Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking

Abstract

Traditional multiple object tracking methods divide the task into two parts: affinity learning and data association. The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted cost function of data association stage, which prevents the tracking goals from learning directly from the feature. In this paper, we present a new multiple object tracking (MOT) framework with data-driven association method, named as Tracklet Association Tracker (TAT). The framework aims at gluing feature learning and data association into a unity by a bi-level optimization formulation so that the association results can be directly learned from features. To boost the performance, we also adopt the popular hierarchical association and perform the necessary alignment and selection of raw detection responses. Our model trains over 20X faster than a similar approach, and achieves the state-of-the-art performance on both MOT2016 and MOT2017 benchmarks.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• MOT16: A Benchmark for Multi-Object Tracking
• Multiple Object Tracking: A Literature Review
• Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation
• Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies
• Fusion of Head and Full-Body Detectors for Multi-Object Tracking

Cited by in corpus (7)

• Multiple Object Tracking by Flowing and Fusing
• Refinements in Motion and Appearance for Online Multi-Object Tracking
• Multi-object Tracking via End-to-end Tracklet Searching and Ranking
• Local Metrics for Multi-Object Tracking
• State-aware Re-identification Feature for Multi-target Multi-camera Tracking
• Online Multiple Object Tracking with Cross-Task Synergy
• End-to-End Multi-Object Tracking with Global Response Map