Contact : 9561854529 Email : submitpaper@ijaea.com editorinchief.ijaea@gmail.com Working Hours: 9am to 9PM

International Journal of Advanced Engineering Application

ISSN: 3048-6807

Submit Paper Apply for Reviewer

FPGA-Based Real-Time Image Processing Systems: Design and Implementation

Author(s):Vihan Sharma P.1, Ananya Pandey S.2, Rohit M.3

Affiliation: 1,2,3Department of Electronics and Communication Engineering, Indira Gandhi Engineering College, India

Page No: 24-28

Volume issue & Publishing Year: Volume 2 Issue 7,July-2025

Journal: International Journal of Advanced Engineering Application (IJAEA)

ISSN NO: 3048-6807

DOI: https://doi.org/10.5281/zenodo.17656793

Download PDF

Article Indexing:

Abstract:
Real-time image processing is a critical requirement in applications such as autonomous vehicles, medical imaging, industrial inspection, and surveillance. Conventional CPU and GPU platforms often fail to meet stringent latency and power constraints due to their sequential execution models and high energy demands. Field Programmable Gate Arrays (FPGAs) provide a promising alternative by leveraging hardware-level parallelism, low latency, and reconfigurability. This paper presents the design and implementation of an FPGA-based image processing system capable of performing edge detection and noise reduction in real-time. A combination of Sobel edge detection and Gaussian filtering algorithms were implemented in Verilog HDL on a Xilinx Artix-7 FPGA. The design was simulated, synthesized, and experimentally validated with live video input. Results indicate that the proposed system achieves 60 fps image processing with an average latency of 12 ms per frame, consuming only 3.5 W of power compared to 65 W on GPU implementations. The findings demonstrate the effectiveness of FPGAs in embedded image processing applications, while highlighting trade-offs in resource utilization and scalability

Keywords: FPGA, Real-Time Image Processing, Sobel Edge Detection, Gaussian Filter, Verilog HDL, Hardware Acceleration

Reference:

  • 1. Gonzalez, R.C., & Woods, R.E. (2008). Digital Image Processing (3rd ed.). Pearson.
  • 2. Suda, N., Chandra, V., Dasika, G., et al. (2016). Throughput-optimized FPGA accelerator for deep convolutional neural networks. Proceedings of the ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, 16–25.
  • 3. Rahman, M., Ahmed, S., & Islam, M.S. (2018). FPGA implementation of Sobel edge detection for real-time image processing. International Journal of Computer Applications, 182(28), 10–15.
  • 4. Zhu, Y., Chen, W., & He, L. (2020). High-level synthesis for FPGA-based image processing systems. Journal of Signal Processing Systems, 92(4), 365–380.
  • 5. Al-Bahadili, H.M., Al-Taani, A.T., & Smadi, A. (2021). FPGA-based architectures for medical image processing: A review. Journal of Imaging, 7(3), 52.
  • 6. Xilinx Inc. (2019). Vivado Design Suite User Guide. Xilinx Documentation.
  • 7. Ochoa, J., et al. (2019). Parallel processing strategies for FPGA-based real-time video analytics. IEEE Access, 7, 114908–114919.
  • 8. Mittal, S. (2018). A survey of FPGA-based accelerators for deep learning. Neurocomputing, 332, 395–408.
  • 9. Jain, P., & Agarwal, R. (2020). FPGA implementation of Gaussian filter for medical image denoising. International Journal of VLSI Design & Communication Systems, 11(5), 45–56.
  • 10. Bai, J., & Yu, H. (2017). Energy-efficient FPGA-based accelerator for image convolution. Electronics Letters, 53(22), 1471–1473.
  • 11. Zhang, C., Li, P., Sun, G., et al. (2015). Optimizing FPGA-based accelerator design for deep convolutional neural networks. Proceedings of FPGA '15, 161–170.
  • 12. Rahman, A., & Javed, F. (2019). Comparative study of GPU vs FPGA for edge detection. Journal of Real-Time Image Processing, 16(5), 1417–1429.
  • 13. Singh, V., & Mehra, R. (2021). Hardware-efficient design of real-time image filters on FPGA. International Journal of Electronics and Communication Engineering, 13(7), 599–606.
  • 14. Krishnan, A., & Rao, K.S. (2018). FPGA-based reconfigurable systems for embedded vision applications. Microprocessors and Microsystems, 62, 142–150.
  • 15. Wang, J., & Li, Y. (2020). A hybrid CPU-FPGA approach for video surveillance. IEEE Transactions on Industrial Informatics, 16(8), 5335–5346.
  • 16. Chen, X., et al. (2021). FPGA-based high-performance architecture for real-time object tracking. Sensors, 21(9), 3142.
  • 17. Banerjee, S., & Dutta, A. (2020). Implementation of convolutional filters using FPGA for UAV image processing. Defence Science Journal, 70(5), 471–478.
  • 18. Yi, S., & Kim, H. (2019). Low-power FPGA implementation of image enhancement algorithms. Electronics, 8(3), 281.
  • 19. Goyal, A., & Sharma, M. (2022). Review of FPGA accelerators for vision-based AI systems. Journal of Artificial Intelligence and Systems, 4(2), 201–218.
  • 20. Praveen, K., & Reddy, D. (2021). High-performance FPGA implementations for real-time image filtering. International Journal of Advanced Research in Electronics and Communication Engineering, 10(6), 122–129.