WO2021134715A1

WO2021134715A1 - Control method and device, unmanned aerial vehicle and storage medium

Info

Publication number: WO2021134715A1
Application number: PCT/CN2019/130971
Authority: WO
Inventors: 周游; 刘洁; 杜劼熹
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2019-12-31
Filing date: 2019-12-31
Publication date: 2021-07-08
Also published as: CN113646606A

Abstract

A control method and device, an unmanned aerial vehicle and a storage medium. The method comprises: acquiring an initial image obtained by means of a photographic apparatus (123) of an unmanned aerial vehicle (12) photographing a target object, wherein the photographic apparatus (123) is carried on a gimbal (122) of the unmanned aerial vehicle (12); controlling the photographic attitude of the photographic apparatus (123) according to the initial image, so that the photographic direction of the photographic apparatus (123) is substantially perpendicular to a target plane of the target object; in response to the photographic direction of the photographic apparatus (123) being substantially perpendicular to the target plane, acquiring a target image obtained by means of the photographic apparatus (123) photographing the target plane, and the distance between the photographic apparatus (123) and the target plane; and determining, according to the target image and the distance, a target plane or size parameters of an object to be measured on the target plane. By means of the method, the size of an object to be measured can be measured by means of controlling the photographic attitude of the photographic apparatus (123) without the need for a specialized instrument and device, thereby simplifying user operations, improving the flexibility and effectiveness of measurement and improving the user experience.

Description

Control method, equipment, unmanned aerial vehicle and storage medium

Technical field

The present invention relates to the field of control technology, in particular to a control method, equipment, unmanned aerial vehicle and storage medium.

Background technique

With the development of current technology, drones are used in more and more scenarios. Making drones fly autonomously is the goal of the development of drone technology. For some industrial applications that need to measure the distance or size of some buildings, signs, etc., the commonly used measurement method is to use the position information of the Global Positioning System (GPS) or the high-precision real-time dynamic differential technology (Real-time kinematic, RTK). ) The positioning system performs measurement. The measurement process is more troublesome and requires professional instruments and equipment. For some difficult-to-reach places, the measurement methods are even more limited. Therefore, how to more effectively control the UAV to measure the distance of the object to be measured is of great significance.

Summary of the invention

The embodiments of the present invention provide a control method, equipment, unmanned aerial vehicle and storage medium, which can measure the size of the object to be measured by controlling the shooting posture of the shooting device without the need for professional equipment, thereby improving the flexibility and effectiveness of the measurement .

In the first aspect, an embodiment of the present invention provides a control method, including:

Acquiring an initial image obtained by photographing a target object by a photographing device of a drone, wherein the photographing device is carried on a pan/tilt of the drone;

Controlling the shooting posture of the shooting device according to the initial image so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object;

In response to the photographing direction of the photographing device being substantially perpendicular to the target plane, acquiring a target image obtained by photographing the target plane by the photographing device and the distance between the photographing device and the target plane;

The size parameter of the target plane or the object to be measured on the target plane is determined according to the target image and the distance.

In the second aspect, an embodiment of the present invention provides a control device, including a memory and a processor;

The memory is used to store programs;

The processor is used to call the program, and when the program is executed, it is used to perform the following operations:

In the third aspect, an embodiment of the present invention provides a drone, including:

body;

The power system configured on the fuselage is used to provide the moving power for the UAV;

Processor for:

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

The embodiment of the present invention can control the shooting posture of the shooting device according to the initial image obtained by the shooting device of the drone to shoot the target object, so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object. On the camera’s PTZ, and in response to the shooting direction of the shooting device being substantially perpendicular to the target plane, the target image obtained by the shooting device shooting the target plane and the distance between the shooting device and the target plane are acquired, so as to determine the distance between the shooting device and the target plane. The target plane or the size parameter of the object to be measured on the target plane. Through this embodiment, it is possible to measure the size of the object to be measured by controlling the shooting posture of the shooting device without the need for professional equipment, which simplifies user operations, improves the flexibility and effectiveness of measurement, and improves user experience.

Description of the drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings that need to be used in the embodiments. Obviously, the drawings in the following description are only some of the present invention. Embodiments, for those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings.

Fig. 1 is a schematic structural diagram of a control system provided by an embodiment of the present invention;

2 is a schematic flowchart of a control method provided by an embodiment of the present invention;

3 is a schematic diagram of controlling the shooting posture of a shooting device according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a measurement method provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of determining a size parameter of an object to be measured according to an embodiment of the present invention;

FIG. 6 is a schematic flowchart of another control method provided by an embodiment of the present invention;

Figure 7a is a schematic diagram of a feature point provided by an embodiment of the present invention;

FIG. 7b is a schematic diagram of obtaining a target image according to an embodiment of the present invention;

FIG. 8 is a schematic flowchart of another control method provided by an embodiment of the present invention;

Fig. 9 is a schematic structural diagram of a control device provided by an embodiment of the present invention.

Detailed ways

The following clearly describes the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

In the following, some embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

The control method provided in the embodiments of the present invention can be executed by a control system, where the control system can include a control device and a drone; in some embodiments, the control device can be installed on the drone, In some embodiments, the control device may be spatially independent from the drone. In some embodiments, the control device may be a component of the drone, that is, the drone includes a control device. In some embodiments, the control device may include, but is not limited to, one or more of a smart phone, a tablet computer, a laptop computer, and a wearable device. In some embodiments, the control method can also be applied to other movable devices such as unmanned vehicles, unmanned boats, VR/AR glasses, and movable robots including camera devices.

The control system provided by the embodiment of the present invention will be schematically described below with reference to FIG. 1.

Please refer to FIG. 1, which is a schematic structural diagram of a control system provided by an embodiment of the present invention. The control system includes: a control device 11 and an unmanned aerial vehicle 12. In some embodiments, the drone 12 includes a power system 121, and the power system 121 is used to provide power for the drone 12 to move; in some embodiments, the drone 12 is mounted on A pan/tilt 122 is mounted on the pan/tilt 122, and a camera 123 is mounted on the pan/tilt 122. In some embodiments, the drone 12 and the control device 11 are independent of each other. For example, the control device 11 can be set in a cloud server, which is connected to the drone 12 and/or other devices on the drone 12 (such as the PTZ 122). ) Establish a communication connection. In some embodiments, the control device 11 may be a controller. In some embodiments, the photographing device 123 includes, but is not limited to, a camera, a camera, an image acquisition sensor, and the like.

In the embodiment of the present invention, the control device 11 may obtain the initial image obtained by the photographing device 123 of the drone 12 photographing the target object, and control the photographing posture of the photographing device 123 according to the initial image, so that the photographing direction of the photographing device 123 The target plane is substantially perpendicular to the target object, and in response to the shooting direction of the shooting device 123 being substantially perpendicular to the target plane, the target image obtained by the shooting device 123 shooting the target plane and the distance between the shooting device 123 and the target plane are acquired, so that according to the target The image and distance determine the target plane or the size parameters of the object to be measured on the target plane.

The control method provided by the embodiments of the present invention will be schematically described below by taking a drone as an example in conjunction with the accompanying drawings.

Please refer to FIG. 2 for details. FIG. 2 is a schematic flowchart of a control method provided by an embodiment of the present invention. The method may be executed by a control device, and the specific explanation of the control device is as described above. Specifically, the method of the embodiment of the present invention includes the following steps.

S201: Acquire an initial image obtained by photographing a target object by a photographing device of a drone, wherein the photographing device is carried on a pan-tilt of the drone.

