Features for Multi-Target Multi-Camera Tracking and Re-Identification

TL;DR

This paper introduces a new neural network-based approach with adaptive loss and hard-identity mining for improved multi-camera person tracking and re-identification, achieving state-of-the-art results on multiple benchmarks.

Contribution

It proposes an adaptive weighted triplet loss and a novel hard-identity mining technique for enhanced feature learning in MTMCT and Re-ID tasks.

Findings

Outperforms state-of-the-art on DukeMTMC tracking benchmarks.

Achieves top results on Market-1501 and DukeMTMC-ReID Re-ID benchmarks.

Provides analysis of correlation between Re-ID and MTMCT performance.

Abstract

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 available.