Autonomous Optical Tracking System (AOTS): Development of A Computer Vision-Based Face-Tracking Pan-Tilt Prototype Using Arduino
Year: 2026
Type: article
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.
Source: Jurnal Penelitian
Institution: Indonesia Defense University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7203820562
FWCI:
Cites:
Cited by:
Related to: