Ground target positioning method and system based on monocular vision of unmanned aerial vehicle

A ground target and UAV technology, applied in the field of ground target positioning based on UAV monocular vision, to achieve the effect of improving usability and accuracy

Pending Publication Date: 2020-12-22
天津(滨海)人工智能军民融合创新中心
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The existing UAV monocular vision target positioning algorithm cannot effectively meet the needs of insufficient calibration conditions and continuous positi

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
  • Ground target positioning method and system based on monocular vision of unmanned aerial vehicle
  • Ground target positioning method and system based on monocular vision of unmanned aerial vehicle
  • Ground target positioning method and system based on monocular vision of unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0051] Example 1:

[0052] A schematic flowchart of a method for locating a ground target based on the monocular vision of an unmanned aerial vehicle provided by the present invention is as follows: figure 1 shown, including:

[0053] S1: Obtain the position of the ground target in each frame of the UAV monocular vision image;

[0054] S2: Based on the position in the image, the field of view angle is used to calculate the real coordinates of the ground target;

[0055] S3: Superimpose the real coordinates of the ground target with the position and attitude information of the UAV to obtain the positioning information of the ground target during the flight of the UAV.

[0056] The specific technical scheme of the present invention is as follows figure 2 shown, including:

[0057] The first step is to implement a camera-based field of view (FOV) ground target localization algorithm to calculate the real coordinates of ground targets during the flight of the UAV.

[0058] T...

Example Embodiment

[0111] Example 2:

[0112] Another embodiment of the method for locating a ground target based on the monocular vision of the UAV is given below.

[0113] This embodiment includes the following steps:

[0114] In step a1, the position of the target in each frame of image is obtained. After the drone takes off, the camera is turned on, and the ground target is in place, the target position is initialized by manually framing the target or a target detection algorithm, and the target position in the image is continuously obtained by the method of target tracking. Manually frame the target, that is, after the camera captures the target, frame the target by hand-drawing a rectangular frame on the image containing the target, and initialize the position of the target in the image; using the target detection algorithm means that when the camera captures the target After that, the detection algorithm will automatically detect the target and use a rectangle to frame the target. The ...

Example Embodiment

[0154] Example 3:

[0155] Based on the same inventive concept, the present invention also provides a ground target positioning system based on UAV monocular vision. Since the principle of these devices for solving technical problems is similar to the ground target positioning method based on UAV monocular vision, repeat the process. It is not repeated here.

[0156] The basic structure of the system is as Figure 4 As shown, including: a position acquisition module, a coordinate calculation module and a positioning module;

[0157] The position acquisition module is used to obtain the position of the ground target in each frame of the UAV monocular vision image;

[0158] The coordinate calculation module is used to calculate the real coordinates of the ground target based on the position in the image using the field of view angle;

[0159] The positioning module is used to superimpose the real coordinates of the ground target with the pose information of the UAV to obtain ...

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 provides a ground target positioning method and system based on unmanned aerial vehicle monocular vision. The method comprises the steps that the position of a ground target in each frame of unmanned aerial vehicle monocular vision image is acquired; based on the position in the image, calculating a real coordinate of the ground target by adopting a field angle; and superposing the real coordinates of the ground target with the pose information of the unmanned aerial vehicle to obtain positioning information of the ground target in the flight process of the unmanned aerial vehicle. For current ground target positioning based on an airborne camera of an unmanned aerial vehicle, calibrated camera focal length parameters need to be used for calculation, and if the camera cannotbe accurately calibrated, a positioning result has a large error. Problems can be solved for scenes with insufficient calibration conditions, the camera focal length needing to be calibrated is not used, the camera field angle parameters are adopted for positioning calculation, only the rated field angle of the camera needs to be obtained, and calibration in advance is not needed. Therefore, the availability and the accuracy of the positioning algorithm under the condition of condition shortage can be improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision and UAV sensors, and in particular relates to a ground target positioning method and system based on UAV monocular vision. Background technique [0002] In recent years, UAV (Unmanned Aerial Vehicle, UAV) has played an important role in various scenarios, such as UAV search and rescue and reconnaissance, environmental monitoring, traffic management, etc. In these application scenarios, a very important task of UAVs is to detect and track objects of interest. For example, in a search and rescue mission, the task of the UAV is to hover over the disaster-stricken area, accurately detect the victims who need to be searched and rescue and provide the location of the personnel, so that rescuers can carry out rescue. In the task of unmanned aerial vehicles to detect and track targets, it is essential to locate the real coordinates of the target. In terms of target positioning, researchers have ...

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
IPC IPC(8): G06T7/70G06T7/277
CPCG06T7/70G06T7/277
Inventor 康颖王宁史殿习张拥军秦伟崔玉宁
Owner 天津(滨海)人工智能军民融合创新中心
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap