Title:
CONVOLUTIONAL NEURAL NETWORK FRAMEWORK USING REVERSE CONNECTIONS AND OBJECTNESS PRIORS FOR OBJECT DETECTION
Document Type and Number:
WIPO Patent Application WO/2019/028725
Kind Code:
A1
Abstract:
A convolutional neural network framework is described that uses reverse connection and obviousness priors for object detection. A method includes performing a plurality of layers of convolutions and reverse connections on a received image to generate a plurality of feature maps, determining an objectness confidence for candidate bounding boxes based on outputs of an objectness prior, determining a joint loss function for each candidate bounding box by combining an objectness loss, a bounding box regression loss and a classification loss, calculating network gradients over positive boxes and negative boxes, updating network parameters within candidate bounding boxes using the joint loss function, repeating performing the convolutions through to updating network parameters until the training converges, and outputting network parameters for object detection based on the training images.
Inventors:
YAO ANBANG (CN)
KONG TAO (CN)
LU MING (CN)
GUO YIWEN (CN)
CHEN YURONG (CN)
KONG TAO (CN)
LU MING (CN)
GUO YIWEN (CN)
CHEN YURONG (CN)
Application Number:
PCT/CN2017/096755
Publication Date:
February 14, 2019
Filing Date:
August 10, 2017
Export Citation:
Assignee:
INTEL CORP (US)
YAO ANBANG (CN)
KONG TAO (CN)
LU MING (CN)
GUO YIWEN (CN)
CHEN YURONG (CN)
YAO ANBANG (CN)
KONG TAO (CN)
LU MING (CN)
GUO YIWEN (CN)
CHEN YURONG (CN)
International Classes:
G06V10/764; G06V20/00
Foreign References:
| CN106682697A | 2017-05-17 | |||
| CN106570453A | 2017-04-19 | |||
| US20080089579A1 | 2008-04-17 |
Attorney, Agent or Firm:
NTD PATENT AND TRADEMARK AGENCY LIMITED (CN)
Download PDF: