WO2018120350A1

WO2018120350A1 - Method and device for positioning unmanned aerial vehicle

Info

Publication number: WO2018120350A1
Application number: PCT/CN2017/072477
Authority: WO
Inventors: 雷志辉; 卞一杰; 杨凯斌; 贾宁
Original assignee: 深圳市道通智能航空技术有限公司; 湖南省道通科技有限公司
Priority date: 2016-12-28
Filing date: 2017-01-24
Publication date: 2018-07-05
Also published as: CN106774402A

Abstract

A method and device for positioning an unmanned aerial vehicle. The method comprises: generating a reference image during flight of an unmanned aerial vehicle (S101); acquiring a current image acquired at a current time (S102); and determining, according to the reference image and the current image, a current position of the unmanned aerial vehicle (S103). The reference image and the current image have a certain degree of correlation, and therefore the current position of the unmanned aerial vehicle can be determined according to the reference image and the current image. Compared to a fixed resolution in the prior art, the present invention enables better dynamic matching during a return trip of an unmanned aerial vehicle, thus reducing systematic errors, and improving positioning precision of the return trip.

Description

Method and device for positioning drone

The present application claims priority to Chinese Patent Application No. 201611240082.2, filed on Dec. 28, 2016, entitled,,,,,,,,,,,,,,,,,,, in.

Technical field

The invention relates to the field of UAV control, and in particular to a method and a device for positioning a UAV.

Background technique

UAVs have broad applications in disaster prevention and rescue, scientific investigations, etc., and flight control systems are an important part of drones, playing an important role in the intelligent and practical use of drones. Usually, after the flight control system is controlled by the flight control system to the destination, the drone can automatically return to the original route.

In order to realize the positioning when the drone is automatically returned to the air, in the prior art, the map data provided by the third party can usually be stored in the flight system of the drone, and then passed through a positioning device such as a Global Position System (GPS). To achieve the positioning and navigation of the drone. However, the resolution of the map data provided by the third party is related to the height of the drone from the ground. Generally, the higher the altitude of the drone's off-ground flight, the lower the resolution. Since the flying height of the drone during the operation will change frequently, the resolution of the ground target is likely to be large, and the matching accuracy is low, resulting in poor positioning accuracy when returning.

Therefore, how to improve the positioning accuracy has become a technical problem to be solved.

Summary of the invention

The technical problem to be solved by the present invention is how to improve the positioning accuracy.

To this end, according to the first aspect, an embodiment of the present invention discloses a method for positioning a drone, including:

During the flight of the drone, a reference image is generated; the current image acquired at the current time is acquired; and the current position of the drone is determined according to the reference image and the current image.

Optionally, generating a reference image includes: collecting a ground image during the flight of the drone; and splicing the ground image to obtain a reference image.

Optionally, during the flight of the drone, the ground image is collected, including: collecting the ground image during the flight of the drone from the starting position to the returning position.

Optionally, before the acquiring the current image collected at the current time, the method for positioning the UAV disclosed in this embodiment further includes: determining the return flight.

Optionally, the method for positioning the UAV disclosed in this embodiment further includes: receiving, by the controller, an instruction sent by the controller for indicating the return flight.

Optionally, after the generating the reference image, the method for positioning the UAV disclosed in this embodiment further includes: determining a reverse trajectory of the UAV flying from the starting position to the returning position.

Optionally, after determining the reverse trajectory, the method for positioning the unmanned aerial vehicle disclosed in this embodiment further includes: flying from the returning position to the starting position according to the reverse trajectory.

Optionally, determining a current location of the drone according to the reference image and the current image, including: matching the current image with the reference image, and obtaining the drone at the current time relative to the reference image a motion vector; determining, according to the motion vector, positioning information of the drone relative to the reference image at the current time; wherein the positioning information includes at least one of: a position of the drone, a height of the drone, a posture of the drone The direction of the drone, the speed of the drone and the heading of the drone.

