Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking

TL;DR

Chained-Tracker (CTracker) is an innovative end-to-end model for multiple-object detection and tracking that integrates detection, feature extraction, and data association into a unified framework using chained paired regression with attention mechanisms.

Contribution

The paper introduces the first fully end-to-end MOT model that chains paired bounding box regressions with attention, achieving state-of-the-art results without extra training data.

Findings

Sets new MOTA records on MOT16 and MOT17 datasets

Operates in real-time with high accuracy

Does not require additional training data

Abstract

Existing Multiple-Object Tracking (MOT) methods either follow the tracking-by-detection paradigm to conduct object detection, feature extraction and data association separately, or have two of the three subtasks integrated to form a partially end-to-end solution. Going beyond these sub-optimal frameworks, we propose a simple online model named Chained-Tracker (CTracker), which naturally integrates all the three subtasks into an end-to-end solution (the first as far as we know). It chains paired bounding boxes regression results estimated from overlapping nodes, of which each node covers two adjacent frames. The paired regression is made attentive by object-attention (brought by a detection module) and identity-attention (ensured by an ID verification module). The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective, setting new MOTA records on MOT16 and MOT17 challenge datasets (67.6 and 66.6, respectively), without relying on any extra training data. The source code of CTracker can be found at: github.com/pjl1995/CTracker.