A Vocabulary Forest-based object matching processor with 2.07M-vec/s throughput and 13.3nJ/vector energy in full-HD resolution

Author

Kyuho Lee ; Gyeonghoon Kim ; Junyoung Park ; Hoi-Jun Yoo

Author_Institution

Dept. of EE, KAIST, Daejeon, South Korea

fYear

2014

fDate

10-13 June 2014

Firstpage

1

Lastpage

2

Abstract

A Vocabulary Forest-based object matching processor is proposed to speed up the feature matching stage for the object recognition system with high accuracy. Adopting Reusable-Vocabulary Tree architecture and hardware sharing technique reduces area, as well as adopting propagate-and-compute-array architecture in the combiner and external database elimination enhances the matching speed more than 16x compared to Approximate Nearest Neighbor searching processors. The proposed Vocabulary Forest processor, implemented in 65nm CMOS process, achieves 2.07M-vec/s throughput and 13.3nJ/vector energy efficiency, and successfully matches 100 objects with 95.7% matching accuracy.

Keywords

CMOS integrated circuits; object recognition; CMOS; feature matching; full-HD resolution; hardware sharing technique; object recognition; propagate-and-compute-array architecture; reusable-vocabulary tree architecture; size 65 nm; vocabulary forest-based object matching processor; Accuracy; Computer architecture; Feature extraction; Throughput; Vectors; Vegetation; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

VLSI Circuits Digest of Technical Papers, 2014 Symposium on

Conference_Location

Honolulu, HI

Print_ISBN

978-1-4799-3327-3

Type

conf

DOI

10.1109/VLSIC.2014.6858386

Filename

6858386