Invention Grant
- Patent Title: System and method for labelling aerial images
-
Application No.: US13924320Application Date: 2013-06-21
-
Publication No.: US09704068B2Publication Date: 2017-07-11
- Inventor: Volodymyr Mnih , Geoffrey E. Hinton
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06K9/00 ; G06T7/11 ; G06T7/143

Abstract:
A system and method for labelling aerial images. A neural network generates predicted map data. The parameters of the neural network are trained by optimizing an objective function which compensates for noise in the map images. The function compensates both omission noise and registration noise.
Public/Granted literature
- US20130343641A1 SYSTEM AND METHOD FOR LABELLING AERIAL IMAGES Public/Granted day:2013-12-26
Information query