Abstract
The problem of choosing methods for tracking recognized objects in real-time for systems with limited hardware capabilities is considered. It was determined that for such scenarios, it is appropriate to integrate tracking methods into the device, bypassing data transmission via the Internet. Existing methods of tracking an arbitrary number of objects in real-time are considered. Among the performance evaluation metrics, the following were used: MOTA, MOTP, F1, MT, ML, ID, and FM. Based on the primary analysis of the effectiveness of such methods according to the metrics mentioned above, it was proposed to use the V-IOU tracking method to track recognized objects on a mobile platform in a mobile cyber-physical system. Key words: V-IOU, Arbitrary Object Class Tracking, Mobile Platform, Real-Time, MOTA, MOTP, Cyber-Physical System.
Publisher
Lviv Polytechnic National University
Reference51 articles.
1. 1. Hambling, D. (2023), Drones killing without oversight?, New Scientist, 260(3461), 1-8.
2. https://doi.org/10.1016/S0262-4079(23)01937-1.
3. 2. Kushnir, D. (2023). Methods and means of searching and recognizing objects in video
4. images on the mobile platform in real-time. [Doctoral dissertation., Lviv Polytechnic National University»].
5. Institutional repository of Lviv Polytechnic National University.