Implementation of a high-performance portable real-time dehazing system using the DCP algorithm

Allan Navarro-Brenes; Luis Chavarria-Zamora

doi:10.1109/URUCON53396.2021.9647322

Implementation of a high-performance portable real-time dehazing system using the DCP algorithm

Allan Navarro-Brenes
, Luis Chavarria-Zamora

Escuela de Ingeniería en Computadores

Costa Rica Institute of Technology

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

1 Scopus citations

Abstract

This document presents a portable, high performance system for real-time image dehazing using the DCP algorithm. The software runs on a CPU-GPU heterogeneous environment in a development platform from NVIDIA with support for CUDA. Three different window sizes for the DCP algorithm were explored. These low values allow a high throughput and reduce the halo artifacts but results in low-luminosity frames which negatively impacts quality. To solve this, a gamma correction was introduced as a final stage. The coefficient for this filter can vary and is a value which can be manually modified with feedback from the users, depending on their preferences. The picture resolution utilized was 1280× 720 pixels, which the system was able to process at a frame rate of 40 fps using a window size of 3. The image capture can come either from an USB camera or from a video file. The output can be store as a file or it can be wirelessly transmitted to a mobile device using the RTP protocol.

Original language	English
Title of host publication	2021 IEEE URUCON, URUCON 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	552-555
Number of pages	4
ISBN (Electronic)	9781665424431
DOIs	https://doi.org/10.1109/URUCON53396.2021.9647322
State	Published - 2021
Event	2021 IEEE URUCON, URUCON 2021 - Montevideo, Uruguay Duration: 24 Nov 2021 → 26 Nov 2021

Publication series

Name	2021 IEEE URUCON, URUCON 2021

Conference

Conference	2021 IEEE URUCON, URUCON 2021
Country/Territory	Uruguay
City	Montevideo
Period	24/11/21 → 26/11/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Dark Channel Prior
DCP
GPU programming
high-performance embedded systems
real-time dehazing

Access to Document

10.1109/URUCON53396.2021.9647322

Cite this

@inproceedings{7e0a219a48ac482a8b3fab97c9e97ddc,

title = "Implementation of a high-performance portable real-time dehazing system using the DCP algorithm",

abstract = "This document presents a portable, high performance system for real-time image dehazing using the DCP algorithm. The software runs on a CPU-GPU heterogeneous environment in a development platform from NVIDIA with support for CUDA. Three different window sizes for the DCP algorithm were explored. These low values allow a high throughput and reduce the halo artifacts but results in low-luminosity frames which negatively impacts quality. To solve this, a gamma correction was introduced as a final stage. The coefficient for this filter can vary and is a value which can be manually modified with feedback from the users, depending on their preferences. The picture resolution utilized was 1280× 720 pixels, which the system was able to process at a frame rate of 40 fps using a window size of 3. The image capture can come either from an USB camera or from a video file. The output can be store as a file or it can be wirelessly transmitted to a mobile device using the RTP protocol.",

keywords = "Dark Channel Prior, DCP, GPU programming, high-performance embedded systems, real-time dehazing",

author = "Allan Navarro-Brenes and Luis Chavarria-Zamora",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE URUCON, URUCON 2021 ; Conference date: 24-11-2021 Through 26-11-2021",

year = "2021",

doi = "10.1109/URUCON53396.2021.9647322",

language = "Ingl{\'e}s",

series = "2021 IEEE URUCON, URUCON 2021",

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

pages = "552--555",

booktitle = "2021 IEEE URUCON, URUCON 2021",

}

Navarro-Brenes, A & Chavarria-Zamora, L 2021, Implementation of a high-performance portable real-time dehazing system using the DCP algorithm. in 2021 IEEE URUCON, URUCON 2021. 2021 IEEE URUCON, URUCON 2021, Institute of Electrical and Electronics Engineers Inc., pp. 552-555, 2021 IEEE URUCON, URUCON 2021, Montevideo, Uruguay, 24/11/21. https://doi.org/10.1109/URUCON53396.2021.9647322

Implementation of a high-performance portable real-time dehazing system using the DCP algorithm. / Navarro-Brenes, Allan; Chavarria-Zamora, Luis.
2021 IEEE URUCON, URUCON 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 552-555 (2021 IEEE URUCON, URUCON 2021).

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

TY - GEN

T1 - Implementation of a high-performance portable real-time dehazing system using the DCP algorithm

AU - Navarro-Brenes, Allan

AU - Chavarria-Zamora, Luis

PY - 2021

Y1 - 2021

N2 - This document presents a portable, high performance system for real-time image dehazing using the DCP algorithm. The software runs on a CPU-GPU heterogeneous environment in a development platform from NVIDIA with support for CUDA. Three different window sizes for the DCP algorithm were explored. These low values allow a high throughput and reduce the halo artifacts but results in low-luminosity frames which negatively impacts quality. To solve this, a gamma correction was introduced as a final stage. The coefficient for this filter can vary and is a value which can be manually modified with feedback from the users, depending on their preferences. The picture resolution utilized was 1280× 720 pixels, which the system was able to process at a frame rate of 40 fps using a window size of 3. The image capture can come either from an USB camera or from a video file. The output can be store as a file or it can be wirelessly transmitted to a mobile device using the RTP protocol.

AB - This document presents a portable, high performance system for real-time image dehazing using the DCP algorithm. The software runs on a CPU-GPU heterogeneous environment in a development platform from NVIDIA with support for CUDA. Three different window sizes for the DCP algorithm were explored. These low values allow a high throughput and reduce the halo artifacts but results in low-luminosity frames which negatively impacts quality. To solve this, a gamma correction was introduced as a final stage. The coefficient for this filter can vary and is a value which can be manually modified with feedback from the users, depending on their preferences. The picture resolution utilized was 1280× 720 pixels, which the system was able to process at a frame rate of 40 fps using a window size of 3. The image capture can come either from an USB camera or from a video file. The output can be store as a file or it can be wirelessly transmitted to a mobile device using the RTP protocol.

KW - Dark Channel Prior

KW - DCP

KW - GPU programming

KW - high-performance embedded systems

KW - real-time dehazing

UR - https://www.scopus.com/pages/publications/85124352134

U2 - 10.1109/URUCON53396.2021.9647322

DO - 10.1109/URUCON53396.2021.9647322

M3 - Contribución a la conferencia

AN - SCOPUS:85124352134

T3 - 2021 IEEE URUCON, URUCON 2021

SP - 552

EP - 555

BT - 2021 IEEE URUCON, URUCON 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE URUCON, URUCON 2021

Y2 - 24 November 2021 through 26 November 2021

ER -

Implementation of a high-performance portable real-time dehazing system using the DCP algorithm

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this