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

Adaptive mean shift algorithm based on local invariant feature detection

A technology of local invariant features and mean shift algorithm, applied in computing, image data processing, instruments, etc., can solve problems such as tracking failure, tracking window expansion, failure, etc., achieve accurate target tracking and improve search accuracy

Inactive Publication Date: 2014-09-03
GUANGDONG UNIV OF TECH
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its remarkable advantage is that the algorithm has a small amount of calculation, is simple and easy to implement, and is very suitable for real-time tracking occasions; but it often fails to track small targets and fast-moving targets, and it cannot self-recover tracking in the case of full occlusion.
When the color of the background is similar to the target, or there is an algorithm comparison object with a similar hue to the target near the target, the search window will automatically include it, causing the tracking window to expand, and sometimes even expand the tracking window to the entire video frame, eventually lead to tracking failure

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
  • Adaptive mean shift algorithm based on local invariant feature detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Such as figure 1 As shown, the present invention provides an adaptive mean shift method based on locally invariant feature detection, and the specific implementation steps of the method are as follows:

[0025] Step 1: At the start frame of the video Select the target area to be tracked .

[0026] Step 2: Convert the image Map from RGB color space to HSV color space and calculate the target area The color probability distribution of .

[0027] Step 3: Calculate and extract the target area local invariant feature points.

[0028] First construct the scale space in is the scale factor, * is the convolution operator. is a Gaussian function. Computing the difference of Gaussian space ;

[0029] Secondly, the differential space is derived to obtain the extreme point ,in is the offset relative to the sampling point; by the threshold , and the Hessian matrix , Remove low-contrast points and edge points; according to the gradient size of pixels ...

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 adaptive mean shift algorithm based on local invariant feature detection. According to the adaptive mean shift algorithm based on local invariant feature detection, local invariant feature detection and the adaptive mean shift algorithm are combined, the detection and matching of local invariant feature points of an object are introduced during searching, and the region of search is recalculated through obtained matched feature points, so that the region of search can be excellently constrained around a target range, and finally, the accuracy of a tracking process is ensured. The adaptive mean shift algorithm based on local invariant feature detection has the advantage that the accuracy and stability of searching are greatly improved relative to those of adaptive mean shift algorithms.

Description

technical field [0001] The invention relates to real-time tracking of moving objects, in particular to an adaptive mean shift algorithm used in a target tracking method. Background technique [0002] Mean shift refers to selecting a point in the image as the starting point, calculating the average difference of the current offset of the point, and moving the point to the new position pointed by its offset, and taking the moved position as the new starting point , continue to calculate and move until reaching a position that satisfies the constraints. Therefore, the algorithm obtains the optimal solution through continuous iteration. The mean shift algorithm is mainly a target tracking method for non-rigid body motion. In this method, the target area is described by a non-parametric histogram kernel density estimation function, and the Bhattacharyya coefficient is used as the similarity criterion, and the mean shift vector is continuously iterated to find the candidate with...

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): G06T7/00
Inventor 蔡延光郭栋蔡颢邢延
Owner GUANGDONG UNIV OF TECH
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