Share Email Print

Proceedings Paper

An improved self-supervised framework for feature point detection
Author(s): Yunhui Wu; Jun li
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The robust image feature point is a critical component of image matching. In order to detect feature points that are robust to illumination changes and viewpoint changes, an improved self-supervised learning framework for feature point detector is proposed. Firstly, feature point detector is trained in simple synthetic datasets. Then, the labeled dataset is generated by applying the Homographic Adaptation to automatically label the unlabeled area image. Finally, the full convolution network is trained with the labeled dataset. In this paper, the convolutional neural network in the selfsupervised learning framework is improved, mainly by increasing the number of layers of the neural network, from the original 8 layers to 11 layers. Experiments on the HPatches dataset show that the improved self-supervised feature point detector has achieved good results

Paper Details

Date Published: 14 August 2019
PDF: 6 pages
Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 1117927 (14 August 2019); doi: 10.1117/12.2540147
Show Author Affiliations
Yunhui Wu, Guilin Univ. of Electronic Technology (China)
Jun li, Guilin Univ. of Electronic Technology (China)

Published in SPIE Proceedings Vol. 11179:
Eleventh International Conference on Digital Image Processing (ICDIP 2019)
Jenq-Neng Hwang; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?