Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering

2025-08-07

AI Summary

In generic multi-object tracking (MOT), tracking failures frequently occur for unknown-category objects due to low-confidence detections, weak motion/appearance constraints, and long-term occlusions. To address these challenges, this paper proposes a robust tracking framework based on multi-trajectory fragment association. Our approach first generates high-reliability short-term trajectory fragments via adaptive detection clustering. It then performs multi-cue joint association by fusing spatiotemporal consistency and appearance similarity. Finally, a dynamic trajectory segmentation mechanism is introduced to suppress error accumulation over extended time horizons. Extensive experiments on generic MOT benchmarks demonstrate that the proposed method significantly improves robustness against low-quality detections and long-term occlusions, achieving state-of-the-art performance while maintaining real-time efficiency.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Tracking, profiling, and countermeasures against them

Abstract

Tracking specific targets, such as pedestrians and vehicles, has been the focus of recent vision-based multitarget tracking studies. However, in some real-world scenarios, unseen categories often challenge existing methods due to low-confidence detections, weak motion and appearance constraints, and long-term occlusions. To address these issues, this article proposes a tracklet-enhanced tracker called Multi-Tracklet Tracking (MTT) that integrates flexible tracklet generation into a multi-tracklet association framework. This framework first adaptively clusters the detection results according to their short-term spatio-temporal correlation into robust tracklets and then estimates the best tracklet partitions using multiple clues, such as location and appearance over time to mitigate error propagation in long-term association. Finally, extensive experiments on the benchmark for generic multiple object tracking demonstrate the competitiveness of the proposed framework.

Problem

• Tracking unseen object categories with low-confidence detections
• Handling weak motion and appearance constraints in tracking
• Mitigating error propagation in long-term occlusions

Innovation

• Adaptive detection clustering for robust tracklets
• Multi-tracklet association with spatio-temporal correlation
• Error mitigation using location and appearance clues