Details
| Original language | English |
|---|---|
| Pages (from-to) | 31-38 |
| Number of pages | 8 |
| Journal | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Volume | 40 |
| Issue number | 3W2 |
| Publication status | Published - 10 Mar 2015 |
| Event | Joint ISPRS Conference on Photogrammetric Image Analysis, PIA 2015 and High Resolution Earth Imaging for Geospatial Information, HRIGI 2015 - Munich, Germany Duration: 25 Mar 2015 → 27 Mar 2015 |
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.
Keywords
- Autoencoder, Descriptor evaluation, Image matching, Learning descriptor, Pooling, Representation learning
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Social Sciences(all)
- Geography, Planning and Development
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Vol. 40, No. 3W2, 10.03.2015, p. 31-38.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Feature descriptor by convolution and pooling autoencoders
AU - Chen, L.
AU - Rottensteiner, F.
AU - Heipke, C.
PY - 2015/3/10
Y1 - 2015/3/10
N2 - 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.
AB - 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.
KW - Autoencoder
KW - Descriptor evaluation
KW - Image matching
KW - Learning descriptor
KW - Pooling
KW - Representation learning
UR - http://www.scopus.com/inward/record.url?scp=84925366146&partnerID=8YFLogxK
U2 - 10.5194/isprsarchives-XL-3-W2-31-2015
DO - 10.5194/isprsarchives-XL-3-W2-31-2015
M3 - Conference article
AN - SCOPUS:84925366146
VL - 40
SP - 31
EP - 38
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SN - 1682-1750
IS - 3W2
T2 - Joint ISPRS Conference on Photogrammetric Image Analysis, PIA 2015 and High Resolution Earth Imaging for Geospatial Information, HRIGI 2015
Y2 - 25 March 2015 through 27 March 2015
ER -