Method, device, equipment and storage medium for semantic understanding of dynamic human posture

A technology for human body posture and semantic understanding, applied in the fields of pattern recognition and computer vision, can solve problems such as blurred images, limited semantics, mutual occlusion of characters, etc., achieve accurate transmission and reduce the difficulty of human body posture recognition

Active Publication Date: 2018-06-22
北京如布科技有限公司
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in a complex environment, there will be situations where people occlude each other, complex postures, blurred images, and human-like objects, etc., which are prone to false detections, resulting in the machine not being able

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
  • Method, device, equipment and storage medium for semantic understanding of dynamic human posture
  • Method, device, equipment and storage medium for semantic understanding of dynamic human posture
  • Method, device, equipment and storage medium for semantic understanding of dynamic human posture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] figure 1 This is a flowchart of a method for semantic understanding of dynamic human gestures provided in Embodiment 1 of the present invention. The method can be executed by a device for semantic understanding of dynamic human gestures, and the device can be applied to any device that needs to recognize human gestures, such as intelligent Vehicle control units, entertainment devices with somatosensory experience, computers, game consoles, or tablet devices, etc. The semantic understanding method of dynamic human pose includes the following steps:

[0066] Step 101, identify the target person from the acquired video stream image frame;

[0067] The video stream may be acquired in real time by a camera, a camera, or other camera device, or may be acquired and saved in advance by a camera device. In this embodiment, the target person can be identified from the current image frame of the video stream acquired in real time. The target person can be individually identified...

Embodiment 2

[0084] image 3 It is a schematic structural diagram of the device for semantic understanding of dynamic human gestures provided in the second embodiment of the present invention. The device includes a person recognition module 11, a to-be-recognized image frame sequence determination module 12, and a semantic recognition module 13, wherein the person recognition module 11 is used for Identify the target person from the acquired video stream image frames; the to-be-identified image frame sequence determination module 12 is configured to determine, according to the instruction image frames in the video stream, the non-instruction image frame sequence between adjacent instruction image frames as Semantic image frame sequence, wherein, the instruction image frame is an image frame in which the target person has an instruction gesture; the semantic recognition module 13 is used for recognizing corresponding semantics according to the gesture in the semantic image frame sequence.

...

Embodiment 3

[0093] On the basis of the above technical solutions, Figure 4 It is a schematic structural diagram of the device for semantic understanding of dynamic human gestures provided in Embodiment 3 of the present invention, and the device further includes: a processing module 14, configured to determine a corresponding control instruction according to the semantics, and execute the control instruction; wherein, the The target person is a traffic policeman, and the control instruction is a traffic gesture; or the target person is a game player, and the control instruction is a gesture for controlling the game.

[0094] The apparatus for semantic understanding of dynamic human body posture provided by the embodiment of the present invention can execute the semantic understanding method of dynamic human body posture provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

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 discloses a method, device, equipment and storage medium for semantic understanding of dynamic human posture. The method for semantic understanding of dynamic human posture comprises the following steps: the target person is identified from the acquired video streaming image frame; a non-mandatory image frame sequence is determined between adjacent command image frames as a semantic image frame sequence according to a command image frame in the video streaming, wherein the said command image frame is an image frame of the target person with command postures; thecorresponding semantics are identified according to the postures in the semantic image frame sequence. The embodiment of the invention is capable to adapt human posture recognition under a richer scene to improve the accuracy of recognition.

Description

technical field [0001] Embodiments of the present invention relate to technologies in the field of pattern recognition and computer vision, and in particular, to a method, apparatus, device, and storage medium for semantic understanding of dynamic human gestures. Background technique [0002] Human pose estimation is an important technology in the field of computer vision. It can be applied to human activity analysis, human-computer interaction and video surveillance by recognizing human actions and trying to figure out human intentions. For example, estimating the athlete's posture, analyzing the key points of the movement during the exercise, and learning the position, direction and scale of the posture can help the athlete to formulate a training plan in a targeted manner; some entertainment equipment with somatosensory experience can use the human body posture Estimate, identify the posture of the human body, and translate the control instructions corresponding to the po...

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): G06K9/00
CPCG06V40/23G06V20/41
Inventor 张丽晶汤炜雷宇
Owner 北京如布科技有限公司
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