LDAM: line descriptors augmented by attention mechanism

Xulong Cao; Yao Huang; Yongdong Huang; Yuanzhan Li; Shen Cai

doi:10.1117/12.2644245

12 October 2022 LDAM: line descriptors augmented by attention mechanism

Xulong Cao, Yao Huang, Yongdong Huang, Yuanzhan Li, Shen Cai

Proceedings Volume 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022); 1234203 (2022) https://doi.org/10.1117/12.2644245
Event: Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 2022, Wuhan, China

Abstract

Compared with point features, line features can provide more geometric information in vision tasks. Although traditional line descriptor methods have been proposed for a long time, learning-based line descriptor methods still need to be strengthened. Inspired by the message passing mechanism of graph neural networks, we propose a new neural network architecture named LDAM that alternately uses two attention mechanisms to augment line descriptors and extract more line correspondences. Compared with previous methods, our method learns the geometric properties and prior knowledge of images through the mutual aggregation of features between a pair of images. The experiments on real data verify the good performance of LDAM in terms of matching accuracy. Furthermore, LDAM is also robust to viewpoint change or occlusion.

Citation Download Citation

Xulong Cao, Yao Huang, Yongdong Huang, Yuanzhan Li, and Shen Cai "LDAM: line descriptors augmented by attention mechanism", Proc. SPIE 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 1234203 (12 October 2022); https://doi.org/10.1117/12.2644245

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available