In the embodiment of the present invention, the control device may obtain the initial image obtained by shooting the target object by the camera of the drone, wherein the camera is carried on the pan/tilt of the drone.

S202: Control the shooting posture of the shooting device according to the initial image, so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object.

In the embodiment of the present invention, the control device may control the shooting posture of the shooting device according to the initial image, so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object. In some embodiments, the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object means that the shooting direction of the shooting device is 90 degrees to the target plane of the target object within a specified error range.

In one embodiment, since the camera is carried on the drone's pan/tilt and moves with the rotation of the pan/tilt, the control device can control the shooting attitude of the camera according to the initial image according to the The initial image controls one or more of the position of the drone, the attitude of the drone, and the attitude of the pan/tilt to control the shooting attitude of the camera. In some embodiments, the attitude of the drone includes any one or more of the pitch angle, roll angle, and yaw angle of the drone.

In one embodiment, when controlling the shooting posture of the shooting device according to the initial image, the control device may acquire multiple feature points in the area image corresponding to the target plane, wherein the initial image includes the An image of the area corresponding to the target plane, and controlling the shooting posture of the shooting device according to the positions of the plurality of feature points on the initial image. In some embodiments, the multiple feature points may be multiple feature points selected by the user in the region image corresponding to the target plane; in some embodiments, the multiple feature points include at least three the above. In some embodiments, the positions of the multiple feature points may be arbitrary position points (such as vertices of a polygon) of the regional image, which is not specifically limited here. Through this implementation manner, the control device can obtain multiple feature points selected by the user according to requirements, thereby improving the flexibility of feature point selection and improving user experience.

In one embodiment, when acquiring multiple feature points in the area image corresponding to the target plane, the control device may determine the area image corresponding to the target plane from the initial image, and run a feature point extraction algorithm to A plurality of feature points are extracted from the regional image. The feature point extraction algorithm can automatically extract multiple feature points from the regional image.

In an embodiment, the control device may also send the initial image to the control terminal communicatively connected with the drone, so that the display device of the control terminal displays the initial image and obtains the control terminal The sent target plane indication information, where the target plane indication information is determined by the control terminal detecting the user's target area selection operation on the display device. In some embodiments, the target area selection operation includes, but is not limited to, a frame selection operation. In some embodiments, the control terminal may include, but is not limited to, smart phones, tablets, laptops, wearable devices, etc.; in some embodiments, the display device of the control terminal may be the Control the user interface of the terminal. In some embodiments, the display device has a touch function (such as a touch screen).

In one embodiment, when the control device acquires multiple feature points in the area image corresponding to the target plane, it may send the initial image to the control terminal communicatively connected with the drone, so that the The display device of the control terminal displays the initial image, and obtains characteristic point indication information sent by the control terminal, where the characteristic point indication information is determined by the control terminal detecting the user's characteristic point selection operation on the display device . In some embodiments, the feature point selection operation includes, but is not limited to, a click operation.

It can be seen that through this implementation manner, the user can determine the target plane of the target object from the initial image through different operation methods such as box selection or click operation according to requirements, which improves the flexibility of determining the target plane and improves the user experience.

In one embodiment, when the control device controls the shooting posture of the photographing device according to the positions of the plurality of feature points on the initial image, it may be based on the positions of the plurality of feature points on the initial image. The normal vector of the target plane is determined, and the shooting attitude of the camera is controlled according to the normal vector.

In one embodiment, when the control device determines the normal vector of the target plane based on the positions of the multiple feature points on the initial image, it is assumed that the three feature points P _k and P _{k that are not on a straight line are used. +1} and P _k+2 constitute the target plane, the plane usage vector

, Then the normal vector of the target plane can be calculated by the following formula (1):

By determining the normal vector of the target plane, the purpose is to control the shooting posture of the photographing device according to the normal vector so that the optical axis direction of the photographing device is parallel to the normal vector of the target plane.

In an embodiment, the number of the feature points is 3; when the control device controls the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, it may be based on the 3 feature points. The location of the feature point on the initial image determines the location of the space point corresponding to the 3 feature points, and the rotation matrix is determined according to the location of the space point corresponding to the 3 feature points, wherein the rotation matrix is The 3 projection pixels of the 3 spatial points projected onto the initial image satisfy: the U axis coordinate of the first projection pixel is equal to the U axis coordinate of the second projection pixel, and the V axis coordinate of the first projection pixel is equal to The V-axis coordinates of the third projection pixel; and controlling the shooting posture of the shooting device according to the rotation matrix. In some embodiments, the U axis is the abscissa in the camera coordinate system, and the V axis is the ordinate in the camera coordinate system. Wherein, the connecting line between the first space point and the second space point in the space points corresponding to the three characteristic points is substantially perpendicular to the connecting line between the second space point and the third space point. In some cases, the display device of the control terminal may display prompt information, where the prompt information is used to prompt the user to select the three characteristic points from the image displayed by the display device.

By determining the rotation matrix, the rotation matrix can be converted into an angle, and the position of the drone and the attitude of the pan/tilt can be controlled to control the shooting attitude of the shooting device, so that the optical axis of the shooting device is perpendicular to the target plane, that is, the optical axis is perpendicular to the target. The normal vectors of the plane are parallel.

In one embodiment, when the control device determines the rotation matrix according to the positions of the spatial points corresponding to the three feature points, it can obtain the parameters of the photographing device, and according to the positions of the spatial points corresponding to the three feature points And the parameters of the photographing device determine the rotation matrix. In some embodiments, the parameters of the photographing device include focal length and optical center.

Specifically, it can be described in conjunction with FIG. 3 and formula (2.1), formula (2.2), formula (2.3), and formula (3). FIG. 3 is a schematic diagram of controlling the shooting attitude of a shooting device according to an embodiment of the present invention, as shown in FIG. As shown in 3, assuming that 3 feature points are determined on the initial image 31, and these 3 feature points are x ₁ , x ₂ , x ₃ , taking x ₁ as an example, normalized to the camera coordinate system is the following formula (2.1):

Among them, c _x and c _y are the positions of the optical center of the photographing device (such as a camera), f is the focal length, and u ₁ and ν ₁ are the abscissa and ordinate of x ₁ on the image, and the unit is pixel.

Similarly, x _{2 is} normalized to the camera coordinate system as the following formula (2.2):

Among them, u ₂ and ν ₂ are the abscissa and ordinate of x ₂ on the image, and the unit is pixel.

Similarly, x _{3 is} normalized to the camera coordinate system as the following formula (2.3):

Among them, u ₃ and ν ₃ are the abscissa and ordinate of x ₃ on the image, and the unit is pixel.

If x ₁ x ₂ ⊥x ₁ x ₃ , a rotation matrix R can be determined according to the following formula (3):

_{_{Wherein, x '1 = Rx 1,}} x' 2 = Rx 2, x '3 = Rx 3, x' 1 (u) represented by x _'1 on the abscissa in the image, x' ₁ (v) represented by x _'1 The ordinate on the image is in pixels.

After the rotation matrix R is determined, the rotation matrix is converted into an angle, and one or more of the position of the drone, the attitude of the gimbal, and the attitude of the drone are controlled to make the adjusted x′ ₁ x′ ₂ ⊥x′ ₁ x′ ₃ , and the shooting direction of the shooting device is basically perpendicular to the target plane at this time, and a target image 32 with the shooting direction of the shooting device shown in FIG. 3 substantially perpendicular to the target plane is obtained.

