GenTrack3: Hybrid Stochastic-Deterministic Online Multi-Object Tracking with Cluster-Aware Association
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionRobotics
AI summaryⓘ
The authors present a new method for tracking multiple objects in videos, combining both predictable (deterministic) and uncertain (stochastic) approaches. Their system keeps track of objects as they move, appear, or disappear by matching detections with tracked paths using a special particle method that handles uncertainty. This method also improves how well the system works when tracking many objects or groups. Overall, their approach aims to be more accurate and efficient in complex scenarios.
Multi-object trackingDeterministic methodsStochastic methodsData associationParticle filterTrackletMotion modelsTracking-by-detectionOnline trackingGroup tracking
Authors
Toan Van Nguyen, Rasmus G. K. Christiansen, Dirk Kraft, Leon Bodenhagen
Abstract
Multi-object tracking (MOT) involves maintaining consistent target identities as objects dynamically enter and leave a scene. Deterministic approaches, such as tracking-by-detection with data association, produce reproducible results and are computationally efficient, but they rely heavily on motion models and are sensitive to noisy detections that can lead to association errors. In contrast, stochastic methods explicitly model uncertainty and can better handle complex non-linear dynamics, albeit at the cost of increased computational complexity and variability arising from random sampling. This paper presents an online MOT framework that integrates deterministic and stochastic principles to achieve robust tracking under uncertainty. Furthermore, a novel track-to-detection matching approach is introduced to enhance scalability with increasing target numbers while supporting group tracking. The tracking inference mechanism employs a tracklet that includes identifiers, states, velocities, track penalties and track ages of targets, supporting a systematic tracking pipeline. Each target is associated with a stochastic particle set to compute the matching cost to detections. Reference implementations of the proposed approach and baseline trackers can be found on GitHub: https://github.com/SDU-VelKoTek/GenTrack3.