Key points are not available for this paper at this time.
With recent advances in both Artificial Intelligence (AI) and Internet of Things (IoT) capabilities, it is more possible than ever to implement surveillance systems that can automatically identify people who might represent a potential security threat to the public in real time. Imagine a surveillance camera system that can detect various on-body weapons, suspicious objects, and traffic. This system could transform surveillance cameras from passive sentries into active observers, which would help prevent a possible mass shooting in a school, stadium, or mall. In this paper, we tried to realize such systems by implementing Smart-Watcher, an AI-powered threat detector for intelligent surveillance cameras. The developed system can be deployed locally on the surveillance cameras at the network edge. Deploying AI-enabled surveillance applications at the edge enables the initial analysis of the captured images onsite, reducing communication overheads and enabling swift security actions. We developed a mobile app that alerts system users about any detected suspicious objects in an image and video captured by several cameras at the network edge. Also, Smart-Watcher can generate a high-quality segmentation mask for each object instance in the photo, along with the confidence percentage. Smart-Watcher can recognize eight object classes, including baseball bats, birds, cats, dogs, guns, hammers, knives, and human faces. Smart-Watcher was evaluated using various performance metrics such as classification time and accuracy.
Ahmed et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: