MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective measure of performance and are therefore important guides for rese...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision Vol. 129; no. 4; pp. 845 - 881
Main Authors: Dendorfer, Patrick, Os̆ep, Aljos̆a, Milan, Anton, Schindler, Konrad, Cremers, Daniel, Reid, Ian, Roth, Stefan, Leal-Taixé, Laura
Format: Journal Article
Language:English
Published: New York Springer US 01.04.2021
Springer
Springer Nature B.V
Subjects:
Algorithms
Artificial Intelligence
Autonomous cars
Benchmarks
Cameras
Computer Imaging
Computer Science
Computer vision
Error analysis
Image Processing and Computer Vision
Labels
Machine learning
Machine vision
Multiple target tracking
Pattern Recognition
Pattern Recognition and Graphics
Pedestrians
Performance evaluation
Special Issue on Performance Evaluation in Computer Vision
Visibility
Vision
Evaluation
Computer vision
MOTA
MOTChallenge
Multi-object-tracking
ISSN:0920-5691, 1573-1405
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective measure of performance and are therefore important guides for research. We present MOTChallenge , a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data and create a framework for the standardized evaluation of multiple object tracking methods. The benchmark is focused on multiple people tracking, since pedestrians are by far the most studied object in the tracking community, with applications ranging from robot navigation to self-driving cars. This paper collects the first three releases of the benchmark: (i) MOT15 , along with numerous state-of-the-art results that were submitted in the last years, (ii) MOT16 , which contains new challenging videos, and (iii) MOT17 , that extends MOT16 sequences with more precise labels and evaluates tracking performance on three different object detectors. The second and third release not only offers a significant increase in the number of labeled boxes, but also provide labels for multiple object classes beside pedestrians, as well as the level of visibility for every single object of interest. We finally provide a categorization of state-of-the-art trackers and a broad error analysis. This will help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light into potential future research directions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-020-01393-0