Robust refinement methods for camera calibration and 3D reconstruction from multiple images

Authors:
Maw-Kae Hor;Cheng-Yuan Tang;Yi-Leh Wu;Kai-Hsuan Chan;Jeng-Jiun Tsai
Affiliations:
Dept. of Computer Science, National Chengchi University, Taipei, Taiwan, ROC;Dept. of Information Management, Huafan University, Taipei, Taiwan, ROC;Dept. of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, ROC;Dept. of Computer Science, National Chengchi University, Taipei, Taiwan, ROC;Dept. of Computer Science, National Chengchi University, Taipei, Taiwan, ROC
Venue:
Pattern Recognition Letters
Year:
2011

Citing 9
Cited 1

Geometry and Texture from Thousands of Images

International Journal of Computer Vision
A Unified Approach to Detecting Spatial Outliers

Geoinformatica
A linear method for reconstruction from lines and points

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Advances in Computational Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multiple View System for Modeling Building Entities

CMV '06 Proceedings of the Fourth International Conference on Coordinated & Multiple Views in Exploratory Visualization
A trimmed mean approach to finding spatial outliers

Intelligent Data Analysis
Inter-image outliers and their application to image classification

Pattern Recognition
3D geometry from uncalibrated images

ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part II

System identification: 3d measurement using structured light system

ACIVS'12 Proceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper proposes robust refinement methods to improve the popular patch multi-view 3D reconstruction algorithm by Furukawa and Ponce (2008). Specifically, a new method is proposed to improve the robustness by removing outliers based on a filtering approach. In addition, this work also proposes a method to divide the 3D points in to several buckets for applying the sparse bundle adjustment algorithm (SBA) individually, removing the outliers and finally merging them. The residuals are used to filter potential outliers to reduce the re-projection error used as the performance evaluation of refinement. In our experiments, the original mean re-projection error is about 47.6. After applying the proposed methods, the mean error is reduced to 2.13.