|
ИСТИНА |
Войти в систему Регистрация |
Интеллектуальная Система Тематического Исследования НАукометрических данных |
||
Neural network-based feature point descriptors for registration of optical and SAR imagesстатья
- Авторы: Abulkhanov D., Konovalenko I., Nikolaev D., Savchik A., Shvets E., Sidorchuk D.
- Сборник: Tenth International Conference on Machine Vision (ICMV 2017)
- Том: 10696
- Год издания: 2018
- Место издания: SPIE Bellingham, Washington 98227-0010 USA
- Первая страница: 106960L1
- Последняя страница: 106960L8
- DOI: 10.1117/12.2310085
- Аннотация: Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method’s effectiveness.
- Добавил в систему: Коноваленко Иван Андреевич