Stereo vision system for car assembly

Yoshikatsu Kimura; Takashi Naito; Masaru Nakano; Hiroshi Moribe; Toshitaka Kuno

doi:10.1109/ROBOT.1995.525474

Stereo vision system for car assembly

Yoshikatsu Kimura, Takashi Naito, Masaru Nakano, Hiroshi Moribe, Toshitaka Kuno

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

This paper presents a stereo vision system suitable for car assembly which requires recognition and localization of typical three dimensional industrial parts. The vision system should meet three requirements: fast processing, high accuracy and robustness. Both to reduce computational cost and to increase localization accuracy, Videorate Pipeline Sub-pixel Edge Extractor (VPSEE/vi:pi:si:/), which can extract sub-pixel accurate edges from a 512 × 512 gray image with Canny edge finder, has been developed. To recover a robust depth-map, the stereo algorithm which embodies several constraints, both to decide matching candidates and to calculate the strength of potential matches, uses information on 2D geometrical features recovered from edge segments. Experimental results show that this vision system can recognize complex industrial parts thus proving applicable for automation tasks.

Original language	English
Title of host publication	Proceedings - IEEE International Conference on Robotics and Automation
Pages	1403-1409
Number of pages	7
DOIs	https://doi.org/10.1109/ROBOT.1995.525474
Publication status	Published - 1995 Jan 1
Externally published	Yes
Event	Proceedings of the 1995 IEEE International Conference on Robotics and Automation. Part 1 (of 3) - Nagoya, Jpn Duration: 1995 May 21 → 1995 May 27

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
Volume	2
ISSN (Print)	1050-4729

Other

Other	Proceedings of the 1995 IEEE International Conference on Robotics and Automation. Part 1 (of 3)
City	Nagoya, Jpn
Period	95/5/21 → 95/5/27

ASJC Scopus subject areas

Software
Control and Systems Engineering
Artificial Intelligence
Electrical and Electronic Engineering

Access to Document

10.1109/ROBOT.1995.525474

Fingerprint Dive into the research topics of 'Stereo vision system for car assembly'. Together they form a unique fingerprint.

Cite this

Stereo vision system for car assembly. / Kimura, Yoshikatsu; Naito, Takashi; Nakano, Masaru; Moribe, Hiroshi; Kuno, Toshitaka.

Proceedings - IEEE International Conference on Robotics and Automation. 1995. p. 1403-1409 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kimura, Y, Naito, T, Nakano, M, Moribe, H & Kuno, T 1995, Stereo vision system for car assembly. in Proceedings - IEEE International Conference on Robotics and Automation. Proceedings - IEEE International Conference on Robotics and Automation, vol. 2, pp. 1403-1409, Proceedings of the 1995 IEEE International Conference on Robotics and Automation. Part 1 (of 3), Nagoya, Jpn, 95/5/21. https://doi.org/10.1109/ROBOT.1995.525474

@inproceedings{6a5843691985476e8ae527a5e6d5b1a2,

title = "Stereo vision system for car assembly",

abstract = "This paper presents a stereo vision system suitable for car assembly which requires recognition and localization of typical three dimensional industrial parts. The vision system should meet three requirements: fast processing, high accuracy and robustness. Both to reduce computational cost and to increase localization accuracy, Videorate Pipeline Sub-pixel Edge Extractor (VPSEE/vi:pi:si:/), which can extract sub-pixel accurate edges from a 512 × 512 gray image with Canny edge finder, has been developed. To recover a robust depth-map, the stereo algorithm which embodies several constraints, both to decide matching candidates and to calculate the strength of potential matches, uses information on 2D geometrical features recovered from edge segments. Experimental results show that this vision system can recognize complex industrial parts thus proving applicable for automation tasks.",

author = "Yoshikatsu Kimura and Takashi Naito and Masaru Nakano and Hiroshi Moribe and Toshitaka Kuno",

year = "1995",

month = jan,

day = "1",

doi = "10.1109/ROBOT.1995.525474",

language = "English",

isbn = "0780319656",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

pages = "1403--1409",

booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

note = "Proceedings of the 1995 IEEE International Conference on Robotics and Automation. Part 1 (of 3) ; Conference date: 21-05-1995 Through 27-05-1995",

}

TY - GEN

T1 - Stereo vision system for car assembly

AU - Kimura, Yoshikatsu

AU - Naito, Takashi

AU - Nakano, Masaru

AU - Moribe, Hiroshi

AU - Kuno, Toshitaka

PY - 1995/1/1

Y1 - 1995/1/1

N2 - This paper presents a stereo vision system suitable for car assembly which requires recognition and localization of typical three dimensional industrial parts. The vision system should meet three requirements: fast processing, high accuracy and robustness. Both to reduce computational cost and to increase localization accuracy, Videorate Pipeline Sub-pixel Edge Extractor (VPSEE/vi:pi:si:/), which can extract sub-pixel accurate edges from a 512 × 512 gray image with Canny edge finder, has been developed. To recover a robust depth-map, the stereo algorithm which embodies several constraints, both to decide matching candidates and to calculate the strength of potential matches, uses information on 2D geometrical features recovered from edge segments. Experimental results show that this vision system can recognize complex industrial parts thus proving applicable for automation tasks.

AB - This paper presents a stereo vision system suitable for car assembly which requires recognition and localization of typical three dimensional industrial parts. The vision system should meet three requirements: fast processing, high accuracy and robustness. Both to reduce computational cost and to increase localization accuracy, Videorate Pipeline Sub-pixel Edge Extractor (VPSEE/vi:pi:si:/), which can extract sub-pixel accurate edges from a 512 × 512 gray image with Canny edge finder, has been developed. To recover a robust depth-map, the stereo algorithm which embodies several constraints, both to decide matching candidates and to calculate the strength of potential matches, uses information on 2D geometrical features recovered from edge segments. Experimental results show that this vision system can recognize complex industrial parts thus proving applicable for automation tasks.

UR - http://www.scopus.com/inward/record.url?scp=0029184074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029184074&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.1995.525474

DO - 10.1109/ROBOT.1995.525474

M3 - Conference contribution

AN - SCOPUS:0029184074

SN - 0780319656

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 1403

EP - 1409

BT - Proceedings - IEEE International Conference on Robotics and Automation

T2 - Proceedings of the 1995 IEEE International Conference on Robotics and Automation. Part 1 (of 3)

Y2 - 21 May 1995 through 27 May 1995

ER -