DESIGN FPGA-BASED MOVING OBJECT RECOGNITION
Main Article Content
Abstract
With the development of intelligent monitoring, robot vision and IoT technologies, the demand for real-time and low-power mobile object recognition is growing. Traditional CPU/GPU schemes suffer from high latency and energy consumption on edge devices, while FPGA, with high-speed parallel computing and reconfigurable features, becomes ideal for efficient real-time visual process. The paper presents an FPGA-based mobile object recognition system, realizing recognition and tracking. It optimizes traditional algorithms via hardware acceleration to achieve low-latency, cost-effective real-time detection. The frame difference method extracts foreground targets, combined with morphological filtering for denoising. DDR3 stores images, and HDMI outputs videos. Leveraging FPGA’s parallelism, hardware pipeline designs for preprocessing, motion and target detection modules are implemented with Verilog. Modules like ov5640 acquisition, DDR3 control, image processing and HDMI display are developed, finally achieving real-time recognition and frame tracking of moving objects. It provides an efficient hardware solution for low-cost, low-power applications, verifying FPGA’s engineering value in visual processing.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
W. He et al., “A Low-Cost High-Speed Object Tracking VLSI System Based on Unified Textural and Dynamic Compressive Features,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 3, pp. 1013–1017, Mar. 2021. DOI: 10.1109/TCSII.2020.3020883.
M. Laimer, T. Kern, L. Brukner, G. Schitter, and E. Csencsics, “Enabling Precise 2-D In-Plane Displacement Sensing With Low Latency for Motion Tracking Applications,” IEEE Transactions on Instrumentation and Measurement, vol. 74, pp. 1–9, 2025, Art. no. 5046009. DOI: 10.1109/TIM.2025.3615282.
J. Wu, Y. Deng, X. He, et al., “Moving Target Detection Algorithm in Complex Background,” Modern Electronics Technique, vol. 45, no. 19, pp. 59–65, Oct. 2022. DOI: 10.16652/j.issn.1004-373x.2022.19.012.
E. Ieno Junior, L. M. Garces, T. C. Pimenta, and A. J. Cabrera, “FPGA-Based EMD Assist Block for Motion Detection in Critical Environments,” IEEE Latin America Transactions, vol. 15, no. 10, pp. 1856–1863, Oct. 2017. DOI: 10.1109/TLA.2017.8071227.
S. Li and S. Shang, “Infrared Image Weak Small Moving Target Recognition Method Based on Background Difference Method,” Laser Journal, vol. 46, no. 3, pp. 142–148, Mar. 2025. DOI: 10.14016/j.cnki.jgzz.2025.03.142.
C. Wang, C. Fan, and N. Jiang, “Implementation of ‘Low Slow Small’ Object Detection System Based on FPGA,” Optoelectronic Technology, vol. 44, no. 1, pp. 29–35, Mar. 2024. DOI: 10.12450/j.gdzjs.202401006.
W. Ding, D. Yin, and S. Qiu, “Improved Three-Frame Difference Moving Target Recognition Algorithm,” Intelligent Computer and Applications, vol. 12, no. 3, pp. 180–182, Mar. 2022.
T. Feng, Z. Mao, and X. Peng, “Design of a Real-Time Motion Target Detection System Based on FPGA,” Application of Electronic Technique, vol. 49, no. 6, pp. 99–103, 2023. DOI: 10.16157/j.issn.0258-7998.223421.
R. A. Amin, M. Hasan, V. Wiese, and R. Obermaisser, “FPGA-Based Real-Time Object Detection and Classification System Using YOLO for Edge Computing,” IEEE Access, vol. 12, pp. 73268–73278, 2024. DOI: 10.1109/ACCESS.2024.3404623.
J. G. Pandey, “An embedded FPGA–SoC framework and its usage in moving object tracking application,” Des. Autom. Embed. Syst., vol. 25, pp. 213–236, Sep. 2021. DOI: 10.1007/s10617-021-09252-y.
T. Li, B. Jiang, D. Wu, X. Yin, and H. Song, “Tracking Multiple Target Cows’ Ruminant Mouth Areas Using Optical Flow and Inter-Frame Difference Methods,” IEEE Access, vol. 7, pp. 185520–185531, 2019. DOI: 10.1109/ACCESS.2019.2961515.
D. Mukherjee, S. Mukhopadhyay, and G. P. Biswas, “FPGA-based parallel implementation of morphological operators for 2D gray-level images,” Arab. J. Sci. Eng., vol. 42, pp. 3191–3206, Aug. 2017. DOI: 10.1007/s13369-017-2429-y.
Y. Wu, D. Yue, Y. Ding, K. Lu, and G. Zhao, “Crack detection algorithm of expansion circle based on image processing,” Nondestructive Testing, vol. 18, no. 3, pp. 9–13, 2020. DOI: 10.11973/wsjc202003003.
Y. Yamamoto, Y. Iriyama, and S. Muto, “Union operation image processing of data cubes separately processed by different objective filters and its application to void analysis in an all-solid-state lithium-ion battery,” Microscopy, vol. 65, no. 2, pp. 191–198, Apr. 2016. DOI: 10.1093/jmicro/dfv373.
W. Lee, K. Kim, W. Ahn, J. Kim, and D. Jeon, “A Real-Time Object Detection Processor With xnor-Based Variable-Precision Computing Unit,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 31, no. 6, pp. 749–761, Jun. 2023. DOI: 10.1109/TVLSI.2023.3257198.
M. Kim and J. So, “Real-Time Driver Monitoring: Implementing FPGA-Accelerated CNNs for Pose Detection,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 33, no. 7, pp. 1848–1857, Jul. 2025. DOI: 10.1109/TVLSI.2025.3554880.