Unlock instant, AI-driven research and patent intelligence for your innovation.

Video event human-like concept learning method and device

A technology for video event and concept learning, applied in computer parts, instruments, computing, etc., to solve the problem of inability to learn video events and concepts

Active Publication Date: 2021-03-16
SHENZHEN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a method and device for learning human-like concepts of video events, aiming to solve the technical problem in the prior art that the concept of video events cannot be learned like a human

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Video event human-like concept learning method and device
  • Video event human-like concept learning method and device
  • Video event human-like concept learning method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

[0026] The technical scheme in the embodiment of the present invention introduces the Bayesian Program Learning (BPL) framework, which can learn a large class of video event concepts from only one video sample, and the concepts are expressed as simple probability programming, that is, Probabilistic generative models expressed by structured pr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a video event human-like concept learning method and device. The method includes: using a random walk algorithm to divide the behavior of moving objects in a video sample to obtain a behavior set, and based on the time stop point of the behavior for the behavior set Each behavior is divided into sub-behaviors to obtain a set of sub-behaviors, determine the spatio-temporal relationship between each sub-behavior and other sub-behaviors in the sub-behavior set, and the prior probability of the spatio-temporal relationship of each sub-behavior, and use the spatio-temporal relationship of each sub-behavior , a priori probability and a set of preset change factors are combined to form a new video event, and the concept of a video event is learned. Compared with the existing technology, the above method can learn the concept of video events, and express the concept through simple random planning, so as to realize the thinking that is close to human for concept learning, and realize the human-like concept learning of video events.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a method and device for learning human-like concepts of video events. Background technique [0002] Humans' learning of new concepts can generalize from a single example, whereas machine learning algorithms typically require a large number of samples to achieve the same accuracy. For example, current video-based behavior analysis and concept learning both require a large number of videos as samples and can only be realized after complex machine learning algorithms, while humans can learn the same number or even more concepts from a single video sample. [0003] Therefore, how to learn the concept of video events like humans is the focus of current research. Contents of the invention [0004] The main purpose of the present invention is to provide a method and device for learning human-like concepts of video events, aiming at solving the technical problem in the prior art ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/42G06F18/214G06F18/2415
Inventor 李岩山徐健杰谢维信
Owner SHENZHEN UNIV