Abstract
Adaptive block-based compressive sensing (ABCS) algorithms are studied in the context of the practical realization 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 256x256 and 512x512 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.
Highlights
Our interest in low-power, autonomous image and video sensors, for example, for use in wireless sensor networks [1], has led us to explore compressive sensing (CS) as a means of reducing complexity and power requirements at the sensor
In this paper, we propose two adaptive algorithms to estimate sparsity block boundary variation (BBV) and DCT domain (DD) - that can be applied to compressive image sensing
Extensive MATLAB simulations show that our algorithms achieve state-of-the-art performance amongst CPU reconstructed, real-time algorithms that can be reconstructed from measurements collected from single-pixel cameras, multi-pixel cameras and focal plane processing image sensors
Summary
Our interest in low-power, autonomous image and video sensors, for example, for use in wireless sensor networks [1], has led us to explore compressive sensing (CS) as a means of reducing complexity and power requirements at the sensor. Computing the measurements requires inner products of size B×B rather than H × W and much more energy efficient, and each block can be measured independently, for example, using a multi-pixel camera, thereby accelerating the measurement and reconstruction of the image These benefits come at the expense of reconstruction quality, for example, as measured using the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) [18]. In this paper, we propose two adaptive algorithms to estimate sparsity block boundary variation (BBV) and DCT domain (DD) - that can be applied to compressive image sensing. Extensive MATLAB simulations show that our algorithms achieve state-of-the-art performance amongst CPU reconstructed, real-time algorithms that can be reconstructed from measurements collected from single-pixel cameras, multi-pixel cameras and focal plane processing image sensors These algorithms are reconstructed using one iteration of the inverse 2D DCT transform, in under 8 ms and 30 ms for 256×256 and 512×512 images, respectively. If the adaptive algorithms are further processed by the IDA reconstruction algorithm, we add the hyphenated suffixes -IDA-DnCNN or -IDA-BM3D to show whether the IDA algorithm uses the DnCNN [21] or BM3D [22] denoiser
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