It can be seen that the rotation matrix can be determined according to the positions of the three feature points on the initial image and the parameters of the shooting device, thereby helping to control the shooting posture of the shooting device according to the rotation matrix.

S203: In response to the photographing direction of the photographing device being substantially perpendicular to the target plane, acquire a target image obtained by photographing the target plane by the photographing device and the distance between the photographing device and the target plane.

In the embodiment of the present invention, the control device may respond to the shooting direction of the shooting device being substantially perpendicular to the target plane, acquiring the target image obtained by the shooting device shooting the target plane, and the distance between the shooting device and the target plane. distance.

In one embodiment, the drone includes a distance measuring device carried on the pan/tilt, wherein the measuring direction of the distance measuring unit is substantially parallel to the optical axis direction of the photographing device; the control device is acquiring When determining the distance between the imaging device and the target plane, the distance between the imaging device and the target plane can be measured by the distance measuring device. In some embodiments, the distance measuring device is a laser distance measuring device. In some embodiments, the distance measuring device and the photographing device are installed together, and both are carried on the pan/tilt of the drone, and move with the rotation of the pan/tilt.

S204: Determine a target plane or a size parameter of the object to be measured on the target plane according to the target image and the distance.

In the embodiment of the present invention, the control device may determine the target plane or the size parameter of the object to be measured on the target plane according to the target image and the distance. In some embodiments, the size parameter includes one or more of length, width, and area.

In an embodiment, FIG. 4 can be used as an example for description. FIG. 4 is a schematic diagram of a measurement method provided by an embodiment of the present invention. As shown in Figure 4, assuming that the shooting direction of the camera 41 is substantially perpendicular to the target plane, measuring the object to be measured 421 on the ground 42 to obtain the target image 43, the object to be measured 431 is determined from the target image 43, the focal length of the camera 41 is f, The distance between the camera 41 and the ground 42 measured by the device (not shown in Fig. 4) is z, and the length of the object to be measured 431 on the target image 43 is d1 and the area is s1. Then the measured distance on the ground 42 can be calculated The real length d2 of the object 421 is the following formula (4), and the real area s2 is the following formula (5):

In one embodiment, when the control device determines the size parameter of the target plane or the object to be measured on the target plane according to the target image and the distance, it may be based on the target plane or the object to be measured on the target plane. The number of pixels of the image and the distance determine the target plane or the size parameter of the object to be measured on the target plane.

In an embodiment, each pixel contains a size parameter, and the control device can determine the target plane composed of multiple pixels according to the number of pixels of the target plane or the object to be measured in the target image and the size parameter of each pixel. Or the size parameter of the object to be measured on the target plane.

In one embodiment, when determining the size parameter of the object to be measured on the target plane according to the target image and the distance, the control device may recognize the target image to determine the object to be measured; or , Receiving the object-to-be-measured indication information sent by the control terminal of the drone, and determining the object-to-be-measured according to the object-to-be-measured indication information, wherein the object-to-be-measured indication information is that the control terminal displays the target image by detecting the user Control the selection operation of the object to be measured on the display device of the terminal; thereby determining the size parameter of the determined object to be measured according to the target image and the distance. In some embodiments, the object to be measured may be a target image. In some embodiments, the target image may include an object to be measured. In some embodiments, the object to be measured may be a target object. In other embodiments, the object to be tested may not be a target object.

In one embodiment, when the control device determines the determined size parameter of the object to be measured according to the target image and the distance, it can acquire the circumscribed polygonal area of the object to be measured in the target image, and The size parameter of the object to be measured is determined according to the circumscribed polygonal area and the distance.

Taking Figure 5 as an example, Figure 5 is a schematic diagram of determining the size parameters of the object to be measured according to an embodiment of the present invention. As shown in Figure 5, assuming that the object to be measured is curve 51 (such as a dam crack), the control device can According to the curve 51 (such as a dam crack), the circumscribed polygonal area 53 (such as a rectangle) corresponding to the curve 51 is determined on the target image 52, and according to the circumscribed polygonal area 53 and the distance between the shooting device and the target plane Determine the size parameters of the curve 51 (such as the length and width of the rectangle).

In one embodiment, the control device may also send the target image to the control terminal communicatively connected with the drone so that the display device of the control terminal displays the target image, and obtains the control terminal to send The indication information of the object to be tested is determined by the control terminal detecting the user's selection operation of the object to be tested on the display device.

Through this embodiment, the user can independently select the object to be tested from the display device of the control terminal that displays the target image according to requirements, thereby improving the flexibility of selecting the object to be tested and improving the user experience.

In one embodiment, the control device may also place the target image in a preset recognition model of the object to be measured to obtain the object-to-be-measured indication information output by the model, and determine the object according to the indication information of the object-to-be-measured The object to be measured on the target plane. The preset object-to-be-tested recognition model can automatically recognize the object-to-be-tested indication information, thereby improving the efficiency of determining the object to be tested, and meeting the user's intelligence and automation requirements for determining the object to be tested.

The embodiment of the present invention can control the shooting posture of the shooting device according to the initial image obtained by the shooting device of the drone to shoot the target object, so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object. On the camera’s PTZ, and in response to the shooting direction of the shooting device being substantially perpendicular to the target plane, the target image obtained by the shooting device shooting the target plane and the distance between the shooting device and the target plane are acquired, so as to determine the distance between the shooting device and the target plane. The target plane or the size parameter of the object to be measured on the target plane. Through this implementation mode, professional instruments and equipment are not required, cost is reduced, and the size of the object to be measured is directly measured by controlling the shooting posture of the shooting device, which simplifies user operations, improves the flexibility and effectiveness of measurement, and improves user experience.

Please refer to FIG. 6 for details. FIG. 6 is a schematic flowchart of another control method provided by an embodiment of the present invention. The method may be executed by a control device, wherein the specific explanation of the control device is as described above. The difference between the embodiment of the present invention and the embodiment described in FIG. 2 is that the embodiment of the present invention is a schematic description of manually or automatically selecting multiple feature points, thereby controlling the shooting posture of the shooting device according to the position information of the multiple feature points. Specifically, the method of the embodiment of the present invention includes the following steps.

S601: Acquire an initial image obtained by photographing a target object by a camera of the drone, where the camera is carried on the pan/tilt of the drone.

In the embodiment of the present invention, the control device may obtain the initial image obtained by shooting the target object by the camera of the drone, wherein the camera is carried on the pan/tilt of the drone. The specific embodiments and examples are described above, and will not be repeated here.

S602: Acquire multiple feature points in an area image corresponding to a target plane, where the initial image includes an area image corresponding to the target plane.

In the embodiment of the present invention, the control device may acquire multiple feature points in the area image corresponding to the target plane, where the initial image includes the area image corresponding to the target plane of the target object. In some embodiments, the multiple feature points may be multiple feature points selected by the user in the region image corresponding to the target plane; in some embodiments, the multiple feature points include at least three Or 3 or more. In some embodiments, the positions of the multiple feature points may be arbitrary position points (such as vertices of a polygon) of the regional image, which is not specifically limited here.

Taking FIG. 7a as an example, FIG. 7a is a schematic diagram of a feature point provided by an embodiment of the present invention. As shown in FIG. 7a, the control device can obtain 4 feature points selected by the user on the display device of the control terminal that displays the initial image. , Which are respectively a feature point 711, a feature point 712, a feature point 713, and a feature point 714, where the initial image includes the area image 73 corresponding to the target plane 72 of the target object.