Optionally, the current image is matched with the reference image to obtain a motion vector of the drone relative to the reference image at the current time, including: matching the current image with the reference image to obtain a scene of the drone relative to the reference at the current time. The motion vector of the image.

Optionally, the current image is matched with the reference image to obtain a motion vector of the drone relative to the reference image at the current time, including: selecting a feature point of the reference image, wherein the selected feature point is used as the reference feature point. Determining a feature point matching the reference feature point in the current image, wherein the matched feature point is used as the current feature point; matching the current feature point with the reference feature point to obtain a drone at the current time relative to the reference The motion vector of the image.

According to a second aspect, an embodiment of the present invention discloses an apparatus for positioning a drone, including:

a reference module for generating a reference image during the flight of the drone; an acquisition module for acquiring the current image acquired at the current time; and a positioning module for the reference image generated by the reference module and the current image acquired by the acquisition module , determine the current location of the drone.

Optionally, the reference module includes: a sampling unit, configured to collect a ground image during the flight of the drone; and a splicing unit configured to splicing the ground image collected by the sampling unit to obtain a reference image.

Optionally, the sampling unit is specifically configured to collect a ground image during the flight of the drone from the starting position to the returning position.

Optionally, the apparatus for positioning the UAV disclosed in this embodiment further includes: a determining module, Used to determine the return flight.

Optionally, the determining module is further configured to receive an instruction sent by the controller to indicate a return flight.

Optionally, the apparatus for positioning the UAV according to the embodiment further includes: a trajectory module, configured to determine, after the reference module generates the reference image, a reverse trajectory of the UAV flying from the starting position to the returning position.

Optionally, the device for positioning the UAV disclosed in this embodiment further includes: a returning module, configured to fly from the return position to the starting position according to the reverse trajectory determined by the trajectory module.

Optionally, the positioning module includes: a matching unit, configured to match the current image with the reference image to obtain a motion vector of the drone relative to the reference image at the current time; and a positioning information unit configured to determine the drone according to the motion vector Positioning information relative to the reference image at the current time; wherein the positioning information includes at least one of: a position of the drone, a height of the drone, a posture of the drone, an azimuth of the drone, a drone The speed and heading of the drone.

Optionally, the matching unit is specifically configured to perform scene matching on the current image and the reference image to obtain a motion vector of the drone relative to the reference image at the current time.

Optionally, the matching unit includes: a selecting subunit for selecting a feature point of the reference image, wherein the selected feature point is used as a reference feature point; and the feature point determining subunit is configured to determine the reference feature in the current image Point matching feature points, wherein the matched feature points are used as the current feature points; the vector subunits are used to match the current feature points with the reference feature points to obtain the movement of the drone relative to the reference image at the current time. Vector.

The technical solution of the present invention has the following advantages:

The method and device for positioning a drone according to an embodiment of the present invention generate a reference image during the flight of the drone, and the reference image can reflect the latest ground situation, and then obtain Taking the current image collected at the current time, since the reference image and the current image are acquired during the flight of the drone, there is a certain correlation between the reference image and the current image, and then, according to the reference image and the current image, Determining the current position of the drone; in the solution of the embodiment of the invention, the reference image is generated during the flight of the drone, and the current image is also acquired during the flight of the drone, and therefore, the generated reference The image can dynamically compensate for the difference in resolution generated during the flight of the UAV. Compared with the fixed resolution in the prior art, the UAV can better achieve dynamic matching during the return process, reducing system errors and thus improving The positioning accuracy of the return flight.

As an optional technical solution, after generating the reference image, determining a reverse trajectory of the drone flying from the starting position to the returning position, so that the drone can directly follow the reverse trajectory when flying from the returning position to the starting position. The return position is flying to the starting position, which reduces the return planning of the flight path and improves the efficiency of determining the flight path when returning. In addition, the drone can fly back to the starting position by following the reverse trajectory in the case of no signal or communication failure, so that the drone can smoothly return to the starting position.

