Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm

Sungho Hong, Jae-Bok Song, Joo Hyun Baek, Jae Kwan Ryu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Stereo vision based visual odometry faces few challenges when it is performed in the outdoor environment. The first problem is the inaccurate depth values which result in poor distance estimation. This problem can be solved by tilting a stereo camera downward and using features from the ground texture. Second, self-shadow made by the sun can causes errors in estimating the robot movement since it looks stationary in the robot's perspective. This was resolved by estimating the sun ray direction and excluding the self-shadow area in the camera image. This process can be conducted by using only a first image that the robot grabs. These two algorithms were proven to be successful in improving the accuracy of visual odometry in the outdoor environment.

Original languageEnglish
Title of host publicationInternational Conference on Control, Automation and Systems
Pages960-963
Number of pages4
Publication statusPublished - 2012 Dec 1
Event2012 12th International Conference on Control, Automation and Systems, ICCAS 2012 - Jeju, Korea, Republic of
Duration: 2012 Oct 172012 Oct 21

Other

Other2012 12th International Conference on Control, Automation and Systems, ICCAS 2012
CountryKorea, Republic of
CityJeju
Period12/10/1712/10/21

Fingerprint

Cameras
Robots
Sun
Stereo vision
Textures

Keywords

  • Outdoor navigation
  • Self-shadow
  • Visual odometry

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Hong, S., Song, J-B., Baek, J. H., & Ryu, J. K. (2012). Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm. In International Conference on Control, Automation and Systems (pp. 960-963). [6393363]

Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm. / Hong, Sungho; Song, Jae-Bok; Baek, Joo Hyun; Ryu, Jae Kwan.

International Conference on Control, Automation and Systems. 2012. p. 960-963 6393363.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hong, S, Song, J-B, Baek, JH & Ryu, JK 2012, Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm. in International Conference on Control, Automation and Systems., 6393363, pp. 960-963, 2012 12th International Conference on Control, Automation and Systems, ICCAS 2012, Jeju, Korea, Republic of, 12/10/17.
Hong S, Song J-B, Baek JH, Ryu JK. Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm. In International Conference on Control, Automation and Systems. 2012. p. 960-963. 6393363
Hong, Sungho ; Song, Jae-Bok ; Baek, Joo Hyun ; Ryu, Jae Kwan. / Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm. International Conference on Control, Automation and Systems. 2012. pp. 960-963
@inproceedings{a52a075421d54ad7b7cbdcb79feec592,
title = "Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm",
abstract = "Stereo vision based visual odometry faces few challenges when it is performed in the outdoor environment. The first problem is the inaccurate depth values which result in poor distance estimation. This problem can be solved by tilting a stereo camera downward and using features from the ground texture. Second, self-shadow made by the sun can causes errors in estimating the robot movement since it looks stationary in the robot's perspective. This was resolved by estimating the sun ray direction and excluding the self-shadow area in the camera image. This process can be conducted by using only a first image that the robot grabs. These two algorithms were proven to be successful in improving the accuracy of visual odometry in the outdoor environment.",
keywords = "Outdoor navigation, Self-shadow, Visual odometry",
author = "Sungho Hong and Jae-Bok Song and Baek, {Joo Hyun} and Ryu, {Jae Kwan}",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9781467322478",
pages = "960--963",
booktitle = "International Conference on Control, Automation and Systems",

}

TY - GEN

T1 - Visual odometry for outdoor environment using a downward-tilting camera and self-shadow removal algorithm

AU - Hong, Sungho

AU - Song, Jae-Bok

AU - Baek, Joo Hyun

AU - Ryu, Jae Kwan

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Stereo vision based visual odometry faces few challenges when it is performed in the outdoor environment. The first problem is the inaccurate depth values which result in poor distance estimation. This problem can be solved by tilting a stereo camera downward and using features from the ground texture. Second, self-shadow made by the sun can causes errors in estimating the robot movement since it looks stationary in the robot's perspective. This was resolved by estimating the sun ray direction and excluding the self-shadow area in the camera image. This process can be conducted by using only a first image that the robot grabs. These two algorithms were proven to be successful in improving the accuracy of visual odometry in the outdoor environment.

AB - Stereo vision based visual odometry faces few challenges when it is performed in the outdoor environment. The first problem is the inaccurate depth values which result in poor distance estimation. This problem can be solved by tilting a stereo camera downward and using features from the ground texture. Second, self-shadow made by the sun can causes errors in estimating the robot movement since it looks stationary in the robot's perspective. This was resolved by estimating the sun ray direction and excluding the self-shadow area in the camera image. This process can be conducted by using only a first image that the robot grabs. These two algorithms were proven to be successful in improving the accuracy of visual odometry in the outdoor environment.

KW - Outdoor navigation

KW - Self-shadow

KW - Visual odometry

UR - http://www.scopus.com/inward/record.url?scp=84872590627&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872590627&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781467322478

SP - 960

EP - 963

BT - International Conference on Control, Automation and Systems

ER -