Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Multi-Camera Multi-Person Tracking Using Reinforcement Learning

Kärrholm, Axel LU and Rickman, Linus LU (2022) In Master'sTheses in Mathematical Sciences FMAM05 20221
Mathematics (Faculty of Engineering)
Abstract
The problem of multi-object-tracking in a network of cameras is an interesting and non-trivial problem. Given videos from a number of cameras the goal of Multi-Camera Multi-Object Tracking (MCMOT) is to find the full visible trajectory of each pedestrian from the videos as the pedestrians move across cameras. Compared to monocular tracking the main difficulties lie in associating pedestrian detections to tracks in locations where the camera views overlap. We develop two MCMOT methods; a traditional threshold-based Simple Online and Realtime Tracking (SORT) algorithm and a reinforcement learning track management method. The methods are evaluated on Blender 3D simulated data sets and on real-world recordings from calibrated cameras. The... (More)
The problem of multi-object-tracking in a network of cameras is an interesting and non-trivial problem. Given videos from a number of cameras the goal of Multi-Camera Multi-Object Tracking (MCMOT) is to find the full visible trajectory of each pedestrian from the videos as the pedestrians move across cameras. Compared to monocular tracking the main difficulties lie in associating pedestrian detections to tracks in locations where the camera views overlap. We develop two MCMOT methods; a traditional threshold-based Simple Online and Realtime Tracking (SORT) algorithm and a reinforcement learning track management method. The methods are evaluated on Blender 3D simulated data sets and on real-world recordings from calibrated cameras. The reinforcement learning model outperforms the more traditional method in Multi-Object Tracking Accuracy (MOTA) up to 4 % on the simulated and real data sets. Finally, our experiments show that the reinforcement learning method can transfer knowledge from simulated to real data during inference. (Less)
Please use this url to cite or link to this publication:
author
Kärrholm, Axel LU and Rickman, Linus LU
supervisor
organization
course
FMAM05 20221
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Multi-Camera Multi-Object Tracking, Reinforcement Learning, Computer Vision, Machine Learning, Object Detection
publication/series
Master'sTheses in Mathematical Sciences
report number
LUTFMA-3480-2022
ISSN
1404-6342
other publication id
2022:E32
language
English
id
9091287
date added to LUP
2022-06-27 15:05:55
date last changed
2022-06-27 15:05:55
@misc{9091287,
  abstract     = {{The problem of multi-object-tracking in a network of cameras is an interesting and non-trivial problem. Given videos from a number of cameras the goal of Multi-Camera Multi-Object Tracking (MCMOT) is to find the full visible trajectory of each pedestrian from the videos as the pedestrians move across cameras. Compared to monocular tracking the main difficulties lie in associating pedestrian detections to tracks in locations where the camera views overlap. We develop two MCMOT methods; a traditional threshold-based Simple Online and Realtime Tracking (SORT) algorithm and a reinforcement learning track management method. The methods are evaluated on Blender 3D simulated data sets and on real-world recordings from calibrated cameras. The reinforcement learning model outperforms the more traditional method in Multi-Object Tracking Accuracy (MOTA) up to 4 % on the simulated and real data sets. Finally, our experiments show that the reinforcement learning method can transfer knowledge from simulated to real data during inference.}},
  author       = {{Kärrholm, Axel and Rickman, Linus}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master'sTheses in Mathematical Sciences}},
  title        = {{Multi-Camera Multi-Person Tracking Using Reinforcement Learning}},
  year         = {{2022}},
}