Invention Grant
- Patent Title: Cascaded convolutional neural network
-
Application No.: US15749693Application Date: 2017-04-20
-
Publication No.: US10296815B2Publication Date: 2019-05-21
- Inventor: Lior Wolf , Assaf Mushinsky
- Applicant: Ramot at Tel Aviv University Ltd.
- Applicant Address: IL Tel Aviv
- Assignee: Ramot at Tel Aviv University Ltd.
- Current Assignee: Ramot at Tel Aviv University Ltd.
- Current Assignee Address: IL Tel Aviv
- Agency: Brown Rudnick LLP
- Priority: GB1614009.7 20160816
- International Application: PCT/IL2017/050461 WO 20170420
- International Announcement: WO2017/183034 WO 20171026
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06K9/00 ; G06K9/46 ; G06K9/66 ; G06N3/04 ; G06N5/04 ; G06T7/70

Abstract:
A convolutional neural network system for detecting at least one object in at least one image. The system includes a plurality of object detectors, corresponding to a predetermined image window size in the at least one image. Each object detector is associated with a respective down-sampling ratio with respect to the at least one image. Each object detector includes a respective convolutional neural network and an object classifier coupled with the convolutional neural network. The respective convolutional neural network includes a plurality of convolution layers. The object classifier classifies objects in the image according to the results from the convolutional neural network. Object detectors associated with the same respective down-sampling ratio define at least one group of object detectors. Object detectors in a group of object detectors being associated with common convolution layers.
Public/Granted literature
- US20190042892A1 CASCADED CONVOLUTIONAL NEURAL NETWORK Public/Granted day:2019-02-07
Information query