Title :
An 1.92mW Feature Reuse Engine based on inter-frame similarity for low-power object recognition in video frames
Author :
Dongjoo Shin ; Injoon Hong ; Hoi-Jun Yoo
Author_Institution :
Dept. of Electr. Eng., KAIST, Daejeon, South Korea
Abstract :
A Feature Reuse Engine (FReE) is proposed to achieve low-power object recognition in video frames. Previous object recognition processors perform redundant processing for repeated features of sequential frames in video. Unlike previous works, proposed FReE reuses 58% of features from previous frame with inter-frame similarity. However, false reuse can degrade the object recognition accuracy. By pixel intensity-based Near Pixel Information (NPI), FReE can decide the reusability with 96% of accuracy. Additionally, to minimize latency and power overhead of FReE, a dedicated integral image generator and NPI generator are proposed. As a result, power consumption of object recognition processor is reduced by 31% with the proposed FReE which consumes only 1.92mW in a 130nm CMOS technology.
Keywords :
object recognition; video signal processing; FReE; NPI; feature reuse engine; interframe similarity; low power object recognition; near pixel information; object recognition accuracy; object recognition processors; video sequential frames; Engines; Feature extraction; Generators; Object recognition; Power demand; Program processors; Streaming media; feature reuse; inter-frame similarity; low-power; object recognition; video frame;
Conference_Titel :
Circuits and Systems (ISCAS), 2014 IEEE International Symposium on
Conference_Location :
Melbourne VIC
Print_ISBN :
978-1-4799-3431-7
DOI :
10.1109/ISCAS.2014.6865246
