An Efficient Computer Vision AI Powered Application based Fast Harris Corner Detection Accelerator on Zynq-7000 FPGA
Keywords:
HDL, HDL Coder, Fast Harris corner detection, Computer vision, Artificial Intelligence, Object DetectionAbstract
Tools for rapid prototyping have been crucial in the race to market. A frequently-used computer vision, object detection and Artificial Intelligence tool for image processing, real-time contrast enhancement, is the focus of our study as we investigate the possibility of developing an intellectual property core using a fast prototyping technique. In this research paper, we provide a new method that uses HDL Coder-based high-level synthesis (HLS) rapidly to prototype fast corner detection on FPGAs. Implementing image processing algorithms on FPGAs using traditional RTL-based design approaches may prove a tedious, error-prone procedure. By providing a more abstract level of description, HLS frees up designers to concentrate on algorithmic functionality rather than writing inefficient hardware specifications by hand. We employ this feature by using the Harris corner detection method in MATLAB/Simulink, then using the HDL Coder methodology automatically to transform it into generated VHDL code that can be synthesized on Zynq7000 FPGA. Compared to the conventional RTL method, this design flow drastically reduces the development time and complexity. The suggested method for rapid FPGA prototyping in image processing applications is demonstrated to be successful by our practical findings, which indicate that the HLS-based Harris corner detector achieves the performance of real time video processing on a Xilinx Zynq7000 FPGA platform.
Downloads
References
Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 779–788.
V.H. Schulz, F.G. Bombardelli, E. Todt, A Harris corner detector implementation in SoC-FPGA for visual SLAM, in: F. Santos Osorio, ´ R. Sales Gonçalves (Eds.), Robotics. SBR 2016, LARS 2016. Communications in Computer and Information Science 619, Springer, Cham., 2016.
Sui Xuyang, Chen Zhuo, Liu Yicong, et al. Real-time Video Edge Detection System Based on FPGA. Ordnance Industry Automation, 2021, 40(2): 58-60
Jason Cong, Jason Lau, Gai Liu, Stephen Neuendorffer, Peichen Pan, Kees Vissers, and Zhiru Zhang. 2022. FPGA HLS today: Successes, challenges, and opportunities. ACM Trans. Reconfigurable Technol. Syst. 15, 4, Article 51 (Aug. 2022), 42 pages. https://doi.org/10.1145/3530775
Z. Tan and J. S. Smith, "Real-time Detection on FPGAs using High-level Synthesis,"2020 7th International Conference on Information Science and Control Engineering (ICISCE), 2020, pp. 1068-1071, doi: 10.1109/ICISCE50968.2020.00217
Fuentes-Alventosa, A., Gómez-Luna, J. & Medina-Carnicer, R. GUD-Canny: a real-time GPU- based unsupervised and distributed detector. J Real-Time Image Proc 19, 591–605(2022). https://doi.org/10.1007/s11554-022-01208-0
T Saidani and R. Ghodhbani, "Hardware Acceleration of Video Edge Detection with Hight Level Synthesis on the Xilinx Zynq Platform," Engineering, Technology & Applied Science Research, vol. 12, no. 1, pp. 8007–8012, Feb. 2022. DOI: https://doi.org/10.48084/etasr.4615
Fahad Siddiqui, Sam Amiri, Umar Ibrahim Minhas, Tiantai Deng, Roger Woods, Karen Rafferty, and Daniel Crookes. 2019. FPGA-based processor acceleration for image processing applications. Journal of Imaging 5, 1 (2019). https: //doi.org/10.3390/jimaging5010016.
Babu, P.; Parthasarathy, E. Hardware acceleration for object detection using YOLOv4 algorithm on Xilinx Zynq platform. J. Real-Time Image Process. 2022, 19, 931–940.
Farah Naz Taher, Mostafa Kishani, and Benjamin Carrion Schafer. “Design and Optimization of Reliable Hardware Accelerators: Leveraging the Advantages of High-Level Synthesis”. In: 2018 IEEE 24th International Symposium on On-Line Testing And Robust System Design (IOLTS). 2018, pp. 232–235. doi: 10.1109/IOLTS.2018.8474222
"AXI4-Stream Video IP and System Design Guide", Xilinx Inc. Manual, Oct. 2019.
S Neuendorffer, T. Li and D. Wang, "Accelerating OpenCV Applications with Zynq-7000 All Programmable SoC using Vivado HLS Video Libraries", Xilinx Inc. Application Note, June 2015.Vivado Design Suite User Guide: High-Level Synthesis," Xilinx, UG902 (v2018.3), 2018.
Kintail, K., Gu, Y.: Model-based Design with Simulink, HDL Coder, and Xilinx System Generator for DSP, pp. 1–15. MathWorks, Inc (2012)
S. Liu, Real time implementation of Harris corner detection system based on FPGA, in: 2017 IEEE International Conference on Real time Computing and Robotics (RCAR), Okinawa, 2017, pp. 339–343, https://doi.org/10.1109/ RCAR.2017.8311884.
MMathWorks, “Limitations for MATLAB Loop Optimization,” HDL coder user guide, pp. 8-30, 2023.
S. Titri, C. Larbes and K. Y. Toumi, “Rapid prototyping of PVS into FPGA: From Model-Based Design to FPGA/ASICs Implementation,” 2014 9th International Design and Test Symposium (IDT), Algeries, Algeria, pp. 162-167, 2014.
El Hajjouji, I., Mars, S., Asrih, Z., & El Mourabit, A. (2020). A novel FPGA implementation of hough transform for straight lane detection. Engineering Science and Technology, an International Journal, 23(2), 274-280. https://doi.org/10.1016/j.jestch.2019.05.0
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
