Abstract

In this paper we present a method for 3D urban reconstruction from a single catadioptric omnidirectional image. Firstly, we classify the catadioptric omnidirectional image to horizontal ground, vertical building surface and vertical background surface through the registration between catadioptric omnidirectional image and remote sensing image. According to the classification results, we recover the geometry based on the catadioptric projection model. The experiment shows that our method is feasible and realizes a precise 3D reconstruction for the city scenes.

Highlights

  • Image-based rendering (IBR) is a technique to generate novel views from a set of reference images

  • According to the classification results, we recover the geometry of the catadioptric omnidirectional image (COI) by using the algorithm in Section 2, and the result is represented as a depth map shown in Fig. 7(a)

  • It is noted that there are some artifacts in the rendering: 1) since it is difficult to recover the geometry of sky, we give the sky a constant color when rendering; 2) the background scenes are rendered as a vertical surface in a circle round the viewpoint with the biggest distance (D =655.36m)

Read more

Summary

INTRODUCTION

Image-based rendering (IBR) is a technique to generate novel views from a set of reference images. It produces photo-realistic output without a complex lighting model [1]. IBR generally requires a large number of reference images It will have high laboring cost and consume a significant amount of time in the image capturing process. Reference [7] uses a semi-automatic reconstruction process, in which the user marks the room corners in the panoramic images. The corners can be translated into the viewing-angle measurements, from which the exact sizes of the walls can be computed This method can realize a coarse reconstruction of the indoor environment. Compared with the previous approaches, the proposed method has the advantages of simple and compact hardware system, low cost and automatic processing

GEOMETRY RECOVERY FROM A SINGLE CATADIOPTRIC OMNIDIRECTIONAL IMAGE
Geometry Recovery of Points on a Horizontal Surface
Geometry Recovery of Points on a Vertical Surface
REGION CLASSIFICATION OF CATADIOPTRIC OMNIDIRECTIONAL IMAGES
Registration between the Ground Panorama and Remote Sensing Images
Extraction of the Horizon and the Bottom borderline of building
Skyline Extraction
EXPERIMENTS
CONCLUSION

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.