In one embodiment, when acquiring multiple feature points in the area image corresponding to the target plane, the control device may determine the area image corresponding to the target plane from the initial image, and run a feature point extraction algorithm to obtain the Multiple feature points are extracted from the regional image. In some embodiments, the feature point algorithm includes feature point extraction rules. In one example, the extraction rule may be the extraction of corner points (such as the vertices of a polygon).

Taking Figure 7a as an example, the control device can determine the area image 73 corresponding to the target plane 72 after acquiring the initial image obtained by the shooting device shooting the target object, and run the feature point extraction algorithm to extract the feature points from the area image 73 711, feature point 712, feature point 713, feature point 714.

Through this implementation manner, it is possible to avoid the user from manually selecting feature points, to achieve the user's automation and intelligence requirements for selecting feature points, to improve the efficiency of selecting feature points, and to improve user experience.

In an embodiment, the control device may also send the initial image to the control terminal communicatively connected with the drone, so that the display device of the control terminal displays the initial image and obtains the control terminal The sent target plane indication information, where the target plane indication information is determined by the control terminal detecting the user's target area selection operation on the display device.

In one embodiment, when the target area selection operation is a frame selection operation, the user can frame and select the closed area including the target object on the display device according to the position of the target object displayed on the display device of the control terminal. , And generate target plane indication information, where the target plane indication information is used to indicate that the enclosed area including the target object selected by the frame selection operation box is determined to be the target plane of the target object.

For example, assuming that the control device sends the acquired initial image to the control terminal, and displays the initial image on the display interface of the control terminal, the user can display the initial image on the display interface according to the position of the target object on the initial image of the display interface. The enclosed area including the target object is selected by frame, and target plane indication information is generated. The control terminal may send the generated target plane indication information to the control device, so that the control device can determine, according to the indication of the target plane indication information, that the enclosed area including the target object selected by the frame selection operation is the target object The target plane.

It can be seen that through this implementation manner, the user can select the target plane of the target object from the initial image according to requirements, which improves the flexibility of determining the target plane and improves the user experience.

In one embodiment, when the control device acquires multiple feature points in the area image corresponding to the target plane, it may send the initial image to the control terminal communicatively connected with the drone, so that the control terminal The display device of the display device displays the initial image, and obtains the characteristic point indication information sent by the control terminal, where the characteristic point indication information is determined by the control terminal detecting a user's characteristic point selection operation on the display device. In some embodiments, the feature point selection operation includes, but is not limited to, a click operation.

In one embodiment, when the feature point selection operation is a click operation, the user can click 3 or more feature points according to the position of the target object displayed on the display device of the control terminal, so that the control terminal can According to the position information and/or click sequence of 3 or more characteristic points determined by the user on the display interface, the characteristic point indication information is generated, wherein the characteristic point indication information is used to indicate that the determination is based on the 3 The location information of one or more feature points and/or the closed area including the target object generated by the click sequence is the target plane of the target object.

For example, assuming that the control device sends the acquired initial image to the control terminal, and displays the initial image on the display interface of the control terminal, the user can display the initial image on the display interface according to the position of the target object on the initial image of the display interface. Click 4 feature points to generate feature point indication information based on these 4 feature points. The control terminal may send the generated characteristic point indication information to the control device, so that the control device can determine the enclosed area generated by the four characteristic points as the target plane of the target object according to the indication of the characteristic point indication information.

It can be seen that through this implementation, the user can select multiple feature points from the initial image by clicking according to requirements, so as to generate feature point indication information based on the multiple feature points, and send the feature point indication information to the control device. The instruction control device generates a target plane according to the multiple feature points, thereby improving the flexibility of determining the target plane and improving the user experience.

S603: Control the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object.

In the embodiment of the present invention, the control device may control the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, so that the shooting direction of the shooting device is substantially perpendicular to the direction of the target object. Target plane.

In an embodiment, the control device may control one or more of the position of the drone, the attitude of the drone, and the attitude of the pan/tilt according to the positions of the multiple feature points on the initial image. , To control the shooting posture of the shooting device.

Taking FIG. 7a as an example, after determining the area image 73 corresponding to the target plane 72, and extracting the feature points 711, 712, 713, and 714 from the area image 73, the control device can use the feature points 711 The position of the feature point 712, the feature point 713, and the feature point 714 on the initial image adjust one or more of the position of the drone, the attitude of the drone, and the attitude of the pan/tilt to control the camera The posture is taken, and the adjusted area image 74 is obtained.

In one embodiment, when the control device controls the shooting posture of the photographing device according to the positions of the plurality of feature points on the initial image, it may be based on the positions of the plurality of feature points on the initial image. The normal vector of the target plane is determined, and the shooting attitude of the camera is controlled according to the normal vector. The specific implementation is as described above and will not be repeated here.

S604: In response to the photographing direction of the photographing device being substantially perpendicular to the target plane, acquire a target image obtained by photographing the target plane by the photographing device and the distance between the photographing device and the target plane.

In an embodiment, it may be specifically described with reference to FIG. 7a and FIG. 7b that the control device obtains the target image obtained by the shooting device shooting the target plane in response to the shooting direction of the shooting device being substantially perpendicular to the target plane. . Fig. 7b is a schematic diagram of obtaining a target image according to an embodiment of the present invention. As shown in Fig. 7b, after adjusting the shooting posture of the camera, the camera 75 photographs the object 76 included in the area image 74 in Fig. 7a. The shooting direction of the shooting device 75 may be substantially perpendicular to the target plane of the area image to obtain the target image 77 obtained by the shooting device 75 shooting the target plane.

In some embodiments, the implementation of the control device to obtain the distance between the imaging device and the target plane is as described above, and will not be repeated here.

S605: Determine a target plane or a size parameter of the object to be measured on the target plane according to the target image and the distance.

In the embodiment of the present invention, the control device may determine the target plane or the size parameter of the object to be measured on the target plane according to the target image and the distance. The specific implementation is as described above and will not be repeated here.

The embodiment of the present invention can acquire multiple feature points of the region image corresponding to the target plane of the initial image according to the initial image obtained by the drone's shooting device shooting the target object, and control the shooting according to the positions of the multiple feature points on the initial image The shooting posture of the device so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object, so that in response to the shooting direction of the shooting device being substantially perpendicular to the target plane, the target image, the shooting device and the target obtained by the shooting device shooting the target plane are acquired. The distance between the planes determines the target plane or the size parameter of the object to be measured on the target plane according to the target image and the distance. Through this implementation, feature points can be manually selected according to requirements to improve the flexibility of feature point selection, and feature points can be automatically extracted according to a preset feature point extraction algorithm, which simplifies user operations and improves the efficiency of feature point selection. Improve the user experience, thereby helping to improve the flexibility and effectiveness of measurement.

Please refer to FIG. 8 for details. FIG. 8 is a schematic flowchart of another control method provided by an embodiment of the present invention. The method may be executed by a control device, and the specific explanation of the control device is as described above. The difference between the embodiment of the present invention and FIG. 6 is that the embodiment of the present invention is a schematic description of controlling the shooting posture of the shooting device through the position information of three feature points. Specifically, the method of the embodiment of the present invention includes the following steps .

S801: Acquire an initial image obtained by photographing a target object by a photographing device of a drone, wherein the photographing device is carried on a pan/tilt of the drone.

