CN114353667A - Ground target measurement method based on AR and unmanned aerial vehicle monocular vision and application thereof - Google Patents
Ground target measurement method based on AR and unmanned aerial vehicle monocular vision and application thereof Download PDFInfo
- Publication number
- CN114353667A CN114353667A CN202111538465.9A CN202111538465A CN114353667A CN 114353667 A CN114353667 A CN 114353667A CN 202111538465 A CN202111538465 A CN 202111538465A CN 114353667 A CN114353667 A CN 114353667A
- Authority
- CN
- China
- Prior art keywords
- ground target
- unmanned aerial
- aerial vehicle
- pixel
- ground
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000691 measurement method Methods 0.000 title abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000005259 measurement Methods 0.000 claims abstract description 23
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000003416 augmentation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention belongs to the field of unmanned aerial vehicle reconnaissance, and relates to a ground target measuring method based on AR and unmanned aerial vehicle monocular vision and application thereof. The method comprises the following steps: the unmanned aerial vehicle flies to a position S1 meters away from the ground target and hovers and obtains a first unmanned aerial vehicle picture; drawing a ground target in a first unmanned aerial vehicle picture by utilizing an AR plotting technology, and measuring a first length pixel and a first width pixel of the ground target in the first unmanned aerial vehicle picture; controlling the unmanned aerial vehicle to fly to a position S2 meters away from the ground target and hover to obtain a second unmanned aerial vehicle picture; drawing a ground target in a second unmanned aerial vehicle picture by utilizing an AR plotting technology, and measuring a second length pixel and a second width pixel of the ground target in the second unmanned aerial vehicle picture; and calculating the geometric dimension of the ground target according to the measured data. The method can effectively improve the operability and the measurement precision of the original monocular distance measurement method, and can sense, quickly calculate and accurately acquire the size of the ground reconnaissance target in advance.
Description
Technical Field
The invention belongs to the field of unmanned aerial vehicle reconnaissance, and particularly relates to a ground target measuring method based on AR and unmanned aerial vehicle monocular vision and application thereof.
Background
Unmanned aerial vehicle is a have power, steerable, can execute the unmanned aircraft of multiple task, and in recent years, unmanned aerial vehicle is also more and more in the aspect of civilian application, and a plurality of fields such as public safety, emergent search and rescue, agriculture and forestry, environmental protection, traffic, communication, weather, movie & TV aerial photograph are taken photo to the wide application. Through the cloud platform camera that unmanned aerial vehicle carried on to aerial visual angle utilizes monocular vision measurement technique, realizes the accurate measurement of the ground target size in the place ahead, can assist the reconnaissance personnel to carry out early warning and commander in advance.
In the prior art, CN107479059A discloses an overhead line and vegetation distance measuring device and method based on an unmanned aerial vehicle, which is characterized in that a flight control system and a sensing detection integrated system are arranged on an unmanned aerial vehicle body, wherein the sensing detection integrated system is connected with a three-axis pan-tilt stability augmentation system, an imaging device, a two-dimensional 360-degree laser scanner, a large-capacity information storage unit and an airborne second communication module. CN109978948A discloses a distance measuring method based on vision, which takes a picture of the real-world space at N different viewing angles through a mobile intelligent terminal, and performs three-dimensional reconstruction to obtain a three-dimensional model of the real-world space, thereby measuring the distance between any two points in the real-world space. The vision measurement based on the unmanned aerial vehicle is only limited to the naked eye identification of visible light photos, or certain image processing is carried out through binocular stereo images to achieve the analysis work of the space distance. Simultaneously, use unmanned aerial vehicle to carry out distance measurement in the current patent, it is more, the hardware cost is higher to need integrated unmanned aerial vehicle airborne sensor usually, has the problem that the hardware cost is higher, the processing procedure is complicated, the real-time is relatively poor, can't be applicable to and carry out the work of ground target real-time measurement and early warning under the operational environment.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a ground target measuring method based on AR and unmanned aerial vehicle monocular vision and application thereof, and aims to solve the problems of higher hardware cost, complex processing process and poorer real-time performance of the existing unmanned aerial vehicle vision measuring method.
