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

A system and method for onboard vision intelligent processing of unmanned aerial vehicles

A technology of visual intelligence and processing methods, which is applied in the field of drones, can solve problems affecting system timeliness, poor stability, and target loss, and achieve the effects of reducing over-rotation, clear images, and reduced lens shake

Active Publication Date: 2022-04-05
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the target tracking task, the traditional way is for the drone to be equipped with an airborne camera, such as a monocular camera or a binocular camera. However, the relative position information of the target obtained in this way needs to compensate for the current movement of the drone. State, in order to make the relative position information accurate, and the camera lens is fixed with the UAV, the flight attitude of the UAV will affect the continuous tracking effect of the camera on the target, and the phenomenon of target loss often occurs
[0004] In the prior art, there is still a tracking method in which the UAV is equipped with the gimbal to capture the target image, and then obtain the relative position of the target. However, the existing gimbal PID control algorithm will cause over-rotation when controlling the rotation of the gimbal lens. For example, when the pan / tilt is actually required to rotate from 20° to 40°, under traditional PID control, the pan / tilt will over-rotate from 20° to 45°, then rotate to 35°, and then rotate to 40°, even multiple times. Rotation phenomenon, if the target moves too fast at this time, it is easy to lose the target, and when the UAV moves violently, the conventional PID control algorithm is less stable, and it is easy to cause the target to be lost
[0005] In addition, most of the current UAV tracking methods are that after the UAV captures the image, it transmits the image to the ground station, and the ground station controls the UAV to track. However, this process not only affects the timeliness of the system, but also affects the transmission of information. The integrity of the

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
  • A system and method for onboard vision intelligent processing of unmanned aerial vehicles
  • A system and method for onboard vision intelligent processing of unmanned aerial vehicles
  • A system and method for onboard vision intelligent processing of unmanned aerial vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0111] Carry out a simulation experiment, using a UAV equipped with a photoelectric pod, an information processing module and a screen projector to track a moving target. The photoelectric pod is a two-degree-of-freedom photoelectric pod, and the lens adopts a visible light lens. The information processing module includes an image recognition tracking submodule, a pan / tilt PID controller submodule, and a parameter correction submodule.

[0112] In step S1, the unmanned aerial vehicle takes an image through the photoelectric pod;

[0113] In step S2, the image is recognized by the image recognition and tracking sub-module, and the rotation angle rate parameter of the photoelectric pod lens is calculated when the target is moved to the middle position of the image;

[0114] In step S3, the information detected by the inertial measurement unit and the lens rotation angular rate parameter are fused through the parameter correction sub-module to realize the correction of the lens r...

experiment example 1

[0139] In record embodiment 1 and comparative example 1, the target recognition success rate within 10 minutes after the UAV discovers the target, the target recognition rate refers to the number of images with the target identified by the image recognition tracking sub-module and the photoelectric pod Pass the ratio of the total number of images.

[0140] The results are shown in Table 1:

[0141] Table I

[0142]

[0143] It can be seen from Table 1 that the proportion of successfully recognized targets in Example 1 is significantly higher than that in Comparative Example 1, which indicates that the lens rotation stability of the photoelectric pod is improved by correcting the lens rotation angular rate parameters, and the lens shake is greatly reduced. The image is clearer, and it is easier for the image recognition and tracking sub-module to identify the target therein.

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 unmanned aerial vehicle airborne vision intelligent processing system and method. The system includes an unmanned aerial vehicle, an optoelectronic pod mounted on the unmanned aerial vehicle, and an information processing module. The information processing module includes an image recognition and tracking submodule, The gimbal PID controller sub-module and the parameter correction sub-module, the parameter correction sub-module obtains the detection data of the gyroscope, accelerometer and geomagnetometer, and corrects the lens rotation angular rate parameter output by the image recognition and tracking sub-module through the detection data. The method includes the following steps: collecting an image, identifying a target in the image, outputting a lens rotation angular rate parameter, correcting the lens rotation angular rate parameter, and controlling the rotation of the photoelectric pod lens through a PID controller. The intelligent processing system and method for on-board vision of the unmanned aerial vehicle of the present invention can solve or reduce the over-rotation phenomenon, the rotation of the photoelectric pod lens is stable, the shake of the lens is greatly reduced, and the captured image is clearer.

Description

technical field [0001] The invention relates to a system and method for onboard vision intelligent processing of an unmanned aerial vehicle, belonging to the field of unmanned aerial vehicles. Background technique [0002] In recent years, UAVs have been vigorously developed. After going through the transition from military to civilian use, they have successfully become a practical tool that is recognized by the majority of industries and can replace manpower to complete complex tasks. Among them, the use of unmanned aerial vehicles Machine-to-target continuous tracking is a common task. [0003] In the target tracking task, the traditional way is for the UAV to carry an airborne camera, such as a monocular camera or a binocular camera. However, the relative position information of the target obtained in this way needs to compensate for the current movement of the UAV. In order to make the relative position information accurate, and the camera lens is fixed with the drone, ...

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): H04N5/232H04N5/225B64D47/08B64D47/00B64C39/02
CPCB64D47/08B64D47/00B64C39/02H04N23/57H04N23/61H04N23/695B64U2101/00
Inventor 宋韬李希明莫雳金忍林德福
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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