Time-series Meets Complex Motion Modeling: Robust and Computational-effective Motion Predictor for Multi-object Tracking

2026-04-30

AI Summary

This work addresses the challenge of modeling complex nonlinear motion—such as abrupt stops and sharp turns—in multi-object tracking, which often incurs high computational costs and limits practical applicability in existing approaches. The authors propose TCMP, an efficient motion prediction framework built upon an enhanced temporal convolutional network that integrates dilated convolutions with a lightweight regression head to accurately capture motion dynamics over arbitrary temporal context lengths. Departing from computationally intensive generative modeling paradigms, TCMP achieves state-of-the-art performance with only 1.4% of the parameters and 5% of the computational overhead of current best methods, surpassing them on key metrics including HOTA (63.4%), IDF1 (65.0%), and AssA (49.1%), thereby offering a compelling balance of accuracy, robustness, and efficiency.

Abstract

Multi-object tracking (MOT) is critical in numerous real-world applications, including surveillance, autonomous driving, and robotics. Accurately predicting object motion is fundamental to MOT, but current methods struggle with the complexities of real-world, non-linear motion (e.g., sudden stops, sharp turns). While recent research has gravitated towards increasingly complex and computationally expensive generative models to tackle this problem, their practical utility is often constrained. This paper challenges that paradigm, arguing that such complexity is not only unnecessary but can be outperformed by a more efficient, purpose-built approach. We introduce the Temporal Convolutional Motion Predictor (TCMP), a novel framework for MOT that leverages a modified Temporal Convolutional Network (TCN) featuring dilated convolutions and a regression head. This design allows for effective motion prediction across arbitrary temporal context lengths. Experimental results demonstrate that our approach achieves state-of-the-art performance, specifically improves upon the previous best method in several key metrics: HOTA (a measure of overall tracking accuracy) increases from 62.3% to 63.4%, IDF1 (a measure of identity preservation) rises from 63.0% to 65.0%, and AssA (a measure of association accuracy) improves from 47.2% to 49.1%. Significantly, TCMP achieves this performance while being highly efficient; it has only 0.014 times the parameters and requires only 0.05 times the computational cost (FLOPs) compared to the SOTA method. while is only 0.014 times the size (in terms of parameters) and requires only 0.05 times the computational cost (in terms of FLOPs). These findings highlight the robustness of our method to advance MOT systems by ensuring adaptability, accuracy, and efficiency in complex tracking environments.

Problem

• Multi-object tracking
• motion prediction
• non-linear motion
• computational efficiency
• real-world complexity

Innovation

• Temporal Convolutional Network
• Multi-object Tracking
• Motion Prediction
• Computational Efficiency
• Dilated Convolutions