Deep Learning based Effective Surveillance System for Low-Illumination Environments

In Su Kim, Yunju Jeong, Seock Ho Kim, Jae Seok Jang, Soon Ki Jung

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 Scopus citations

Abstract

Surveillance cameras are installed in various locations and contribute to security maintenance and safety. Thus, the video quality of surveillance cameras is important for safety. However, in situations such as nighttime, low-illumination often causes poor image quality. To solve this problem, we propose a system to help acquire quality images of general surveillance cameras utilized in various places through a combination of image quality improvement networks and object detect networks. This will improve safety in low-illumination areas at night. It is also possible to establish a more effective monitoring system for situations occurring in low-illumination areas.

Original languageEnglish
Title of host publicationICUFN 2019 - 11th International Conference on Ubiquitous and Future Networks
PublisherIEEE Computer Society
Pages141-143
Number of pages3
ISBN (Electronic)9781728113395
DOIs
StatePublished - Jul 2019
Event11th International Conference on Ubiquitous and Future Networks, ICUFN 2019 - Zagreb, Croatia
Duration: 2 Jul 20195 Jul 2019

Publication series

NameInternational Conference on Ubiquitous and Future Networks, ICUFN
Volume2019-July
ISSN (Print)2165-8528
ISSN (Electronic)2165-8536

Conference

Conference11th International Conference on Ubiquitous and Future Networks, ICUFN 2019
Country/TerritoryCroatia
CityZagreb
Period2/07/195/07/19

Keywords

  • deep learning
  • image enhancement
  • low-illumination
  • object detection
  • surveillance

Fingerprint

Dive into the research topics of 'Deep Learning based Effective Surveillance System for Low-Illumination Environments'. Together they form a unique fingerprint.

Cite this