Learning to detect and match keypoints with deep architectures
Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt
Feature detection and description is a pivotal step in many computer vision pipelines. Traditionally, human engineered features have been the main workhorse in this domain. In this paper, we present a novel approach for learning to detect and describe keypoints from images leveraging deep architectures. To allow for a learning based approach, we collect a large-scale dataset of patches with matching multiscale keypoints. The proposed model learns from this vast dataset to identify and describe meaningful keypoints. We evaluate our model for the effectiveness of its learned representations for detecting multiscale keypoints and describing their respective support regions.
Originalsprog | Engelsk |
---|---|
Publikationsdato | 2016 |
DOI | |
Status | Udgivet - 2016 |
Eksternt udgivet | Ja |
Begivenhed | 27th British Machine Vision Conference, BMVC 2016 - York, Storbritannien Varighed: 19 sep. 2016 → 22 sep. 2016 |
Konference
Konference | 27th British Machine Vision Conference, BMVC 2016 |
---|---|
Land | Storbritannien |
By | York |
Periode | 19/09/2016 → 22/09/2016 |
Sponsor | ARM, Disney Research, et al., HP, Ocado Technology, OSRAM |
Bibliografisk note
Publisher Copyright:
© 2016. The copyright of this document resides with its authors.
ID: 301828084