Deep Learning based Effective Surveillance System for Low-Illumination Environments
In Su Kim, Yunju Jeong, Seock Ho Kim, Jae Seok Jang, Soon Ki Jung · 2019
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.