Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Has files: NoSubject: search.filters.subject.Compressed Sensing

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Single image super resolution from compressive samples using two level sparsity based reconstruction
    (Elsevier B.V., 2015) Nath, A.G.; Nair, M.S.; Rajan, J.
    Super Resolution based on Compressed Sensing (CS) considers low resolution (LR) image patch as the compressive samples of its high resolution (HR) patch. Compressed sensing based image acquisition systems acquire less number of random linear measurements without first collecting all the pixel values. But using these compressive measurements directly to reconstruct the image causes quality issues. In this paper an image super-resolution method with two level sparsity based reconstruction via patch based image interpolation and dictionary learning is proposed. The first level reconstruction generates a low resolution image from random samples and the interpolation scheme used in this algorithm reduces the HR-LR patch coherency due to neighborhood issue which is a major drawback of single image super resolution algorithms. The dictionary based reconstruction phase generates the high resolution image from the low resolution output of the first level reconstruction phase. The experimental results proved that the proposed two level reconstruction scheme recovers more details of the image and yields improved results from very few samples (around 35-45%) than the state-of-the-art algorithms which uses low resolution image itself as input. The results are compared by considering both PSNR values and visual perception. © 2015 The Authors.
  • No Thumbnail Available
    Item
    Compressed Sensing for Energy and Bandwidth Starved IoT Applications
    (Institute of Electrical and Electronics Engineers Inc., 2018) Ramachandra, G.; Bhat, M.S.
    Ensuring security through the use of video surveillance cameras at public places is becoming attractive these days, thanks to the efficient compression, transmission and storage schemes. To up-scale the surveillance mechanism to large sensor networks, it is imperative that the applications become compatible to wireless sensor networks using Internet of Things (IoT) infrastructure. IoT nodes are generally energy and bandwidth-limited owing to their small size and large scale deployment. Therefore, any image/video acquisition application using IoT infrastructure should function within these constraints. Compressed sensing (CS) is one such paradigm that uses simultaneous sensing and compression and provides a technique for efficient image/video acquisition. This paper investigates the use of compressed sensing for image acquisition in IoT based applications that suffer from energy, bandwidth and storage limitations. © 2018 IEEE.
  • No Thumbnail Available
    Item
    Vision in Versatility: Dual CCD-CMOS Imaging with Compressed Sensing for Sustainable IoT Surveillance Drones
    (Institute of Electrical and Electronics Engineers Inc., 2024) Gambheer, R.; Bhat, M.S.
    In the evolving IoT technology landscape, deploying surveillance drones with advanced imaging for security and efficiency is crucial, particularly in low-light conditions. Traditional imaging relies on either Charge-Coupled Device (CCD) sensors for their low-light prowess or Complementary Metal-Oxide-Semiconductor (CMOS) sensors for their energy efficiency. Our research introduces a novel approach by combining CCD and CMOS sensors into a single hardware platform. This allows for smart switching based on ambient light, optimizing energy use and improving image quality in varied environments. We tackle the high energy use of CCD sensors and the inconsistent performance of CMOS sensors under different lighting by applying compressed sensing (CS) techniques. These are designed to lower energy, bandwidth, and storage needs, making CCD sensors more efficient in the dark. Additionally, we've developed optimized sparse reconstruction algorithms to enhance this dual-sensor system's performance in IoT networks, ensuring high image quality with less resource use. This dual-sensor approach is a breakthrough in using CCD sensors for night surveillance, supporting sustainable IoT goals by saving energy and extending drone lifespans. Our research, backed by theoretical analysis, simulations, and empirical tests, proves our algorithms' ability to reconstruct high-quality images efficiently. Introducing this dual-sensor solution represents a significant step in sustainable IoT surveillance, offering potential for widespread use in various settings. © 2024 IEEE.