Feature descriptor by convolution and pooling autoencoders

Download statistics - Document (COUNTER):

Chen, L.; Rottensteiner, F.; Heipke, C.: Feature descriptor by convolution and pooling autoencoders. In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 40 (2015), Nr. 3W2, S. 31-38. DOI: https://doi.org/10.5194/isprsarchives-XL-3-W2-31-2015

Repository version

To cite the version in the repository, please use this identifier: https://doi.org/10.15488/843

Selected time period:

year: 
month: 

Sum total of downloads: 115




Thumbnail
Abstract: 
In this paper we present several descriptors for feature-based matching based on autoencoders, and we evaluate the performance of these descriptors. In a training phase, we learn autoencoders from image patches extracted in local windows surrounding key points determined by the Difference of Gaussian extractor. In the matching phase, we construct key point descriptors based on the learned autoencoders, and we use these descriptors as the basis for local keypoint descriptor matching. Three types of descriptors based on autoencoders are presented. To evaluate the performance of these descriptors, recall and 1-precision curves are generated for different kinds of transformations, e.g. zoom and rotation, viewpoint change, using a standard benchmark data set. We compare the performance of these descriptors with the one achieved for SIFT. Early results presented in this paper show that, whereas SIFT in general performs better than the new descriptors, the descriptors based on autoencoders show some potential for feature based matching.
License of this version: CC BY 3.0
Document Type: article
Publishing status: publishedVersion
Issue Date: 2015
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 56 48.70%
2 image of flag of Belgium Belgium 20 17.39%
3 image of flag of United States United States 10 8.70%
4 image of flag of China China 8 6.96%
5 image of flag of Slovakia Slovakia 6 5.22%
6 image of flag of No geo information available No geo information available 3 2.61%
7 image of flag of Russian Federation Russian Federation 3 2.61%
8 image of flag of Netherlands Netherlands 3 2.61%
9 image of flag of Japan Japan 1 0.87%
10 image of flag of United Kingdom United Kingdom 1 0.87%
    other countries 4 3.48%

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