Accelerated stereo matching for autonomous vehicles using an upright pinhole camera model

Chen Chen, Jiangbo Lu, Do Kyoung Kwon, Darnell Moore, Minh N Do

Research output: Contribution to journalConference article

Abstract

In this paper, we propose a new method for accelerating stereo matching in autonomous vehicles using an upright pinhole camera model. It is motivated by that stereo videos are more restricted when the camera is fixed on the vehicles driving on the road. Assuming that the imaging plane is perpendicular to the road and the road is generally flat, we can derive the current disparity based on the previous one and the flow. The prediction is very efficient that only requires two multiplications per pixel. In practice, this model may not hold strictly but we still can use it for disparity initialization. Results on real datasets demonstrate the our method reduces the disparity search range from 128 to 61 with only slightly accuracy decreasing.

Original languageEnglish (US)
Pages (from-to)18-21
Number of pages4
JournalIS and T International Symposium on Electronic Imaging Science and Technology
DOIs
StatePublished - Jan 1 2017
EventAutonomous Vehicles and Machines 2017, AVM 2017 - Burlingame, United States
Duration: Jan 29 2017Feb 2 2017

Fingerprint

Pinhole cameras
pinhole cameras
roads
vehicles
Pixels
Cameras
Imaging techniques
multiplication
pixels
cameras
predictions

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Human-Computer Interaction
  • Software
  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics

Cite this

Accelerated stereo matching for autonomous vehicles using an upright pinhole camera model. / Chen, Chen; Lu, Jiangbo; Kwon, Do Kyoung; Moore, Darnell; Do, Minh N.

In: IS and T International Symposium on Electronic Imaging Science and Technology, 01.01.2017, p. 18-21.

Research output: Contribution to journalConference article

@article{ba42f3866d9c4805ac328b086673899f,
title = "Accelerated stereo matching for autonomous vehicles using an upright pinhole camera model",
abstract = "In this paper, we propose a new method for accelerating stereo matching in autonomous vehicles using an upright pinhole camera model. It is motivated by that stereo videos are more restricted when the camera is fixed on the vehicles driving on the road. Assuming that the imaging plane is perpendicular to the road and the road is generally flat, we can derive the current disparity based on the previous one and the flow. The prediction is very efficient that only requires two multiplications per pixel. In practice, this model may not hold strictly but we still can use it for disparity initialization. Results on real datasets demonstrate the our method reduces the disparity search range from 128 to 61 with only slightly accuracy decreasing.",
author = "Chen Chen and Jiangbo Lu and Kwon, {Do Kyoung} and Darnell Moore and Do, {Minh N}",
year = "2017",
month = "1",
day = "1",
doi = "10.2352/ISSN.2470-1173.2017.19.AVM-013",
language = "English (US)",
pages = "18--21",
journal = "IS and T International Symposium on Electronic Imaging Science and Technology",
issn = "2470-1173",

}

TY - JOUR

T1 - Accelerated stereo matching for autonomous vehicles using an upright pinhole camera model

AU - Chen, Chen

AU - Lu, Jiangbo

AU - Kwon, Do Kyoung

AU - Moore, Darnell

AU - Do, Minh N

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this paper, we propose a new method for accelerating stereo matching in autonomous vehicles using an upright pinhole camera model. It is motivated by that stereo videos are more restricted when the camera is fixed on the vehicles driving on the road. Assuming that the imaging plane is perpendicular to the road and the road is generally flat, we can derive the current disparity based on the previous one and the flow. The prediction is very efficient that only requires two multiplications per pixel. In practice, this model may not hold strictly but we still can use it for disparity initialization. Results on real datasets demonstrate the our method reduces the disparity search range from 128 to 61 with only slightly accuracy decreasing.

AB - In this paper, we propose a new method for accelerating stereo matching in autonomous vehicles using an upright pinhole camera model. It is motivated by that stereo videos are more restricted when the camera is fixed on the vehicles driving on the road. Assuming that the imaging plane is perpendicular to the road and the road is generally flat, we can derive the current disparity based on the previous one and the flow. The prediction is very efficient that only requires two multiplications per pixel. In practice, this model may not hold strictly but we still can use it for disparity initialization. Results on real datasets demonstrate the our method reduces the disparity search range from 128 to 61 with only slightly accuracy decreasing.

UR - http://www.scopus.com/inward/record.url?scp=85041738766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041738766&partnerID=8YFLogxK

U2 - 10.2352/ISSN.2470-1173.2017.19.AVM-013

DO - 10.2352/ISSN.2470-1173.2017.19.AVM-013

M3 - Conference article

AN - SCOPUS:85041738766

SP - 18

EP - 21

JO - IS and T International Symposium on Electronic Imaging Science and Technology

JF - IS and T International Symposium on Electronic Imaging Science and Technology

SN - 2470-1173

ER -