The Community for Technology Leaders
Green Image
Issue No. 06 - Nov.-Dec. (2012 vol. 32)
ISSN: 0272-1732
pp: 38-50
Junyoung Park , Korea Advanced Institute of Science and Technology
Injoon Hong , Korea Advanced Institute of Science and Technology
Gyeonghoon Kim , Korea Advanced Institute of Science and Technology
Jinwook Oh , Korea Advanced Institute of Science and Technology
Seungjin Lee , Korea Advanced Institute of Science and Technology
Joo-Young Kim , Korea Advanced Institute of Science and Technology
Jeong-Ho Woo , Korea Advanced Institute of Science and Technology
Hoi-Jun Yoo , Korea Advanced Institute of Science and Technology
ABSTRACT
A new low-power object-recognition processor achieves real-time robust recognition, satisfying modern mobile vision systems' requirements. The authors introduce an attention-based object-recognition algorithm for energy efficiency, a heterogeneous multicore architecture for data- and thread-level parallelism, and a network on a chip for high on-chip bandwidth. The fabricated chip achieves 30 frames/second throughput and an average 320 mW power consumption on test 720p video sequences, yielding 640 GOPS/W and 10.5 nJ/pixel energy efficiency.
INDEX TERMS
Decision support systems, Robustness, Object recognition, Multicore processing, Network-on-a-chip, Low power electronics, SIFT, object recognition, attention, attention-based object recognition, network-on-chip, multicore processor, heterogeneous multicore, object-recognition pipeline, scale invariant feature transform
CITATION
Junyoung Park, Injoon Hong, Gyeonghoon Kim, Jinwook Oh, Seungjin Lee, Joo-Young Kim, Jeong-Ho Woo, Hoi-Jun Yoo, "Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems", IEEE Micro, vol. 32, no. , pp. 38-50, Nov.-Dec. 2012, doi:10.1109/MM.2012.90
84 ms
(Ver 3.1 (10032016))