Submitted by Angela Walters on Mon, 27/04/2020 - 10:28
Abstract
When looking at in-building or urban settings, information about the number of people present and the way they move through the space is useful for helping designers to understand what they have created, fire marshals to identify potential safety hazards, planners to speculate about what is needed in the future, and the public to have real data on which to base opinions about communal choices. We propose a network of edge devices based on Raspberry Pi and TensorFlow, which will ultimately push data via LoRaWAN to a real-time data server. This network is being integrated into a Digital Twin of a local site which includes several dozen buildings spread over approximately 500,000 square metres. We share and discuss issues regarding privacy, accuracy and performance.
People
Theme
Citation
Matthew Danish, Justas Brazauskas, Rob Bricheno, Ian Lewis, and Richard Mortier. 2020. DeepDish: Multi-Object Tracking with an Off-the-Shelf Raspberry Pi . In 3rd International Workshop on Edge Systems, Analytics and Networking (EdgeSys ’20), April 27, 2020, Heraklion, Greece. ACM, New York, NY, USA, 6 pages. https://doi.org/10.1145/3378679.3394535