A visual-based artificial intelligence (AI) technology developed by South Korea's Electronics and Telecommunications Research Institute (ETRI) will be deployed on CCTV cameras for detecting and preventing various crimes.
The AI technology 'Deep View', developed by ETRI is applied to the precise recognition of human behavior on the joint level of the human body in CCTV images. The technology helps precisely track down movements of people placing down or throwing objects as well as those illegally throwing away garbage. Applying this technology in the future will help proactively detect and prevent various crimes and incidents from happening in city areas.
So far, there have been much difficulty in recognizing actions appearing in CCTVs as studies on action comprehension utilized widely accessible online data such as YouTube videos.
As part of the efforts to resolve such difficulty, ETRI focused developing action comprehension technology that can operate on actual environment by pulling together necessary requirements and data with local governments.
Using deep learning based AI technology, ETRI developed a method to analyze the movements of human body joints and moving objects. For example, it detects a pile of garbage and analyzes the human body joint point and corresponding movements. Patterns of various garbage dumping behavior are also detected by machine learning methods. The research team used deep learning-based recognition technology to detect location of passersby as well.
Overall, this new technology is expected to significantly reduce crime rates by applying visual-based AI technology on CCTV cameras
About Electronics and Telecommunications Research Institute (ETRI):
ETRI is a non-profit government-funded research institute.
Since its foundation in 1976, ETRI, a global ICT research institute, has been making its immense effort to provide Korea a remarkable growth in the field of ICT industry.
ETRI delivers Korea as one of the top ICT nations in the World, by unceasingly developing world's first and best technologies.