An intelligent vision-based system for detecting self-harm behavior

点击翻译按钮获取中文摘要

Self-harm is a common cause of death in correctional settings. The constant monitoring and the rapid detection of self-harm events are crucial for protecting inmates' lives and reducing the mortality rates. During the last decades, several technologies have been developed for preventing suicide attempts in prisons. However, most of them use cumbersome devices and/or are greatly depending on human guard attention and intervention. Our objective is to develop autonomous video surveillance solutions in order to intelligently detect life-threatening events in prisons, and allow a rapid and reactive intervention. The proposed system will be designed to operate continuously in realistic conditions to detect suicide attempts by hanging or by wrist cutting; 2- fights between two inmates; 3- and symptoms of life threatening situations. These objectives will be achieved by ensuring the efficient exploitation of recent advances in visual acquisition technologies, computer vision methods and artificial intelligence. This project will lead to new knowledge in the intelligent video surveillance domain, while contributing to training highly qualified personnel who will acquire an expertise in high demand across Canada. Our work will also allow our industrial partner to develop a commercial product to be deployed in correctional services. The impact of this product is expected to be more than merely economic. It will help saving the lives of incarcerated people at risk, and avoid the resulting suffering.