing, quality enhancement technique. IDA trades off real-time operation to yield performance improvement over state-of-the-art GPU-assisted algorithms of 1.31 dB and 0.0152 in terms of PSNR and SSIM, respectively. It also exceeds the PSNR performance of a state-of-the-art deep neural network by 0.4 dB and SSIM by 0.0126.