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

Multi-view video identification method, device and equipment and storage medium

A video recognition and multi-view technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as limited recognition accuracy

Active Publication Date: 2019-04-02
BEIJING SENSETIME TECH DEV CO LTD
View PDF10 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of these methods ignore the use of unique features of each view, so the recognition accuracy is limited

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
  • Multi-view video identification method, device and equipment and storage medium
  • Multi-view video identification method, device and equipment and storage medium
  • Multi-view video identification method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] In order to make the purpose, technical solution and advantages of this embodiment clearer, the specific technical solution of the invention will be further described in detail below in conjunction with the accompanying drawings in this embodiment. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0072] This embodiment first provides a network architecture, Figure 1A It is a schematic diagram of the composition structure of the network architecture of the embodiment of the present application, such as Figure 1A As shown, the network architecture includes two or more computer devices 11 to 1N and a server 31 , wherein the computer devices 11 to 1N and the server 31 interact through the network 21 . The computer equipment may be various types of computer equipment with information processing capabilities during implementation, for example, the computer equipment may include mobile phones, tabl...

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 embodiment of the invention provides a multi-view video identification method, device and equipment and a storage medium, and the method comprises the steps of obtaining a to-be-identified multi-view video, wherein the multi-view video at least comprises videos corresponding to two views; inputting the multi-view video into a neural network model obtained through training, wherein the neural network model comprises the steps of determining specific characteristics of the multi-view video at different view angles, and classifying the specific characteristics of the multi-view video at different view angles to obtain the identification result of the multi-view video; and outputting the identification result of the multi-view video.

Description

technical field [0001] The embodiments of the present application relate to the technical field of computer image processing, and relate to, but are not limited to, a multi-view video recognition method, device, device, and storage medium. Background technique [0002] Modeling human behavior in video is an important problem in the field of computer vision and intelligent video surveillance. Behavior recognition models can have important applications in many fields, such as abnormal behavior detection, personnel action prediction, etc. At the same time, behavior recognition models are also the basis of other more complex intelligent systems. [0003] The neural network-based deep learning technology has achieved good results in behavior recognition, and the behavior recognition accuracy for single-view videos exceeds 90%. However, the modeling of multi-view video is more complicated, because in multi-view video, different behaviors may show similar characteristics due to oc...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/41G06V20/46G06F18/254
Inventor 王东昂欧阳万里李文徐东
Owner BEIJING SENSETIME TECH DEV CO LTD