专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20190303725A1 NEURAL NETWORK TRAINING SYSTEM 审中-公开
公开(公告)号：US20190303725A1
公开(公告)日：2019-10-03
申请号：US15942226
申请日：2018-03-30
申请人： FRINGEFY LTD.
发明人： Roni Gurvich , Idan Ilan , Ofer Avni , Stav Yagev
IPC分类号： G06K9/62 , G06N3/08
摘要： In order for the feature extractors to operate with sufficient accuracy, a high degree of training is required. In this situation, a neural network implementing the feature extractor may be trained by providing it with images having known correspondence. A 3D model of a city may be utilized in order to train a neural network for location detection. 3D models are sophisticated and allow manipulation of viewer perspective and ambient features such as day/night sky variations, weather variations, and occlusion placement. Various manipulations may be executed in order to generate vast numbers of image pairs having known correspondence despite having variations. These image pairs with known correspondence may be utilized to train the neural network to be able to generate feature maps from query images and identify correspondence between query image feature maps and reference feature maps. This training can be accomplished without requiring the capture of real images with known correspondence. Capture of real images with known correspondence is cumbersome, time and resource-intensive, and difficult to manage.

2. 发明授权

US10592780B2 Neural network training system 有权
公开(公告)号：US10592780B2
公开(公告)日：2020-03-17
申请号：US15942226
申请日：2018-03-30
申请人： FRINGEFY LTD.
发明人： Roni Gurvich , Idan Ilan , Ofer Avni , Stav Yagev
IPC分类号： G06K9/00 , G06K9/62 , G06N3/08
摘要： In order for the feature extractors to operate with sufficient accuracy, a high degree of training is required. In this situation, a neural network implementing the feature extractor may be trained by providing it with images having known correspondence. A 3D model of a city may be utilized in order to train a neural network for location detection. 3D models are sophisticated and allow manipulation of viewer perspective and ambient features such as day/night sky variations, weather variations, and occlusion placement. Various manipulations may be executed in order to generate vast numbers of image pairs having known correspondence despite having variations. These image pairs with known correspondence may be utilized to train the neural network to be able to generate feature maps from query images and identify correspondence between query image feature maps and reference feature maps. This training can be accomplished without requiring the capture of real images with known correspondence. Capture of real images with known correspondence is cumbersome, time and resource-intensive, and difficult to manage.

你已经成功收藏专利！

检索式保存成功!

IPRDB