CN110221625A - The Autonomous landing guidance method of unmanned plane exact position - Google Patents

Abstract

The invention provides an autonomous landing guidance method for the precise position of the drone. The method includes: guiding the unmanned aerial vehicle to fly to a set distance range of a landing target on the ground through a satellite navigation system; acquiring a video image of the ground through an airborne camera, and identifying the landing target contained in the video image through a graphic detection rule According to the semantic icon on the target, the center position information of the landing target is calculated according to the semantic icon; according to the center position information of the landing target, the landing target in the earth coordinate system is calculated through the posture and relative position relationship between the airborne camera and the UAV position and dynamic characteristics; continuously calculate the relative position and relative speed of the UAV and the landing target in the geodetic coordinate system, and control the UAV to land at the center of the landing target through the triple PID control algorithm. The method of the present invention realizes the positioning and tracking of the landing target by identifying the semantic icon in the landing target, and realizes the accurate and autonomous landing of the UAV on the dynamic target.

Description

Autonomous Landing Guidance Method for UAV Precise Position

technical field

The invention relates to the technical field of unmanned aerial vehicle control, in particular to an autonomous landing guidance method for the precise position of an unmanned aerial vehicle.

Background technique

Rotor UAV has the advantages of convenient use, flexible maneuverability, low operating cost, and high flight accuracy. Autonomous take-off and landing of drones has been a research hotspot in the field of drones for many years.

At present, the autonomous landing of drones mostly uses GNSS (Global Navigation Satellite System, Global Navigation Satellite System) navigation and positioning with altitude data for fixed-point landing. Altitude data is usually measured by GNSS, barometer, ultrasound or ground radar. However, GNSS signals are easily affected by building occlusion and weather conditions, the data drift is serious, and the accuracy in the height direction is very limited; ranging sensors based on ultrasonic, microwave, laser, etc. are difficult to distinguish the landing platform from the ground, and cannot be directly used for UAVs Land on a moving platform.

At present, for mobile landing platforms, the autonomous landing of UAVs in the prior art usually adopts manual guidance and control, which has high requirements for GNSS accuracy and operator proficiency, and cannot achieve autonomous landing. Under some complex conditions, such as taking off and landing on a mobile platform on the sea surface or a bumpy moving ground platform, it is still a severe challenge for the flight control system and controllers of this type of UAV, which restricts the use of UAVs in a wider range of fields. .

Contents of the invention

The embodiment of the present invention provides an autonomous landing guidance method for the precise position of the UAV, so as to overcome the problems in the prior art.

In order to achieve the above object, the present invention adopts the following technical solutions.

An autonomous landing guidance method for a precise position of an unmanned aerial vehicle, comprising:

Guide the UAV to fly to the set distance range of the landing target on the ground through the satellite navigation system;

The video image of the ground is acquired by the airborne camera, the semantic icon on the landing target contained in the video image is recognized through the graphic detection rule, and the center position information of the landing target is calculated according to the semantic icon on the landing target ;

Calculate the position and dynamic characteristics of the landing target in the geodetic coordinate system through the attitude and relative position relationship between the airborne camera and the UAV according to the center position information of the landing target;

Based on the position and dynamic characteristics of the landing target, the relative position and relative speed of the UAV and the landing target in the geodetic coordinate system are continuously calculated, and the UAV is controlled to land at the center of the landing target through a triple PID control algorithm Location.

Preferably, the interior of the landing target contains a plurality of non-overlapping semantic icons, the size, position and corresponding semantics of each semantic icon are known, and the plurality of semantic icons are arranged according to certain rules, so that no During the landing process, the onboard camera can always see at least one semantic icon.

Preferably, the main body of the semantic icon is a black rectangle, and white rectangles with different positions and numbers are drawn inside the semantic icon according to semantic rules, and the semantic information contained in each semantic icon is stored in the semantic icon database.

Preferably, the video image of the ground is acquired by the airborne camera, the semantic icon on the landing target contained in the video image is recognized through the graphic detection rule, and the landing target is calculated according to the semantic icon on the landing target. Target center position information, including:

The ground video image is taken by the drone's onboard camera, the video image is converted into a grayscale image, and the adaptive threshold corresponding to each pixel is calculated according to the neighborhood of each pixel in the grayscale image , compare the gray value of each pixel with the corresponding adaptive threshold, when the gray value of a certain pixel is greater than the adaptive threshold, set the certain pixel to white, when a certain pixel When the gray value of the point is not greater than the adaptive threshold, the certain pixel is set to black otherwise;

Extract the black rectangle in the grayscale image after resetting the pixels, and detect whether the black rectangle is a correct semantic icon according to the semantic rules. Since the UAV is always at the position above the target, and the attitude change is small, it can filter out the contours with too small area and too biased shape to reduce the amount of calculation.

