Multiple-Joint Pedestrian Tracking Using Periodic Models
Estimating accurate positions of multiple pedestrians is a critical task in robotics and autonomous cars. We propose a tracker based on typical human motion patterns to track multiple pedestrians. This paper assumes that the legs’ reflection and extension angles are approximately changing periodical...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/23/6917 |
id |
doaj-fae4e2dbc9624224bc778b69b49d70fb |
---|---|
record_format |
Article |
spelling |
doaj-fae4e2dbc9624224bc778b69b49d70fb2020-12-04T00:03:19ZengMDPI AGSensors1424-82202020-12-01206917691710.3390/s20236917Multiple-Joint Pedestrian Tracking Using Periodic ModelsMarzieh Dolatabadi0Jos Elfring1René van de Molengraft2Control Systems Technology Group, Department of Mechanical Engineering, University of Eindhoven, 5600 MB Eindhoven, The NetherlandsControl Systems Technology Group, Department of Mechanical Engineering, University of Eindhoven, 5600 MB Eindhoven, The NetherlandsControl Systems Technology Group, Department of Mechanical Engineering, University of Eindhoven, 5600 MB Eindhoven, The NetherlandsEstimating accurate positions of multiple pedestrians is a critical task in robotics and autonomous cars. We propose a tracker based on typical human motion patterns to track multiple pedestrians. This paper assumes that the legs’ reflection and extension angles are approximately changing periodically during human motion. A Fourier series is fitted in order to describe the moving, such as describing the position and velocity of the hip, knee, and ankle. Our tracker receives the position of the ankle, knee, and hip as measurements. As a proof of concept, we compare our tracker with state-of-the-art methods. The proposed models have been validated by experimental data, the Human Gait Database (HuGaDB), and the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) tracking benchmark. The results indicate that our tracker is able to estimate the reflection and extension angles with a precision of 90.97%. Moreover, the comparison shows that the tracking precision increases up to 1.3% with the proposed tracker when compared to a constant velocity based tracker.https://www.mdpi.com/1424-8220/20/23/6917tracking algorithmpedestrian–car interactionharmonic motionkinematics estimationjoint tracking |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Marzieh Dolatabadi Jos Elfring René van de Molengraft |
spellingShingle |
Marzieh Dolatabadi Jos Elfring René van de Molengraft Multiple-Joint Pedestrian Tracking Using Periodic Models Sensors tracking algorithm pedestrian–car interaction harmonic motion kinematics estimation joint tracking |
author_facet |
Marzieh Dolatabadi Jos Elfring René van de Molengraft |
author_sort |
Marzieh Dolatabadi |
title |
Multiple-Joint Pedestrian Tracking Using Periodic Models |
title_short |
Multiple-Joint Pedestrian Tracking Using Periodic Models |
title_full |
Multiple-Joint Pedestrian Tracking Using Periodic Models |
title_fullStr |
Multiple-Joint Pedestrian Tracking Using Periodic Models |
title_full_unstemmed |
Multiple-Joint Pedestrian Tracking Using Periodic Models |
title_sort |
multiple-joint pedestrian tracking using periodic models |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-12-01 |
description |
Estimating accurate positions of multiple pedestrians is a critical task in robotics and autonomous cars. We propose a tracker based on typical human motion patterns to track multiple pedestrians. This paper assumes that the legs’ reflection and extension angles are approximately changing periodically during human motion. A Fourier series is fitted in order to describe the moving, such as describing the position and velocity of the hip, knee, and ankle. Our tracker receives the position of the ankle, knee, and hip as measurements. As a proof of concept, we compare our tracker with state-of-the-art methods. The proposed models have been validated by experimental data, the Human Gait Database (HuGaDB), and the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) tracking benchmark. The results indicate that our tracker is able to estimate the reflection and extension angles with a precision of 90.97%. Moreover, the comparison shows that the tracking precision increases up to 1.3% with the proposed tracker when compared to a constant velocity based tracker. |
topic |
tracking algorithm pedestrian–car interaction harmonic motion kinematics estimation joint tracking |
url |
https://www.mdpi.com/1424-8220/20/23/6917 |
work_keys_str_mv |
AT marziehdolatabadi multiplejointpedestriantrackingusingperiodicmodels AT joselfring multiplejointpedestriantrackingusingperiodicmodels AT renevandemolengraft multiplejointpedestriantrackingusingperiodicmodels |
_version_ |
1724400939934154752 |