Feature descriptor by convolution and pooling autoencoders

Show simple item record

dc.identifier.uri http://dx.doi.org/10.15488/843
dc.identifier.uri http://www.repo.uni-hannover.de/handle/123456789/867
dc.contributor.author Chen, Lin
dc.contributor.author Rottensteiner, Franz
dc.contributor.author Heipke, Christian
dc.date.accessioned 2016-12-16T09:16:36Z
dc.date.available 2016-12-16T09:16:36Z
dc.date.issued 2015
dc.identifier.citation 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
dc.description.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. eng
dc.description.sponsorship China Scholarship Council
dc.language.iso eng
dc.publisher Hannover : International Society for Photogrammetry and Remote Sensing
dc.relation.ispartofseries International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives 40 (2015), Nr. 3W2
dc.rights CC BY 3.0 Unported
dc.rights.uri http://creativecommons.org/licenses/by/3.0/
dc.subject Autoencoder eng
dc.subject Descriptor evaluation eng
dc.subject Image matching eng
dc.subject Learning descriptor eng
dc.subject Benchmarking eng
dc.subject Auto encoders eng
dc.subject Benchmark data eng
dc.subject Descriptor matching eng
dc.subject Descriptors eng
dc.subject Feature based matching eng
dc.subject Feature descriptors eng
dc.subject Pooling eng
dc.subject Representation learning eng
dc.subject Learning systems eng
dc.subject.classification Konferenzschrift ger
dc.subject.ddc 500 | Naturwissenschaften ger
dc.title Feature descriptor by convolution and pooling autoencoders
dc.type Article
dc.type Text
dc.relation.issn 16821750
dc.relation.doi https://doi.org/10.5194/isprsarchives-XL-3-W2-31-2015
dc.bibliographicCitation.issue 3W2
dc.bibliographicCitation.volume 40
dc.bibliographicCitation.firstPage 31
dc.bibliographicCitation.lastPage 38
dc.description.version publishedVersion
tib.accessRights frei zug�nglich

Files in this item

This item appears in the following Collection(s):

Show simple item record


Search the repository


My Account

Usage Statistics