Supercharge Your Innovation With Domain-Expert AI Agents!

A method for image recognition and tracking

An image recognition and tracking algorithm technology, applied in the field of image recognition and tracking, can solve the problems of low tracking accuracy and slow image recognition speed.

Inactive Publication Date: 2020-10-20
QISDA OPTRONICS (SUZHOU) CO LTD +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to improve the above problems of slow image recognition speed and low tracking accuracy, the present invention provides an image recognition and tracking method

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 method for image recognition and tracking
  • A method for image recognition and tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] figure 1 It is a flow chart of the image recognition and tracking method of the present invention. see figure 1 The image recognition and tracking method 100 is used to identify and track the first object in the image. In this embodiment, the first object can be a person. Of course, in other embodiments, the first object can also be other objects to be identified and tracked. Objects, for example, cats, cars, etc.

[0028] The image recognition and tracking method 100 includes steps S1 to S4.

[0029] Step S1: Capture a plurality of consecutive initial images, and analyze the plurality of initial images to obtain a corresponding foreground image. The above-mentioned plurality of initial images include a continuous first initial image and a second initial image; in this embodiment, an image capture device (such as a camera or a monitoring device) is used to capture the initial images. In actual operation, the first initial image and the second initial image are two c...

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 discloses an image identification tracking method. The method comprises the following steps of stepS1, retrieving continuous initial images and analyzing foreground images; stepS2, carrying out spot detection on a first foreground image so as to determine a motion spot set and a range; stepS3, filtering the motion spot set and defining a filtered area as a first filtered area; stepS4, tracking an interested spot set and taking as a determination basis of a second initial image; and stepS5, identifying the first filtered area, wherein the step S4 includes the following steps of S41, calculating a first prediction area which is calculated and acquired according to a first tracking input area based on a tracking algorithm; and stepS42, calculating an overlap proportion, and if the overlap proportion is greater than a first threshold, taking the first filtered area as a second tracking input area; otherwise, taking the first prediction area as the second tracking input area.

Description

technical field [0001] The invention relates to an image recognition and tracking method, in particular to an image recognition and tracking method with fast recognition speed and high tracking precision. Background technique [0002] In the prior art, the image equipment used to detect the existence of the human body mostly adopts the establishment of various human-shaped templates or modules, and compares them with the detected images to perform human body recognition, but the calculation of the required image comparison The amount is huge, it takes a long time, and the speed of image recognition is slow. [0003] In addition, the general method for tracking the target image is to first select the block to be tracked as the tracking input block of the next image, and then use this block as the output block after the tracking calculation of the next input image as the next input block. The tracking block of the next image will be continuously tracked accordingly. Due to t...

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 Patents(China)
IPC IPC(8): G06T7/246
CPCG06T7/246
Inventor 郑智太
Owner QISDA OPTRONICS (SUZHOU) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com