To achieve the above object, according to an aspect of the present invention, there is provided a ground target measuring method based on AR and monocular vision of an unmanned aerial vehicle, the method comprising the steps of:
s1 the unmanned aerial vehicle flies to a position S1 meters away from the ground target and hovers to obtain a first unmanned aerial vehicle picture;
s2, drawing a ground target in the first unmanned aerial vehicle picture by utilizing an AR plotting technology, and measuring a first length and a first width of the ground target in the first unmanned aerial vehicle picture;
s3, controlling the unmanned aerial vehicle to fly to a position S2 meters away from the ground target and hover to obtain a second unmanned aerial vehicle picture;
s4, drawing the ground target in the second unmanned aerial vehicle picture by utilizing an AR plotting technology, and measuring a second length and a second width of the ground target in the second unmanned aerial vehicle picture;
s5 calculating the ground target geometric dimension according to the data measured in the steps S2 and S4.
Further preferably, in steps S1 and S3, the pan/tilt camera pitch angle of the drone is maintained at 90 degrees.
As a further preferable, in step S1 and step S3, it is ensured that the ground target is located in the middle of the drone screen.
Preferably, in step S5, the geometric dimension of the ground target is calculated by the following formula:
in the formula, l is the actual length of the ground target, r is the focal length of the pan-tilt camera, M is the long frame of the pan-tilt camera, N is the short frame of the pan-tilt camera, a1 is the first length pixel of the ground target, a2 is the second length pixel of the ground target, M is the length pixel of the unmanned aerial vehicle frame, w is the actual width of the ground target, b1 is the first width pixel of the ground target, b2 is the second width pixel of the ground target, and N is the width pixel of the unmanned aerial vehicle frame.
More preferably, the relation between the height S1 and the height S2 is 1/2 to 2/1.
Further preferably, in steps S2 and S4, the starting point of the length measurement is the left edge of the ground target and the ending point of the length measurement is the right edge of the ground target; the starting point of the width measurement is the upper edge of the ground target and the ending point of the width measurement is the lower edge of the ground target.
According to another aspect of the invention, the application of the above ground target measurement method based on AR and monocular vision of the unmanned aerial vehicle in the unmanned aerial vehicle is provided.
Generally, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:
1. the invention provides a method for measuring the geometric dimension of a ground target by combining monocular vision of an unmanned aerial vehicle with an AR technology, and the actual dimension is calculated by utilizing the dimension of the ground target in the pictures of the unmanned aerial vehicles with different heights, so that the operability and the measurement precision of the original monocular distance measuring method can be effectively improved, and the size of the ground reconnaissance target can be sensed, calculated quickly and accurately obtained in advance;
2. meanwhile, the angle, the position and the height of the unmanned aerial vehicle are limited, so that the drawing accuracy of the AR measurement line is ensured, and the accuracy of the ground target size measurement can be further improved;
3. in addition, the invention also provides application of the ground target measurement method based on the AR and the monocular vision of the unmanned aerial vehicle in the unmanned aerial vehicle, which can be suitable for the operation environment of the small unmanned aerial vehicle and improves the reliability of unmanned aerial vehicle reconnaissance.
Drawings
Fig. 1 is a flowchart of a ground target measurement method based on AR and unmanned aerial vehicle monocular vision provided in an embodiment of the present invention;
fig. 2 is a schematic view of a drone provided by an embodiment of the present invention at a height of S1 meters;
fig. 3 is a schematic view of a drone provided by an embodiment of the present invention at a height of S2 meters;
the same reference numbers will be used throughout the drawings to refer to the same or like elements or structures, wherein:
1-unmanned plane, 2-camera frame, 3-ground target.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1 to 3, the invention provides a ground target measurement method based on AR and unmanned aerial vehicle monocular vision, which comprises the following steps:
s1, commanding the unmanned aerial vehicle 1 to fly to a position S1 meters away from a ground target through an unmanned aerial vehicle ground station to hover, switching the state of the unmanned aerial vehicle to enter a target measurement mode, displaying a scout video of the unmanned aerial vehicle in real time by the ground station, adjusting the pitch angle of a pan-tilt camera to be 90 degrees and ensuring that the ground target 3 is positioned in the middle vertical direction of a picture of the unmanned aerial vehicle, and then obtaining a first unmanned man-machine picture, wherein the focal distance of the pan-tilt camera is r millimeters, and the camera picture 2 of the pan-tilt camera is m millimeters multiplied by n millimeters;
s2, drawing the ground target 3 in the first unmanned plane picture by utilizing an AR plotting technology through the ground station touch screen, and measuring that the pixel size of the length measuring line of the ground target 3 in the first unmanned plane picture is a1 and the pixel size of the width measuring line is b 1;
s3, controlling the unmanned aerial vehicle to fly to hover at a position S2 meters away from the ground target, keeping the pitch angle of the pan-tilt camera unchanged at 90 degrees, ensuring that the ground target 3 is positioned in the middle vertical direction of the unmanned aerial vehicle picture, and then obtaining a second unmanned aerial vehicle picture;
s4, drawing a ground target in a second unmanned aerial vehicle picture by utilizing an AR plotting technology through a ground station touch screen, and measuring that the pixel size of a length measuring line of the ground target 3 in the second unmanned aerial vehicle picture is a2 and the pixel size of a width measuring line is b 2;
s5 calculates the geometric size of the ground target 3 based on the data measured in steps S2 and S4.
