Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking

Abstract

To help accelerate progress in multi-target, multi-camera tracking systems, we present (i) a new pair of precision-recall measures of performance that treats errors of all types uniformly and emphasizes correct identification over sources of error; (ii) the largest fully-annotated and calibrated data set to date with more than 2 million frames of 1080p, 60fps video taken by 8 cameras observing more than 2,700 identities over 85 minutes; and (iii) a reference software system as a comparison baseline. We show that (i) our measures properly account for bottom-line identity match performance in the multi-camera setting; (ii) our data set poses realistic challenges to current trackers; and (iii) the performance of our system is comparable to the state of the art.

ECCV 2016 Workshop on Benchmarking Multi-Target Tracking

References in corpus (2)

• MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
• Ten Years of Pedestrian Detection, What Have We Learned?

Cited by in corpus (18)

• Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets
• A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
• Unsupervised Person Re-identification via Softened Similarity Learning
• Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
• Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
• PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network
• BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving
• Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
• Learning Diverse Features with Part-Level Resolution for Person Re-Identification
• Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification
• Deep Multi-Index Hashing for Person Re-Identification
• Cross-Correlated Attention Networks for Person Re-Identification
• Temporal Continuity Based Unsupervised Learning for Person Re-Identification
• VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification
• Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification
• Adaptive Deep Metric Embeddings for Person Re-Identification under Occlusions
• Person Re-identification with Bias-controlled Adversarial Training
• End-to-End Multi-Object Tracking with Global Response Map