Human body behavior identification method based on point cloud data

A technology of point cloud data and recognition methods, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as human behavior recognition methods without deep learning, achieve multi-processing methods and usage methods, reduce costs, Applicable effect

Inactive Publication Date: 2019-07-09
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently no deep learning human behavior recognition method based on point clouds.

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
  • Human body behavior identification method based on point cloud data
  • Human body behavior identification method based on point cloud data
  • Human body behavior identification method based on point cloud data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be further described below in conjunction with specific examples.

[0061] Such as figure 1 As shown, the human behavior recognition method based on point cloud data provided in this embodiment combines the point cloud data converted from the depth map and the deep neural network, including the following steps:

[0062] 1) Obtain basic data, including depth map data and camera parameters; depth map data such as Figure 2a As shown, in this embodiment, the camera internal parameter f x = f y =f / z c , f is the focal length of the camera. Since the data set used does not clearly indicate the camera focal length z c , so the focal length corresponding to each frame of depth map data passes calculated.

[0063] 2) Preprocessing the data, including smoothing the depth map, converting the depth map to point cloud, and normalizing the point cloud data.

[0064] 2.1) Use bilateral filtering to smooth the depth map data:

[0065]

[0066] ...

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 human body behavior identification method based on point cloud data, which comprises the following steps: 1) acquiring basic data including depth map data and camera parameters; 2) preprocessing the data, including smoothing the depth map, converting the depth map to a point cloud, and normalizing the point cloud data; and 3) inputting the processed data into the networkfor behavior recognition, and providing deep learning human body behavior recognition based on the point cloud data, so that the point cloud data obtained from the depth map can be directly utilized for human body behavior recognition, and a good result is obtained.

Description

technical field [0001] The present invention relates to the technical fields of image processing algorithm research, three-dimensional data processing algorithm research, human body behavior recognition algorithm research and deep learning algorithm research, and in particular refers to a human body behavior recognition method based on point cloud data. Background technique [0002] Human behavior recognition mainly analyzes human behavior based on collected videos, which is widely used in video surveillance, medical rehabilitation, fitness assessment, human-computer interaction and other fields, and is a hot issue in computer vision research. Point cloud data is a set of discrete points distributed in three-dimensional space collected by a structured light scanner or a three-dimensional laser scanner. It has unique advantages in expressing complex scenes and the shape of objects, coupled with the rapidity and convenience of its acquisition. , Has been widely used in compute...

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): G06K9/00G06N3/04
CPCG06N3/049G06V40/20G06N3/048
Inventor 吴秋霞康力许鸿斌杨晓伟
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap