Research on static vision-based target localization for astronaut assistant robots

Fengwei Gu; Hongwei Gao; Jinguo Liu; Qing Gao; Zhaojie Ju

doi:10.1109/ACCESS.2019.2939347

Research on static vision-based target localization for astronaut assistant robots

Fengwei Gu, Hongwei Gao, Jinguo Liu, Qing Gao, Zhaojie Ju

School of Computing

Research output: Contribution to journal › Article › peer-review

147 Downloads (Pure)

Abstract

Aiming at the problem of localizing and grasping targets by an astronaut assistant robot, developing assisting staff to complete specific tasks, and using a self-built visual system as an experimental platform, this paper proposes two improved static target localization methods based on binocular vision and the traditional localization method: (a) a localization method based on region of interest matching and (b) a localization method based on a pixel coordinate offset.Under the same conditions, the traditional binocular vision localization method and the two improved localization methods are used to locate a spherical target. The experimental results are compared and analysed, and the effectiveness of the improved methods is verified by two performance indicators: the localization accuracy and the localization time efficiency. The experimental results show that to a certain extent, the two improved localization methods can improve the localization efficiency of the vision system and positively affect the performance and flexibility of the astronaut assistant robots.

Original language	English
Pages (from-to)	128394-128407
Journal	IEEE Access
Volume	7
DOIs	https://doi.org/10.1109/ACCESS.2019.2939347
Publication status	Published - 4 Sept 2019

Access to Document

10.1109/ACCESS.2019.2939347

Research on StaticFinal published version, 3.82 MBLicence: CC BY

Cite this

@article{bf1091ba00ea4d6f97f179560b5f8919,

title = "Research on static vision-based target localization for astronaut assistant robots",

abstract = "Aiming at the problem of localizing and grasping targets by an astronaut assistant robot, developing assisting staff to complete specific tasks, and using a self-built visual system as an experimental platform, this paper proposes two improved static target localization methods based on binocular vision and the traditional localization method: (a) a localization method based on region of interest matching and (b) a localization method based on a pixel coordinate offset.Under the same conditions, the traditional binocular vision localization method and the two improved localization methods are used to locate a spherical target. The experimental results are compared and analysed, and the effectiveness of the improved methods is verified by two performance indicators: the localization accuracy and the localization time efficiency. The experimental results show that to a certain extent, the two improved localization methods can improve the localization efficiency of the vision system and positively affect the performance and flexibility of the astronaut assistant robots.",

author = "Fengwei Gu and Hongwei Gao and Jinguo Liu and Qing Gao and Zhaojie Ju",

year = "2019",

month = sep,

day = "4",

doi = "10.1109/ACCESS.2019.2939347",

language = "English",

volume = "7",

pages = "128394--128407",

journal = "IEEE Access",

issn = "2169-3536",

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

}

TY - JOUR

T1 - Research on static vision-based target localization for astronaut assistant robots

AU - Gu, Fengwei

AU - Gao, Hongwei

AU - Liu, Jinguo

AU - Gao, Qing

AU - Ju, Zhaojie

PY - 2019/9/4

Y1 - 2019/9/4

N2 - Aiming at the problem of localizing and grasping targets by an astronaut assistant robot, developing assisting staff to complete specific tasks, and using a self-built visual system as an experimental platform, this paper proposes two improved static target localization methods based on binocular vision and the traditional localization method: (a) a localization method based on region of interest matching and (b) a localization method based on a pixel coordinate offset.Under the same conditions, the traditional binocular vision localization method and the two improved localization methods are used to locate a spherical target. The experimental results are compared and analysed, and the effectiveness of the improved methods is verified by two performance indicators: the localization accuracy and the localization time efficiency. The experimental results show that to a certain extent, the two improved localization methods can improve the localization efficiency of the vision system and positively affect the performance and flexibility of the astronaut assistant robots.

AB - Aiming at the problem of localizing and grasping targets by an astronaut assistant robot, developing assisting staff to complete specific tasks, and using a self-built visual system as an experimental platform, this paper proposes two improved static target localization methods based on binocular vision and the traditional localization method: (a) a localization method based on region of interest matching and (b) a localization method based on a pixel coordinate offset.Under the same conditions, the traditional binocular vision localization method and the two improved localization methods are used to locate a spherical target. The experimental results are compared and analysed, and the effectiveness of the improved methods is verified by two performance indicators: the localization accuracy and the localization time efficiency. The experimental results show that to a certain extent, the two improved localization methods can improve the localization efficiency of the vision system and positively affect the performance and flexibility of the astronaut assistant robots.

U2 - 10.1109/ACCESS.2019.2939347

DO - 10.1109/ACCESS.2019.2939347

M3 - Article

SN - 2169-3536

VL - 7

SP - 128394

EP - 128407

JO - IEEE Access

JF - IEEE Access

ER -

Research on static vision-based target localization for astronaut assistant robots

Abstract

Access to Document

Fingerprint

Cite this