Further, in step S5, the geometric dimension of the ground target 3 is calculated as follows:
l=l1×[1-l1/(l1+l2)]+l2×[1-l2/(l1+l2)]
w=w1×[1-w1/(w1+w2)]+w2×[1-w2/(w1+w2)]
is obtained by substituting the above formula
In the formula, L is an actual length of the ground target, L1 is a first length of the ground target, L2 is a second length of the ground target, W is an actual width of the ground target, W1 is a first width of the ground target, W2 is a second width of the ground target, L1 is a first real length of the unmanned aerial vehicle picture, M is a length pixel of the unmanned aerial vehicle picture, a1 is a first length pixel of the ground target, L2 is a second real length of the unmanned aerial vehicle picture, a2 is a second length pixel of the ground target, W1 is a first real width of the unmanned aerial vehicle picture, W2 is a second real width of the unmanned aerial vehicle picture, r is a focal length of the pan/tilt/zoom camera, M is a long frame of the pan/tilt/.
Further, the relation between the height S1 and the height S2 is 1/2-2/1, so that inaccurate measurement caused by overlarge size difference of ground targets in the pan-tilt camera is avoided, and the ground targets can be conveniently drawn in the unmanned aerial vehicle picture by utilizing an AR plotting technology.
Further, in steps S2 and S4, the starting point of the length measurement is the left edge of the ground target 3, and the ending point of the length measurement is the right edge of the ground target; the starting point of the width measurement is the upper edge of the ground target 3 and the end point of the width measurement is the lower edge of the ground target.
The ground target measuring method based on the AR and the unmanned aerial vehicle monocular vision adopts the AR plotting technology to draw the ground target in the unmanned aerial vehicle picture, the actual length and the actual width of the ground target can be obtained according to the picture of the pan-tilt camera, the pixel of the ground target in the unmanned aerial vehicle picture and the pixel of the unmanned aerial vehicle picture, excessive matching hardware is not needed, the processing process is simple, and the method has wide applicability.
According to another aspect of the invention, the application of the ground target measurement method based on AR and unmanned aerial vehicle monocular vision in the unmanned aerial vehicle is provided, the method is suitable for a small unmanned aerial vehicle operation environment, the reliability of unmanned aerial vehicle reconnaissance is improved, and the size of the ground reconnaissance target can be sensed, calculated quickly and accurately obtained in advance.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. A ground target measuring method based on AR and unmanned aerial vehicle monocular vision is characterized by comprising the following steps:
s1 the unmanned aerial vehicle flies to a position S1 meters away from the ground target and hovers to obtain a first unmanned aerial vehicle picture;
s2, drawing a ground target in the first unmanned aerial vehicle picture by utilizing an AR plotting technology, and measuring a first length pixel and a first width pixel of the ground target in the first unmanned aerial vehicle picture;
s3, controlling the unmanned aerial vehicle to fly to a position S2 meters away from the ground target and hover to obtain a second unmanned aerial vehicle picture;
s4, drawing the ground target in the second unmanned aerial vehicle picture by utilizing an AR plotting technology, and measuring a second length pixel and a second width pixel of the ground target in the second unmanned aerial vehicle picture;
s5 calculating the ground target geometric dimension according to the data measured in the steps S2 and S4.
