We want to bring the recent advances in Artificial Intelligence (AI) and machine learning to enhance safety and security of our community without jeopardizing the privacy of citizens.
The emergence of intelligent technologies is enabling a new era of connection between community residents and the surrounding environments, both in the United States and around the world. With the new wave of growth in urban areas, ensuring public safety is an essential precursor toward “smart” cities and communities. This project proposes a novel “intelligent” policing technology as a transformative solution to efficiently enhance law enforcement, while minimizing unnecessary interactions and maintaining resident privacy. The proposed technology offers a network of smart cameras that do not require continuous monitoring, but instead are trained to generate alerts on the spot in real-time. Since the cameras identify behaviors and not identities, they can reduce biases, minimize false alarms, and protect personal privacy. The intelligent policing technology will be co-designed and co-created with the direct help of community residents, neighborhood leaders, and local business owners, as well as agencies including the City of Charlotte, and local law enforcement departments.
The aim of this project is to minimize the tension and achieve much higher coverage in community environments, filtering out unnecessary calls while maintaining the privacy of community individuals. Few examples are movement patterns of individuals indicating criminal intent such as attempting to unlock multiple parked cars. This project proposes a context-aware sensing system which primarily relies on the real-time video analytics next to the video cameras (edge video analytics). We will leverage the recent advances in edge computing, computer vision, and deep learning, and extend them, to enable real-time pedestrian/vehicle detection and tracking as well as top-level behavioral analysis completely integrated to the community environment, without the need to store and save the actual video data and transfer them to the cloud. Our aim is to push video analytics toward disaggregation, as such to be integrated to the fabric of our community. To this end, we build algorithms and processing platforms for custom on-the-fly execution of deep learning algorithms (real-time edge video analytics engine). At the same time, the technology offers the capability of selective recording and storing the video data if a potential threat (or criminal activities) is detected.
Acknowledgments: National Science Foundation (NSF), Charlotte-Mecklenburg Police Department (CMPD), Gaston County Police Department (GCPD)
Team Information: Hamed Tabkhi