Method and device for detecting human hands based on action sequential characteristics

A detection method and feature detection technology, applied in the field of visual detection, can solve the problem of high false detection rate, achieve the effects of avoiding interference, easy construction and maintenance, and improving information utilization.

Active Publication Date: 2018-06-05
哈尔滨拓讯科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Aiming at the problem of high false detection rate in complex scenes and similar target interference, the present invention proposes a huma

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 and device for detecting human hands based on action sequential characteristics
  • Method and device for detecting human hands based on action sequential characteristics
  • Method and device for detecting human hands based on action sequential characteristics

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0072] Example 1:

[0073] This embodiment proposes a hand detection method based on action timing characteristics. The method first performs single-frame detection on each frame of a monocular video signal or image sequence to obtain candidate targets, and then compares the single-frame detection result with adjacent frame detection The results are compared and analyzed, and the time sequence features of each candidate target are extracted, that is, the feature state under different frames in the selected time period, and matched with the preset action time sequence features. If the matching results are inconsistent, it will be regarded as a false detection, and then the target will be filtered ROI (Region of Interest, region of interest), and finally the actual hand position is obtained by detecting the human hand again in the target ROI.

[0074] In order to explain the detection process in detail, the following takes the human hand "grabbing" action as the preset action, that i...

Example Embodiment

[0126] Example 2

[0127] This embodiment proposes a hand detection device based on action timing characteristics, which is used to implement the method proposed in Embodiment 1 for hand detection, and can output digital signals to provide input for subsequent systems according to actual application requirements. The detection device includes four modules: main controller, data acquisition, data processing and data output. The connection methods of the modules are as follows: Picture 8 Shown. The device includes a main controller 1, a data acquisition module 2, a data processing module 3, and a data output module 4; the data acquisition signal interaction terminal of the main controller 1 is connected to the signal interaction terminal of the data acquisition module 2; The data transmission signal interaction terminal of the main controller 1 is connected to the signal interaction terminal of the data output module 4; the data output terminal of the data acquisition module 2 is ...

Example Embodiment

[0130] Example 3

[0131] This embodiment integrates the main controller, data processing module, and data output module into the embedded platform. The system structure is shown in Figure 9. The data acquisition module is separately external, and the module contains a monocular camera, which can capture video data in real time, and Into the embedded platform through the data line. The main controller calls the data acquisition module to monitor user actions, and calls the data processing module to perform manual detection and analysis, and finally uses the data output module to output the detection results. The whole device is an independent whole, and the data output module modulates the detection result and transmits it to external equipment through 2.4GHz wireless signal.

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 provides a method and a device for detecting human hands based on action sequential characteristics and belongs to the technical field of visual inspection. According to the method, based on traditional human hand detection, the detection accuracy is improved by detecting the sequential characteristics of specific action sequence of the human hands. The method has the advantages thatthe problem of higher false detection rate in complex scenes and existence of the interference of similar targets is solved; the method is suitable for detecting the human hands in monocular video signal or image sequence.

Description

technical field [0001] The invention relates to a human hand detection method and device based on motion sequence features, and belongs to the technical field of visual detection. Background technique [0002] With the rapid development of machine vision technology, gesture control based on machine vision has become an important research direction in human-computer interaction, and accurate and fast human hand detection is one of the core technologies to realize gesture control. [0003] At present, the hand detection methods based on machine vision can be divided into three categories: based on physical hand marks, based on monocular two-dimensional images and based on depth images. [0004] The detection method based on the physical mark of the hand relies on wearable devices with special color and shape marks, such as gloves, wristbands, etc., to directly determine the position of the human hand through the detection of the physical mark of the device, or to further impro...

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): G06K9/00G06K9/32
CPCG06V40/107G06V20/46G06V10/25
Inventor 孙晅张建峰冯大志杜国铭金钊
Owner 哈尔滨拓讯科技有限公司
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