Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Driver action recognition method based on combination of target detection and key point detection

An action recognition and target detection technology, applied in the field of action technology detection technology improvement, can solve the problems of strong subjective consciousness, impossibility of objective evaluation, time-consuming and labor-consuming, etc., and achieve the goal of reducing manpower and time costs and improving accuracy Effect

Pending Publication Date: 2021-11-16
SHENZHEN BEYEBE NETWORK TECH CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This process is not only time-consuming and labor-intensive, but also people's subjective consciousness is too strong to make an objective evaluation

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
  • Driver action recognition method based on combination of target detection and key point detection
  • Driver action recognition method based on combination of target detection and key point detection
  • Driver action recognition method based on combination of target detection and key point detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The general framework of the driver action recognition method described in the present invention is as follows: figure 1 As shown, it mainly includes three parts: gesture recognition, pose estimation and action level analysis. The first part detects whether there is a gesture in the standardized operation, the second part detects whether the driver has performed the movement trend of the standardized operation, and the third part judges the degree of standardization of the action.

[0040] Gesture Recognition

[0041] This part is mainly to detect the driver's standardized action gestures. In order to make the detection results more accurate, Faster-RCNN is used here, which is an end-to-end intelligent target detection method. Through deep convolutional neural network learning, it can automatically Fit the target position, and at the same time determine the category of the target according to the extracted image features.

[0042] The process of establishing the gestu...

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 is suitable for the field of action detection technology improvement, and provides a driver action recognition method based on combination of target detection and key point detection. The method comprises the following steps: S1, extracting action gesture image features from an input video frame to determine the category of a target; S2, predicting key points of human bones in the video frames, and performing candidate action recognition and action direction estimation on the key points; S3, judging whether a human body in the video acts or not according to results of action gesture recognition and candidate action recognition; and S4, estimating and judging a human body action level according to the action result and the action direction, and obtaining an action recognition result according to the human body action level. An artificial intelligence analysis method in which target detection and key point detection are combined is adopted to identify and analyze some standardized actions of the user, so that the manpower and time cost can be effectively reduced, and the accuracy of objective evaluation is improved.

Description

technical field [0001] The invention belongs to the field of motion technology detection technology improvement, in particular to a driver motion recognition method based on the combination of target detection and key point detection. Background technique [0002] In recent years, in order to alleviate the traffic pressure of people traveling, many first-tier and second-tier cities are gradually planning and deploying rail transit. Among them, the subway, as a tool of rail transit, has gradually become the main way of travel for people due to its convenience and punctuality. However, due to the large passenger volume of the subway, safe operation and maintenance has become an essential part of it. Among them, safe operation and maintenance cannot be separated from the code of conduct of subway drivers. Therefore, the subway has standardized some driving behaviors of drivers. And the driver needs to be assessed every month. The usual practice is to install a surveillance ca...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/217G06F18/214
Inventor 袁志成杜卫红谢立欧陈炯黄友文
Owner SHENZHEN BEYEBE NETWORK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com