Matchability prediction for full-search template matching algorithms

Cita com:
hdl:2117/85330
Document typeConference report
Defense date2015
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessOpen Access
This work is protected by the corresponding intellectual and industrial property rights.
Except where otherwise noted, its contents are licensed under a Creative Commons license
:
Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
While recent approaches have shown that it is possible to do template matching by exhaustively scanning the parameter space, the resulting algorithms are still quite demanding. In this paper we alleviate the computational load of these algorithms by proposing an efficient approach for predicting the match ability of a template, before it is actually performed. This avoids large amounts of unnecessary computations. We learn the match ability of templates by using dense convolutional neural network descriptors that do not require ad-hoc criteria to characterize a template. By using deep learning descriptions of patches we are able to predict match ability over the whole image quite reliably. We will also show how no specific training data is required to solve problems like panorama stitching in which you usually require data from the scene in question. Due to the highly parallelizable nature of this tasks we offer an efficient technique with a negligible computational cost at test time.
CitationPeñate, A., Porzi, L., Moreno-Noguer, F. Matchability prediction for full-search template matching algorithms. A: International Conference on 3D Vision. "3D Vision (3DV), 2015 International Conference on". Lyon: Institute of Electrical and Electronics Engineers (IEEE), 2015, p. 353-361.
Publisher versionhttp://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7335503
Collections
- IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos [609]
- VIS - Visió Artificial i Sistemes Intel·ligents - Ponències/Comunicacions de congressos [300]
- ROBiri - Grup de Percepció i Manipulació Robotitzada de l'IRI - Ponències/Comunicacions de congressos [283]
Files | Description | Size | Format | View |
---|---|---|---|---|
1696-Matchabili ... te-Matching-Algorithms.pdf | 14,43Mb | View/Open |