Journal Articles) Geo_Registration

Geo-registration of Wide-baseline Panoramic Image Sequences using a Digital Map Reference

Hyungki Kim, Soonhung Han, Multimedia Tools and Applications

Abstract

This paper describes a method of geo-registering a sequence of panoramic images to digital map by matching pixel information with building footprint information contained in a digital map. Recently, images captured at the ground level through a Mobile Mapping System (MMS), such as panoramic images seen in Google Street View, have been considered as a valuable resource for three-dimensional (3D) building modeling. However, the wide intervals between these panoramic images, as well as locational and directional error from the related sensors, make it difficult to analyze the image data. In this paper, a method of formulation is shown that connects pixels on panoramic images with footprint vertices and lines of buildings in digital map. To allow both pixel and footprint information consistent in 3D space, each panoramic images are tilt-corrected in pre-processing to upright the images using estimated pitch and roll of a vehicle and remove the effect of it in pixels of panoramic images. Through the proposed formulation, a single panoramic image can be easily geo-registered with simple user-provided constraints, and adjacent sequential images can then be automatically geo-registered using point feature matching. Experimental results showed a significant reduction in the locational and directional error of sequential panoramic images, and the proposed vanishing point (VP) based validation process was found to successfully detect failure cases.