The semantic rule described is: divide each side of the black rectangle into 6 equal parts, connect the corresponding equal parts of the opposite sides, thus divide the black rectangle into 6×6 small rectangles, except for the outermost layer, all are In each of the small rectangles outside the black and inside, the rectangle with the majority of black is recorded as 0, and the rectangle with the majority of white is recorded as 1, and the data of each row in the black rectangle is concatenated from top to bottom to obtain concatenated data , using the series data as the semantic information contained in the semantic icon, comparing the semantic information represented by the series data with the semantic information of each semantic icon stored in the semantic icon database, and when the comparison results are consistent , then determine that the black rectangle corresponding to the above concatenated data is the correct semantic icon;

The center position information of the landing target is calculated according to the semantic information contained in all the semantic icons on the landing target.

Preferably, according to the center position information of the landing target, the position and dynamic characteristics of the landing target in the geodetic coordinate system are calculated through the attitude and relative position relationship between the airborne camera and the UAV, including:

The target coordinate system is established according to the center position information of the landing target, and the coordinate position of the vertex and center of the semantic icon in the target coordinate system is obtained according to the semantic information contained in each semantic icon;

The rotation and translation matrix from the target plane to the camera imaging plane is obtained through the one-to-one correspondence between the semantic icon in the target coordinate system and the image pixel coordinates, and the semantic icon is placed on the target according to the rotation and translation matrix from the target plane to the camera imaging plane. The coordinates in the coordinate system are transformed into the coordinates of the semantic icon in the camera coordinate system. According to the conversion formula from the camera coordinate system to the earth coordinate system, the spatial coordinates of the semantic icon in the camera coordinate system are converted into the coordinates of the semantic icon in the earth coordinate system. coordinate;

Taking the geodetic coordinates of the east and north directions of the semantic icon as input, the position and velocity of the landing target in the geodetic coordinate system are calculated by Kalman filtering, and the state vector X=[x , y, v _x , v _y ] ^T and the output vector Y=[x, y] ^T , the state equation of the landing target under the geodetic coordinate system is shown in formula (1):

in, Δt is the sampling time interval; W represents system noise with zero mean, which is a Gaussian variable with covariance Q; V represents measurement noise with zero mean, which is a Gaussian variable with covariance R;

The rotation and translation matrix from the target plane to the camera imaging plane is shown in formula (2):

Among them, (u, v) are the image pixel coordinates, (x, y) are the coordinates of the semantic icon in the target coordinate system, is the internal reference matrix, R is a 3×3 rotation matrix, and T is a 3×1 translation vector;

The conversion formula of the camera coordinate system to the earth coordinate system is as shown in formula (3):

X _g ＝R _p X _p +X _g0 ＝R _p R _c X _c +X _g0 (3)

Among them, X _g , X _p , and X _c are the coordinates of the landing target in the earth coordinate system, the UAV coordinate system, and the camera coordinate system; X _g0 is the current coordinate of the UAV in the earth coordinate system, which is positioned by GNSS The coordinate transformation is obtained; R _p and R _c are the rotation matrices from the UAV system to the earth coordinate system, and from the camera to the UAV coordinate system, respectively. The calculation formula is shown in formula (4), where α is the roll angle and β is the pitch angle, and γ is the yaw angle.

Preferably, based on the position and dynamic characteristics of the landing target, the relative position and relative speed between the UAV and the landing target in the geodetic coordinate system are continuously calculated, and the UAV is controlled to land on the ground by a triple PID control algorithm. The center position of the landing target, including:

Continuously calculate the relative position and relative velocity of the UAV and the landing target in the geodetic coordinate system based on the position and dynamic characteristics of the landing target;

Taking the relative position of the UAV and the landing target as input, the UAV is controlled to move to the target through the PID control algorithm;

The relative speed of the UAV and the landing target is used as input, superimposed on the speed obtained by the position control, and the dynamic landing target is tracked through the PID control algorithm;

Taking the relative height of the UAV and the landing target as input, the UAV is controlled to land on the target through the PID control algorithm.

From the technical solutions provided by the above-mentioned embodiments of the present invention, it can be seen that the autonomous landing guidance method of the precise position of the UAV in the embodiment of the present invention realizes the positioning and tracking of the landing target by identifying the semantic icons in the landing target , and estimate the moving speed of the landing target, make up for the lack of large positioning error of the landing target caused by the lack of GNSS positioning accuracy, and realize the accurate and autonomous landing of the UAV on the dynamic target. By adopting the method of image recognition, the semantic icons in the landing target can be automatically recognized, so as to quickly calculate the relative position and relative speed of the UAV and the target.

