Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera

In this paper, we address the problem of automatically detecting and tracking a variable number of persons in complex scenes using a monocular, potentially moving, uncalibrated camera. We propose a novel approach for multiperson tracking-by-detection in a particle filtering framework. In addition to...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2011-09, Vol.33 (9), p.1820-1833
Main Authors: Breitenstein, M. D., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Cameras
Categories
Computer science
control theory
systems
detector confidence
detector confidence particle filter
Detectors
Exact sciences and technology
Filtering
Gaussian distribution
Ground plane
Heuristic algorithms
Motion analysis
Multi-object tracking
Object detection
On-line systems
Online
online learning
particle filtering
Pattern recognition. Digital image processing. Computational geometry
pedestrian detection
sequential Monte Carlo estimation
sports analysis
Studies
surveillance
Target tracking
Tracking
tracking-by-detection
traffic safety
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we address the problem of automatically detecting and tracking a variable number of persons in complex scenes using a monocular, potentially moving, uncalibrated camera. We propose a novel approach for multiperson tracking-by-detection in a particle filtering framework. In addition to final high-confidence detections, our algorithm uses the continuous confidence of pedestrian detectors and online-trained, instance-specific classifiers as a graded observation model. Thus, generic object category knowledge is complemented by instance-specific information. The main contribution of this paper is to explore how these unreliable information sources can be used for robust multiperson tracking. The algorithm detects and tracks a large number of dynamically moving people in complex scenes with occlusions, does not rely on background modeling, requires no camera or ground plane calibration, and only makes use of information from the past. Hence, it imposes very few restrictions and is suitable for online applications. Our experiments show that the method yields good tracking performance in a large variety of highly dynamic scenarios, such as typical surveillance videos, webcam footage, or sports sequences. We demonstrate that our algorithm outperforms other methods that rely on additional information. Furthermore, we analyze the influence of different algorithm components on the robustness.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2010.232