Accelerated shadow detection and removal method

Edward Richter; Ryan Raettig; Joshua Mack; Spencer Valancius; Burak Unal; Ali Akoglu

doi:10.1109/AICCSA47632.2019.9035242

Accelerated shadow detection and removal method

Edward Richter, Ryan Raettig, Joshua Mack, Spencer Valancius, Burak Unal, Ali Akoglu

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

1 Scopus citations

Abstract

Shadows can have a negative effect on the ability of computer vision techniques for object detection, tracking, and recognition. Therefore, ability to remove shadows and byproducts of illumination is an important problem to enable effective object recognition actions. As applications move into levels of higher information extraction and higher required processing speeds, efficient and sophisticated shadow detection and removal becomes even more necessary. In this study we propose a shadow removal method, parallelize using a Tesla P100 GPU, and achieve a speedup of 21.67× on an 18 megapixel (MP) resolution image compared to the same method implemented in Matlab.

Original language	English (US)
Title of host publication	16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019
Publisher	IEEE Computer Society
ISBN (Electronic)	9781728150529
DOIs	https://doi.org/10.1109/AICCSA47632.2019.9035242
State	Published - Nov 2019
Externally published	Yes
Event	16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019 - Abu Dhabi, United Arab Emirates Duration: Nov 3 2019 → Nov 7 2019

Publication series

Name	Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA
Volume	2019-November
ISSN (Print)	2161-5322
ISSN (Electronic)	2161-5330

Conference

Conference	16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	11/3/19 → 11/7/19

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Hardware and Architecture
Signal Processing
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/AICCSA47632.2019.9035242

Cite this

Richter, E., Raettig, R., Mack, J., Valancius, S., Unal, B., & Akoglu, A. (2019). Accelerated shadow detection and removal method. In 16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019 Article 9035242 (Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA; Vol. 2019-November). IEEE Computer Society. https://doi.org/10.1109/AICCSA47632.2019.9035242

Accelerated shadow detection and removal method. / Richter, Edward; Raettig, Ryan; Mack, Joshua et al.
16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019. IEEE Computer Society, 2019. 9035242 (Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA; Vol. 2019-November).

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

Richter, E, Raettig, R, Mack, J, Valancius, S, Unal, B & Akoglu, A 2019, Accelerated shadow detection and removal method. in 16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019., 9035242, Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA, vol. 2019-November, IEEE Computer Society, 16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019, Abu Dhabi, United Arab Emirates, 11/3/19. https://doi.org/10.1109/AICCSA47632.2019.9035242

Richter E, Raettig R, Mack J, Valancius S, Unal B, Akoglu A. Accelerated shadow detection and removal method. In 16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019. IEEE Computer Society. 2019. 9035242. (Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA). doi: 10.1109/AICCSA47632.2019.9035242

@inproceedings{4bd0971f752444db9c35c0c21c91dcac,

title = "Accelerated shadow detection and removal method",

abstract = "Shadows can have a negative effect on the ability of computer vision techniques for object detection, tracking, and recognition. Therefore, ability to remove shadows and byproducts of illumination is an important problem to enable effective object recognition actions. As applications move into levels of higher information extraction and higher required processing speeds, efficient and sophisticated shadow detection and removal becomes even more necessary. In this study we propose a shadow removal method, parallelize using a Tesla P100 GPU, and achieve a speedup of 21.67× on an 18 megapixel (MP) resolution image compared to the same method implemented in Matlab.",

author = "Edward Richter and Ryan Raettig and Joshua Mack and Spencer Valancius and Burak Unal and Ali Akoglu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019 ; Conference date: 03-11-2019 Through 07-11-2019",

year = "2019",

month = nov,

doi = "10.1109/AICCSA47632.2019.9035242",

language = "English (US)",

series = "Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA",

publisher = "IEEE Computer Society",

booktitle = "16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019",

}

TY - GEN

T1 - Accelerated shadow detection and removal method

AU - Richter, Edward

AU - Raettig, Ryan

AU - Mack, Joshua

AU - Valancius, Spencer

AU - Unal, Burak

AU - Akoglu, Ali

PY - 2019/11

Y1 - 2019/11

N2 - Shadows can have a negative effect on the ability of computer vision techniques for object detection, tracking, and recognition. Therefore, ability to remove shadows and byproducts of illumination is an important problem to enable effective object recognition actions. As applications move into levels of higher information extraction and higher required processing speeds, efficient and sophisticated shadow detection and removal becomes even more necessary. In this study we propose a shadow removal method, parallelize using a Tesla P100 GPU, and achieve a speedup of 21.67× on an 18 megapixel (MP) resolution image compared to the same method implemented in Matlab.

AB - Shadows can have a negative effect on the ability of computer vision techniques for object detection, tracking, and recognition. Therefore, ability to remove shadows and byproducts of illumination is an important problem to enable effective object recognition actions. As applications move into levels of higher information extraction and higher required processing speeds, efficient and sophisticated shadow detection and removal becomes even more necessary. In this study we propose a shadow removal method, parallelize using a Tesla P100 GPU, and achieve a speedup of 21.67× on an 18 megapixel (MP) resolution image compared to the same method implemented in Matlab.

UR - http://www.scopus.com/inward/record.url?scp=85082656157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85082656157&partnerID=8YFLogxK

U2 - 10.1109/AICCSA47632.2019.9035242

DO - 10.1109/AICCSA47632.2019.9035242

M3 - Conference contribution

AN - SCOPUS:85082656157

T3 - Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA

BT - 16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019

PB - IEEE Computer Society

T2 - 16th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2019

Y2 - 3 November 2019 through 7 November 2019

ER -

Accelerated shadow detection and removal method

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this