Repairing IR depth image with 2D RGB image

Yeh Wei Yu; Tzu Kai Wang; Chi Chung Lau; Jia Ching Wang; Tsung Hsun Yang; Jann Long Chern; Ching Cherng Sun

doi:10.1117/12.2321205

Repairing IR depth image with 2D RGB image

Yeh Wei Yu, Tzu Kai Wang, Chi Chung Lau, Jia Ching Wang, Tsung Hsun Yang, Jann Long Chern, Ching Cherng Sun

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

Abstract

3D-image technologies produce RGBD images use 2D RGB image combing with depth image. The most popular depth imaging methods including structure light, time-of-flight, and stereoscopic image. Since no point cloud detection method can prevent depth information loss, the complement methods is therefore important. Therefore, we proposed depth information complement method, which use a novel iterative low-pass pervasion method to apply depth image pervasion. We make two experiments to demonstrate the idea. The first experiment induces strong IR noise to destroy parts of the depth image. Then we successfully complement the depth image by the proposed method. The second experiment demonstrates the complement performance of iterative low-pass pervasion method and shows good Accuracy and Precision.

Original language	English
Title of host publication	Current Developments in Lens Design and Optical Engineering XIX
Editors	R. Barry Johnson, Simon Thibault, Virendra N. Mahajan
Publisher	SPIE
ISBN (Electronic)	9781510620612
DOIs	https://doi.org/10.1117/12.2321205
State	Published - 2018
Event	19th Conference on Current Developments in Lens Design and Optical Engineering 2018 - San Diego, United States Duration: 21 Aug 2018 → 22 Aug 2018

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	10745
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	19th Conference on Current Developments in Lens Design and Optical Engineering 2018
Country/Territory	United States
City	San Diego
Period	21/08/18 → 22/08/18

Keywords

3D-image
Holistically-Nested Edge Detection method
IR noise
RGB image
RGBD image
depth image complementation
depth information loss
iterative low-pass pervasion

Access to Document

10.1117/12.2321205

Study of Holographic Data Storage with High Surrounding Tolerance Technology(3/3)
Sun, C.-C. (PI)
1/08/17 → 31/10/18
Project: Research
價創計畫：智慧居家照護技術－主動式3D室內掃描、定位與導航系統
Sun, C.-C. (PI)
1/05/17 → 30/04/18
Project: Research

Cite this

Yu, Y. W., Wang, T. K., Lau, C. C., Wang, J. C., Yang, T. H., Chern, J. L., & Sun, C. C. (2018). Repairing IR depth image with 2D RGB image. In R. B. Johnson, S. Thibault, & V. N. Mahajan (Eds.), Current Developments in Lens Design and Optical Engineering XIX Article 1074505 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10745). SPIE. https://doi.org/10.1117/12.2321205

@inproceedings{6b15fcb5ca624a2aa8f6bc24d98b4e75,

title = "Repairing IR depth image with 2D RGB image",

abstract = "3D-image technologies produce RGBD images use 2D RGB image combing with depth image. The most popular depth imaging methods including structure light, time-of-flight, and stereoscopic image. Since no point cloud detection method can prevent depth information loss, the complement methods is therefore important. Therefore, we proposed depth information complement method, which use a novel iterative low-pass pervasion method to apply depth image pervasion. We make two experiments to demonstrate the idea. The first experiment induces strong IR noise to destroy parts of the depth image. Then we successfully complement the depth image by the proposed method. The second experiment demonstrates the complement performance of iterative low-pass pervasion method and shows good Accuracy and Precision.",

keywords = "3D-image, Holistically-Nested Edge Detection method, IR noise, RGB image, RGBD image, depth image complementation, depth information loss, iterative low-pass pervasion",

author = "Yu, {Yeh Wei} and Wang, {Tzu Kai} and Lau, {Chi Chung} and Wang, {Jia Ching} and Yang, {Tsung Hsun} and Chern, {Jann Long} and Sun, {Ching Cherng}",