In addition, usually the drone will plan a better trajectory such as bypassing obstacles when flying from the starting position to the returning position, so that the reverse trajectory according to the outward trajectory is from the returning position to the starting position. When flying, you can return to a better trajectory.

DRAWINGS

In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings to be used in the specific embodiments or the description of the prior art will be briefly described below, and obviously, the attached in the following description The figures are some embodiments of the invention, for the field For the sake of the skilled person, other drawings can be obtained from these drawings without any creative work.

1 is a flow chart of a method for positioning a drone according to an embodiment of the present invention;

2 is a flowchart of a method for matching a scene to obtain a motion vector of a drone according to an embodiment of the present invention;

3 is a schematic structural diagram of an apparatus for positioning a drone according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a system for positioning a drone according to an embodiment of the present invention.

detailed description

The technical solutions of the present invention will be clearly and completely described in the following with reference to the accompanying drawings. It is obvious that the described embodiments are a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

In the description of the present invention, it is to be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. The orientation or positional relationship of the indications is based on the orientation or positional relationship shown in the drawings, and is merely for the convenience of the description of the invention and the simplified description, rather than indicating or implying that the device or component referred to has a specific orientation, in a specific orientation. The construction and operation are therefore not to be construed as limiting the invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and are not to be construed as indicating or implying a relative importance or a prior order.

In the description of the present invention, it should be noted that the terms "installation", "connected", and "connected" are to be understood broadly, and, for example, may be fixed connections, unless explicitly stated and defined otherwise. It can also be a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or can be indirectly connected through an intermediate medium, or can be internal communication between two components, and can be a wireless connection. It can also be a wired connection. The specific meaning of the above terms in the present invention can be understood in a specific case by those skilled in the art.

Further, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not constitute a conflict with each other.

In order to improve the positioning accuracy of the drone flight, the embodiment discloses a method for positioning the unmanned aerial vehicle. Referring to FIG. 1 , a flow chart of the method for positioning the unmanned aerial vehicle is performed. The methods of positioning include:

In step S101, a reference image is generated during the flight of the drone.

In this embodiment, the ground image can be collected after the drone takes off from the starting position, and the ground image collected by the drone during the moving to the destination is spliced, and the stitched result is used as the reference image. The so-called ground image refers to an image taken by the drone in a bird's eye view during a flight, and the angle between the overhead viewing direction and the vertical direction is less than 90 degrees. Preferably, the overhead viewing direction may be vertically downward, in which case the angle of view of the overhead viewing angle is 0 degrees from the vertical.

The drone can store the generated reference image for subsequent use of the reference image. As an alternative, after the dive machine generates the reference image, the reference image can also be sent to other drones, so that other drones can also use the reference image. It should be noted that, for the same drone, since the hardware parameters of the drone do not change during the flight of the drone, the reference image generated by the drone itself can represent the drone. The way to go. The so-called departure trajectory refers to the flight path of the drone from the starting position to the destination position. trace.

Step S102: Acquire a current image collected at a current time.

After the reference image is generated, the current image acquired at the current time can be acquired during the flight of the drone.

For example, in the process of returning the drone, the drone acquires the image acquired by the image acquisition device on the drone at the current moment in order to determine the current time position.

Step S103, determining the current position of the drone based on the reference image and the current image.

In this embodiment, after the reference image is obtained, the current image and the reference image may be compared to obtain a difference between the current image and the reference image, and the motion vector of the drone may be estimated according to the difference, thereby determining the drone's motion vector. current position.

In an optional embodiment, in step S101, the operation of generating the reference image may include: collecting a ground image during the flight of the drone; and splicing the ground image to obtain a reference image. In a specific embodiment, the ground image may be collected at preset intervals, and the preset interval may be determined according to prior knowledge to determine a time interval preset in the time domain, or a preset distance interval in the position. The preset intervals may be equal intervals or non-equal intervals.

