Tracking and Reconstruction of Vehicles for Accurate Position Estimation

Hanna Källén; Håkan Ardö; Olof Enqvist

doi:10.1109/WACV.2011.5711491

Tracking and Reconstruction of Vehicles for Accurate Position Estimation

Hanna Källén, Håkan Ardö, Olof Enqvist

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

307 Downloads (Pure)

Abstract

To improve traffic safety it is important to evaluate the safety of roads and intersections. Today this requires a large amount of manual labor so an automated system using cameras would be very beneficial. We focus on the geometric part of the problem, that is, how to get accurate three-dimensional data from images of a road or an intersection. This is essential in order to correctly identify different events and incidents, for example to estimate when two cars gets dangerously close to each other.

The proposed method uses a standard tracker to find corresponding points between frames. Then a RANSAC-type algorithm detects points that are likely to belong to the same vehicle. To fully exploit the fact that vehicles rotate and translate only in the ground plane, the structure from motion is estimated using an optimization approach based on the L-infinity-norm. The same approach also allows for easy setup of the system by estimating the camera orientation relative to the ground plane. Promising results for real-world data are presented.

Original language	English
Title of host publication	Applications in Computer Vision (WACV), 2011 Workshop on
Publisher	IEEE - Institute of Electrical and Electronics Engineers Inc.
Pages	110-117
Number of pages	8
ISBN (Print)	978-1-4244-9496-5 (print), 1-4244-9496-6 (print)
DOIs	https://doi.org/10.1109/WACV.2011.5711491
Publication status	Published - 2011
Event	2011 IEEE Workshop on Applications in Computer Vision (WACV 2011) - Hawaii, United States Duration: 2011 Jan 5 → 2011 Jan 7

Conference

Conference	2011 IEEE Workshop on Applications in Computer Vision (WACV 2011)
Country/Territory	United States
City	Hawaii
Period	2011/01/05 → 2011/01/07

Subject classification (UKÄ)

Computer graphics and computer vision
Mathematical Sciences

Free keywords

tracking
automated traffic surveillance
3D reconstruction

Access to Document

10.1109/WACV.2011.5711491

artikel

Cite this

@inproceedings{9c73fc8c927e45a0a11001c2b4edfe1a,

title = "Tracking and Reconstruction of Vehicles for Accurate Position Estimation",

abstract = "To improve traffic safety it is important to evaluate the safety of roads and intersections. Today this requires a large amount of manual labor so an automated system using cameras would be very beneficial. We focus on the geometric part of the problem, that is, how to get accurate three-dimensional data from images of a road or an intersection. This is essential in order to correctly identify different events and incidents, for example to estimate when two cars gets dangerously close to each other. The proposed method uses a standard tracker to find corresponding points between frames. Then a RANSAC-type algorithm detects points that are likely to belong to the same vehicle. To fully exploit the fact that vehicles rotate and translate only in the ground plane, the structure from motion is estimated using an optimization approach based on the L-infinity-norm. The same approach also allows for easy setup of the system by estimating the camera orientation relative to the ground plane. Promising results for real-world data are presented.",

keywords = "tracking, automated traffic surveillance, 3D reconstruction",

author = "Hanna K{\"a}ll{\'e}n and H{\aa}kan Ard{\"o} and Olof Enqvist",

year = "2011",

doi = "10.1109/WACV.2011.5711491",

language = "English",

isbn = "978-1-4244-9496-5 (print)",

pages = "110--117",

booktitle = "Applications in Computer Vision (WACV), 2011 Workshop on",

publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2011 IEEE Workshop on Applications in Computer Vision (WACV 2011) ; Conference date: 05-01-2011 Through 07-01-2011",

}

Källén, H, Ardö, H & Enqvist, O 2011, Tracking and Reconstruction of Vehicles for Accurate Position Estimation. in Applications in Computer Vision (WACV), 2011 Workshop on. IEEE - Institute of Electrical and Electronics Engineers Inc., pp. 110-117, 2011 IEEE Workshop on Applications in Computer Vision (WACV 2011), Hawaii, United States, 2011/01/05. https://doi.org/10.1109/WACV.2011.5711491

Tracking and Reconstruction of Vehicles for Accurate Position Estimation. / Källén, Hanna; Ardö, Håkan; Enqvist, Olof.
Applications in Computer Vision (WACV), 2011 Workshop on. IEEE - Institute of Electrical and Electronics Engineers Inc., 2011. p. 110-117.

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Tracking and Reconstruction of Vehicles for Accurate Position Estimation

AU - Källén, Hanna

AU - Ardö, Håkan

AU - Enqvist, Olof

PY - 2011

Y1 - 2011

N2 - To improve traffic safety it is important to evaluate the safety of roads and intersections. Today this requires a large amount of manual labor so an automated system using cameras would be very beneficial. We focus on the geometric part of the problem, that is, how to get accurate three-dimensional data from images of a road or an intersection. This is essential in order to correctly identify different events and incidents, for example to estimate when two cars gets dangerously close to each other. The proposed method uses a standard tracker to find corresponding points between frames. Then a RANSAC-type algorithm detects points that are likely to belong to the same vehicle. To fully exploit the fact that vehicles rotate and translate only in the ground plane, the structure from motion is estimated using an optimization approach based on the L-infinity-norm. The same approach also allows for easy setup of the system by estimating the camera orientation relative to the ground plane. Promising results for real-world data are presented.

AB - To improve traffic safety it is important to evaluate the safety of roads and intersections. Today this requires a large amount of manual labor so an automated system using cameras would be very beneficial. We focus on the geometric part of the problem, that is, how to get accurate three-dimensional data from images of a road or an intersection. This is essential in order to correctly identify different events and incidents, for example to estimate when two cars gets dangerously close to each other. The proposed method uses a standard tracker to find corresponding points between frames. Then a RANSAC-type algorithm detects points that are likely to belong to the same vehicle. To fully exploit the fact that vehicles rotate and translate only in the ground plane, the structure from motion is estimated using an optimization approach based on the L-infinity-norm. The same approach also allows for easy setup of the system by estimating the camera orientation relative to the ground plane. Promising results for real-world data are presented.

KW - tracking

KW - automated traffic surveillance

KW - 3D reconstruction

UR - https://www.scopus.com/pages/publications/79952512483

U2 - 10.1109/WACV.2011.5711491

DO - 10.1109/WACV.2011.5711491

M3 - Paper in conference proceeding

SN - 978-1-4244-9496-5 (print)

SN - 1-4244-9496-6 (print)

SP - 110

EP - 117

BT - Applications in Computer Vision (WACV), 2011 Workshop on

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - 2011 IEEE Workshop on Applications in Computer Vision (WACV 2011)

Y2 - 5 January 2011 through 7 January 2011

ER -

Tracking and Reconstruction of Vehicles for Accurate Position Estimation

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Other files and links

Fingerprint

Mathematical Imaging Group

Cite this

Tracking and Reconstruction of Vehicles for Accurate Position Estimation

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Other files and links

Fingerprint

Projects

Mathematical Imaging Group

Cite this