The proliferation of Internet of Things (IoT) and the success of rich cloud services have pushed the horizon of a new computing paradigm, edge computing, which calls for processing the data at the edge of the network. Edge computing has the potential to address the concerns of response time requirement, battery life constraint, bandwidth cost saving, as well as data safety and privacy.
The core Public Safety community consists of traditional first responders such as Fire, Law Enforcement, Transportation, Public Health, and others. However, existing cloud-centric analytics solutions require that all data must be preloaded to a centralized cluster or Cloud, which suffers high response latency and formidable cost of data transmission especially in a video analytics case. On the other hand, the data is rarely shared among multiple stakeholders due to various concerns, which restricts the practical deployment of data analytics that takes advantages of many data sources to make a smart decision.
To attack the aforementioned issues, our mission is to improve public safety leveraging Edge Computign techniques, coined as EdgeCOPS (Edge Computing for Public Safety). By working closely with two major stakeholders of local public safety community, i.e., Detroit Police Department (DPD) and Detroit Fire Department (DFD), we will explore the challenges of real-time video analytics systems for public safety applications and develop these applications to improve Public Safety.
Emergency medical service (EMS) systems are public services that provide quick response, transportation as well as appropriate emergency medical care to the emergent patient. For EMS, every second is critical. Unfortunately, current EMS systems have many challenges: lack effective communication between EMS providers and hospital professionals, less attention on care quality and limited resources of medical equipment and personnel. Motivated by this, in this paper, we explore the use of wearable sensing, smart mobile as well as video technology to propose STREMS: an efficient smart real-time prehospital communication system for EMS. Specifically, we first introduce a cost-effective wearable physiological sensing solution to support multi-dimensional telemetry monitoring for an ambulance operating at as Basic Life Support, a type of EMS service level without sophisticated medical equipment or paramedics. Then we propose to build a cloud-based real-time data sharing platform, enabling automated streaming all gathered prehospital data (e.g., vital signs, EKG and image/short videos about accident scene) to the hospital prior to ambulance arrival, thus giving a complete figure about the incoming patient. This can significantly decrease the handoff time and improve the efficiency at the hospital. Additionally, a live point to point video communication is proposed to support EMS telemedicine to enhance prehospital care quality, through directly video conversation, to assist EMS providers in consultation, triage, early medical examination and treatment.
In a blazing building, there is a compelling need to pinpoint the firefighters' physical location, dynamically track their moving trajectory and their proximity environmental data in real time to improve the field situational awareness. To achieve this goal, we will leverage a range of transformative wireless, sensing and computing technologies to build Firefighting Assitant SysTem (FAST), a real time firefighter location and monitoring system with the capabilities of quickly creating a 3D building model, dynamically locating, tracking the firefighter's indoor ubiquitous 3D location, mapping them in the generated 3D model as well as streaming the live video data from the handheld infrared camera to a centralized station.
Real-time video analysis at the edge of the network can reduce response latency and cost of transmission, which is very promising to significantly improve public safety. The Detroit Police Department initiated a crime-fighting project called "Project Green Light Detroit", which leverages the real-time video streams between police headquarters and partners who have installed more than hundred high-quality video cameras. The collected video data will be the input of the EVAPS. In the EVAPS, it will analyze the live and archived video data simultaneously at edge nodes that are computing resources closing to the video data sources, to identify potential dangerous events/objects (e.g., gunshot in a crime, the kidnapper's vehicle of an AMBER alert).
- Detroit Police Department
- Detroit Fire Department
- Detroit Open Data Initiative
- Montgomery County, MD
- Weisong Shi, Wayne State University
- Robert Dunne, Detroit Fire Department/Wayne State University
- Daniel Hoffman, CIO, Montgomery County, MD
- Joel H. Heeres, Detroit Open Data Initiative
- Derek Hillman, Detroit Fire Department
- David Martin, Center for Urban Studies
- Kim Lagerquist, St. John Hospital and Medical Center
- Zhifeng Yu, EdgeMind LLC.
- Postdoctor and Students
- Undergraduate Student
- Yinzhe Luo
- Hui Sun, Xu Liang, Wei Liu and Weisong Shi, VU: Video Userfulness and Its Application in Large-Scale Video Surveillance Systems, Technical Report MIST-TR-2018-001, January 2018.
- Qingyang Zhang, Quan Zhang, Weisong Shi and Hong Zhong, Distributed Collaborative Execution on the Edges and Its
Application on AMBER Alert, accepted by IEEE Internet of Things Journal. January 2018.
- Qingyang Zhang, Quan Zhang, Weisong Shi and Hong Zhong, Poster: Enhancing AMBER Alert using Collaborative Edges, in Proceedings of 2nd ACM/IEEE Symposium on Edge Computing (SEC), San Jose, Oct 12-14, 2017.
- Xiaopei Wu, Robert Dunne, Qingyang Zhang and Weisong Shi, Edge Computing Enabled Smart Firefighting: Opportunities and Challenges, in Proceedings of 4th HotWeb, in conjunction with SEC 2017, San Jose, Oct 14, 2017.
- Shanhe Yi, Zijiang Hao, Qingyang Zhang, Quan Zhang, Weisong Shi and Qun Li, LAVEA: Latency-aware Video Analytics on Edge Computing Platform, in Proceedings of 2nd ACM/IEEE Symposium on Edge Computing (SEC), San Jose, Oct 12-14, 2017.
- Hui Sun, Xu Liang and Weisong Shi, Video Usefulness and Its Application in Large-Scale Video Surveillance Systems: An Early Experience, in Proceedings of 1st SmartIoT Workshop, in conjunction with SEC 2017, San Jose, Oct 14, 2017.
- Quan Zhang, Qingyang Zhang, Weisong Shi and Hong Zhong, Firework: Data Processing and Sharing for Hybrid Cloud-Edge Analytics, Technical Report MIST-TR-2017-002, January 2017.
- Xiaopei Wu, Robert Dunne, Zhifeng Yu and Weisong Shi, STREMS: A Smart Real-time Solution Toward Enhancing EMS Prehospital Quality, in Proceedings of 2nd IEEE/ACM International Conference on Connected Health (CHASE), Philadelphia, July 17-19, 2017.
- Qingyang Zhang, Zhifeng Yu, Weisong Shi and Hong Zhong, Demo Abstract: EVAPS: Edge Video Analysis for Public Safety, in Proceedings of 1st IEEE/ACM Symposium on Edge Computing (SEC), Washington DC, Oct 27-28, 2016.
- Weisong Shi, Jie Cao, Quan Zhang, Youhuizi Li and Lanyu Xu, Edge Computing: Vision and Challenges, IEEE Internet of Things Journal, Vol. 3, No. 5, October 2016, pp. 637-646.
- Quan Zhang, Xiaohong Zhang, Qingyang Zhang, Weisong Shi and Hong Zhong, Firework: Big Data Sharing and Processing in Collaborative Edge Environment, in Proceedings of 4th IEEE Workshop on Hot Topics in Web Systems and Technologies (HotWeb), Washington DC, Oct. 24-25, 2016.
- Lanyu Xu, Heather Ann Fritz and Weisong Shi, User Centric Design for Aging Population: Early Experiences and Lessons, in Proceedings of the 1st IEEE Conference on Connected Health: Applications, Systems, and Engineering Technologies (CHASE 2016), June 27-29, 2016. Washington DC.