S802: Acquire 3 feature points in the area image corresponding to the target plane, where the initial image includes the area image corresponding to the target plane, and the 3 feature points are based on the characteristics of the user on the display device of the control terminal Click the selection operation to confirm.

In the embodiment of the present invention, the control device can acquire 3 feature points in the area image corresponding to the target plane, where the initial image includes the area image corresponding to the target plane, and the 3 feature points are based on the user's control The feature point selection operation on the display device of the terminal is determined. In some embodiments, the feature point selection operation includes, but is not limited to, a click operation, a press operation, and the like.

In one embodiment, the control device can obtain that the user can click and select any three feature points that are not on a straight line on the display device of the control terminal that displays the initial image.

S803: Determine the positions of the spatial points corresponding to the 3 characteristic points according to the positions of the 3 characteristic points on the initial image.

In the embodiment of the present invention, the control device may determine the positions of the spatial points corresponding to the three characteristic points according to the positions of the three characteristic points on the initial image. In some embodiments, the positions of the three feature points on the initial image include position coordinates of the three feature points on the initial image respectively, wherein the position coordinates include an abscissa u and an ordinate v.

In an embodiment, the positions of the spatial points corresponding to the three feature points are three-dimensional coordinates determined according to the horizontal and vertical coordinates of the three feature points in the initial image. Wherein a feature point in an example x _1, x ₁ assume the position coordinates on the original image is (u, v, 1), it is determined that the three-dimensional coordinates x ₁ _{_{(x w, y w, 1}} ) must satisfy the following formula (6.1):

Among them, R is the rotation matrix, T is the displacement matrix, and the matrix K is obtained according to the following formula (6.2):

Among them, α _x =fm _x , α _y =fm _y , f is the focal length, m _x and m _y are the number of pixels per unit distance in the x and y directions, γ is the distortion parameter between the x and y axes, c _x And c _y are the optical centers.

S804: Determine a rotation matrix according to the positions of the spatial points corresponding to the three feature points.

In the embodiment of the present invention, the control device may determine the rotation matrix according to the positions of the spatial points corresponding to the three characteristic points. In some embodiments, the rotation matrix projects the 3 spatial points onto the 3 projection pixels on the initial image, so that: the U axis coordinate of the first projection pixel is equal to the U of the second projection pixel. Axis coordinate, the V axis coordinate of the first projection pixel is equal to the V axis coordinate of the third projection pixel. The specific implementation is as described above and will not be repeated here.

S805: Control the shooting posture of the shooting device according to the rotation matrix, so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object.

In the embodiment of the present invention, the control device may control the shooting posture of the shooting device according to the rotation matrix, so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object.

In one embodiment, the control device can convert the rotation matrix into an angle, and adjust one or more of the position of the drone, the attitude of the PTZ, and the attitude of the drone to make the light of the adjusted camera The axis direction is parallel to the normal vector of the target plane, that is, the shooting direction of the shooting device is substantially perpendicular to the target plane. The specific implementation is as described above.

It can be seen that the rotation matrix is determined by the positions of the spatial points corresponding to the three feature points and the parameters of the shooting device, thereby helping to control the shooting posture of the shooting device according to the rotation matrix.

S806: In response to the photographing direction of the photographing device being substantially perpendicular to the target plane, acquire a target image obtained by photographing the target plane by the photographing device and the distance between the photographing device and the target plane.

In the embodiment of the present invention, the control device may respond to the shooting direction of the shooting device being substantially perpendicular to the target plane, acquiring the target image obtained by the shooting device shooting the target plane, and the distance between the shooting device and the target plane. distance. The specific implementation is as described above and will not be repeated here.

S807: Determine the target plane or the size parameter of the object to be measured on the target plane according to the target image and the distance.

In the embodiment of the present invention, the three feature points of the area image corresponding to the target plane of the initial image can be obtained from the initial image obtained by shooting the target object by the camera of the drone, and the location of the three feature points on the initial image can be determined. The positions of the spatial points of the characteristic points and the shooting posture are such that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object, so that in response to the shooting direction of the shooting device being substantially perpendicular to the target plane, the shooting target plane of the shooting device is obtained. According to the target image and the distance between the shooting device and the target plane, the size parameter of the target plane or the object to be measured on the target plane is determined according to the target image and the distance. Through this implementation, feature points can be manually selected according to requirements to improve the flexibility of feature point selection, and feature points can be automatically extracted according to a preset feature point extraction algorithm, which simplifies user operations and improves the efficiency of feature point selection. Improve the user experience, thereby helping to improve the flexibility and effectiveness of measurement.

Please refer to FIG. 9, which is a schematic structural diagram of a control device according to an embodiment of the present invention. Specifically, the control device includes: a memory 901 and a processor 902.

In an embodiment, the control device further includes a data interface 903, and the data interface 903 is used to transfer data information between the control device and other devices.

The memory 901 may include a volatile memory (volatile memory); the memory 901 may also include a non-volatile memory (non-volatile memory); the memory 901 may also include a combination of the foregoing types of memories. The processor 902 may be a central processing unit (CPU). The processor 902 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), or any combination thereof.

The memory 901 is used to store program instructions, and the processor 902 can call a program stored in the memory 901 to perform the following steps:

Further, the size parameter includes one or more of length, width, and area.

Further, when the processor 902 controls the shooting posture of the shooting device according to the initial image, it is specifically configured to:

Control one or more of the position of the drone, the attitude of the drone, and the attitude of the pan/tilt according to the initial image to control the shooting attitude of the shooting device.

Further, the unmanned aerial vehicle includes a distance measuring device carried on the pan/tilt, wherein the measuring direction of the distance measuring unit is substantially parallel to the optical axis direction of the photographing device; the processor 902 obtains the When the distance between the photographing device and the target plane is described, it is specifically used for:

The distance between the photographing device and the target plane is measured by the distance measuring device.

Further, the distance measuring device is a laser distance measuring device.

Acquiring a plurality of feature points in a region image corresponding to the target plane, wherein the initial image includes the region image corresponding to the target plane;

The shooting posture of the shooting device is controlled according to the positions of the plurality of feature points on the initial image.

Further, when the processor 902 acquires multiple feature points in the region image corresponding to the target plane, it is specifically configured to:

Determining the area image corresponding to the target plane from the initial image;

Run a feature point extraction algorithm to extract multiple feature points from the region image.

Further, the processor 902 is further configured to:

Sending the initial image to a control terminal communicatively connected with the drone, so that a display device of the control terminal displays the initial image;

Acquire target plane indication information sent by the control terminal, where the target plane indication information is determined by the control terminal detecting a user's target area selection operation on the display device.

Acquire the characteristic point indication information sent by the control terminal, where the characteristic point indication information is determined by the control terminal detecting the characteristic point selection operation of the user on the display device.

Further, when the processor 902 controls the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, it is specifically configured to:

Determining the normal vector of the target plane according to the positions of the multiple feature points on the initial image;

The shooting posture of the shooting device is controlled according to the normal vector.

Further, the number of the feature points is three; when the processor 902 controls the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, it is specifically configured to:

Determining the positions of the spatial points corresponding to the 3 characteristic points according to the positions of the 3 characteristic points on the initial image;

The rotation matrix is determined according to the positions of the spatial points corresponding to the three feature points, wherein the rotation matrix projects the three spatial points onto the initial image and the three projection pixels satisfy the following requirements: The U-axis coordinate of is equal to the U-axis coordinate of the second projection pixel, and the V-axis coordinate of the first projection pixel is equal to the V-axis coordinate of the third projection pixel;

The shooting posture of the shooting device is controlled according to the rotation matrix.

