Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps

Carsten Høilund, Thomas B. Moeslund, Claus B. Madsen, Mohan M. Trivedi

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

3 Citations (Scopus)

Abstract

This paper presents a method for determining the free space in a scene as viewed by a vehicle-mounted camera.
Using disparity maps from a stereo camera and known camera motion, the disparity maps are first filtered by an iconic Kalman filter, operating on each pixel individually, thereby reducing variance and increasing the density of the filtered disparity map. Then, a stochastic occupancy grid is calculated from the filtered disparity map, providing a top-down view of the scene where the uncertainty of disparity measurements are taken into account. These occupancy grids are segmented to indicate a maximum depth free of obstacles, enabling the marking of free space in the accompanying intensity image. The test shows successful marking of free space in the evaluated scenarios in addition to significant improvement in disparity map quality.
Original languageEnglish
Title of host publicationInternational Conference on Computer Vision Theory and Applications (VISAPP)
Number of pages4
Volume1
PublisherInstitute for Systems and Technologies of Information, Control and Communication
Publication date17 May 2010
Pages164-167
ISBN (Electronic)978-989-674-028-3
Publication statusPublished - 17 May 2010
EventThe International Conference on Computer Vision Theory and Applications - Angers, France
Duration: 17 May 201021 May 2010

Conference

ConferenceThe International Conference on Computer Vision Theory and Applications
CountryFrance
CityAngers
Period17/05/201021/05/2010

Fingerprint

Cameras
Kalman filters
Pixels
Uncertainty

Cite this

Høilund, C., Moeslund, T. B., Madsen, C. B., & Trivedi, M. M. (2010). Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps. In International Conference on Computer Vision Theory and Applications (VISAPP) (Vol. 1, pp. 164-167). Institute for Systems and Technologies of Information, Control and Communication.
Høilund, Carsten ; Moeslund, Thomas B. ; Madsen, Claus B. ; Trivedi, Mohan M. / Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps. International Conference on Computer Vision Theory and Applications (VISAPP). Vol. 1 Institute for Systems and Technologies of Information, Control and Communication, 2010. pp. 164-167
@inproceedings{75258713d9144a988afb17c66c2153d2,
title = "Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps",
abstract = "This paper presents a method for determining the free space in a scene as viewed by a vehicle-mounted camera.Using disparity maps from a stereo camera and known camera motion, the disparity maps are first filtered by an iconic Kalman filter, operating on each pixel individually, thereby reducing variance and increasing the density of the filtered disparity map. Then, a stochastic occupancy grid is calculated from the filtered disparity map, providing a top-down view of the scene where the uncertainty of disparity measurements are taken into account. These occupancy grids are segmented to indicate a maximum depth free of obstacles, enabling the marking of free space in the accompanying intensity image. The test shows successful marking of free space in the evaluated scenarios in addition to significant improvement in disparity map quality.",
author = "Carsten H{\o}ilund and Moeslund, {Thomas B.} and Madsen, {Claus B.} and Trivedi, {Mohan M.}",
year = "2010",
month = "5",
day = "17",
language = "English",
volume = "1",
pages = "164--167",
booktitle = "International Conference on Computer Vision Theory and Applications (VISAPP)",
publisher = "Institute for Systems and Technologies of Information, Control and Communication",

}

Høilund, C, Moeslund, TB, Madsen, CB & Trivedi, MM 2010, Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps. in International Conference on Computer Vision Theory and Applications (VISAPP). vol. 1, Institute for Systems and Technologies of Information, Control and Communication, pp. 164-167, The International Conference on Computer Vision Theory and Applications, Angers, France, 17/05/2010.

Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps. / Høilund, Carsten; Moeslund, Thomas B.; Madsen, Claus B.; Trivedi, Mohan M.

International Conference on Computer Vision Theory and Applications (VISAPP). Vol. 1 Institute for Systems and Technologies of Information, Control and Communication, 2010. p. 164-167.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps

AU - Høilund, Carsten

AU - Moeslund, Thomas B.

AU - Madsen, Claus B.

AU - Trivedi, Mohan M.

PY - 2010/5/17

Y1 - 2010/5/17

N2 - This paper presents a method for determining the free space in a scene as viewed by a vehicle-mounted camera.Using disparity maps from a stereo camera and known camera motion, the disparity maps are first filtered by an iconic Kalman filter, operating on each pixel individually, thereby reducing variance and increasing the density of the filtered disparity map. Then, a stochastic occupancy grid is calculated from the filtered disparity map, providing a top-down view of the scene where the uncertainty of disparity measurements are taken into account. These occupancy grids are segmented to indicate a maximum depth free of obstacles, enabling the marking of free space in the accompanying intensity image. The test shows successful marking of free space in the evaluated scenarios in addition to significant improvement in disparity map quality.

AB - This paper presents a method for determining the free space in a scene as viewed by a vehicle-mounted camera.Using disparity maps from a stereo camera and known camera motion, the disparity maps are first filtered by an iconic Kalman filter, operating on each pixel individually, thereby reducing variance and increasing the density of the filtered disparity map. Then, a stochastic occupancy grid is calculated from the filtered disparity map, providing a top-down view of the scene where the uncertainty of disparity measurements are taken into account. These occupancy grids are segmented to indicate a maximum depth free of obstacles, enabling the marking of free space in the accompanying intensity image. The test shows successful marking of free space in the evaluated scenarios in addition to significant improvement in disparity map quality.

M3 - Article in proceeding

VL - 1

SP - 164

EP - 167

BT - International Conference on Computer Vision Theory and Applications (VISAPP)

PB - Institute for Systems and Technologies of Information, Control and Communication

ER -

Høilund C, Moeslund TB, Madsen CB, Trivedi MM. Free Space Computation From Stochastic Occupancy Grids Based On Iconic Kalman Filtered Disparity Maps. In International Conference on Computer Vision Theory and Applications (VISAPP). Vol. 1. Institute for Systems and Technologies of Information, Control and Communication. 2010. p. 164-167