← Back to papers
2018 CVPR CVPR 2018

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

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.

🌉 Interdisciplinary Bridge — Computer Vision and Deep Learning
🧭 Keyword Pioneer — multi-target multi-camera tracking
🐣 Hot Topic Early Bird — triplet loss
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Ergys Ristani , Carlo Tomasi

Topics

Computer Vision > Analysis > Object Tracking Computer Vision > Analysis > Person Re-Identification Deep Learning > Learning Types > Representation Learning Deep Learning > Learning Types > Metric Learning

Keywords

metric learning feature learning person re-identification convolutional neural network triplet loss multi-camera tracking multi-target multi-camera tracking hard-identity mining
Download PDF

Related papers

Multi-Shot Pedestrian Re-Identification via Sequential Decision Making 2018
Multi-Cue Correlation Filters for Robust Visual Tracking 2018
Pointwise Convolutional Neural Networks 2018
Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking 2018
Image Generation From Scene Graphs 2018