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

fYear

2014

fDate

1-5 June 2014

Firstpage

758

Lastpage

761

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;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems (ISCAS), 2014 IEEE International Symposium on

Conference_Location

Melbourne VIC

Print_ISBN

978-1-4799-3431-7

Type

conf

DOI

10.1109/ISCAS.2014.6865246

Filename

6865246