Design and Evaluation of an Affordable and Reliable Pan-Tilt Tracking System

eng Artykuł w języku angielskim DOI: 10.14313/PAR_256/101

wyślij Damian Łoziński *, Bartosz Kozłowski ** * Independent researcher, IEEE Member, Warsaw, Poland ** Warsaw University of Technology, Faculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Nowowiejska 15/19, 00-665 Warsaw, Poland

Pobierz Artykuł

Abstract

This paper presents the design and evaluation of an affordable and reliable pan-tilt tracking system. The proposed solution addresses the limitations of existing professional remote-controlled camera systems by offering a low-cost, modular hardware design combined with a finetunable control algorithm for real-time person or face tracking. Leveraging widely available components and 3D printing technology, the system is optimized for ease of production and accessibility. Experimental results demonstrate that the system achieves stable and smooth tracking performance, balancing responsiveness and precision while maintaining affordability. This work contributes to making advanced tracking technologies more accessible for applications such as video production, conferencing, and robotics.

Keywords

3D printing, adaptive PID control, camera automation, embedded system, face detection, low-cost mechatronics, object tracking, pan-tilt control, signal filtering, vision system

Projekt i ocena niskokosztowego i niezawodnego systemu śledzenia z dwuosiowym mechanizmem obrotu (pan-tilt)

Streszczenie

W artykule przedstawiono projekt oraz ocenę niskokosztowego i niezawodnego systemu śledzenia z dwuosiowym mechanizmem obrotu (pan-tilt). Proponowane rozwiązanie stanowi odpowiedź na ograniczenia występujące w profesjonalnych, zdalnie sterowanych systemach kamer, oferując modułową konstrukcję sprzętową oraz precyzyjnie dostrajalny algorytm sterowania, umożliwiający śledzenie osób lub twarzy w czasie rzeczywistym. System wykorzystuje ogólnodostępne komponenty oraz technologię druku 3D, co sprzyja łatwości jego wytwarzania i szerokiej dostępności. Wyniki badań eksperymentalnych potwierdzają, że zaprojektowane rozwiązanie zapewnia stabilne i płynne działanie, skutecznie równoważąc responsywność z precyzją, przy zachowaniu niskich kosztów implementacji. Przedstawiony system stanowi istotny krok w kierunku upowszechnienia zaawansowanych technologii śledzenia w takich obszarach zastosowań, jak produkcja wideo, wideokonferencje czy robotyka.

Słowa kluczowe

adaptacyjne sterowanie PID, automatyzacja kamer, druk 3D, filtracja sygnałów, mechatronika niskokosztowa, śledzenie obiektów, sterowanie pan-tilt, system wizyjny, systemy wbudowane, wykrywanie twarzy

