A Pervasive Framework for Human Detection and Tracking
This addresses surveillance needs for edge computing users, but appears incremental as it builds on existing detection and tracking methods.
The paper tackles human detection and tracking on edge devices by proposing two models and algorithms, achieving evaluation of accuracy and resource requirements for embedded execution.
The advent of the Edge Computing (EC) leads to a huge ecosystem where numerous nodes can interact with data collection devices located close to end users. Human detection and tracking can be realized at edge nodes that perform the surveillance of an area under consideration through the assistance of a set of sensors (e.g., cameras). Our target is to incorporate the discussed functionalities to embedded devices present at the edge keeping their size limited while increasing their processing capabilities. In this paper, we propose two models for human detection accompanied by algorithms for tracing the corresponding trajectories. We provide the description of the proposed models and extend them to meet the challenges of the problem. Our evaluation aims at identifying models' accuracy while presenting their requirements to have them executed in embedded devices.