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

Target re-detection method, device and unmanned aerial vehicle

A re-detection, UAV technology, applied in the field of computer vision, can solve problems such as mistracking, flight stop, UAV cannot quickly reposition and track the target, etc., to achieve the effect of high efficiency and high accuracy

Active Publication Date: 2020-02-28
CHENGDU TOPPLUSVISION TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the tracking process, once the target is lost, the UAV will not be able to quickly relocate the tracking target, resulting in flight stop or mistracking

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 re-detection method, device and unmanned aerial vehicle
  • Target re-detection method, device and unmanned aerial vehicle
  • Target re-detection method, device and unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0033] Please refer to figure 2 , figure 2 A flow chart of the object re-detection method provided by the embodiment of the present invention is shown. The object re-detection method includes the following steps:

[0034] Step S101, acquiring a plurality of potential targets in the first image of the video, wherein the first image is any frame image in the video except the initial frame image.

[0035] In the embodiment of the present invention, the video may be a video collected by the UAV 100 , for example, an aerial video of geographical features, landscapes, people, and the like. The first image can be any frame image except the initial frame image in the video collected by the UAV 100, and the object to be tracked in the first image has been lost, that is to say, the object to be tracked in the first image needs to be re-detected. track target. The potential target may be, but not limited to, a foreground target similar to the target to be tracked that needs to be r...

no. 2 example

[0072] Please refer to Figure 7 , Figure 7 A schematic block diagram of an object re-detection device 200 provided by an embodiment of the present invention is shown. The target re-detection device 200 includes a potential target acquisition module 201 , a potential target screening module 202 and an execution module 203 .

[0073] The potential target acquisition module 201 is configured to acquire multiple potential targets in the first image of the video, wherein the first image is any frame image in the video except the initial frame image.

[0074] In the embodiment of the present invention, the potential target acquisition module 201 may be used to execute step S101.

[0075] Please refer to Figure 8 , Figure 8 for Figure 7 A schematic block diagram of the potential target acquisition module 201 in the target re-detection device 200 is shown. The potential target acquisition module 201 includes a first image acquisition unit 2011 , a salient detection unit 201...

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 invention relates to the field of computer vision technology, and provides a target re-detection method, device, and unmanned aerial vehicle. The method includes: acquiring a plurality of potential targets in the first image of the video, wherein the first image is the first image in the video Any frame of image other than the initial frame image; according to the color characteristics of each potential target, multiple potential targets are screened to obtain a specific target; according to the similarity between the specific target and the target to be tracked, it is judged whether the specific target is the target to be tracked , wherein the target to be tracked is determined by the initial frame image, the invention solves the problem in the prior art that the UAV cannot quickly relocate the target when the tracking target is lost, and has the advantages of high efficiency and high accuracy.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a target re-detection method, device and unmanned aerial vehicle. Background technique [0002] Moving target tracking technology is a high-tech subject that integrates multiple fields such as image processing, pattern recognition, artificial intelligence, and automatic control. It is also one of the key technologies for realizing intelligent robots and intelligent weapons. It has broad applications in many fields. Application prospects and practical significance, for example, applied to UAV target tracking. [0003] The modern UAV tracking system has been able to accurately obtain the motion trajectory of the non-specific tracking target based on the first frame of the target image, and can perform short-term tracking calculations on the target to be tracked in real time. For the single target tracking problem, the current UAV tracking system mainly focuses on i...

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): G06K9/00G06K9/46
CPCG06V20/46G06V10/462G06V10/56
Inventor 陈志超马骁周剑
Owner CHENGDU TOPPLUSVISION TECH 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