8 February 2017 Trainable Siamese keypoint descriptors for real-time applications
Author Affiliations +
Proceedings Volume 10253, 2016 International Conference on Robotics and Machine Vision; 1025306 (2017); doi: 10.1117/12.2266351
Event: 2016 International Conference on Robotics and Machine Vision, 2016, Moscow, Russia
Abstract
Computing image patch descriptors for correspondence problems relies heavily on hand-crafted feature transformations, e.g. SIFT, SURF. In this paper, we explore a Siamese pairing of fully connected neural networks for the purpose of learning discriminative local feature descriptors. Resulting ANN computes 128-D descriptors, and demonstrates consistent speedup as compared to such state-of-the-art methods as SIFT and FREAK on PCs as well as in embedded systems. We use L2 distance to reflect descriptor similarity during both training and testing. In this way, feature descriptors we propose can be easily compared to their hand-crafted counterparts. We also created a dataset augmented with synthetic data for learning local features, and it is available online. The augmentations provide training data for our descriptors to generalise well against scaling and rotation, shift, Gaussian noise, and illumination changes.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fedor A. Fedorenko, Alena A. Ivanova, Elena E. Limonova, Ivan A. Konovalenko, "Trainable Siamese keypoint descriptors for real-time applications", Proc. SPIE 10253, 2016 International Conference on Robotics and Machine Vision, 1025306 (8 February 2017); doi: 10.1117/12.2266351; http://dx.doi.org/10.1117/12.2266351
PROCEEDINGS
5 PAGES


SHARE
KEYWORDS
Neural networks

Cameras

Network architectures

Neurons

Embedded systems

Image resolution

Matrices

Back to Top