Reconstructing Intensity Images from Binary Spatial Gradient Cameras

Suren Jayasuriya; Orazio Gallo; Jinwei Gu; Timo Aila; Jan Kautz

doi:10.1109/CVPRW.2017.47

Reconstructing Intensity Images from Binary Spatial Gradient Cameras

Suren Jayasuriya, Orazio Gallo, Jinwei Gu, Timo Aila, Jan Kautz

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

Abstract

Binary gradient cameras extract edge and temporal information directly on the sensor, allowing for low-power, low-bandwidth, and high-dynamic-range capabilities - all critical factors for the deployment of embedded computer vision systems. However, these types of images require specialized computer vision algorithms and are not easy to interpret by a human observer. In this paper we propose to recover an intensity image from a single binary spatial gradient image with a deep auto-encoder. Extensive experimental results on both simulated and real data show the effectiveness of the proposed approach.

Original language	English (US)
Title of host publication	Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Publisher	IEEE Computer Society
Pages	337-343
Number of pages	7
ISBN (Electronic)	9781538607336
DOIs	https://doi.org/10.1109/CVPRW.2017.47
State	Published - Aug 22 2017
Externally published	Yes
Event	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States Duration: Jul 21 2017 → Jul 26 2017

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2017-July
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Other

Other	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Country/Territory	United States
City	Honolulu
Period	7/21/17 → 7/26/17

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW.2017.47

Cite this

Jayasuriya, S., Gallo, O., Gu, J., Aila, T., & Kautz, J. (2017). Reconstructing Intensity Images from Binary Spatial Gradient Cameras. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 (pp. 337-343). Article 8014781 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2017.47

Reconstructing Intensity Images from Binary Spatial Gradient Cameras. / Jayasuriya, Suren; Gallo, Orazio; Gu, Jinwei et al.
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society, 2017. p. 337-343 8014781 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July).

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

Jayasuriya, S, Gallo, O, Gu, J, Aila, T & Kautz, J 2017, Reconstructing Intensity Images from Binary Spatial Gradient Cameras. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017., 8014781, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2017-July, IEEE Computer Society, pp. 337-343, 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 7/21/17. https://doi.org/10.1109/CVPRW.2017.47

Jayasuriya S, Gallo O, Gu J, Aila T, Kautz J. Reconstructing Intensity Images from Binary Spatial Gradient Cameras. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society. 2017. p. 337-343. 8014781. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2017.47

@inproceedings{595bca24eb5246418109fe3fb43138f1,

title = "Reconstructing Intensity Images from Binary Spatial Gradient Cameras",

abstract = "Binary gradient cameras extract edge and temporal information directly on the sensor, allowing for low-power, low-bandwidth, and high-dynamic-range capabilities - all critical factors for the deployment of embedded computer vision systems. However, these types of images require specialized computer vision algorithms and are not easy to interpret by a human observer. In this paper we propose to recover an intensity image from a single binary spatial gradient image with a deep auto-encoder. Extensive experimental results on both simulated and real data show the effectiveness of the proposed approach.",

author = "Suren Jayasuriya and Orazio Gallo and Jinwei Gu and Timo Aila and Jan Kautz",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 ; Conference date: 21-07-2017 Through 26-07-2017",

year = "2017",

month = aug,

day = "22",

doi = "10.1109/CVPRW.2017.47",

language = "English (US)",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "337--343",

booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017",

}

TY - GEN

T1 - Reconstructing Intensity Images from Binary Spatial Gradient Cameras

AU - Jayasuriya, Suren

AU - Gallo, Orazio

AU - Gu, Jinwei

AU - Aila, Timo

AU - Kautz, Jan

PY - 2017/8/22

Y1 - 2017/8/22

N2 - Binary gradient cameras extract edge and temporal information directly on the sensor, allowing for low-power, low-bandwidth, and high-dynamic-range capabilities - all critical factors for the deployment of embedded computer vision systems. However, these types of images require specialized computer vision algorithms and are not easy to interpret by a human observer. In this paper we propose to recover an intensity image from a single binary spatial gradient image with a deep auto-encoder. Extensive experimental results on both simulated and real data show the effectiveness of the proposed approach.

AB - Binary gradient cameras extract edge and temporal information directly on the sensor, allowing for low-power, low-bandwidth, and high-dynamic-range capabilities - all critical factors for the deployment of embedded computer vision systems. However, these types of images require specialized computer vision algorithms and are not easy to interpret by a human observer. In this paper we propose to recover an intensity image from a single binary spatial gradient image with a deep auto-encoder. Extensive experimental results on both simulated and real data show the effectiveness of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=85030249174&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030249174&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2017.47

DO - 10.1109/CVPRW.2017.47

M3 - Conference contribution

AN - SCOPUS:85030249174

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 337

EP - 343

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

PB - IEEE Computer Society

T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

Y2 - 21 July 2017 through 26 July 2017

ER -

Reconstructing Intensity Images from Binary Spatial Gradient Cameras

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this