Learning to Assign Orientations to Feature Points

We show how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point. Our method improves feature point matching upon the state-of-the art and can be used in conjunction with any existing rotation sensitive descriptors. To avoid the tedious and almost impossible task of finding a target orientation to learn, we propose to use Siamese networks which implicitly find the optimal orientations during training. We also propose a new type of activation function for Neural Networks that generalizes the popular ReLU, maxout, and PReLU activation functions. This novel activation performs better for our task. We validate the effectiveness of our method extensively with four existing datasets, including two non-planar datasets, as well as our own dataset. We show that we outperform the state-of-the-art without the need of retraining for each dataset.


Présenté à:
Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, June 26-July 1, 2016
Année
2016
Mots-clefs:
Laboratoires:




 Notice créée le 2016-04-11, modifiée le 2019-12-05

Preprint:
Télécharger le documentPDF
Supplementary:
Télécharger le documentPDF
Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)