AI RESEARCH
Tiny Neural Networks for Multi-Object Tracking in a Modular Kalman Framework
arXiv CS.LG
•
ArXi:2504.02519v2 Announce Type: replace-cross We present a modular, production-ready approach that integrates compact Neural Network (NN) into a Kalmanfilter-based Multi-Object Tracking (MOT) pipeline. We design three tiny task-specific networks to retain modularity, interpretability and eal-time suitability for embedded Automotive Driver Assistance Systems: (i) SPENT (Single-Prediction Network) - predicts per-track states and replaces heuristic motion models used by the Kalman Filter (KF.