In the specific splicing process, the overall mode splicing may be used, or the segmentation mode may be used for image splicing. Specifically, in the splicing process, there is usually an overlapping area between adjacent frame images, and the front and rear two frames of the overlapping portion may be combined into a large seamless image. For two adjacent frames with overlapping images, the overlapping area of one of the images may be directly rounded off, and the extra portion of the image may be stitched to another frame image, and the fusion is performed in the seam region to obtain a mosaic image. .

In the embodiment of the present invention, the ground image is acquired during the flight of the drone from the starting position to the returning position. The so-called starting position refers to the position where the drone starts to take off; the so-called return position is Refers to the position where the drone starts to return to the starting position after taking off. Usually, the returning position is the destination of the drone, but in the specific implementation process, the returning position may also be the location where the drone receives the returning instruction during the flight to the destination. The return location can also be a location where the drone encounters a special situation in the process of flying to the destination to determine the need to return. For example, during the flight, there are sudden situations such as insufficient power, no GPS signal, and drone failure. At this time, the flight control system in the drone determines the return flight.

Optionally, before performing step S102, the method may further include:

In step S104, it is determined that the return flight.

In one of the embodiments, the drone may actively determine the return flight, for example, the drone encounters a special situation during the flight and needs to return. For example, when the drone is in a state of insufficient power, no GPS signal, or a drone failure during the flight, the flight control system in the drone determines the return flight. After flying to the destination to complete the task, the drone can also take the initiative to determine the need to return.

In another embodiment, the controller may also control the drone to return. Specifically, the drone receives an instruction sent by the controller to indicate a return flight. After receiving the instruction, the drone determines to return. In this embodiment, the controller may be a remote control dedicated to the drone, or a terminal that remotely controls the drone, such as a mobile terminal, a computer, a notebook, or the like.

In order to provide the returning trajectory reference for the drone when returning, optionally, after performing step S101, the method further includes:

Step S105, determining a reverse trajectory of the drone flying from the starting position to the returning position.

In this embodiment, for a drone, since the physical parameters of the drone have not changed during the flight, the captured image is in the process of flying from the starting position to the returning position. After splicing, the flight path of the drone can be determined according to the image attributes. This implementation In the example, the flight path from the return position to the starting position along the departure path forms a reverse trajectory of the drone flying from the starting position to the returning position. When the drone returns, the drone can perform the returning operation based on the reverse trajectory.

Optionally, the step S103 may specifically include: matching the current image with the reference image to obtain a motion vector of the drone relative to the reference image at the current time; and determining, according to the motion vector, the positioning of the drone relative to the reference image at the current time. information.

In this embodiment, the positioning information includes at least one of the following: the position of the drone, the height of the drone, the attitude of the drone, the azimuth of the drone, the speed of the drone, and the heading of the drone. . The direction of the UAV refers to the relative angle between the current image and the reference image acquired by the aircraft at the current time. The heading of the UAV refers to the actual flight direction of the UAV. When the current image is matched with the reference image, since the flight path of the returning process is the reverse trajectory of the outward trajectory, the motion vector of the current time of the drone relative to the reference image can be obtained by matching the current image with the reference image. The motion vector can obtain information such as the position, height, posture, and azimuth of the drone in the reference image at the current time, and thus, the position of the drone at the current time can be determined.

In a specific embodiment, when the current image is matched with the reference image to obtain a motion vector of the current time of the drone relative to the reference image, the current image and the reference image may be scene-matched to obtain a current time of the drone relative to the reference image. The motion vector, specifically, please refer to Figure 2. The method shown in Figure 2 includes:

Step S201, selecting feature points of the reference image, and the selected feature points are used as reference feature points.

You can select easily identifiable points or buildings as reference feature points, such as texture-rich Object edge points, etc. After the reference feature points are selected, the feature points can be described by mathematical methods such as gradient histograms and local random binary features.

Step S202, determining a feature point matching the reference feature point in the current image, and the feature point obtained by the matching is used as the current feature point.

In a particular embodiment, the pixels in the current image can be described by the same mathematical description, and the current feature points in the current image that match the reference feature points can be determined using mathematical knowledge.

