Title :
A low-power and real-time augmented reality processor for the next generation smart glasses
Author :
Gyeonghoon Kim;Hoi-Jun Yoo
Author_Institution :
Korea Advanced Institute of Science and Technology (KAIST)
Abstract :
This article consists of a single slide from the authors´ conference presentation. Topics covered include: hardware requirements of augmented reality in smart glasses systems; algorithm-hardware mapping and network congestion problem; neural network scheduler for 2-D-mesh network-on-chip; and chip and smart glass system implementation.
Keywords :
"Artificial neural networks","Visualization","Throughput","Real-time systems","Feature extraction","Augmented reality","Network-on-chip"
Conference_Titel :
Hot Chips 27 Symposium (HCS), 2015 IEEE
DOI :
10.1109/HOTCHIPS.2015.7477476