AutoVAPS: an IoT-enabled public safety service on vehicles

With the rapid development of Internet-of-Things, sensors and devices are connected enabling a variety of applications. One of the most attractive applications is Video Analysis for Public Safety (VAPS), which has got massive attention from both research community and industry. However, there are still challenges in the system design and implementation of the VAPS service, especially in the mobile environment. For example, law enforcement officers are equipped with body-worn camera when they are on duty, how to connect body-worn cameras with the law enforcement vehicle and enable the law enforcement vehicle to perform near real-time video analysis for the officer are still open questions. Inspired by the promising edge computing technology, we propose an IoT-Enabled public safety service called AutoVAPS which integrates body-worn cameras and other sensors on the vehicle for public safety. In AutoVAPS, we propose a reference architecture that consists of the data layer for data management, the model layer for edge intelligence, and the access layer for privacy-preserving data sharing and access. Object detection is implemented as a case study of AutoVAPS. Early evaluation illustrated the applicability and challenges of AutoVAPS.

[1]  Andrew Weinert,et al.  Using open-source hardware to support disadvantaged communications , 2015, 2015 IEEE Global Humanitarian Technology Conference (GHTC).

[2]  Xiaopei Wu,et al.  OpenVDAP: An Open Vehicular Data Analytics Platform for CAVs , 2018, 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS).

[3]  Weisong Shi,et al.  Edge Computing: Vision and Challenges , 2016, IEEE Internet of Things Journal.

[4]  Henning Schulzrinne,et al.  Real-Time Streaming Protocol Version 2.0 , 2016, RFC.

[5]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[6]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[7]  Saurabh Amin,et al.  Semantic Topic Analysis of Traffic Camera Images , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[8]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[9]  Sergio Guadarrama,et al.  Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Warren Smith,et al.  Cloud computing in tactical environments , 2017, MILCOM 2017 - 2017 IEEE Military Communications Conference (MILCOM).

[11]  Carlos Parra,et al.  Designing public safety mobile applications for disconnected, interrupted, and low bandwidth communication environments , 2013, 2013 IEEE International Conference on Technologies for Homeland Security (HST).

[12]  Jason Thornton,et al.  Learning Network Architectures of Deep CNNs Under Resource Constraints , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[13]  Andrew Weinert,et al.  Outreach to Define a Public Safety Communications Model For Broadband Cellular Video , 2018, 2018 IEEE International Symposium on Technologies for Homeland Security (HST).

[14]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Simson L. Garfinkel,et al.  First Workshop on Video Analytics in Public Safety | NIST , 2017 .

[16]  Tiago M. Fernández-Caramés,et al.  A Review on Internet of Things for Defense and Public Safety , 2016, Sensors.

[17]  Andy Vidan,et al.  Integrated sensing and command and control system for disaster response , 2010, 2010 IEEE International Conference on Technologies for Homeland Security (HST).