Main Article Content
Abstract
Recent advances in computer vision and embedded control have enabled low-cost systems to detect and follow visual targets in real time. This study developed and preliminarily evaluated an Autonomous Optical Tracking System (AOTS) that combines MediaPipe/CVZone and OpenCV face detection on a laptop with Arduino Uno control of two SG90 pan-tilt servos and a 5 mW KY-008 visual alignment indicator. Face-centroid coordinates were converted into pan and tilt commands and transmitted through serial communication. Eight functional scenarios were each repeated 20 times, producing 160 trials. A trial was successful when the face state and the expected actuator or indicator response were correct. The system achieved 159 successful trials (99.4%): seven scenarios reached 20/20, while the centered-target scenario reached 19/20 (95%). Representative response times across six movement conditions ranged from 0.32 to 0.42 s for the pan servo and from 0.28 to 0.50 s for the tilt servo. These results demonstrate prototype feasibility under controlled conditions but should not be interpreted as benchmark face-detection accuracy because pixel-level tracking error, environmental variation, and repeated timing distributions were not recorded. The system is intended solely for benign laboratory and educational use. Further work should evaluate repeated latency, tracking error, illumination, distance, and user safety under standardized conditions.
Keywords
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
- Bazarevsky, V., Kartynnik, Y., Vakunov, A., Raveendran, K., & Grundmann, M. (2019). BlazeFace: Sub-millisecond neural face detection on mobile GPUs [Preprint]. arXiv. https://arxiv.org/abs/1907.05047
- Bradski, G. (2000). The OpenCV library. Dr. Dobb's Journal of Software Tools, 25(11), 120, 122–125.
- Guo, J., Yuan, C., Zhang, X., & Chen, F. (2021). Vision-based target detection and tracking for a miniature pan-tilt inertially stabilized platform. Electronics, 10(18), Article 2243. https://doi.org/10.3390/electronics10182243
- International Electrotechnical Commission. (2014). Safety of laser products—Part 1: Equipment classification and requirements (IEC 60825-1:2014, 3rd ed.). https://webstore.iec.ch/en/publication/3587
- Jiang, M., Shimasaki, K., Hu, S., Senoo, T., & Ishii, I. (2021). A 500-fps pan-tilt tracking system with deep-learning-based object detection. IEEE Robotics and Automation Letters, 6(2), 691–698. https://doi.org/10.1109/LRA.2020.3048653
- Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M. G., Lee, J., Chang, W.-T., Hua, W., Georg, M., & Grundmann, M. (2019). MediaPipe: A framework for building perception pipelines [Preprint]. arXiv. https://arxiv.org/abs/1906.08172
- Nebeluk, R., Zarzycki, K., Seredyński, D., Chaber, P., Figat, M., Domański, P. D., & Zieliński, C. (2023). Predictive tracking of an object by a pan–tilt camera of a robot. Nonlinear Dynamics, 111, 8383–8395. https://doi.org/10.1007/s11071-023-08295-z
- Qu, Y., Yang, B., Yu, Z., Song, Y., & Sun, Y. (2020). Active visual servo pan/tilt control design based on improved augmented LQR. In Proceedings of the 32nd Chinese Control and Decision Conference (CCDC 2020) (pp. 3702–3707). IEEE. https://doi.org/10.1109/CCDC49329.2020.9164025
- Szeliski, R. (2022). Computer vision: Algorithms and applications (2nd ed.). Springer. https://doi.org/10.1007/978-3-030-34372-9
- Zhou, G., Zhang, B., Li, Q., Zhao, Q., & Zhang, S. (2025). Optimizing success rate with nonlinear mapping control in a high-performance Raspberry Pi-based light source target tracking system. PLOS ONE, 20(2), Article e0319071. https://doi.org/10.1371/journal.pone.0319071