An efficient method to detect mutual overlap of a large set of unordered images for structure-from-motion

Download statistics - Document (COUNTER):

X. Wang; Z.Q. Zhan; Christian Heipke: An efficient method to detect mutual overlap of a large set of unordered images for structure-from-motion. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2017 (2017), S. 191-198. DOI: https://doi.org/10.5194/isprs-annals-iv-1-w1-191-2017

Repository version

To cite the version in the repository, please use this identifier: https://doi.org/10.15488/5164

Selected time period:

year: 
month: 

Sum total of downloads: 95




Thumbnail
Abstract: 
Recently, low-cost 3D reconstruction based on images has become a popular focus of photogrammetry and computer vision research. Methods which can handle an arbitrary geometric setup of a large number of unordered and convergent images are of particular interest. However, determining the mutual overlap poses a considerable challenge. We propose a new method which was inspired by and improves upon methods employing random k-d forests for this task. Specifically, we first derive features from the images and then a random k-d forest is used to find the nearest neighbours in feature space. Subsequently, the degree of similarity between individual images, the image overlaps and thus images belonging to a common block are calculated as input to a structure-from-motion (sfm) pipeline. In our experiments we show the general applicability of the new method and compare it with other methods by analyzing the time efficiency. Orientations and 3D reconstructions were successfully conducted with our overlap graphs by sfm. The results show a speed-up of a factor of 80 compared to conventional pairwise matching, and of 8 and 2 compared to the VocMatch approach using 1 and 4 CPU, respectively.
License of this version: CC BY 3.0 Unported
Document Type: Article
Publishing status: publishedVersion
Issue Date: 2017
Appears in Collections:Fakultät für Bauingenieurwesen und Geodäsie

distribution of downloads over the selected time period:

downloads by country:

pos. country downloads
total perc.
1 image of flag of Germany Germany 29 30.53%
2 image of flag of United States United States 22 23.16%
3 image of flag of China China 8 8.42%
4 image of flag of United Kingdom United Kingdom 4 4.21%
5 image of flag of Canada Canada 4 4.21%
6 image of flag of France France 3 3.16%
7 image of flag of Austria Austria 3 3.16%
8 image of flag of India India 2 2.11%
9 image of flag of Hungary Hungary 2 2.11%
10 image of flag of Algeria Algeria 2 2.11%
    other countries 16 16.84%

Further download figures and rankings:


Hinweis

Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.

Search the repository


Browse