Automated surveillance is essential for the protection of Critical Infrastructures (CIs) in future Smart Cities. The dynamic environments and bandwidth requirements demand systems that adapt themselves to react when events of interest occur. We present a reconfigurable Cyber Physical System for the protection of CIs using distributed cloud-edge smart video surveillance. Our local edge nodes perform people detection via Deep Learning. Processing is embedded in high performance SoCs (System-on-Chip) achieving real-time performance (≈ 100 fps-frames per second) which enables efficiently managing video streams of more cameras source at lower frame rate. Cloud server gathers results from nodes to carry out biometric facial identification, tracking, and perimeter monitoring. A Quality and Resource Management module monitors data bandwidth and triggers reconfiguration adapting the transmitted video resolution. This also enables a flexible use of the network by multiple cameras while maintaining the accuracy of biometric identification. A real-world example shows a reduction of ≈ 75% bandwidth use with respect to the no-reconfiguration scenario.

No abstract

The pace of population ageing is increasing and is currently becoming one of the challenges our society faces. The introduction of Cyber-Physical Systems (CPS) has fostered the development of e-Health solutions that ease the associated economic and social burden. In this work, a CPS-based solution is presented to partially tackle the problem: a Deep Multimodal Habit Tracking system. The aim is to monitor daily life activities to alert in case of life-threatening situations improving their autonomy and supporting healthy lifestyles while living alone at home. Our approach combines video and heart rate cues to accurately identify indoor actions, running the processing locally in embedded edge nodes. Local processing provides inherent protection of data privacy since no image or vital signs are transmitted to the network, and reduces data bandwidth usage. Our solution achieves an accuracy of more than 80% in average, reaching up to a 95% for specific subjects after adapting the system. Adding heart-rate information improves F1-score by 2.4%. Additionally, the precision and recall for critical actions such as falls reaches up to 93.75%. Critical action detection is crucial due to their dramatic consequences, it helps to reduce false alarms, leading to building trust in the system and reducing economic cost. Also, the model is optimized and integrated in a Nvidia Jetson Nano embedded device, reaching real-time performance below 3.75 Watts. Finally, a dataset specifically designed for indoor action recognition using synchronized video and heart rate pulses has been collected.

No abstract