2. The method of claim 1, wherein in steps S1 and S3, the pan-tilt camera pitch angle of the drone is maintained at 90 degrees.
3. The method of claim 1, wherein in steps S1 and S3, the ground target is guaranteed to be located in the middle of the frame of the UAV.
4. The method for measuring a ground target based on AR and UAV monocular vision of claim 1, wherein in step S5, the geometric dimension of the ground target is calculated by the following formula:
in the formula, l is the actual length of the ground target, r is the focal length of the pan-tilt camera, M is the long frame of the pan-tilt camera, N is the short frame of the pan-tilt camera, a1 is the first length pixel of the ground target, a2 is the second length pixel of the ground target, M is the length pixel of the unmanned aerial vehicle frame, w is the actual width of the ground target, b1 is the first width pixel of the ground target, b2 is the second width pixel of the ground target, and N is the width pixel of the unmanned aerial vehicle frame.
5. The method of claim 1, wherein the height S1 and the height S2 have a relation of 1/2-2/1.
6. The method for measuring the ground target based on the AR and the unmanned aerial vehicle monocular vision of any one of claims 1 to 5, wherein the starting point of the length measurement is the left edge of the ground target, and the ending point of the length measurement is the right edge of the ground target; the starting point of the width measurement is the upper edge of the ground target and the ending point of the width measurement is the lower edge of the ground target.
7. Use of the method of any of claims 1 to 6 in a drone of a ground target measurement based on AR and drone monocular vision.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111538465.9A CN114353667A (en) | 2021-12-15 | 2021-12-15 | Ground target measurement method based on AR and unmanned aerial vehicle monocular vision and application thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111538465.9A CN114353667A (en) | 2021-12-15 | 2021-12-15 | Ground target measurement method based on AR and unmanned aerial vehicle monocular vision and application thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114353667A true CN114353667A (en) | 2022-04-15 |
Family
ID=81098979
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111538465.9A Pending CN114353667A (en) | 2021-12-15 | 2021-12-15 | Ground target measurement method based on AR and unmanned aerial vehicle monocular vision and application thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114353667A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114941989A (en) * | 2022-04-18 | 2022-08-26 | 东风汽车集团股份有限公司 | Vehicle-mounted unmanned aerial vehicle-based road width deficiency early warning method and system |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000121354A (en) * | 1998-10-16 | 2000-04-28 | Japan Aviation Electronics Industry Ltd | Range finding method |
CN103134489A (en) * | 2013-01-29 | 2013-06-05 | 北京凯华信业科贸有限责任公司 | Method of conducting target location based on mobile terminal |
CN105203034A (en) * | 2015-07-29 | 2015-12-30 | 四川大学 | Height and area measurement method based on monocular camera three-dimensional distance measurement model |
CN105758319A (en) * | 2016-03-21 | 2016-07-13 | 北京小米移动软件有限公司 | Method and device for measuring height of target object through mobile terminal |
CN107091636A (en) * | 2017-04-27 | 2017-08-25 | 广东容祺智能科技有限公司 | A kind of method of unmanned plane measurement tree and grass coverage and length |
CN108416091A (en) * | 2018-01-29 | 2018-08-17 | 华南农业大学 | A kind of measurement method of easy camera ground resolution and drone flying height relationship |
CN108680143A (en) * | 2018-04-27 | 2018-10-19 | 南京拓威航空科技有限公司 | Object localization method, device based on long-distance ranging and unmanned plane |
CN111339921A (en) * | 2020-02-24 | 2020-06-26 | 南京邮电大学 | Insect disease detection unmanned aerial vehicle based on lightweight convolutional neural network and detection method |
CN111457895A (en) * | 2020-03-31 | 2020-07-28 | 彩虹无人机科技有限公司 | Target size calculation and display method for photoelectric load of unmanned aerial vehicle |
CN111626987A (en) * | 2020-04-29 | 2020-09-04 | 南京邮电大学 | Vehicle detection method based on unmanned aerial vehicle and anchor-frame-free network |
-
2021
