Stable multi-target tracking in real-time surveillance video

TLDR

Existing pedestrian trackers focus on identity maintenance, but surveillance systems need stable bounding‑boxes around pedestrians rather than approximate locations. The authors develop a multi‑target tracking system that delivers stable, accurate head location estimates and release a hand‑annotated dataset for future comparisons. The system performs sliding‑window data association using a multi‑threaded pipeline that fuses asynchronous HOG detections, KLT tracking, and MCMC data association guided by a Minimal Description Length objective to achieve real‑time high‑definition tracking. Qualitative and quantitative tests show the system can provide precise head location estimates for large crowds of pedestrians in real time.

Abstract

The majority of existing pedestrian trackers concentrate on maintaining the identities of targets, however systems for remote biometric analysis or activity recognition in surveillance video often require stable bounding-boxes around pedestrians rather than approximate locations. We present a multi-target tracking system that is designed specifically for the provision of stable and accurate head location estimates. By performing data association over a sliding window of frames, we are able to correct many data association errors and fill in gaps where observations are missed. The approach is multi-threaded and combines asynchronous HOG detections with simultaneous KLT tracking and Markov-Chain Monte-Carlo Data Association (MCM-CDA) to provide guaranteed real-time tracking in high definition video. Where previous approaches have used ad-hoc models for data association, we use a more principled approach based on a Minimal Description Length (MDL) objective which accurately models the affinity between observations. We demonstrate by qualitative and quantitative evaluation that the system is capable of providing precise location estimates for large crowds of pedestrians in real-time. To facilitate future performance comparisons, we make a new dataset with hand annotated ground truth head locations publicly available.