Additional aspects and advantages of the invention will be set forth in part in the description which follows, and will become apparent from the description, or may be learned by practice of the invention.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

Fig. 1 is an overall flow chart of an autonomous precise position landing guidance for a UAV provided by an embodiment of the present invention.

FIG. 2 is a schematic diagram of a landing target pattern provided by an embodiment of the present invention.

FIG. 3 is a schematic diagram of a process for identifying semantic icons in a target according to an embodiment of the present invention.

Fig. 4 is a schematic diagram illustrating an example of a semantic icon provided by an embodiment of the present invention.

FIG. 5 is a schematic diagram of the relative relationship between a camera coordinate system, a drone coordinate system, and a ground coordinate system provided by an embodiment of the present invention.

Detailed ways

Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

Those skilled in the art will understand that unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the word "comprising" used in the description of the present invention refers to the presence of said features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Additionally, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in commonly used dictionaries should be understood to have a meaning consistent with the meaning in the context of the prior art, and unless defined as herein, are not to be interpreted in an idealized or overly formal sense explain.

In order to facilitate the understanding of the embodiments of the present invention, several specific embodiments will be taken as examples for further explanation below in conjunction with the accompanying drawings, and each embodiment does not constitute a limitation to the embodiments of the present invention.

Embodiment one

In order to solve the problem that the GNSS positioning accuracy in the prior art is not enough to cause the drone to land on the mobile platform accurately and autonomously, and improve the autonomy of the drone, the embodiment of the present invention provides an autonomous landing of the precise position of the drone Guidance method, the processing flow of this method is as shown in Figure 1, including the following processing steps:

Step S1: Guide the UAV over the landing target through the guidance of the GNSS satellite navigation system. The current GNSS satellite navigation positioning accuracy is usually within 10 meters, which can ensure that when the UAV reaches the position marked by the GNSS satellite, the airborne downward-looking camera can see the landing target.

Described UAV refers to multi-rotor UAV and unmanned helicopter. The landing target used in the embodiment of the present invention is shown in Figure 2, which can be installed on the ground or on a mobile vehicle to mark the landing range of the drone.

Step S2: Identify the landing target through the onboard camera, adjust the attitude and angle of the UAV, and lower the height of the UAV while keeping the landing target within the field of view.

In the embodiment of the present invention, the viewing angle of the down-looking camera of the drone is 90°. According to the test, the semantic target can be clearly identified when the drone drops to a height of 3 meters.

Step S3: Identify the semantic icons in the target through graphic detection, and judge whether the recognized icon is an icon on the landing target, and calculate the center position of the landing target after filtering out falsely detected icons.

The interior of the landing target contains a plurality of non-overlapping semantic icons, the size, position and corresponding semantics of each semantic icon are known, and the plurality of semantic icons are arranged according to certain rules, so that the drone lands During the process, the onboard camera can always see at least 1 semantic icon. The main body of the semantic icon is a black rectangle, and white rectangles with different positions and numbers are drawn inside the semantic icon according to semantic rules. When designing the target, the semantic information contained in each semantic icon is stored in the semantic icon database. When a semantic icon is detected, the semantic information is compared with the semantic icon database, and the successful comparison is the correct semantic icon.

A process for identifying semantic icons in a target provided by an embodiment of the present invention is shown in Figure 3, and the specific processing process includes:

Firstly, the video image of the ground is captured by an airborne camera, and the above video image is converted into a grayscale image, and then the grayscale image is binarized by an adaptive threshold. The adaptive threshold is a local thresholding method. Its principle is to calculate the adaptive threshold value corresponding to each pixel point according to the neighborhood of each pixel point in the image, then compare the gray value of each pixel point with the corresponding adaptive threshold value, and set each threshold value according to the comparison result. Pixels are either white or black. This avoids thresholding errors due to uneven lighting. For each pixel in the image, the calculation of adaptive thresholding is shown in formula (5),

Among them, P _{i, j} is the image pixel gray value of row i and column j, N is the total number of pixels in the window, and C is the calculation bias. After the threshold is obtained, compare the corresponding pixel gray value with the threshold. When the gray value is greater than the threshold, the pixel is set to 255 (white), otherwise it is set to 0 (black), as shown in formula (6) .

Extract the black rectangle in the repixelated image. Since the UAV is always above the target and its attitude changes little, it is possible to first filter out the black rectangles with too small area and too biased shape to reduce the amount of calculation. Corresponding to the remaining black rectangle, check whether the black rectangle is a correct semantic icon according to the semantic rules.

