A Video-Based Kneading Fingertip Tracking Method

A video and video frame technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as difficult tracking and complex shape of kneading fingertips

Active Publication Date: 2019-01-29
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current tracking and recognition method for pinching fingertips is still blank, and the shape of pinching fingertips is relatively complex, and it is difficult to track; therefore, it is necessary to design a tracking method for pinching fingertips, so that the pinching fingertip writing method can be applied to the air writing system middle

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
  • A Video-Based Kneading Fingertip Tracking Method
  • A Video-Based Kneading Fingertip Tracking Method
  • A Video-Based Kneading Fingertip Tracking Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] Such as Figure 1 to Figure 4 As shown, a video-based pinching fingertip tracking method of the present invention is used to continuously track pinching fingers in air writing; including the following five steps:

[0054] The first step is to capture the video frame image, convert the video frame image from an RGB image to a YCbCr image, segment the skin color area through the YCbCr skin color detector, and use the fist detector to segment the skin color area to obtain the fist area. In the fist area, use The pinch fingertip cascade classifier locates the pinch fingertip area, and determines the initial position of the pinch fingertip;

[0055] The second step is to capture the next video frame image as the currently processed video frame image; the center point of the pinched fingertip area obtained from the previous frame video frame image is used as the center to establish a target search area on the current processed video frame image; YCbCr skin color detection is ...

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 video-based pinching fingertip tracking method, which is characterized in that: firstly, a YCbCr skin color detector, a fist detector and a pinching fingertip cascade classifier are used to form a multi-component correlation detector to locate the position of the pinching fingertip ; Then extract the skin color target search area, obtain the contour and sample the contour points, determine the motion distance of the skin color target search area through frame matching before and after; then map the kneading fingertip area to the kneading fingertip skin color mapping table, and combine the gray value to get CbCr ‑Gray color features, and calculate HOG features, so as to obtain CbCr‑Gray‑HOG features; finally, use the filter tracking method based on Gaussian kernel function to locate and determine the center point of the pinch fingertip area of ​​the currently processed video frame image. The method is applied in the air writing system, and can accurately identify the movement trajectory of the pinched fingertips, thereby realizing the pinched fingertips in the air writing system.

Description

technical field [0001] The invention relates to the technical field of image processing and analysis, and more specifically, relates to a video-based pinching fingertip tracking method. Background technique [0002] In recent years, with the rapid development of virtual reality and augmented reality, human-computer interaction technology has been greatly developed, attracting more and more researchers' attention. At present, as one of the core technologies of human-computer interaction, finger detection and tracking are widely used in various fields, such as gesture recognition, writing in the air, etc. Among them, in-air writing based on video has been widely used in fields such as character recognition and trajectory authentication of air-writing systems. [0003] In the traditional aerial writing system, the situation of human handwriting is mainly simulated by extracting the trajectory of a single fingertip in front of the camera. However, this method of writing in the...

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 & AuthorityPatents(China)
IPC IPC(8): G06T7/11G06T7/20G06T7/40G06K9/00G06K9/46
CPCG06T2207/30196G06T2207/10016G06T2207/10024G06T2207/20056G06V20/48G06V20/49G06V20/46G06V10/56G06V10/462
Inventor康文雄吴桂乐
OwnerSOUTH CHINA UNIV OF TECH