Home // SMART 2021, The Tenth International Conference on Smart Cities, Systems, Devices and Technologies // View article

Enhancing Spatial Image Datasets for Utilisation in a Simulator for Smart City Transport Navigation

Authors:
Lepekola Lenkoe
Ben Kotze

Keywords: Image-Based Rendering; Blender3D; Simulation; Datasets; Google Street Views; Smart Cities

Abstract:
The introduction of Google Street Views, has bought to the surface a method for roof-mounted mobile cameras on vehicles. This method is regarded as one of the highly known and adopted methodologies for capturing street-level images. This article contributes to the development and implementation of Image-Based Rendering techniques by presenting a technique utilising a hexagon-based camera configuration model for image capturing. Upon the image capture stage, each segment camera is stored in a specific folder relative to the camera number (i.e., camera 1 = folder 1). Subsequently, the optimal image rendering process of each image blending takes place inside Blender3D software where image datasets are rendered for utilisation in a simulator. Utilising the Structure of Motion algorithm, dense point image, and its features, match detection is obtained. This article further contributes to the results process that allows for free movement within a 3D rendered scene by permitting for back and forward movement as compared to a slide show that only permits for forwarding motion.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2021

Publication date: May 30, 2021

Published in: conference

ISSN: 2308-3727

ISBN: 978-1-61208-805-1

Location: Valencia, Spain

Dates: from May 30, 2021 to June 3, 2021