Action recognition method based on skeleton sequence

A technology of action recognition and skeleton, applied in neural learning methods, character and pattern recognition, instruments, etc.

Inactive Publication Date: 2016-12-07
TIANJIN UNIV
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, how to adopt convolutional neural network to deal

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
  • Action recognition method based on skeleton sequence
  • Action recognition method based on skeleton sequence
  • Action recognition method based on skeleton sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] 1) Mapping of bone sequence to picture

[0015] Capture human actions through the Kinect camera, perform skeleton tracking in the captured data stream, and obtain a 3D skeleton sequence containing multiple skeleton nodes. Suppose a skeleton sequence has n frames in total, and m skeleton nodes are extracted from the depth map in each frame, use to represent the three-dimensional position information of the jth bone node in the ith frame. All bones in the entire video sequence can be projected onto three planes (front, side, and top) of three Cartesian orthogonal systems according to three-dimensional information. After such projection, each skeleton sequence can get three black and white pictures describing the distribution of the skeleton of the action. It has rich spatial information, but does not have the description of temporal information.

[0016] In order to make the skeleton display more complete action information, the present invention adds time information...

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 relates to an action recognition method based on a skeleton sequence. The method comprises the steps that all skeletons of the skeleton sequence are projected to the front surface, the side surface and the top surface of a Descartes orthogonal system according to three-dimensional information, and a skeleton distribution diagram is generated; time information is added into the skeleton distribution diagram through color change; convolutional neural network model training is conducted on the skeleton distribution diagram, which is generated based on a training dataset and formed on the three projection surfaces and to which the time information is added, through the convolutional neural network; for each test sample, three Scores vectors are calculated according to three trained convolutional neural network models and targeted at the skeleton distribution diagram which is formed on the three projection surfaces and to which the time information is added; after the Scores vectors of the three projection surfaces are added, the category to which the maximum value belongs is taken as a subordinate category of the video sequence. Through the method, human actions can be recognized accurately and reliably.

Description

technical field [0001] The method relates to the field of multimedia information processing, including the fields of computer intelligence, pattern recognition, and machine learning. Background technique [0002] Human action detection and recognition methods have a very wide range of applications in today's society, such as: intelligent monitoring, human-computer interaction somatosensory games, video retrieval and so on. Human action detection and recognition based on RGB-D (color and depth) video sequences is especially popular in the field of computer vision today. Compared with traditional RGB video sequences, RGB-D video sequences are less sensitive to illumination and have richer three-dimensional information. Based on depth information, many traditional methods have proposed extensions in the third dimension, and many new features have been extracted. Skeleton sequence, as a feature extracted from depth information, is currently widely recognized. The Kinect SDK h...

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
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/2111G06F18/214
Inventor 侯永宏李照洋董嘉蓉叶熠琳邢家明
Owner TIANJIN UNIV
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