Step S203, matching the current feature point with the reference feature point to obtain a motion vector of the drone relative to the reference image at the current time.

The current feature points and the reference feature points can be matched by an affine transformation model or a projective transformation model. A description of the affine transformation model or the projective transformation model is as follows.

(1) For the affine transformation model, the affine transformation model can be established by means of equations. Specifically, the transformation model established by the equations is as follows:

Where (x, y) is the coordinate of the reference feature point in the reference image, and (x', y') is the coordinate of the feature point matching the reference feature point in the current image, a, b, c, d, m, and n Transform parameters for affine. In this embodiment, when the matched feature points are three sets of feature points that are not collinear, the complete affine transformation parameters can be solved; when the matched feature points are more than three groups, the least squares solution can be solved. More precise affine transformation parameters.

In a specific embodiment, the affine transformation model can also be established by the form of a matrix. Specifically, the transformation model established by the matrix is as follows:

Where (x, y) is the coordinate of the reference feature point in the reference image, and (x', y') is the coordinate of the feature point in the current image that matches the reference feature point, a0, a1, a2, b0, b1, and b2 Transform parameters for affine. In this embodiment, when the matched feature points are three sets of feature points that are not collinear, the complete affine transformation parameters can be solved; when the matched feature points are more than three groups, the least squares solution can be solved. More precise affine transformation parameters.

The affine transformation parameters calculated from the affine transformation model can be used to represent the motion vector of the drone.

(2) For the projective transformation model, the projective transformation model can be established by means of equations. Specifically, the transformation model is established by the following formula:

Where (x, y) is the coordinate of the reference feature point in the reference image, and (x', y') is the coordinate of the feature point in the current image that matches the reference feature point, (w'x'w'y'w' And (wx wy w) are the homogeneous coordinates of (x, y) and (x', y', respectively.

For a projective transformation matrix, in a particular embodiment, a transformation matrix

Can be split into 4 parts, of which

Represents a linear transformation, [a31 a32] for translation, [a13 a23] ^T produces a projective transformation, a33=1.

The projective transformation matrix calculated from the projective transformation model can be used to represent the motion vector of the drone.

The embodiment also discloses a device for positioning the UAV. Referring to FIG. 3, the UAV return positioning device includes: a reference module 301, an acquisition module 302, and a positioning module 303, where:

The reference module 301 is configured to generate a reference image during the flight of the drone; the acquisition module 302 is configured to acquire the current image acquired at the current time; the positioning module 303 is configured to collect the reference image generated by the reference module 301 and the acquisition module 302. The current image determines the current location of the drone.

In an optional embodiment, the reference module 301 includes: a sampling unit, configured to collect a ground image during the flight of the drone; and a splicing unit configured to splicing the ground image collected by the sampling unit to obtain a reference image.

In an alternative embodiment, the sampling unit is specifically configured to acquire a ground image during the flight of the drone from the starting position to the return position.

It should be noted that the sampling unit may be an imaging device, such as a camera, a digital camera, etc.; the splicing unit may be a processor or a chip or the like. The acquisition module 302 can be an imaging device such as a camera, a digital camera, or the like. The location module 303 can be a processor or a chip. Alternatively, the sampling unit and the acquisition module 302 may be the same camera device.

In an optional embodiment, the method further includes: a determining module, configured to determine a return flight.

In an optional embodiment, the determining module is further configured to receive an instruction sent by the controller to indicate a return flight.

In one implementation, the determining module may be a wireless signal receiver, such as an antenna for receiving a WiFi signal, an antenna for receiving an LTE (Long Term Evolution) signal, or an antenna for receiving a Bluetooth signal. In another implementation, the determining module can also include a processor on this basis.

In an optional embodiment, the method further includes: a trajectory module, configured to determine, after the reference module 301 generates the reference image, a reverse trajectory of the drone flying from the starting position to the returning position.