Bibliografia

  1. Viola P., Jones M., Rapid object detection using a boosted cascade of simple features, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, DOI: 10.1109/CVPR.2001.990517.
  2. Lienhart R., Maydt J., An extended set of Haar-like features for rapid object detection, Proceedings of the International Conference on Image processing, IEEE, 2002, DOI: 10.1109/ICIP.2002.1038171.
  3. Dalal N., Histograms of oriented gradients for human detection, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, DOI: 10.1109/CVPR.2005.177.
  4. Girschick R., Fast R-CNN, Proceedings of the IEEE International Conference on Computer Vision, 2015, 1440–1448, DOI: 10.1109/ICCV.2015.169.
  5. Ren S., He K., Girshick R., Sun J., Faster R-CNN: Towards real-time object detection with region proposal networks, Advances in Neural Information Processing Systems, 2015, 91–99.
  6. Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.-Y., Berg A.C., SSD: Single Shot MultiBox Detector, European Conference on Computer Vision, Springer, LNIP Vol. 9905, 2016, 21–37.
  7. Hussain M., YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection, “Machines”, Vol. 11, No. 7, 2023, DOI: 10.3390/machines11070677.
  8. Tian Y., Ye Q., Doermann D., YOLOv12: Attention-Centric Real-Time Object Detectors, “Computer Vision and Pattern Recognition”, 2025, DOI: 10.48550/arXiv.2502.12524.
  9. Terven J., Córdova-Esparza D.-M., Romero-González J.-A., A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS, “Machine Learning and Knowledge Extraction”, Vol. 5, No. 4, 2023, 1680–1716, DOI: 10.3390/make5040083.
  10. Dong C., Du G., An enhanced real-time human pose estimation method based on modified YOLOv8 framework, “Scientific Reports”, Vol. 14, 2024, DOI: 10.1038/s41598-024-58146-z.
  11. Wadekar S.N., Chaurasia A., MobileViTv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features, “Computer Vision and Pattern Recognition”, 2022, DOI: 10.48550/arXiv.2209.15159.
  12. Wu W., Peng H., Yu S., YuNet: A tiny millisecond-level face detector, “Machine Intelligence Research”, Vol. 20, No. 5, 2023, 656–665, DOI: 10.1007/s11633-023-1423-y.
  13. Bazarevsky V., Kartynnik Y., Vakunov A., Raveendran K., Grundmann M., BlazeFace: Sub-millisecond neural face detection on mobile GPUs, “Computer Vision and Pattern Recognition”, 2019, DOI: 10.48550/arXiv.1907.05047.
  14. Chen S., Yang Y., Liu W., Shao J., Yan J., MobileFaceNets: Efficient CNNs for accurate real-time face verification on mobile devices, Springer, LNIP Vol. 10996, 2018, 428–438, DOI: 10.1007/978-3-319-97909-0_46.
  15. Bradski G.R., Real time face and object tracking as a component of a perceptual user interface, Proceedings Fourth IEEE Workshop on Applications of Computer Vision (WACV’98), 1998, 214–219, DOI: 10.1109/ACV.1998.732882.
  16. Bolme D., Beveridge J., Draper B., Lui Y., Visual object tracking using adaptive correlation filters, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010, 2544–2550, DOI: 10.1109/CVPR.2010.5539960.
  17. LukežičA., Vojíř T., Čehovin L., Matas J., Kristan M., Discriminative correlation filter with channel and spatial reliability, “International Journal of Computer Vision”, Vol. 126, 2018, 671–688, DOI: 10.1007/s11263-017-1061-3.
  18. Tsai C.Y., Song K.T., Dutoit X., Brussel H., Nuttin M., Robust mobile robot visual tracking control system using self-tuning Kalman filter, Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA), 2007, 161–166, DOI: 10.1109/CIRA.2007.382860.
  19. Chen X., Wang X., Xuan J., Tracking multiple moving objects using unscented Kalman filtering techniques, “Computer Vision and Pattern Recognition”, 2018, DOI: 10.48550/arXiv.1802.01235.
  20. Henriques J., Caseiro R., Martins P., Batista J., High-speed tracking with kernelized correlation filters, “IEEE Transactions on Pattern Analysis and Machine Intelligence”, Vol. 37, No. 3, 2015, 583–596, DOI: 10.1109/TPAMI.2014.2345390.