Further, when the processor 902 determines the positions of the spatial points corresponding to the 3 characteristic points according to the positions of the 3 characteristic points on the initial image, it is specifically configured to:

Acquire 3 feature points in the area image corresponding to the target plane, where the initial image includes the area image corresponding to the target plane, and the 3 feature points are based on the characteristics of the user on the display device of the control terminal Click the selection operation to confirm;

The location of the spatial point corresponding to the three feature points is determined according to the locations of the three feature points on the initial image.

Further, when the processor 902 determines the size parameter of the target plane or the object to be measured on the target plane according to the target image and the distance, it is specifically configured to:

The size parameter of the target plane or the object to be measured on the target plane is determined according to the number of pixels of the target plane or the object to be measured in the target image and the distance.

Further, when the processor 902 determines the size parameter of the object to be measured on the target plane according to the target image and the distance, it is specifically configured to:

Recognizing the target image to determine the object to be tested; or,

Receive the object-to-be-measured indication information sent by the control terminal of the drone, and determine the object-to-be-measured according to the object-to-be-measured indication information, where the object-to-be-measured indication information is that the control terminal detects the user’s Control the selection operation of the object to be tested on the display device of the terminal;

The size parameter of the determined object to be measured is determined according to the target image and the distance.

Further, when the processor 902 determines the determined size parameter of the object to be measured according to the target image and the distance, it is specifically configured to:

Acquiring the circumscribed polygonal area of the object to be measured in the target image;

The size parameter of the object to be measured is determined according to the circumscribed polygonal area and the distance.

Further, the processor 902 is further configured to:

Sending the target image to a control terminal communicatively connected with the drone, so that the display device of the control terminal displays the target image;

Obtain the object to be measured indication information sent by the control terminal, where the object to be measured indication information is determined by the control terminal detecting the user's selection operation of the object to be measured on the display device.

Further, the processor 902 is further configured to:

Placing the target image in a preset recognition model of the object to be measured to obtain the object indication information output by the model;

The object to be measured on the target plane is determined according to the indication information of the object to be measured.

The embodiment of the present invention also provides an unmanned aerial vehicle, including: a fuselage; a power system configured on the fuselage to provide moving power for the vertical take-off and landing unmanned aerial vehicle; and a processor for acquiring the unmanned aerial vehicle The initial image obtained by the photographing device photographing the target object, wherein the photographing device is carried on the pan/tilt of the drone; the photographing posture of the photographing device is controlled according to the initial image, so that the photographing device is The shooting direction is substantially perpendicular to the target plane of the target object; in response to the shooting direction of the shooting device being substantially perpendicular to the target plane, the target image obtained by the shooting device shooting the target plane, the shooting device and the The distance between the target planes; the size parameter of the target plane or the object to be measured on the target plane is determined according to the target image and the distance.

Further, the size parameter includes one or more of length, width, and area.

Further, when the processor controls the shooting posture of the shooting device according to the initial image, it is specifically configured to:

Further, the unmanned aerial vehicle includes a distance measuring device carried on the pan/tilt, wherein the measuring direction of the distance measuring unit is substantially parallel to the optical axis direction of the photographing device; the processor obtains the When the distance between the photographing device and the target plane is specifically used for:

Further, the distance measuring device is a laser distance measuring device.

Further, when the processor acquires multiple feature points in the region image corresponding to the target plane, it is specifically configured to:

Further, the processor is also used for:

Further, when the processor controls the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, it is specifically configured to:

Further, the number of the feature points is three; when the processor controls the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, it is specifically configured to:

Further, when the processor determines the positions of the spatial points corresponding to the 3 characteristic points according to the positions of the 3 characteristic points on the initial image, it is specifically configured to:

Further, when the processor determines the size parameter of the target plane or the object to be measured on the target plane according to the target image and the distance, it is specifically configured to:

Further, when the processor determines the size parameter of the object to be measured on the target plane according to the target image and the distance, it is specifically configured to:

Recognizing the target image to determine the object to be tested; or,

Further, when the processor determines the determined size parameter of the object to be measured according to the target image and the distance, it is specifically configured to:

Further, the processor is also used for:

The embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, the computer program is executed by a processor to achieve the present invention corresponding to Figure 2, Figure 6 or Figure 8 The method described in the embodiment can also implement the device corresponding to the embodiment of the present invention shown in FIG. 9, which is not repeated here.

The computer-readable storage medium may be an internal storage unit of the device described in any of the foregoing embodiments, such as a hard disk or memory of the device. The computer-readable storage medium may also be an external storage device of the device, such as a plug-in hard disk equipped on the device, a Smart Media Card (SMC), or a Secure Digital (SD) card. , Flash Card, etc. Further, the computer-readable storage medium may also include both an internal storage unit of the device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

The above-disclosed are only some of the embodiments of the present invention, which of course cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.

Claims

A control method, characterized in that it comprises:

Acquiring an initial image obtained by photographing a target object by a photographing device of a drone, wherein the photographing device is carried on a pan/tilt of the drone;

Controlling the shooting posture of the shooting device according to the initial image so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object;

In response to the photographing direction of the photographing device being substantially perpendicular to the target plane, acquiring a target image obtained by photographing the target plane by the photographing device and the distance between the photographing device and the target plane;

The size parameter of the target plane or the object to be measured on the target plane is determined according to the target image and the distance.
The method according to claim 1, wherein the size parameter includes one or more of length, width, and area.
The method according to claim 1 or 2, wherein the controlling the shooting posture of the shooting device according to the initial image comprises:

Control one or more of the position of the drone, the attitude of the drone, and the attitude of the pan/tilt according to the initial image to control the shooting attitude of the shooting device.
The method according to any one of claims 1 to 3, wherein the drone comprises a distance measuring device carried on the pan/tilt, wherein the measuring direction of the distance measuring unit is the same as that of the shooting The direction of the optical axis of the device is basically parallel;

The acquiring the distance between the photographing device and the target plane includes:

The distance between the photographing device and the target plane is measured by the distance measuring device.
The method according to claim 4, wherein the distance measuring device is a laser distance measuring device.
The method according to any one of claims 1-5, wherein the controlling the shooting posture of the shooting device according to the initial image comprises:

Acquiring a plurality of feature points in a region image corresponding to the target plane, wherein the initial image includes the region image corresponding to the target plane;

The shooting posture of the shooting device is controlled according to the positions of the plurality of feature points on the initial image.
The method according to claim 6, wherein the acquiring multiple feature points in the region image corresponding to the target plane comprises:

Determining the area image corresponding to the target plane from the initial image;

Run a feature point extraction algorithm to extract multiple feature points from the region image.
The method according to claim 7, wherein the method further comprises:

Sending the initial image to a control terminal communicatively connected with the drone, so that a display device of the control terminal displays the initial image;

Acquire target plane indication information sent by the control terminal, where the target plane indication information is determined by the control terminal detecting a user's target area selection operation on the display device.
The method according to claim 6, wherein the acquiring multiple feature points in the region image corresponding to the target plane comprises:

Sending the initial image to a control terminal communicatively connected with the drone, so that a display device of the control terminal displays the initial image;

Acquire the characteristic point indication information sent by the control terminal, where the characteristic point indication information is determined by the control terminal detecting the characteristic point selection operation of the user on the display device.
The method according to any one of claims 6-9, wherein the controlling the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image comprises:

