3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging

Yasunori Sakuramoto; Yuichi Kanematsu; Hiroki Ohno; Shuichi Akizuki; Manabu Hashimoto; Kiyotaka Watanabe; Makito Seki

doi:10.2493/jjspe.81.944

3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging

Yasunori Sakuramoto, Yuichi Kanematsu, Hiroki Ohno, Shuichi Akizuki, Manabu Hashimoto, Kiyotaka Watanabe, Makito Seki

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

Abstract

This paper introduces an object detection method using features described information about a concavo-convex shape of an object that are obtained by using a small camera that controls the illumination direction. An image of the binarized gradient feature containing information about the shape of the object is generated by the Coded Multi Flash Imaging. The proposed method can reliably detect a texture-less object by using this feature image in the matching process. In addition, processing time for matching is significantly reduced by using a small number of pixels. Experiments using 200 actual images confirmed that the proposed method achieves a 98.5% recognition success rate and a 607 msec processing time.

Original language	English
Pages (from-to)	944-950
Number of pages	7
Journal	Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume	81
Issue number	10
DOIs	https://doi.org/10.2493/jjspe.81.944
Publication status	Published - 2015 Oct

Keywords

Binarized gradient features
Binary code
Image matching
Object detection
Texture-less

ASJC Scopus subject areas

Mechanical Engineering

Access to Document

10.2493/jjspe.81.944

Cite this

3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging. / Sakuramoto, Yasunori; Kanematsu, Yuichi; Ohno, Hiroki; Akizuki, Shuichi; Hashimoto, Manabu; Watanabe, Kiyotaka; Seki, Makito.

In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, Vol. 81, No. 10, 10.2015, p. 944-950.

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

@article{77ab8aa9d37e4b479a021b22468241c5,

title = "3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging",

abstract = "This paper introduces an object detection method using features described information about a concavo-convex shape of an object that are obtained by using a small camera that controls the illumination direction. An image of the binarized gradient feature containing information about the shape of the object is generated by the Coded Multi Flash Imaging. The proposed method can reliably detect a texture-less object by using this feature image in the matching process. In addition, processing time for matching is significantly reduced by using a small number of pixels. Experiments using 200 actual images confirmed that the proposed method achieves a 98.5% recognition success rate and a 607 msec processing time.",

keywords = "Binarized gradient features, Binary code, Image matching, Object detection, Texture-less",

author = "Yasunori Sakuramoto and Yuichi Kanematsu and Hiroki Ohno and Shuichi Akizuki and Manabu Hashimoto and Kiyotaka Watanabe and Makito Seki",

year = "2015",

month = oct,

doi = "10.2493/jjspe.81.944",

language = "English",

volume = "81",

pages = "944--950",

journal = "Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering",

issn = "0912-0289",

publisher = "Japan Society for Precision Engineering",

number = "10",

}

TY - JOUR

T1 - 3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging

AU - Sakuramoto, Yasunori

AU - Kanematsu, Yuichi

AU - Ohno, Hiroki

AU - Akizuki, Shuichi

AU - Hashimoto, Manabu

AU - Watanabe, Kiyotaka

AU - Seki, Makito

PY - 2015/10

Y1 - 2015/10

N2 - This paper introduces an object detection method using features described information about a concavo-convex shape of an object that are obtained by using a small camera that controls the illumination direction. An image of the binarized gradient feature containing information about the shape of the object is generated by the Coded Multi Flash Imaging. The proposed method can reliably detect a texture-less object by using this feature image in the matching process. In addition, processing time for matching is significantly reduced by using a small number of pixels. Experiments using 200 actual images confirmed that the proposed method achieves a 98.5% recognition success rate and a 607 msec processing time.

AB - This paper introduces an object detection method using features described information about a concavo-convex shape of an object that are obtained by using a small camera that controls the illumination direction. An image of the binarized gradient feature containing information about the shape of the object is generated by the Coded Multi Flash Imaging. The proposed method can reliably detect a texture-less object by using this feature image in the matching process. In addition, processing time for matching is significantly reduced by using a small number of pixels. Experiments using 200 actual images confirmed that the proposed method achieves a 98.5% recognition success rate and a 607 msec processing time.

KW - Binarized gradient features

KW - Binary code

KW - Image matching

KW - Object detection

KW - Texture-less

UR - http://www.scopus.com/inward/record.url?scp=84981719440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981719440&partnerID=8YFLogxK

U2 - 10.2493/jjspe.81.944

DO - 10.2493/jjspe.81.944

M3 - Article

AN - SCOPUS:84981719440

VL - 81

SP - 944

EP - 950

JO - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

JF - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

SN - 0912-0289

IS - 10

ER -

3-D object detection based-on features of local concavo-convex structure by coded multi flash imaging

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this