Features for Multi-target Multi-camera Tracking and Re-identification

Multi-Target Multi-Camera Tracking (MTMCT) tracks many people through video taken from several cameras. Person Re-Identification (Re-ID) retrieves from a gallery images of people similar to a person query image. We learn good features for both MTMCT and Re-ID with a convolutional neural network. Our contributions include an adaptive weighted triplet loss for training and a new technique for hard-identity mining. Our method outperforms the state of the art both on the DukeMTMC benchmarks for tracking, and on the Market-1501 and DukeMTMC-ReID benchmarks for Re-ID. We examine the correlation between good Re-ID and good MTMCT scores, and perform ablation studies to elucidate the contributions of the main components of our system. Code is available¹.

1. Introduction

Multi-Target Multi-Camera Tracking (MTMCT) aims to determine the position of every person at all times from video streams taken by multiple cameras. The resulting multi-camera trajectories enable applications including visual surveillance, suspicious activity and anomaly detection, sport player tracking, and crowd behavior analysis. In recent years, the number of cameras has increased dramatically in airports, train stations, and shopping centers, so it has become necessary to automate MTMC tracking.