Invention Grant
- Patent Title: Neural network for skeletons from input images
-
Application No.: US16396513Application Date: 2019-04-26
-
Publication No.: US11429842B2Publication Date: 2022-08-30
- Inventor: Lijuan Wang , Kevin Lin , Zicheng Liu , Kun Luo
- Applicant: Microsoft Technology Licensing, LLC
- Applicant Address: US WA Redmond
- Assignee: Microsoft Technology Licensing, LLC
- Current Assignee: Microsoft Technology Licensing, LLC
- Current Assignee Address: US WA Redmond
- Agency: Alleman Hall Creasman & Tuttle LLP
- Main IPC: G06T7/10
- IPC: G06T7/10 ; G06N3/04 ; G06N3/08 ; G06F17/15 ; G06V40/10

Abstract:
A computing system is provided. The computing system includes a processor configured to execute a convolutional neural network that has been trained, the convolutional neural network including a backbone network that is a concatenated pyramid network, a plurality of first head neural networks, and a plurality of second head neural networks. At the backbone network, the processor is configured to receive an input image as input and output feature maps extracted from the input image. The processor is configured to: process the feature maps using each of the first head neural networks to output corresponding keypoint heatmaps; process the feature maps using each of the second head neural networks to output corresponding part affinity field heatmaps; link the keypoints into one or more instances of virtual skeletons using the part affinity fields; and output the instances of the virtual skeletons.
Public/Granted literature
- US20200272888A1 NEURAL NETWORK FOR SKELETONS FROM INPUT IMAGES Public/Granted day:2020-08-27
Information query