Live Demonstration: Deep Learning-Based Visual Tracking of Multiple Objects on a Low-Power Embedded System

TítuloLive Demonstration: Deep Learning-Based Visual Tracking of Multiple Objects on a Low-Power Embedded System
AutoresBeatriz Blanco-Filgueira, Daniel García-Lesta, Mauro Fernández-Sanjurjo, Víctor M. Brea, Paula López
TipoComunicación para congreso
Fonte 2019 IEEE International Symposium on Circuits and Systems, Sapporo (Japón), pp. 1 , 2019.
AbstractMultiple object visual tracking of real time detected objects using a low-power embedded solution is shown. The proposal is implemented on a NVIDIA Jetson TX2 development kit demonstrating the feasibility of deep learning techniques for IoT and mobile edge computing applications.
Palabras chaveDeep Learning, Embedded GPU, PBAS, Go-TURN