Check patentability & draft patents in minutes with Patsnap Eureka AI!

Symmetrical target image tracking method based on local optical flow

A target image and local optical flow technology, applied in the field of image processing, can solve the problems of low tracking efficiency and poor tracking performance, and achieve the effect of improving performance and efficiency and reducing the amount of calculation

Active Publication Date: 2019-08-20
HUIZHOU DESAY SV INTELLIGENT TRANSPORTATION TECH INST CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a symmetrical target image tracking method based on local optical flow, which solves the technical problem that the existing target object tracking method requires a large amount of calculation of optical flow, and the tracking performance is poor and the tracking efficiency is low

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
  • Symmetrical target image tracking method based on local optical flow

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] When it is determined as a symmetrical target, the current image is the first frame image of the previous two frames, and the step S21 specifically includes the steps:

[0045] S21-1. Detect the edge contour and contour corners of the first frame image and thereby calculate the centroid A of the first frame image 1 (and its centroid moving vector P 1 , is a zero vector and has no meaning for calculation), the first frame image is the first frame when the machine starts to capture the image;

[0046] S21-2. Read in the second frame of image;

[0047] S21-3. Detect the edge contour and contour corner points of the second frame image and calculate the centroid A of the second frame image thereby 2 ;

[0048] S21-4. According to the centroid A of the first frame image 1 and the centroid A of the second frame image 2 Calculate the centroid moving vector P of the second frame image 2 =A 2 -A 1 ;

[0049] S21-5. According to the centroid movement vector P of the secon...

Embodiment 2

[0052] When it is determined as a symmetrical target, if the current image is the second frame image of the previous two frames, the step S21 specifically includes the steps:

[0053] S21-1. Detect the edge contour and contour corners of the second frame image and calculate the centroid A of the second frame image thereby 2 ;

[0054] S21-2. According to the centroid A of the first frame image 1 and the centroid A of the second frame image 2 Calculate the centroid moving vector P of the second frame image 2 =A 2 -A 1 , the first frame image is the first frame when the machine starts to capture the image; the centroid A of the first frame image 1 (and its centroid moving vector P 1 , which is a zero vector and has no meaning for calculation) has been calculated when it is captured;

[0055] S21-3. According to the centroid movement vector P of the second frame image2 and contour corner points to infer the motion trend of the target object.

Embodiment 3

[0058] When it is determined to be a symmetric target, if the current image is any one of the subsequent m frames (n≥3), the step S21 specifically includes the steps:

[0059] S21-1. Detecting the edge contour and contour corners of the current image and thus calculating the centroid of the current image;

[0060] S21-2. According to the centroid A of the current image n and the centroid A of the previous frame image of the current image n-1 Calculate the centroid movement vector P of the current image n =A n -A n-1 (It is necessary to find the centroid of two consecutive images);

[0061] S21-3. Move the vector P according to the centroid of the current image n and contour corner points to infer the motion trend of the target object.

[0062] It should be noted that, in the step S21-2, if the centroid of the previous frame image has been obtained (if the current image is the third frame and the second frame is also symmetrical, then its centroid is in the embodiment 1 o...

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 relates to the technical field of image processing, and particularly discloses a symmetrical target image tracking method based on a local optical flow, which comprises the following steps: S1, reading a frame of image of a target object in sequence, judging whether the target object is symmetrical or not, if not, exiting tracking, and if so, entering the next step; and S2, inferringthe movement trend of the target object according to the movement of the centroid optical flow. The invention provides a symmetrical target image tracking method based on a local optical flow. Basedon the fact that part of an object target needing to be tracked in daily life is of a symmetrical shape, when the optical flow is calculated, the motion trend of the whole target object can be deducedby only using part of the optical flow difference, so that the calculated amount is correspondingly reduced, and the tracking performance and efficiency are improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for tracking a symmetrical target image based on local optical flow. Background technique [0002] In the field of object tracking, the objects in the world coordinate system are mapped to the image coordinate system of the camera after proper transformation. Tracking objects in the world coordinate system is transformed into corresponding processing of two-dimensional plane images in the image coordinate system. When tracking, the object target can be of any shape. During the tracking process, calculating the optical flow of the entire tracking target object requires a lot of computation, and the tracking performance becomes unsatisfactory. Contents of the invention [0003] The invention provides a method for tracking a symmetrical target image based on local optical flow, and solves the technical problem that the existing tracking method for a target obje...

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): G06T7/246G06T7/269G06T7/66
CPCG06T2207/10016G06T2207/20164G06T7/246G06T7/269G06T7/66
Inventor 李晓川
Owner HUIZHOU DESAY SV INTELLIGENT TRANSPORTATION TECH INST 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