note = "Publisher Copyright: {\textcopyright} 2018 SPIE.; 19th Conference on Current Developments in Lens Design and Optical Engineering 2018 ; Conference date: 21-08-2018 Through 22-08-2018",

year = "2018",

doi = "10.1117/12.2321205",

language = "???core.languages.en_GB???",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Johnson, {R. Barry} and Simon Thibault and Mahajan, {Virendra N.}",

booktitle = "Current Developments in Lens Design and Optical Engineering XIX",

}

Yu, YW, Wang, TK, Lau, CC, Wang, JC , Yang, TH, Chern, JL & Sun, CC 2018, Repairing IR depth image with 2D RGB image. in RB Johnson, S Thibault & VN Mahajan (eds), Current Developments in Lens Design and Optical Engineering XIX., 1074505, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10745, SPIE, 19th Conference on Current Developments in Lens Design and Optical Engineering 2018, San Diego, United States, 21/08/18. https://doi.org/10.1117/12.2321205

Repairing IR depth image with 2D RGB image. / Yu, Yeh Wei; Wang, Tzu Kai; Lau, Chi Chung et al.
Current Developments in Lens Design and Optical Engineering XIX. ed. / R. Barry Johnson; Simon Thibault; Virendra N. Mahajan. SPIE, 2018. 1074505 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10745).

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

TY - GEN

T1 - Repairing IR depth image with 2D RGB image

AU - Yu, Yeh Wei

AU - Wang, Tzu Kai

AU - Lau, Chi Chung

AU - Wang, Jia Ching

AU - Yang, Tsung Hsun

AU - Chern, Jann Long

AU - Sun, Ching Cherng

PY - 2018

Y1 - 2018

N2 - 3D-image technologies produce RGBD images use 2D RGB image combing with depth image. The most popular depth imaging methods including structure light, time-of-flight, and stereoscopic image. Since no point cloud detection method can prevent depth information loss, the complement methods is therefore important. Therefore, we proposed depth information complement method, which use a novel iterative low-pass pervasion method to apply depth image pervasion. We make two experiments to demonstrate the idea. The first experiment induces strong IR noise to destroy parts of the depth image. Then we successfully complement the depth image by the proposed method. The second experiment demonstrates the complement performance of iterative low-pass pervasion method and shows good Accuracy and Precision.

AB - 3D-image technologies produce RGBD images use 2D RGB image combing with depth image. The most popular depth imaging methods including structure light, time-of-flight, and stereoscopic image. Since no point cloud detection method can prevent depth information loss, the complement methods is therefore important. Therefore, we proposed depth information complement method, which use a novel iterative low-pass pervasion method to apply depth image pervasion. We make two experiments to demonstrate the idea. The first experiment induces strong IR noise to destroy parts of the depth image. Then we successfully complement the depth image by the proposed method. The second experiment demonstrates the complement performance of iterative low-pass pervasion method and shows good Accuracy and Precision.

KW - 3D-image

KW - Holistically-Nested Edge Detection method

KW - IR noise

KW - RGB image

KW - RGBD image

KW - depth image complementation

KW - depth information loss

KW - iterative low-pass pervasion

UR - http://www.scopus.com/inward/record.url?scp=85058264280&partnerID=8YFLogxK

U2 - 10.1117/12.2321205

DO - 10.1117/12.2321205

M3 - 會議論文篇章

AN - SCOPUS:85058264280

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Current Developments in Lens Design and Optical Engineering XIX

A2 - Johnson, R. Barry

A2 - Thibault, Simon

A2 - Mahajan, Virendra N.

PB - SPIE

T2 - 19th Conference on Current Developments in Lens Design and Optical Engineering 2018

Y2 - 21 August 2018 through 22 August 2018

ER -

Repairing IR depth image with 2D RGB image

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

Study of Holographic Data Storage with High Surrounding Tolerance Technology(3/3)

價創計畫：智慧居家照護技術－主動式3D室內掃描、定位與導航系統

Cite this