The semantic rule described is: each side of the black rectangle is divided into 6 equal parts, and the corresponding equal parts of the opposite sides are connected, thereby dividing the black rectangle into 6×6 small rectangles; except the outermost layer, all are Outside the black, in each small rectangle inside, the rectangle with the majority of black is recorded as 0, and the rectangle with the majority of white is recorded as 1.

Fig. 4a and Fig. 4b are schematic diagrams illustrating an example of a semantic icon provided by an embodiment of the present invention. As shown in FIG. 4a, the data of each row is connected in series from top to bottom to obtain series data, which is the semantic information contained in the semantic icon. Comparing the semantic information represented by the above concatenated data with the semantic information of each semantic icon stored in the semantic icon database, and when the comparison results are consistent, it is determined that the black rectangle corresponding to the above concatenated data is the correct semantic icon. As shown in Figure 4b, the concatenated data (semantic information) generated by the same black rectangle rotated 90°, 180°, and 270° is considered to contain the same information, ensuring the unique correspondence between the semantic icon and the semantic information; at the same time, in order to avoid Confused, not using centrosymmetric and axisymmetric semantic icons.

Then, calculate the center position information of the landing target according to the semantic information contained in all the semantic icons on the landing target, establish the target coordinate system, and obtain the position and size information of the semantic icon on the target according to the semantic information, That is, the coordinate information of the semantic icon on the target coordinate system is obtained, including the pixel coordinates of the corner point and the center point of the semantic icon.

Step S4: Calculate the position of the landing target in the earth coordinate system through the attitude and relative position relationship between the airborne camera and the UAV, and calculate the dynamic characteristics of the landing target through Kalman filtering.

The semantic icons used in the embodiment of the present invention are shown in FIG. 2 , and the positions of the vertices and centers of the semantic graph in the target coordinate system are obtained according to the semantic information contained in each semantic icon. Through the one-to-one correspondence between the semantic icon in the target coordinate system and the image pixel coordinates, the rotation and translation matrix from the target plane to the camera imaging plane is calculated, as shown in formula (7).

Among them, (u, v) are the image pixel coordinates, (x, y) are the coordinates of the semantic icon in the target coordinate system, is the internal reference matrix, R is a 3×3 rotation matrix, and T is a 3×1 translation vector.

The space coordinates of the target plane in the camera coordinate system can be quickly obtained by using the rotation and translation matrix shown in the above formula (3) by the least square method.

The geodetic coordinate system is the northeast geodetic coordinate system with the take-off point of the drone as the origin; the dynamic characteristics of the landing target include the geodetic coordinates of the target, the orientation of the target, the eastward velocity, the northward velocity, and the rotational angular velocity Wait.

The relative relationship between the camera coordinate system, the UAV coordinate system and the earth coordinate system provided by the embodiment of the present invention is shown in Fig. Axis attitude (roll angle, pitch angle, heading angle), the three-axis attitude of the camera relative to the drone can be obtained through the camera gimbal or calibration. The formula for transforming the landing target from the camera coordinate system to the earth coordinate system is shown in formula (8).

X _g ＝R _p X _p +X _g0 ＝R _p R _c X _c +X _g0 (8)

Among them, X _g , X _p , and X _c are the coordinates of the landing target in the earth coordinate system, the UAV coordinate system, and the camera coordinate system; X _g0 is the current coordinate of the UAV in the earth coordinate system, which is positioned by GNSS The coordinate transformation is obtained; R _p and R _c are the rotation matrices from the UAV system to the earth coordinate system, and from the camera to the UAV coordinate system, respectively, and the calculation formula is shown in formula (9). Among them, α is the roll angle, β is the pitch angle, and γ is the yaw angle.

Taking the geodetic coordinates in the east and north directions of the landing target as input, the position and velocity of the landing target are predicted by Kalman filtering. The state vector X=[x, y, v _x , v _y ] ^T and the output vector Y=[x, y] ^T are composed of the east and north coordinates and velocity of the landing target, and the state equation of the system is given by formula (10) Show.

in, Δt is the sampling time interval; W represents the system noise with zero mean and is a Gaussian variable with covariance Q; V represents the measurement noise with zero mean and is a Gaussian variable with covariance R.

Based on the position and dynamic characteristics of the landing target, the relative position and relative speed between the UAV and the landing target in the geodetic coordinate system are continuously calculated, and the relative position includes the relative distance and relative height.

Step S5: According to the relative position and relative speed of the UAV and the landing target in the geodetic coordinate system, the UAV is accurately landed at the center of the target through a triple PID (proportional, integral, differential) control algorithm.

