Robust object detection and adaptive background estimation based on radial reach correlation

Author

Itoh, Masaya

Author_Institution

Hitachi Res. Lab., Hitachi, Ltd., Hitachi, Japan

fYear

2015

fDate

28-30 Jan. 2015

Firstpage

1

Lastpage

5

Abstract

A method of real-time object detection using Radial Reach Correlation (RRC) has been developed. We also apply a statistical background estimation to cope with dynamic and complex environments. In order to reduce the computational cost of RRC for an embedded image processing device, we apply two techniques: fast RRC algorithm and background estimation based on statistical approach with cumulative averaging process. As a result, it is possible to reduce the RRC calculation process to about 1/4 in comparison with normal RRC. By combining these techniques, we can achieve robust real-time object detection.

Keywords

correlation methods; object detection; statistical analysis; RRC; adaptive background estimation; computational cost reduction; cumulative averaging process; embedded image processing device; radial reach correlation; real-time object detection; robust object detection; statistical approach; statistical background estimation; Algorithm design and analysis; Correlation; Decision support systems; Estimation; Object detection; Real-time systems; Robustness; background estimation; embedded system; increment sign code; object detection; radial reach correlation; surveillance system;

fLanguage

English

Publisher

ieee

Conference_Titel

Frontiers of Computer Vision (FCV), 2015 21st Korea-Japan Joint Workshop on

Conference_Location

Mokpo

Type

conf

DOI

10.1109/FCV.2015.7103742

Filename

7103742