Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
STOCHASTIC TRAJECTORY PREDICTION USING SOCIAL GRAPH NETWORKS
Document Type and Number:
WIPO Patent Application WO/2021/051224
Kind Code:
A1
Abstract:
Systems, methods, apparatuses, and computer program products to provide stochastic trajectory prediction using social graph networks. An operation may comprise determining a first feature vector describing destination features of a first person depicted in an image, generating a directed graph for the image based on all people depicted in the image, determining, for the first person, a second feature vector based on the directed graph and the destination features, sampling a value of a latent variable from a learned prior distribution, the latent variable to correspond to a first time interval, and generating, based on the sampled value and the feature vectors by a hierarchical long short-term memory (LSTM) executing on a processor, an output vector comprising a direction of movement and a speed of the direction of movement of the first person at a second time interval, subsequent to the first time interval.

Inventors:
ZHANG LIDAN (CN)
SHE QI (CN)
GUO PING (CN)
Application Number:
PCT/CN2019/105898
Publication Date:
March 25, 2021
Filing Date:
September 16, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
INTEL CORP (US)
ZHANG LIDAN (CN)
SHE QI (CN)
GUO PING (CN)
International Classes:
G06F16/29
Foreign References:
CN110147892A2019-08-20
CN110059144A2019-07-26
US20180322368A12018-11-08
US20110002390A12011-01-06
Other References:
PENG QU; DING ZHI-MING; GUO LI-MIN: "Prediction of Trajectory Based on Markov Chains", COMPUTER SCIENCE, vol. 37, no. 8, 31 August 2010 (2010-08-31), pages 189 - 193, XP009526957, ISSN: 1002-137X
Attorney, Agent or Firm:
CHINA PATENT AGENT (H.K.) LTD. (CN)
Download PDF: