Document Type
Article
Publication Date
8-24-2025
Abstract
This thesis presents the design and implementation of a lightweight surveillance system capable of realtime motion detection, object tracking, and behavioral history reconstruction in controlled environments. The system uses System-on-Chip devices such as Raspberry Pi boards equipped with NOIR cameras, monocular cameras, and break-beam sensors that work together to detect and track single or multiple moving objects like colored balls. The prototype is validated in structured settings with the goal of eventual deployment in more dynamic environments, addressing the challenge of reliably tracking visually similar objects with minimal distinguishing features. The architecture integrates computer vision with sensor fusion by combining camera image data with binary signals from break-beam sensors, applying motion prediction to estimate object states over time and using data association strategies to maintain consistent identities across frames. Supporting both centralized and distributed configurations, the framework provides flexibility and scalability for varied deployment scenarios. This research demonstrates the feasibility of reconstructing accurate motion trajectories and behavioral narratives using synchronized, time-stamped data from multiple distributed nodes, contributing to the development of low-cost, scalable surveillance systems with applications in security, automation, and robotics.
Keywords
Computer vision, motion detection, motion tracking, robotics
Disciplines
Artificial Intelligence and Robotics | Computer and Systems Architecture | Digital Communications and Networking | Robotics
Sponsoring Agency
Berry Summer Thesis Institute, Berry Family Foundation
eCommons Citation
Khaung, Aung Myat and Stiffler, Nicholas Michael, "Intelligent Motion Tracking: A Low-Cost Surveillance Framework Using SoC Devices and Sensor Fusion" (2025). Proceedings of the Berry Summer Thesis Institute, 2025. 4.
https://ecommons.udayton.edu/uhp_bsti_2025/4
Included in
Artificial Intelligence and Robotics Commons, Computer and Systems Architecture Commons, Digital Communications and Networking Commons, Robotics Commons
Comments
This research was conducted under the sponsorship of the Berry Summer Thesis Institute and the University Honors Program at the University of Dayton. I would like to give my special thanks to my mentors, Dr. Nicholas M. Stiffler and Dr. Krishna B Kidambi, and my peers from DaRC-ARMS Lab.