Cover Image

Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification

In this paper, a new method is proposed to estimate the pose of a moving vehicle in a typical traffic scene. Pose determination is crucial in the process of fitting or matching an existing 3D model in the database with the captured moving object. In this work, pose estimat...

Full description

Saved in:
Bibliographic Details
Main Authors: Sheikh, Usman Ullah, Syed Abu Bakar, Syed Abdul Rahman
Format: Book Section
Language:English
Published: WSEAS International Conference 2007
Online Access:http://eprints.utm.my/id/eprint/12114/1/Three-Dimensional%20Vehicle%20Pose%20Estimation%20From%20Two-Dimensional%20Monocular%20Camera%20Image%20for%20Vehicle%20Classification_2007.pdf
http://eprints.utm.my/id/eprint/12114/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.12114
record_format eprints
spelling my.utm.121142017-10-02T05:06:02Z http://eprints.utm.my/id/eprint/12114/ Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification Sheikh, Usman Ullah Syed Abu Bakar, Syed Abdul Rahman In this paper, a new method is proposed to estimate the pose of a moving vehicle in a typical traffic scene. Pose determination is crucial in the process of fitting or matching an existing 3D model in the database with the captured moving object. In this work, pose estimation is determined by estimating the 3D position of the moving vehicle in world space and the n computing the motion vector of the vehicle. The pose estimation is first initialized by loosely calibrating the camera view port and the perspective distortion. The 3D position is then determined by computing the intersection of a ray trace of the vehicle ’s centroid obtained from the video image originating from the camera eye to the vehicle ’s motion plane, i .e. the ground. Once a motion vector is obtained, the 3D model is aligned to match the vehicle’s pose. The computation is performed on a 3D graphics card. Results on real -world traffic scenes as well as synthetic data are presented and several issues are outlined. WSEAS International Conference 2007 Book Section PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/12114/1/Three-Dimensional%20Vehicle%20Pose%20Estimation%20From%20Two-Dimensional%20Monocular%20Camera%20Image%20for%20Vehicle%20Classification_2007.pdf Sheikh, Usman Ullah and Syed Abu Bakar, Syed Abdul Rahman (2007) Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification. In: 6th WSEAS International Conference on Circuits, Systems, Electrnics, Control and Signal Processing CSECS 07. WSEAS International Conference.
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
description In this paper, a new method is proposed to estimate the pose of a moving vehicle in a typical traffic scene. Pose determination is crucial in the process of fitting or matching an existing 3D model in the database with the captured moving object. In this work, pose estimation is determined by estimating the 3D position of the moving vehicle in world space and the n computing the motion vector of the vehicle. The pose estimation is first initialized by loosely calibrating the camera view port and the perspective distortion. The 3D position is then determined by computing the intersection of a ray trace of the vehicle ’s centroid obtained from the video image originating from the camera eye to the vehicle ’s motion plane, i .e. the ground. Once a motion vector is obtained, the 3D model is aligned to match the vehicle’s pose. The computation is performed on a 3D graphics card. Results on real -world traffic scenes as well as synthetic data are presented and several issues are outlined.
format Book Section
author Sheikh, Usman Ullah
Syed Abu Bakar, Syed Abdul Rahman
spellingShingle Sheikh, Usman Ullah
Syed Abu Bakar, Syed Abdul Rahman
Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification
author_facet Sheikh, Usman Ullah
Syed Abu Bakar, Syed Abdul Rahman
author_sort Sheikh, Usman Ullah
title Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification
title_short Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification
title_full Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification
title_fullStr Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification
title_full_unstemmed Three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification
title_sort three-dimensional vehicle pose estimation from two-dimensional monocular camera image for vehicle classification
publisher WSEAS International Conference
publishDate 2007
url http://eprints.utm.my/id/eprint/12114/1/Three-Dimensional%20Vehicle%20Pose%20Estimation%20From%20Two-Dimensional%20Monocular%20Camera%20Image%20for%20Vehicle%20Classification_2007.pdf
http://eprints.utm.my/id/eprint/12114/
_version_ 1643645864893218816
score 13.211869

Similar Items