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

Unmanned aerial vehicle wide area search device and method based on deep learning

A technology of deep learning and drones, applied in the field of wide-area search devices for drones, can solve problems such as low pixels, difficult execution efficiency of photoelectric pods, and small field of view, achieving high detection efficiency and wide coverage , the effect of reducing risk

Pending Publication Date: 2022-05-31
XIAMEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Photoelectric pods can transmit video streams in real time during drone flight, but the disadvantages are low pixels and small field of view
When it is necessary to perform a scanning search in a large range, the execution efficiency of the photoelectric pod is a bit difficult

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 wide area search device and method based on deep learning
  • Unmanned aerial vehicle wide area search device and method based on deep learning
  • Unmanned aerial vehicle wide area search device and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The following embodiments will further illustrate the present invention in conjunction with the accompanying drawings.

[0040] like figure 1 As shown in the figure, a device for UAV wide-area space search based on target detection algorithm, including UAV platform, embedded AI processing platform, high-definition camera array, photoelectric pod, flight control computer, data transmission equipment, ground monitoring end. The embedded AI processing platform is connected with the high-definition camera array and the photoelectric pod using USB to read the video picture data captured by the camera, and the embedded AI processing platform is connected with the serial port of the flight control computer to read the relevant data information of the drone.

[0041] The data transmission device is connected to the embedded AI processing platform and the ground monitoring terminal, and the data transmission device is also connected to the flight control computer and the ground...

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 wide area search device and method based on deep learning, and belongs to the field of artificial intelligence. The device comprises an unmanned aerial vehicle platform, an embedded AI processing platform, a high-definition camera array, a photoelectric pod, a flight control computer, data transmission equipment and a ground monitoring end. The method comprises the following steps: determining a target to be searched, primarily selecting several target detection models suitable for use, training the models on a prepared target data set by using a deep learning server, selecting the most suitable model, and storing the best primary model weight during training; loading a Ubuntu operating system on the embedded AI processing equipment, and configuring a target detection algorithm operating environment; writing a search task system program, and setting the search task system program as a startup program; all equipment is loaded to an unmanned aerial vehicle platform, and the unmanned aerial vehicle is released to execute tasks; and after a suspected target is detected, the unmanned aerial vehicle descends to spirally call the photoelectric pod to confirm the target at a low altitude. Operation is simple, and cost and risk are low; the coverage range is wide, the detection efficiency is high, and real-time observation is realized.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and in particular relates to a device and method for wide-area search of unmanned aerial vehicles based on deep learning. Background technique [0002] Ground target search has always been a time-consuming and labor-intensive task, especially in the vast mountainous areas, deserts and other sparsely populated areas. At present, large-scale ground search is still the main method, which requires coordination with governments at all levels to mobilize a large number of personnel, vehicles and other resources. With the development of social economy, UAV technology is becoming more and more mature. UAVs are widely used in target search tasks due to their high durability, low cost, easy deployment and high flexibility. The installation and application of optoelectronic pods on UAV platforms is very common, and it is one of the most commonly used loads in target search tasks. The optoelectronic ...

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): G05D1/12
CPCG05D1/12
Inventor 吴了泥郭伟杰李先江
Owner XIAMEN UNIV
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