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

Unmanned aerial vehicle airborne target detection system and method

A target detection algorithm and target detection technology are applied in the field of UAV airborne target detection system and UAV data processing, which can solve the problems of low detection efficiency and low real-time performance, and improve real-time performance and detection efficiency fast effect

Active Publication Date: 2020-10-02
GUANGDONG POWER GRID CO LTD
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This application provides a UAV airborne target detection system and method, which are used to solve the problems of UAV target detection in the prior art and the lack of real-time performance and low detection efficiency of obtaining the position coordinates and flight attitude of the UAV. high technical issues

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
  • Unmanned aerial vehicle airborne target detection system and method
  • Unmanned aerial vehicle airborne target detection system and method
  • Unmanned aerial vehicle airborne target detection system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] For ease of understanding, see figure 1 and figure 2 , a UAV airborne target detection system provided by the application, comprising: a camera, a calculation module, an IMU inertial measurement unit, a GPS positioning module and a sensor information acquisition module;

[0042] The camera is used to obtain the target video stream in real time;

[0043] The GPS positioning module is used to obtain the position coordinates of the drone;

[0044] The IMU inertial measurement unit is used to obtain the acceleration and angular velocity of the drone;

[0045] The sensor information collection module is used to collect and transmit the position coordinates obtained by the GPS positioning module and the acceleration and angular velocity information of the UAV obtained by the IMU inertial measurement unit to the calculation module;

[0046] The calculation module is set on the UAV, and the calculation module includes a deep learning target detection algorithm module, a KLT...

Embodiment 2

[0061] The second embodiment is based on the first embodiment, further, the deep learning target detection algorithm module is embedded with the tiny-yolo target detection algorithm.

[0062] It should be noted that the detection speed of the tiny-yolo target detection algorithm is far faster than other deep learning detection algorithms, which can better meet the real-time requirements of UAV airborne applications.

[0063] Further, the calculation module also includes an image preprocessing module, which is used to perform noise reduction processing on the target video stream acquired by the camera.

[0064] It can be understood that performing noise reduction processing on the target video stream can reduce the degree of interference caused to the target detection in the later stage.

[0065] Further, the calculation module adopts the FPGA chip to integrate the deep learning target detection algorithm module.

[0066] Further, the calculation module uses an ARM chip to int...

Embodiment 3

[0071] The present embodiment three provides a kind of UAV airborne target detection method, refer to Image 6 , including the following steps:

[0072] Step S01: Obtain the target video stream through the camera, obtain the position coordinates of the drone through the GPS positioning module, and obtain the acceleration and angular velocity of the drone through the IMU inertial measurement unit;

[0073] Step S02: collect and transmit the position coordinates obtained by the GPS positioning module and the acceleration and angular velocity information of the drone obtained by the IMU inertial measurement unit through the sensor information collection module;

[0074] Step S03: Detect the target to be detected and the corresponding video frame in the target video stream acquired by the camera based on the pre-stored deep learning target detection algorithm through the deep learning target detection algorithm module, and use the KLT target tracking and counting algorithm module ...

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 target detection system and method. A video stream is acquired by a camera, a to-be-detected target object is detected through a deep learning target detection algorithm module arranged in an airborne calculation module, a KLT target tracking and counting algorithm module is used for tracking and counting the to-be-detected target object,the position coordinates of an unmanned aerial vehicle are obtained through a GPS positioning module, the acceleration and the angular velocity of the unmanned aerial vehicle are obtained through anIMU inertial measurement unit, data calibration is carried out on the acceleration and the angular velocity through an average value algorithm module in a calculation module, the accurate aircraft attitude is obtained through a Kalman filtering algorithm module, and the obtained data, position coordinates and flight attitude of the to-be-measured target object and the to-be-measured target objectare recorded and stored. The real-time performance of target detection of the unmanned aerial vehicle is improved, and meanwhile the detection efficiency is higher.

Description

technical field [0001] The present application relates to the technical field of unmanned aerial vehicles, in particular to the data processing technology of unmanned aerial vehicles, and more specifically, to a detection system and method for airborne targets of unmanned aerial vehicles. Background technique [0002] With the popularization of artificial intelligence, traditional industries are constantly changing. As far as drones are concerned, more and more organizations are using technologies such as machine vision or deep learning to make drones smarter. However, due to the constraints of the flight control performance of most UAVs, it is usually necessary to compress and encode the captured images, transmit them to the ground, decode them, and finally perform corresponding processing. At the same time, the location coordinates of the UAV will Determine the shooting path of the UAV, and the flight attitude of the UAV will also affect the stability of the captured imag...

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): G01S19/42G01C21/16G06K9/00G06T5/00G06T7/277
CPCG01S19/42G01C21/16G06T7/277G06T2207/30242G06V20/10G06V20/40G06T5/70
Inventor 潘岐深陈慧坤刘文松张壮领陈彩娜莫一夫毕明利郑松源
Owner GUANGDONG POWER GRID CO LTD