Embedded System for Visual Odometry and Localization of Moving Objects in Images Acquired by Unmanned Aerial Vehicles

Author

Reboucas, Rodrigo Augusto ; da Cruz Eller, Quenaz ; Habermann, Mateus ; Hideiti Shiguemori, Elcio

Author_Institution

Inst. for Adv. Studies - IEAv, São José dos Campos, Brazil

fYear

2013

fDate

4-8 Dec. 2013

Firstpage

35

Lastpage

40

Abstract

In this paper is presented the visual odometry and the localization of moving objects from aerial images embedded in an Unmanned Aerial Vehicle system with use of the Raspberry Pi and an IP camera. The techniques used are the Oriented FAST and Rotated BRIEF (ORB) descriptor to detect and extract the interest points and the RANdom SAmple Consensus (RANSAC) method to estimate the parameters from a matched points matrix for finding the camera translation. The visual odometry and morphological operations to point out moving objects have been performed.

Keywords

autonomous aerial vehicles; distance measurement; embedded systems; image sensors; robot vision; IP camera; ORB; RANSAC; Raspberry Pi; acquired images; camera translation; embedded system; morphological operations; moving object localization; oriented FAST and rotated BRIEF; random sample consensus; unmanned aerial vehicles; visual odometry; Cameras; Embedded systems; IP networks; Transforms; Unmanned aerial vehicles; Visualization; ORB; RANSAC; Raspberry Pi; UAV; embedded system; moving objects; visual odometry;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing Systems Engineering (SBESC), 2013 III Brazilian Symposium on

Conference_Location

Niteroi

Type

conf

DOI

10.1109/SBESC.2013.34

Filename

6825339