TY - GEN
T1 - Accelerating mobile augmented reality on a handheld platform
AU - Lee, Seung Eun
AU - Zhang, Yong
AU - Fang, Zhen
AU - Srinivasan, Sadagopan
AU - Iyer, Ravi
AU - Newell, Donald
PY - 2009
Y1 - 2009
N2 - Mobile Augmented Reality (MAR) is an emerging visual computing application for the mobile internet device (MID). In one MAR usage model, the user points the handheld device to an object (like a wine bottle or a building) and the MID automatically recognizes and displays information regarding the object. Achieving this in software on the handheld requires significant compute processing for object recognition and matching. In this paper, we identify hotspot functions of the MAR workload on a low-power x86 platform that motivates acceleration. We present the detailed design of two hardware accelerators, one for object recognition (MAR-HA) and the other for match processing (MAR-MA). We also quantify the performance and area efficiency of the hardware accelerators. Our analysis shows that hardware acceleration has the potential to improve the individual hotspot functions by as much as 20x, and overall response time by 7x. As a result, user response time can be reduced significantly.
AB - Mobile Augmented Reality (MAR) is an emerging visual computing application for the mobile internet device (MID). In one MAR usage model, the user points the handheld device to an object (like a wine bottle or a building) and the MID automatically recognizes and displays information regarding the object. Achieving this in software on the handheld requires significant compute processing for object recognition and matching. In this paper, we identify hotspot functions of the MAR workload on a low-power x86 platform that motivates acceleration. We present the detailed design of two hardware accelerators, one for object recognition (MAR-HA) and the other for match processing (MAR-MA). We also quantify the performance and area efficiency of the hardware accelerators. Our analysis shows that hardware acceleration has the potential to improve the individual hotspot functions by as much as 20x, and overall response time by 7x. As a result, user response time can be reduced significantly.
UR - https://www.scopus.com/pages/publications/77950975466
U2 - 10.1109/ICCD.2009.5413123
DO - 10.1109/ICCD.2009.5413123
M3 - Conference contribution
AN - SCOPUS:77950975466
SN - 9781424450282
T3 - Proceedings - IEEE International Conference on Computer Design: VLSI in Computers and Processors
SP - 419
EP - 426
BT - 2009 IEEE International Conference on Computer Design, ICCD 2009
T2 - 2009 IEEE International Conference on Computer Design, ICCD 2009
Y2 - 4 October 2009 through 7 October 2009
ER -