In an optional embodiment, the method further includes: a returning module for flying from the returning position to the starting position according to the reverse trajectory determined by the trajectory module.

In an implementation manner, the foregoing trajectory module and the returning module may be a processor or a computing chip, respectively. Optionally, the above trajectory module and the returning module may be the same processor or a computing chip.

In an optional embodiment, the positioning module includes: a matching unit configured to match the current image with the reference image to obtain a motion vector of the drone relative to the reference image at the current time; and a positioning information unit configured to use the motion vector Determining the positioning information of the drone relative to the reference image at the current time; wherein the positioning information includes at least one of the following: the position of the drone, the height of the drone, the posture of the drone, and the orientation of the drone The speed of the drone and the heading of the drone.

In an optional embodiment, the matching unit is further configured to perform scene matching on the current image with the reference image to obtain a motion vector of the drone relative to the reference image at the current time.

In an optional embodiment, the matching unit includes: a selecting subunit for selecting a feature point of the reference image, wherein the selected feature point is used as a reference feature point; and the feature point determining subunit is configured to determine the current image a feature point matching the reference feature point, wherein the matched feature point is used as the current feature point; the vector sub-unit is used to match the current feature point with the reference feature point to obtain a drone relative to the current time The motion vector of the reference image.

This embodiment also discloses a drone, please refer to FIG. 4. The drone includes a body 401, an image capture device 402, and a processor (not shown), wherein:

The body 401 is used to carry various components of the drone, such as a battery, an engine (motor), and a camera Like first class;

The image capture device 402 is disposed on the body 401, and the image capture device 402 is configured to acquire images.

It should be noted that, in this embodiment, the image collection device 402 may be a camera. Alternatively, image acquisition device 402 can be used for panoramic photography. For example, the image capture device 402 can include a multi-view camera, can also include a panoramic camera, and can include both a multi-view camera and a panoramic camera to capture images or video from multiple angles.

The processor is for performing the method disclosed in the embodiment shown in FIG.

The method and device for positioning a drone provided by the embodiment of the present invention provide a method and a device for positioning a drone according to an embodiment of the present invention, and generate a reference image during the flight of the drone, and the reference image can reflect The latest ground situation, and then, the current image acquired at the current time is acquired. Since the reference image and the current image are acquired during the flight of the drone, there is a certain correlation between the reference image and the current image, and then, The current position of the drone can be determined according to the reference image and the current image. In the solution of the embodiment of the present invention, the reference image is generated during the flight of the drone, and the current image is acquired during the flight of the drone. Therefore, the generated reference image can dynamically compensate for the difference in resolution generated during the flight of the drone, and the dynamic matching can be better achieved in the return process of the drone compared to the fixed resolution in the prior art. The system error is reduced, thereby improving the positioning accuracy of the return flight.

In an optional embodiment, after generating the reference image, determining a reverse trajectory of the drone flying from the starting position to the returning position, so that the drone can directly follow the reverse trajectory when flying from the returning position to the starting position. Flying from the return position to the starting position reduces the amount of return planning for the flight path and improves the efficiency of determining the flight path when returning. In addition, drones encounter no signal Or in the case of a communication failure, the UAV can smoothly return to the starting position by flying from the returning position to the starting position in accordance with the reverse trajectory.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The device is implemented in a flow chart A function specified in a block or blocks of a process or multiple processes and/or block diagrams.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

It is apparent that the above-described embodiments are merely illustrative of the examples, and are not intended to limit the embodiments. Other variations or modifications of the various forms may be made by those skilled in the art in light of the above description. There is no need and no way to exhaust all of the implementations. Obvious changes or variations resulting therefrom are still within the scope of the invention.

