Title :
A 201.4GOPS 496mW real-time multi-object recognition processor with bio-inspired neural perception engine
Author :
Kim, Joo-Young ; Kim, Minsu ; Lee, Seungjin ; Oh, Jinwook ; Kim, Kwanho ; Oh, Sejong ; Woo, Jeong-Ho ; Kim, Donghyun ; Yoo, Hoi-Jun
Author_Institution :
KAIST, Daejeon
Abstract :
The visual attention mechanism, which is the way humans perform object recognition, was applied to the implementation of a high performance object recognition chip. Even though the previous chip achieved 50% gain of computational cost, it could recognize only one object in a frame so that it is not suitable for advanced multi-object recognition applications such as video surveillance, intelligent robots, and autonomous vehicle
Keywords :
computerised navigation; intelligent robots; object recognition; video surveillance; Gaussian; autonomous vehicle; bioinspired neural perception engine; intelligent robots; multiobject recognition applications; object recognition; object recognition chip; real-time multiobject recognition processor; video surveillance; CMOS technology; Circuits; Clocks; Delay; Energy consumption; Energy management; Engines; Network-on-a-chip; Neural networks; Switches;
Conference_Titel :
Solid-State Circuits Conference - Digest of Technical Papers, 2009. ISSCC 2009. IEEE International
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4244-3458-9
DOI :
10.1109/ISSCC.2009.4977352