Determining the normal vector of the target plane according to the positions of the multiple feature points on the initial image;

The shooting posture of the shooting device is controlled according to the normal vector.
The method according to any one of claims 6-9, wherein the number of the feature points is 3; the shooting device is controlled according to the positions of the multiple feature points on the initial image The shooting attitude, including:

Determining the positions of the spatial points corresponding to the 3 characteristic points according to the positions of the 3 characteristic points on the initial image;

The rotation matrix is determined according to the positions of the spatial points corresponding to the three feature points, wherein the rotation matrix projects the three spatial points onto the initial image and the three projection pixels satisfy the following requirements: The U-axis coordinate of is equal to the U-axis coordinate of the second projection pixel, and the V-axis coordinate of the first projection pixel is equal to the V-axis coordinate of the third projection pixel;

The shooting posture of the shooting device is controlled according to the rotation matrix.
The method according to claim 11, wherein the determining the positions of the spatial points corresponding to the three characteristic points according to the positions of the three characteristic points on the initial image comprises:

Acquire 3 feature points in the area image corresponding to the target plane, where the initial image includes the area image corresponding to the target plane, and the 3 feature points are based on the characteristics of the user on the display device of the control terminal Click the selection operation to confirm;

The location of the spatial point corresponding to the three feature points is determined according to the locations of the three feature points on the initial image.
The method according to any one of claims 1-12, wherein the determining the target plane or the size parameter of the object to be measured on the target plane according to the target image and the distance comprises:

The size parameter of the target plane or the object to be measured on the target plane is determined according to the number of pixels of the target plane or the object to be measured in the target image and the distance.
The method according to any one of claims 1-13, wherein the determining the size parameter of the object to be measured on the target plane according to the target image and the distance comprises:

Recognizing the target image to determine the object to be tested; or,

Receive the object-to-be-measured indication information sent by the control terminal of the drone, and determine the object-to-be-measured according to the object-to-be-measured indication information, where the object-to-be-measured indication information is the control terminal by detecting the user’s Control the selection operation of the object to be tested on the display device of the terminal;

The size parameter of the determined object to be measured is determined according to the target image and the distance.
The method according to claim 14, wherein the determining the determined size parameter of the object to be measured according to the target image and the distance comprises:

Acquiring the circumscribed polygonal area of the object to be measured in the target image;

The size parameter of the object to be measured is determined according to the circumscribed polygonal area and the distance.
The method according to any one of claims 1-12, wherein the method further comprises:

Sending the target image to a control terminal communicatively connected with the drone, so that the display device of the control terminal displays the target image;

Obtain the object to be measured indication information sent by the control terminal, where the object to be measured indication information is determined by the control terminal detecting the user's selection operation of the object to be measured on the display device.
The method according to any one of claims 1-13, wherein the method further comprises:

Placing the target image in a preset recognition model of the object to be measured to obtain the object indication information output by the model;

The object to be measured on the target plane is determined according to the indication information of the object to be measured.
A control device, characterized in that it comprises a memory and a processor;

The memory is used to store programs;

The processor is used to call the program, and when the program is executed, it is used to perform the following operations:

Acquiring an initial image obtained by photographing a target object by a photographing device of a drone, wherein the photographing device is carried on a pan/tilt of the drone;

Controlling the shooting posture of the shooting device according to the initial image so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object;

In response to the photographing direction of the photographing device being substantially perpendicular to the target plane, acquiring a target image obtained by photographing the target plane by the photographing device and the distance between the photographing device and the target plane;

The size parameter of the target plane or the object to be measured on the target plane is determined according to the target image and the distance.
The device according to claim 18, wherein the size parameter includes one or more of length, width, and area.
The device according to claim 18 or 19, wherein when the processor controls the shooting posture of the shooting device according to the initial image, it is specifically configured to:

Control one or more of the position of the drone, the attitude of the drone, and the attitude of the pan/tilt according to the initial image to control the shooting attitude of the shooting device.
The device according to any one of claims 18-20, wherein the drone comprises a distance measuring device carried on the pan/tilt, wherein the measuring direction of the distance measuring unit is the same as that of the shooting The direction of the optical axis of the device is basically parallel;

When the processor obtains the distance between the photographing device and the target plane, it is specifically configured to:

The distance between the photographing device and the target plane is measured by the distance measuring device.
The device according to claim 21, wherein the distance measuring device is a laser distance measuring device.
The device according to any one of claims 18-22, wherein when the processor controls the shooting attitude of the shooting device according to the initial image, it is specifically configured to:

Acquiring a plurality of feature points in a region image corresponding to the target plane, wherein the initial image includes the region image corresponding to the target plane;

The shooting posture of the shooting device is controlled according to the positions of the plurality of feature points on the initial image.
The device according to claim 23, wherein when the processor acquires multiple feature points in the region image corresponding to the target plane, it is specifically configured to:

Determining the area image corresponding to the target plane from the initial image;

Run a feature point extraction algorithm to extract multiple feature points from the region image.
The device according to claim 24, wherein the processor is further configured to:

Sending the initial image to a control terminal communicatively connected with the drone, so that a display device of the control terminal displays the initial image;

Acquire target plane indication information sent by the control terminal, where the target plane indication information is determined by the control terminal detecting a user's target area selection operation on the display device.
The device according to claim 23, wherein when the processor acquires multiple feature points in the region image corresponding to the target plane, it is specifically configured to:

Sending the initial image to a control terminal communicatively connected with the drone, so that a display device of the control terminal displays the initial image;

Acquire the characteristic point indication information sent by the control terminal, where the characteristic point indication information is determined by the control terminal detecting the characteristic point selection operation of the user on the display device.
The device according to any one of claims 23-26, wherein when the processor controls the shooting posture of the shooting device according to the positions of the multiple feature points on the initial image, it is specifically configured to :

Determining the normal vector of the target plane according to the positions of the multiple feature points on the initial image;

The shooting posture of the shooting device is controlled according to the normal vector.
The device according to any one of claims 23-26, wherein the number of the feature points is 3; the processor controls the When the shooting posture of the shooting device is specifically used for:

Determining the positions of the spatial points corresponding to the 3 characteristic points according to the positions of the 3 characteristic points on the initial image;

The rotation matrix is determined according to the positions of the spatial points corresponding to the three feature points, wherein the rotation matrix projects the three spatial points onto the initial image and the three projection pixels satisfy the following requirements: The U-axis coordinate of is equal to the U-axis coordinate of the second projection pixel, and the V-axis coordinate of the first projection pixel is equal to the V-axis coordinate of the third projection pixel;

The shooting posture of the shooting device is controlled according to the rotation matrix.
The device according to claim 28, wherein when the processor determines the positions of the spatial points corresponding to the three feature points according to the positions of the three feature points on the initial image, it is specifically configured to :

Acquire 3 feature points in the area image corresponding to the target plane, where the initial image includes the area image corresponding to the target plane, and the 3 feature points are based on the characteristics of the user on the display device of the control terminal Click the selection operation to confirm;

The location of the spatial point corresponding to the three feature points is determined according to the locations of the three feature points on the initial image.
The device according to any one of claims 18-29, wherein the processor determines the size parameter of the target plane or the object to be measured on the target plane according to the target image and the distance, specifically Used for:

The size parameter of the target plane or the object to be measured on the target plane is determined according to the number of pixels of the target plane or the object to be measured in the target image and the distance.
The device according to any one of claims 18-30, wherein when the processor determines the size parameter of the object to be measured on the target plane according to the target image and the distance, it is specifically configured to:

Recognizing the target image to determine the object to be tested; or,

Receive the object-to-be-measured indication information sent by the control terminal of the drone, and determine the object-to-be-measured according to the object-to-be-measured indication information, where the object-to-be-measured indication information is that the control terminal detects the user’s Control the selection operation of the object to be tested on the display device of the terminal;

The size parameter of the determined object to be measured is determined according to the target image and the distance.
The device according to claim 31, wherein, when the processor determines the determined size parameter of the object to be measured according to the target image and the distance, the processor is specifically configured to include:

Acquiring the circumscribed polygonal area of the object to be measured in the target image;

The size parameter of the object to be measured is determined according to the circumscribed polygonal area and the distance.
The device according to any one of claims 18-29, wherein the processor is further configured to:

Sending the target image to a control terminal communicatively connected with the drone, so that the display device of the control terminal displays the target image;

Obtain the object to be measured indication information sent by the control terminal, where the object to be measured indication information is determined by the control terminal detecting the user's selection operation of the object to be measured on the display device.
The device according to any one of claims 18-30, wherein the processor is further configured to:

Placing the target image in a preset recognition model of the object to be measured to obtain the object indication information output by the model;

The object to be measured on the target plane is determined according to the indication information of the object to be measured.
An unmanned aerial vehicle, characterized in that it includes:

body;

The power system configured on the fuselage is used to provide the moving power for the UAV;

The processor is used for:

Acquiring an initial image obtained by photographing a target object by a photographing device of a drone, wherein the photographing device is carried on a pan/tilt of the drone;

Controlling the shooting posture of the shooting device according to the initial image so that the shooting direction of the shooting device is substantially perpendicular to the target plane of the target object;

In response to the photographing direction of the photographing device being substantially perpendicular to the target plane, acquiring a target image obtained by photographing the target plane by the photographing device and the distance between the photographing device and the target plane;

The size parameter of the target plane or the object to be measured on the target plane is determined according to the target image and the distance.
The drone of claim 35, wherein the size parameter includes one or more of length, width, and area.
The drone according to claim 35 or 36, wherein when the processor controls the shooting attitude of the shooting device according to the initial image, it is specifically configured to:

Control one or more of the position of the drone, the attitude of the drone, and the attitude of the pan/tilt according to the initial image to control the shooting attitude of the shooting device.
The unmanned aerial vehicle according to any one of claims 35-37, wherein the unmanned aerial vehicle comprises a distance measuring device carried on the pan/tilt, wherein the measuring direction of the distance measuring unit is the same as that of the distance measuring unit. The direction of the optical axis of the shooting device is substantially parallel;

When the processor obtains the distance between the photographing device and the target plane, it is specifically configured to:

The distance between the photographing device and the target plane is measured by the distance measuring device.
The drone of claim 38, wherein the distance measuring device is a laser distance measuring device.
The drone according to any one of claims 35-39, wherein when the processor controls the shooting attitude of the shooting device according to the initial image, it is specifically configured to:

Acquiring a plurality of feature points in a region image corresponding to the target plane, wherein the initial image includes the region image corresponding to the target plane;

The shooting posture of the shooting device is controlled according to the positions of the plurality of feature points on the initial image.
The UAV according to claim 40, wherein when the processor acquires multiple feature points in the area image corresponding to the target plane, it is specifically configured to:

Determining the area image corresponding to the target plane from the initial image;

Run a feature point extraction algorithm to extract multiple feature points from the region image.
The drone of claim 41, wherein the processor is further configured to:

Sending the initial image to a control terminal communicatively connected with the drone, so that a display device of the control terminal displays the initial image;

Acquire target plane indication information sent by the control terminal, where the target plane indication information is determined by the control terminal detecting a user's target area selection operation on the display device.
The UAV according to claim 40, wherein when the processor acquires multiple feature points in the area image corresponding to the target plane, it is specifically configured to:

Sending the initial image to a control terminal communicatively connected with the drone, so that a display device of the control terminal displays the initial image;

Acquire the characteristic point indication information sent by the control terminal, where the characteristic point indication information is determined by the control terminal detecting the characteristic point selection operation of the user on the display device.
The drone according to any one of claims 40-43, wherein the processor controls the shooting attitude of the shooting device according to the positions of the multiple feature points on the initial image, specifically Used for:

Determining the normal vector of the target plane according to the positions of the multiple feature points on the initial image;

The shooting posture of the shooting device is controlled according to the normal vector.
The unmanned aerial vehicle according to any one of claims 40-43, wherein the number of the feature points is 3; the processor controls according to the positions of the multiple feature points on the initial image The shooting posture of the shooting device is specifically used for:

Determining the positions of the spatial points corresponding to the 3 characteristic points according to the positions of the 3 characteristic points on the initial image;

The rotation matrix is determined according to the positions of the spatial points corresponding to the three feature points, wherein the rotation matrix projects the three spatial points onto the initial image and the three projection pixels satisfy the following requirements: The U-axis coordinate of is equal to the U-axis coordinate of the second projection pixel, and the V-axis coordinate of the first projection pixel is equal to the V-axis coordinate of the third projection pixel;

The shooting posture of the shooting device is controlled according to the rotation matrix.
The drone according to claim 45, wherein when the processor determines the positions of the spatial points corresponding to the three feature points according to the positions of the three feature points on the initial image, specifically Used for:

Acquire 3 feature points in the area image corresponding to the target plane, where the initial image includes the area image corresponding to the target plane, and the 3 feature points are based on the characteristics of the user on the display device of the control terminal Click the selection operation to confirm;

The location of the spatial point corresponding to the three feature points is determined according to the locations of the three feature points on the initial image.
The drone according to any one of claims 35-46, wherein the processor determines the size parameter of the target plane or the object to be measured on the target plane according to the target image and the distance , Specifically used for:

The size parameter of the target plane or the object to be measured on the target plane is determined according to the number of pixels of the target plane or the object to be measured in the target image and the distance.
The drone according to any one of claims 35-47, wherein when the processor determines the size parameter of the object to be measured on the target plane according to the target image and the distance, it specifically uses in:

Recognizing the target image to determine the object to be tested; or,

Receive the object-to-be-measured indication information sent by the control terminal of the drone, and determine the object-to-be-measured according to the object-to-be-measured indication information, where the object-to-be-measured indication information is that the control terminal detects the user’s Control the selection operation of the object to be tested on the display device of the terminal;

The size parameter of the determined object to be measured is determined according to the target image and the distance.
The unmanned aerial vehicle according to claim 48, wherein when the processor determines the size parameter of the determined object to be measured according to the target image and the distance, it is specifically configured to include:

Acquiring the circumscribed polygonal area of the object to be measured in the target image;

The size parameter of the object to be measured is determined according to the circumscribed polygonal area and the distance.
The unmanned aerial vehicle according to any one of claims 35-46, wherein the processor is further configured to:

Sending the target image to a control terminal communicatively connected with the drone, so that the display device of the control terminal displays the target image;

Obtain the object to be measured indication information sent by the control terminal, where the object to be measured indication information is determined by the control terminal detecting the user's selection operation of the object to be measured on the display device.
The drone according to any one of claims 35-47, wherein the processor is further configured to:

Placing the target image in a preset recognition model of the object to be measured to obtain the object indication information output by the model;

The object to be measured on the target plane is determined according to the indication information of the object to be measured.
A computer-readable storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 1 to 17 when the computer program is executed by a processor.