Claims

A method for positioning a drone, characterized in that it comprises:

During the flight of the drone, a reference image is generated;

Obtain the current image collected at the current time;

Determining a current location of the drone based on the reference image and the current image.
The method of claim 1 wherein said generating said reference image comprises:

Collecting a ground image during the flight of the drone;

The ground image is spliced to obtain the reference image.
The method of claim 2, wherein during the flying of the drone, acquiring the ground image comprises:

The ground image is acquired during the flight of the drone from the starting position to the return position.
The method according to any one of claims 1 to 3, wherein before the acquiring the current image acquired at the current time, the method further comprises:

Determine the return flight.
The method of claim 4, wherein prior to determining the return flight, the method further comprises:

The instruction sent by the controller to indicate the return flight.
The method of any of claims 1-5, wherein after the generating the reference image, the method further comprises:

Determining the reverse trajectory of the drone from the starting position to the returning position.
The method of claim 6 wherein after determining the reverse trajectory, the method further comprises:

Flying from the return position to the starting position in accordance with the reverse trajectory.
The method according to any one of claims 1 to 7, wherein the determining the current location of the drone based on the reference image and the current image comprises:

Matching the current image with the reference image to obtain a motion vector of the drone relative to the reference image at the current time;

Determining, according to the motion vector, positioning information of the drone relative to the reference image at the current time;

The positioning information includes at least one of the following:

The position of the drone, the height of the drone, the attitude of the drone, the orientation of the drone, the speed of the drone, and the heading of the drone.
The method according to claim 8, wherein said matching said current image with said reference image to obtain a motion vector of said drone at said current time relative to said reference image comprises :

Performing scene matching on the current image and the reference image to obtain a motion vector of the drone relative to the reference image at the current time.
The method according to claim 9, wherein said matching the current image with the reference image to obtain a motion vector of the drone relative to the reference image at the current time, include:

Selecting feature points of the reference image, wherein the selected feature points are used as reference feature points;

Determining a feature point matching the reference feature point in the current image, wherein the matched feature point is used as a current feature point;

Matching the current feature point with the reference feature point to obtain a motion vector of the drone relative to the reference image at the current time.
A device for positioning a drone, characterized in that it comprises:

a reference module for generating a reference image during flight of the drone;

An acquisition module, configured to acquire a current image collected at a current time;

And a positioning module, configured to determine a current location of the drone according to the reference image generated by the reference module and the current image collected by the acquisition module.
The device of claim 11 wherein said reference module comprises:

a sampling unit, configured to collect a ground image during the flight of the drone;

And a splicing unit, configured to splicing the ground image collected by the sampling unit to obtain the reference image.
The apparatus according to claim 12, wherein said sampling unit is specifically configured to acquire said ground image during said flying of said drone from a starting position to a returning position.
The device of any of claims 11-13, further comprising:

A determination module for determining the return flight.
The apparatus according to claim 14, wherein said determining module is further configured to receive an instruction sent by the controller for indicating a return flight.
The device of any of claims 11-15, further comprising:

a trajectory module, configured to determine, after the reference module generates the reference image, a reverse trajectory of the drone flying from a starting position to a returning position.
The device of claim 16 further comprising:

a returning module for flying from the returning position to the starting position according to a reverse trajectory determined by the trajectory module.
The device according to any one of claims 11-17, wherein the positioning module comprises:

a matching unit, configured to match the current image with the reference image to obtain a motion vector of the drone relative to the reference image at the current time;

a positioning information unit, configured to determine positioning information of the drone relative to the reference image at the current time according to the motion vector;

The positioning information includes at least one of the following:

Position of the drone, height of the drone, attitude of the drone, the absence The orientation of the man machine, the speed of the drone, and the heading of the drone.
The device according to claim 18, wherein the matching unit is specifically configured to perform scene matching on the current image and the reference image to obtain the drone at the current time relative to the reference The motion vector of the image.
The device of claim 19, wherein the matching unit comprises:

Selecting a subunit for selecting a feature point of the reference image, wherein the selected feature point is used as a reference feature point;

a feature point determining subunit, configured to determine a feature point matching the reference feature point in the current image, wherein the matched feature point is used as a current feature point;

And a vector subunit, configured to match the current feature point with the reference feature point to obtain a motion vector of the drone relative to the reference image at the current time.