ANN Ensembles vs DSP for Mobile Object Detection and Filtering

Author

Moorgas, Kevin Emanuel ; Govender, Poobalan

Author_Institution

Dept. of Electron. Eng., Durban Univ. of Technol., Durban, South Africa

fYear

2008

fDate

22-24 Oct. 2008

Firstpage

252

Lastpage

257

Abstract

This paper presents a comparative study between digital signal processing (DSP) systems and artificial neural networks (ANNpsilas) for object motion detection and object extraction and image filtering. The ANNpsilas are arranged as an ensemble to perform the motion detection and image subtraction function. ANN´s are also used for rejecting any noise contained within the image. The ANN system displays a superior performance over the DSP in terms of system complexity and image quality.

Keywords

feature extraction; filtering theory; image denoising; image motion analysis; neural nets; object detection; ANN; DSP; artificial neural network; digital signal processing; image filtering; image noise rejection; image quality; image subtraction function; mobile object motion detection; object extraction; system complexity; Artificial neural networks; Data mining; Digital filters; Digital signal processing; Discrete Fourier transforms; Filtering; Frequency; Intelligent systems; Motion detection; Object detection; artificial neural networks; digital signal processing; ensembles; filtering;

fLanguage

English

Publisher

ieee

Conference_Titel

World Congress on Engineering and Computer Science 2008, WCECS '08. Advances in Electrical and Electronics Engineering - IAENG Special Edition of the

Conference_Location

San Francisco, CA

Print_ISBN

978-1-4244-3545-6

Type

conf

DOI

10.1109/WCECS.2008.38

Filename

5233165