Design and evaluation of a low-cost street-level image capturing vehicle for south-east Asia

Abstract

Purpose – The purpose of this paper is to present a low-cost, highly mobile system for performing street-level imaging. Street-level imaging and geo-location-based services are rapidly growing in both popularity and coverage. Google Street View and Bing StreetSide are two of the free, online services which allow users to search location-based information on interactive maps. In addition, these services also provide software developers and researchers a rich source of street-level images for different purposes – from identifying traffic routes to augmented reality applications. Currently, coverage for Street View and StreetSide is limited to more affluent Western countries with sparse coverage throughout south-east Asia and Africa. In this paper, we present a low-cost system to perform street-level imaging targeted towards the congested, motorcycle-dominant south-east Asian countries. The proposed system uses a catadioptric imaging system to capture 360-degree panoramic images which are geo-located using an on-board GPS. The system is mounted on the back of a motorcycle to provide maximum mobility and access to narrow roads. An innovative backwards remapping technique for flattening the images is discussed along with some results from the first 150 km which have been captured from Southern Vietnam. Design/methodology/approach – The design was a low-cost prototype design using low-cost off-the-shelf hardware with custom software and assembly to facilitate functionality. Findings – The system was shown to work well as a low-cost omnidirectional mapping solution targeted toward sea-of-motorbike road conditions. Research limitations/implications – Some of the pictures returned by the system were unclear. These could be improved by having artificial lighting (currently only ambient light is used), a gyroscope-stabilised imaging platform and a higher resolution camera. Originality/value – This paper discusses a design which facilitates low-cost, street-level imaging for a sea-of-motorcycle environment. The system uses a catadioptric imaging approach to give a wide field of view without excessive image storage requirements using dozens of cameras.