Target tracking method and device

A target tracking and equipment technology, applied in image analysis, instruments, biological neural network models, etc., can solve problems such as long tracking time

Active Publication Date: 2021-03-09
苏州飞搜科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiment of the present application provides a target tracking method and device to solve the problem of long tracking time

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
  • Target tracking method and device
  • Target tracking method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to achieve the purpose of this application, the embodiment of this application provides a target tracking method and equipment, by inputting the first frame image into the convolutional neural network, to obtain the feature map corresponding to the first frame image; to obtain the processed second A feature template of at least one target object in the frame image, the second frame image is in front of the first frame image in time sequence; and then the feature map is matched with the feature template of the at least one target object to obtain the feature map at least one target object matched in the first frame image; thereby determining the target position of the at least one matched target object in the first frame image according to the position information of the matched at least one target object in the feature map corresponding to the first frame image , to achieve the purpose of tracking the target object. The present invention firstly inputs the enti...

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 present application provides a target tracking method and device. The present invention obtains the feature map corresponding to the first frame image by inputting the first frame image into the convolutional neural network; obtains the feature template of at least one target object in the processed second frame image, and the second frame image is higher than the first frame image The image sequence is first; then the feature map is matched with the feature template of at least one target object to obtain at least one target object matched in the feature map; thus according to the matched at least one target object in the feature map corresponding to the first frame image The position information determines the target position of the at least one matched target object in the first frame image, so as to achieve the purpose of tracking the target object. The present invention firstly inputs the entire frame of image into the convolutional neural network to obtain the feature map of the entire image in a short time, and then matches the feature map with the feature template of the target object in the previous frame image to obtain the position of the target object to be tracked, and the tracking speed is fast , which improves the tracking experience.

Description

technical field [0001] The present application relates to the field of target detection and tracking, and in particular to a target tracking method and device. Background technique [0002] Target tracking is mainly used in scenarios such as video surveillance, human-computer interaction, virtual reality, and drone reconnaissance. Usually when tracking a single target object, it is necessary to adjust the size of the image according to the requirements of the convolutional neural network, intercept the image of the target object area in the image for convolution to obtain the corresponding feature map (time-consuming), and then The feature map is matched with the target template to identify whether the target object needs to be tracked, so as to realize the tracking of the target object in the video image. The process of extracting the feature map of the target object area in the original image takes a long time, the process is cumbersome, and the experience of real-time tr...

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): G06T7/246G06N3/04
CPCG06T7/246G06N3/045
Inventor 何智群董远白洪亮熊风烨
Owner 苏州飞搜科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products