FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery

Applications in computer vision and image analysis, including object recognition and diagnostic imaging, are reliant on a fundamental competency in image segmentation. However, high-computation methods are occasionally exceeded by the energy economy and processing speed of typical CPU-based systems....

Full description

Saved in:
Bibliographic Details
Main Authors: Rupali Karthikeyan, Deep Amit Lodaya, Rama Muni Reddy Yanamala, Rayappa David Amar Raj, K. Krishna Prakasha, T. Subeesh, V. Anandkumar, Archana Pallakonda
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11083568/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417225658695680
author Rupali Karthikeyan
Deep Amit Lodaya
Rama Muni Reddy Yanamala
Rayappa David Amar Raj
K. Krishna Prakasha
T. Subeesh
V. Anandkumar
Archana Pallakonda
author_facet Rupali Karthikeyan
Deep Amit Lodaya
Rama Muni Reddy Yanamala
Rayappa David Amar Raj
K. Krishna Prakasha
T. Subeesh
V. Anandkumar
Archana Pallakonda
author_sort Rupali Karthikeyan
collection DOAJ
description Applications in computer vision and image analysis, including object recognition and diagnostic imaging, are reliant on a fundamental competency in image segmentation. However, high-computation methods are occasionally exceeded by the energy economy and processing speed of typical CPU-based systems. To surpass these limitations, a hardware-accelerated picture segmentation method is introduced, leveraging the Alternating Direction Method of Multipliers (ADMM) technology, FPGA parallel processing, and sparse subset selection. ADMM algorithms are designed in high-level synthesis (HLS) C code for deployment on Xilinx Zynq UltraScale+ MPSoC. This approach simplifies hardware integration and maintains accuracy while reducing latency and improving energy efficiency. Significant energy savings and decreased execution times are indicated by experimental results, with FPGA achieving segmentation in 9 ms as opposed to 13 ms on a CPU, thereby proving the tremendous computational efficiency of FPGA-based solutions. These results demonstrate how hardware acceleration can enable scalable real-time applications in limited resources by overcoming computational constraints.
format Article
id doaj-art-0ffcd07a6ee6421e9ead30834248b237
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-0ffcd07a6ee6421e9ead30834248b2372025-08-20T03:32:55ZengIEEEIEEE Access2169-35362025-01-011312824912826110.1109/ACCESS.2025.359016711083568FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution ImageryRupali Karthikeyan0https://orcid.org/0009-0005-1403-2729Deep Amit Lodaya1https://orcid.org/0009-0003-0943-8930Rama Muni Reddy Yanamala2https://orcid.org/0009-0007-9132-4914Rayappa David Amar Raj3https://orcid.org/0000-0002-5888-5513K. Krishna Prakasha4https://orcid.org/0000-0001-7797-1399T. Subeesh5V. Anandkumar6https://orcid.org/0000-0002-4533-9169Archana Pallakonda7https://orcid.org/0009-0005-7865-4156Amrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, IndiaAmrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, IndiaDepartment of Electronics and Communication Engineering, Indian Institute of Information Technology, Design and Manufacturing (IIITDM), Kancheepuram, Chennai, IndiaAmrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, IndiaSchool of Computer Engineering, Manipal Institute of Technology (MIT), Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, IndiaAmrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, IndiaAmrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, IndiaDepartment of Computer Science and Engineering, National Institute of Technology Warangal, Warangal, Telangana, IndiaApplications in computer vision and image analysis, including object recognition and diagnostic imaging, are reliant on a fundamental competency in image segmentation. However, high-computation methods are occasionally exceeded by the energy economy and processing speed of typical CPU-based systems. To surpass these limitations, a hardware-accelerated picture segmentation method is introduced, leveraging the Alternating Direction Method of Multipliers (ADMM) technology, FPGA parallel processing, and sparse subset selection. ADMM algorithms are designed in high-level synthesis (HLS) C code for deployment on Xilinx Zynq UltraScale+ MPSoC. This approach simplifies hardware integration and maintains accuracy while reducing latency and improving energy efficiency. Significant energy savings and decreased execution times are indicated by experimental results, with FPGA achieving segmentation in 9 ms as opposed to 13 ms on a CPU, thereby proving the tremendous computational efficiency of FPGA-based solutions. These results demonstrate how hardware acceleration can enable scalable real-time applications in limited resources by overcoming computational constraints.https://ieeexplore.ieee.org/document/11083568/Aerial imagingcomputer visionimage segmentationoptimizationsparse subset selection
spellingShingle Rupali Karthikeyan
Deep Amit Lodaya
Rama Muni Reddy Yanamala
Rayappa David Amar Raj
K. Krishna Prakasha
T. Subeesh
V. Anandkumar
Archana Pallakonda
FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery
IEEE Access
Aerial imaging
computer vision
image segmentation
optimization
sparse subset selection
title FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery
title_full FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery
title_fullStr FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery
title_full_unstemmed FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery
title_short FPGA-Accelerated Sparse Subset Segmentation Using ADMM for High-Resolution Imagery
title_sort fpga accelerated sparse subset segmentation using admm for high resolution imagery
topic Aerial imaging
computer vision
image segmentation
optimization
sparse subset selection
url https://ieeexplore.ieee.org/document/11083568/
work_keys_str_mv AT rupalikarthikeyan fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery
AT deepamitlodaya fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery
AT ramamunireddyyanamala fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery
AT rayappadavidamarraj fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery
AT kkrishnaprakasha fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery
AT tsubeesh fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery
AT vanandkumar fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery
AT archanapallakonda fpgaacceleratedsparsesubsetsegmentationusingadmmforhighresolutionimagery