Unlock instant, AI-driven research and patent intelligence for your innovation.

Target tracking method and device based on feature map matching and superpixel map sorting

A target tracking and super pixel technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems that the integration of segmentation and tracking is not considered, and the video sequence cannot be realized, so as to achieve convenient segmentation and tracking functions and improve tracking effect of effect

Active Publication Date: 2021-06-22
ANHUI UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is that the prior art target tracking solves segmentation and tracking as two tasks, without considering the integration of segmentation and tracking, so Video sequences cannot achieve more convenient segmentation and tracking functions

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
  • Target tracking method and device based on feature map matching and superpixel map sorting
  • Target tracking method and device based on feature map matching and superpixel map sorting
  • Target tracking method and device based on feature map matching and superpixel map sorting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] A target tracking method based on feature map matching and superpixel map sorting, the method comprising:

[0064] Step a: extract the features of the image pairs of two consecutive frames and perform feature point matching;

[0065] Step b: Perform superpixel segmentation on the previous frame image to obtain the superpixel block of the previous frame, perform superpixel segmentation on the current frame image to obtain the superpixel block of the current frame, and divide the feature points of the previous frame image into the superpixel block The segmentation result is mapped to the binary segmentation mask of the previous frame. If the superpixel block occupied by the feature points of the previous frame in the previous frame corresponds to the foreground in the binary segmentation mask of the previous frame, then the current The superpixel block occupied by the corresponding feature points of the frame image in the current frame is the foreground, otherwise it is t...

Embodiment 2

[0098] Corresponding to Embodiment 1 of the present invention, Embodiment 2 of the present invention also provides an object tracking device based on feature map matching and superpixel map sorting, the device comprising:

[0099] A feature matching module is used to extract the features of the image pair of two consecutive frames and perform feature point matching;

[0100] The superpixel segmentation module is used to perform superpixel segmentation on the previous frame image to obtain the superpixel block of the previous frame, perform superpixel segmentation on the current frame image to obtain the superpixel block of the current frame, and divide the feature points of the previous frame image into The segmentation result of the superpixel block is mapped to the binary segmentation mask of the previous frame. If the feature point of the previous frame image occupies the superpixel block in the previous frame and the binary segmentation mask of the previous frame correspond...

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 a target tracking method and device based on feature map matching and superpixel map sorting. The method comprises the following steps: extracting features of two continuous frames of image pairs, and carrying out feature point matching; carrying out superpixel segmentation on the previous frame of image and on the current frame of image; determining an indication vector of superpixel image sorting, obtaining a sorting result of the current frame image by using a semi-supervised image sorting technology, and further obtaining a binary segmentation mask of the current frame image; and positioning and tracking the target according to the binary segmentation mask of the current frame image. The method has the advantages that segmentation and tracking are integrated in the target tracking process, and more convenient segmentation and tracking functions are achieved.

Description

technical field [0001] The present invention relates to the fields of feature map matching technology, superpixel map sorting technology, and video tracking technology, and more specifically relates to a target tracking method and device based on feature map matching and superpixel map sorting. Background technique [0002] At present, with virtual reality medical image classification and activity analysis, image segmentation and video tracking as key technologies in the field of artificial intelligence, accurate segmentation or tracking technology is a more reliable and usable guarantee for computer vision, but people often regard segmentation as Segmentation and tracking are solved as two tasks, without considering the integration of segmentation and tracking, video sequences cannot achieve more convenient segmentation and tracking functions. [0003] Feature map matching can be an important way to obtain the relationship between graphs. Jiang et al. published the document...

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): G06K9/00G06K9/62G06T7/10
CPCG06T7/10G06T2207/10016G06V20/48G06V10/751G06F18/2411
Inventor 江波张盼盼肖云
Owner ANHUI UNIVERSITY