  21. He C., Zheng Y.F., Ahalt S.C., Object tracking using the Gabor wavelet transform and the golden section algorithm, “IEEE Transactions on Multimedia”, Vol. 4, No. 4, 2002, 528–538, DOI: 10.1109/TMM.2002.806534.
  22. Rui T., Zhang Q., Zhou Y., Xing J., Object tracking using particle filter in the wavelet subspace, “Neurocomputing”, Vol. 119, 2013, 125–130, DOI: 10.1016/j.neucom.2012.03.036.
  23. Kozlowski B., Wavelet enhanced analytical and evolutionary approaches to time series forecasting, Adaptive and natural computing algorithms, ICANNGA 2007, LNTCS Vol. 4431, 2007, 49–57, DOI: 10.1007/978-3-540-71618-1_6.
  24. Bewley A., Ge Z., Ott L., Ramos F., Upcroft B., Simple online and realtime tracking, “Computer Vision and Pattern Recognition”, 2016, DOI: 10.1109/ICIP.2016.7533003.
  25. Cao J., Pang J., Weng X., Khirodkar R., Kitani K., Observation-Centric SORT: Rethinking SORT for robust multi-object tracking, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, 9686–9696, DOI: 10.1109/CVPR52729.2023.00934.
  26. Maggiolino G., Ahmad A., Cao J., Kitani K., Deep OC-SORT: Multi-pedestrian tracking by adaptive re-identification, “Computer Vision and Pattern Recognition”, 2023, DOI: 10.48550/arXiv.2302.11813.
  27. Wojke N., Bewley A., Paulus D., Simple online and realtime tracking with a deep association metric, 2017 IEEE International Conference on Image Processing (ICIP), 2017, 3645–3649, DOI: 10.1109/ICIP.2017.8296962.
  28. Zhang Y., et al., ByteTrack: Multi-object tracking by associating every detection box, “Computer Vision and Pattern Recognition”, 2022, DOI: 10.48550/arXiv.2110.06864.
  29. Zhang Y., Wang C., Wang X., Zeng W., Liu W., FairMOT: On the fairness of detection and re-identification in multiple object tracking, “Computer Vision and Pattern Recognition”, 2021, DOI: 10.1007/s11263-021-01513-4.
  30. Dai Y., Liu W., Li H., Liu L., Efficient foreign object detection between PSDs and metro doors via deep neural networks, “IEEE Access”, Vol. 8, 2020, 46723–46734, DOI: 10.1109/ACCESS.2020.2978912.
  31. Mian A., Realtime face detection and tracking using a single Pan, Tilt, Zoom camera, 23rd International Conference Image and Vision Computing New Zealand, 2008, DOI: 10.1109/IVCNZ.2008.4762103.
  32. Yosafat R., Machbub C., Hidayat E.M.I., Design and implementation of Pan-Tilt control for face tracking, 7th IEEE international conference on system engineering and technology (ICSET), 2017, 217–222, DOI: 10.1109/ICSEngT.2017.8123449.
  33. Permatasari D., Maharani D.A., Backpropagation neural network for tuning PID pan-tilt face tracking, 3rd International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 2018, 357–361, DOI: 10.1109/ICITISEE.2018.8720968.
  34. Nebeluk R., Zarzycki K., Seredyński D., Chaber P., Figat M., Domański P.D., Zieliński C., Predictive tracking of an object by a pan-tilt camera of a robot, “Nonlinear Dynamics”, Vol. 111, No. 9, 2023, 8383–8395, DOI: 10.1007/s11071-023-08295-z.
  35. Yang J., Tang Z., Pei Z., Song X., A novel motion-intelligence-based control algorithm for object tracking by controlling PAN-tilt automatically, “Mathematical Problems in Engineering”, Vol. 2019, No. 1, 2019, DOI: 10.1155/2019/9602460.
  36. Petrov P., An adaptive pan-tilt camera control for visual target tracking, 29th National Conference with International Participation (TELECOM), 2021, 125–128, DOI: 10.1109/TELECOM53156.2021.9659665.
  37. Bradski G., The OpenCV library, “Dr. Dobb’s Journal of Software Tools”, Vol. 25, No. 11, 2000, 120, 122–125.
  38. Harris C.R. et al., Array programming with NumPy, “Nature”, Vol. 585, No. 7825, 2020, 357–362, 2020, DOI: 10.1038/s41586-020-2649-2.
  39. Li X., Xu H., Wang Y., Reproducible evaluation of pan-tilt-zoom tracking, “IEEE Transactions on Circuits and Systems for Video Technology”, Vol. 29, No. 12, 2019, 3609–3622, DOI: 10.1109/TCSVT.2018.2873151.
  40. Kimura H., Kimura H., Umeda S., High speed and wide range object tracking system using pan-tilt cameras, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006, 1019–1024, DOI: 10.1109/IROS.2006.281669.