- 2021-12-15 CN CN202111538465.9A patent/CN114353667A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000121354A (en) * | 1998-10-16 | 2000-04-28 | Japan Aviation Electronics Industry Ltd | Range finding method |
CN103134489A (en) * | 2013-01-29 | 2013-06-05 | 北京凯华信业科贸有限责任公司 | Method of conducting target location based on mobile terminal |
CN105203034A (en) * | 2015-07-29 | 2015-12-30 | 四川大学 | Height and area measurement method based on monocular camera three-dimensional distance measurement model |
CN105758319A (en) * | 2016-03-21 | 2016-07-13 | 北京小米移动软件有限公司 | Method and device for measuring height of target object through mobile terminal |
CN107091636A (en) * | 2017-04-27 | 2017-08-25 | 广东容祺智能科技有限公司 | A kind of method of unmanned plane measurement tree and grass coverage and length |
CN108416091A (en) * | 2018-01-29 | 2018-08-17 | 华南农业大学 | A kind of measurement method of easy camera ground resolution and drone flying height relationship |
CN108680143A (en) * | 2018-04-27 | 2018-10-19 | 南京拓威航空科技有限公司 | Object localization method, device based on long-distance ranging and unmanned plane |
CN111339921A (en) * | 2020-02-24 | 2020-06-26 | 南京邮电大学 | Insect disease detection unmanned aerial vehicle based on lightweight convolutional neural network and detection method |
CN111457895A (en) * | 2020-03-31 | 2020-07-28 | 彩虹无人机科技有限公司 | Target size calculation and display method for photoelectric load of unmanned aerial vehicle |
CN111626987A (en) * | 2020-04-29 | 2020-09-04 | 南京邮电大学 | Vehicle detection method based on unmanned aerial vehicle and anchor-frame-free network |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114941989A (en) * | 2022-04-18 | 2022-08-26 | 东风汽车集团股份有限公司 | Vehicle-mounted unmanned aerial vehicle-based road width deficiency early warning method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11106203B2 (en) | Systems and methods for augmented stereoscopic display | |
US20210319575A1 (en) | Target positioning method and device, and unmanned aerial vehicle | |
CN111448476B (en) | Technique for sharing mapping data between unmanned aerial vehicle and ground vehicle | |
CN105203084B (en) | A kind of unmanned plane 3D panoramic vision devices | |
WO2022170878A1 (en) | System and method for measuring distance between transmission line and image by unmanned aerial vehicle | |
CN106444837A (en) | Obstacle avoiding method and obstacle avoiding system for unmanned aerial vehicle | |
US20200191556A1 (en) | Distance mesurement method by an unmanned aerial vehicle (uav) and uav | |
EP3591490B1 (en) | Obstacle avoidance method and device, and unmanned aerial vehicle | |
US8350894B2 (en) | System and method for stereoscopic imaging | |
US20110013016A1 (en) | Visual Detection of Clear Air Turbulence | |
CN110132226B (en) | System and method for measuring distance and azimuth angle of unmanned aerial vehicle line patrol | |
CN106019264A (en) | Binocular vision based UAV (Unmanned Aerial Vehicle) danger vehicle distance identifying system and method | |
CN108805910A (en) | More mesh Train-borne recorders, object detection method, intelligent driving system and automobile | |
CN210526874U (en) | Airborne three-light photoelectric pod system | |
CN105551032A (en) | Pole image collection system and method based on visual servo | |
CN110750153A (en) | Dynamic virtualization device of unmanned vehicle | |
CN106096207A (en) | A kind of rotor wing unmanned aerial vehicle wind resistance appraisal procedure based on multi-vision visual and system | |
CN112837207A (en) | Panoramic depth measuring method, four-eye fisheye camera and binocular fisheye camera | |
CN114353667A (en) | Ground target measurement method based on AR and unmanned aerial vehicle monocular vision and application thereof | |
CN112907647B (en) | Three-dimensional space size measurement method based on fixed monocular camera | |
CN112351173A (en) | Double-zoom-lens-based stability augmentation holder, unmanned aerial vehicle and target identification method | |
CN111399014A (en) | Local stereoscopic vision infrared camera system and method for monitoring wild animals | |
CN109708659B (en) | Distributed intelligent photoelectric low-altitude protection system | |
CN110989645A (en) | Target space attitude processing method based on compound eye imaging principle | |
CN204297108U (en) | Helicopter obstacle avoidance system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |