Understanding Policy and Technical Aspects of AI-enabled Smart Video Surveillance to Address Public Safety

Abstract

Recent advancements in artificial intelligence (AI) have seen the emergence of smart video surveillance (SVS) in many practical applications, particularly for building safer and more secure communities in our urban environments. Cognitive tasks, such as identifying objects, recognizing actions, and detecting anomalous behaviors, can produce data capable of providing valuable insights to the community through statistical and analytical tools. However, artificially intelligent surveillance systems design requires special considerations for ethical challenges and concerns. The use and storage of personally identifiable information (PII) commonly pose an increased risk to personal privacy. To address these issues, this paper identifies the privacy concerns and requirements needed to address when designing AI-enabled smart video surveillance. Further, we propose the first end-to-end AI-enabled privacy-preserving smart video surveillance system that holistically combines computer vision analytics, statistical data analytics, cloud-native services, and end-user applications. Finally, we propose quantitative and qualitative metrics to evaluate intelligent video surveillance systems. The system shows the 17.8 frame-per-second (FPS) processing in extreme video scenes. However, considering privacy in designing such a system results in preferring the pose-based algorithm to the pixel-based one. This choice resulted in dropping accuracy in both action and anomaly detection tasks. The results drop from 97.48% to 73.72% in anomaly detection and 96% to 83.07% in the action detection task. On average, the latency of the end-to-end system is 36.1 seconds.

Demographic Disparities, Service Efficiency, Safety, and User Satisfaction in Public Bus Transit System: A Survey-based Case Study in the City of Charlotte, NC

“…White participants are less likely to have safety issues than African Americans, who, despite being the majority of bus users, feel more unsafe due to potential socioeconomic gaps and increased crime rates in their areas. This aligns with other studies indicating that safety concerns disproportionately affect minority groups post-pandemic, necessitating targeted safety improvements [11,13,33]. Participants in underserved areas also face more safety issues compared to others, likely due to socioeconomic disparities and higher crime rates.…”

Deep Reinforcement Learning-Empowered Cost-Effective Federated Video Surveillance Management Framework

“…Several studies [25][26][27][28] on anomaly behavior detection have focused mostly on improving the accuracy of DL models, making them tiny on edge devices. In [29][30][31], the authors analyzed the challenges and potential of DL-based pose anomaly detection in video analysis, emphasizing the advantages in terms of privacy and computational efficiency. Nevertheless, these studies did not consider the hierarchical structure of edge computing systems or the practical considerations related to delivering real-time video surveillance services.…”

Research on the Evolution Models and Risk of Disaster-Induced Storage Tank Explosions in a Smart City

“…In a smart city, these safety issues require responsive theories and algorithms to predict, prevent, and handle. The latest researches on smart city safety include information fusion methods in smart city and city environments [5]; Intelligent city safety Human intelligent system [6]; Sustainable service intelligent fire safety management [7]; Artificial Intelligence changes city environment in a smart city [8]; Safety and smart city [9]; Fire safety management Policy for smart cities [10]; smart city public safety data resource management [11]; Artificial intelligence video surveillance to solve public security problems [12]. These studies study smart city safety from multiple perspectives, but they can not provide an effective mathematical model for the role.…”