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

自残是惩教机构中常见的死亡原因。对自残事件的持续监测和快速发现对于保护囚犯的生命和降低死亡率至关重要。在过去的几十年里，已经开发了几种技术来防止监狱中的自杀企图。然而，它们大多使用笨重的设备和/或在很大程度上依赖于人类的保护、注意和干预。我们的目标是开发自主视频监控解决方案，以便智能地检测监狱中的生命威胁事件，并允许快速和反应性的干预。拟议的系统将被设计成在现实条件下连续运行，以检测通过上吊或割腕自杀的企图；2-两名囚犯之间的打斗；3-以及危及生命的症状。这些目标将通过确保有效利用视觉采集技术、计算机视觉方法和人工智能的最新进展来实现。该项目将带来智能视频监控领域的新知识，同时有助于培养高素质的人才，他们将在加拿大各地获得高需求的专业知识。我们的工作还将允许我们的工业合作伙伴开发一种商业产品，用于矫正服务。预计该产品的影响将不仅仅是经济上的。这将有助于挽救处于危险中的被监禁者的生命，并避免由此带来的痛苦。

Self-harm is a common cause of death in correctional settings. The constant monitoring and the rapid detectionof self-harm events are crucial for protecting inmates' lives and reducing the mortality rates. During the lastdecades, several technologies have been developed for preventing suicide attempts in prisons. However, mostof them use cumbersome devices and/or are greatly depending on human guard attention and intervention. Ourobjective is to develop autonomous video surveillance solutions in order to intelligently detect life-threateningevents in prisons, and allow a rapid and reactive intervention. The proposed system will be designed to operatecontinuously in realistic conditions to detect suicide attempts by hanging or by wrist cutting; 2- fights betweentwo inmates; 3- and symptoms of life threatening situations. These objectives will be achieved by ensuring theefficient exploitation of recent advances in visual acquisition technologies, computer vision methods andartificial 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 acrossCanada. Our work will also allow our industrial partner to develop a commercial product to be deployed incorrectional services. The impact of this product is expected to be more than merely economic. It will helpsaving the lives of incarcerated people at risk, and avoid the resulting suffering.