Described triple PID control algorithm is divided into:

(1) Position control, taking the relative position of the UAV and the landing target as input, and controlling the movement of the UAV to the target through the PID control algorithm;

(2) Horizontal speed control, using the relative speed of the UAV and the landing target as input, superimposed on the speed obtained by the position control, and tracking the dynamic landing target through the PID control algorithm;

(3) Landing speed control, taking the relative height of the UAV and the landing target as input, and controlling the UAV to land on the target through the PID control algorithm.

The UAV landing method in the embodiment of the present invention is not only suitable for UAV landing on a fixed target, but also suitable for landing on a moving vehicle or ship.

In summary, the autonomous landing guidance method for the precise position of the UAV in the embodiment of the present invention realizes the positioning and tracking of the landing target by identifying the semantic icons in the landing target, and estimates the moving speed of the landing target. Make up for the lack of large landing target positioning errors caused by insufficient GNSS positioning accuracy, and realize the precise and autonomous landing of UAVs on dynamic targets.

By adopting the method of image recognition, the semantic icon in the landing target can be automatically recognized, so as to quickly calculate the relative position and relative speed of the UAV and the target;

The semantic icons in the landing target can flexibly configure the size, position and attitude under the condition of meeting the camera's field of view to form different landing target graphics;

During the whole process from the UAV reaching the recognizable distance to landing on the target, at least one semantic icon is fully recognized at every moment, thus ensuring the positioning accuracy of the landing target;

The triple PID algorithm is used to control the UAV to track the dynamic target and land autonomously, which is faster and more stable than similar algorithms.

Those skilled in the art can understand that the accompanying drawing is only a schematic diagram of an embodiment, and the modules or processes in the accompanying drawing are not necessarily necessary for implementing the present invention.

It can be seen from the above description of the implementation manners that those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in storage media, such as ROM/RAM, disk , CD, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the present invention.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for relevant parts, refer to part of the description of the method embodiments. The device and system embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, It can be located in one place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without creative effort.

The above is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present invention can easily think of changes or Replacement should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims (6)

1. A self-guiding method for the precise position of an unmanned aerial vehicle, characterized in that it comprises: Guide the UAV to fly to the set distance range of the landing target on the ground through the satellite navigation system; The video image of the ground is acquired by the airborne camera, the semantic icon on the landing target contained in the video image is recognized through the graphic detection rule, and the center position information of the landing target is calculated according to the semantic icon on the landing target ; Calculate the position and dynamic characteristics of the landing target in the geodetic coordinate system through the attitude and relative position relationship between the airborne camera and the UAV according to the center position information of the landing target; Based on the position and dynamic characteristics of the landing target, the relative position and relative speed of the UAV and the landing target in the geodetic coordinate system are continuously calculated, and the UAV is controlled to land at the center of the landing target through a triple PID control algorithm Location. 2. The method according to claim 1, wherein the inside of the landing target contains a plurality of non-overlapping semantic icons, and the size, position and corresponding semantics of each semantic icon are known, Multiple semantic icons are arranged according to certain rules, so that the airborne camera can always see at least one semantic icon during the landing process of the drone. 3. The method according to claim 2, wherein the main body of the semantic icon is a black rectangle, and the inside of the semantic icon is drawn with white rectangles of different positions and quantities according to the semantic rules, and each semantic icon contains Semantic information is stored in a semantic icon database. 4. method according to claim 3, is characterized in that, described obtains the video image of ground by airborne camera, recognizes the semantic icon on the landing target that comprises in described video image by graphic detection rule, according to The semantic icon on the landing target calculates the center position information of the landing target, including: The ground video image is taken by the drone's onboard camera, the video image is converted into a grayscale image, and the adaptive threshold corresponding to each pixel is calculated according to the neighborhood of each pixel in the grayscale image , compare the gray value of each pixel with the corresponding adaptive threshold, when the gray value of a certain pixel is greater than the adaptive threshold, set the certain pixel to white, when a certain pixel When the gray value of the point is not greater than the adaptive threshold, the certain pixel is set to black otherwise; Extract the black rectangle in the grayscale image after resetting the pixels, and detect whether the black rectangle is a correct semantic icon according to the semantic rules; The semantic rule described is: divide each side of the black rectangle into 6 equal parts, connect the corresponding equal parts of the opposite sides, thus divide the black rectangle into 6×6 small rectangles, except for the outermost layer, all are In each of the small rectangles outside the black and inside, the rectangle with the majority of black is recorded as 0, and the rectangle with the majority of white is recorded as 1, and the data of each row in the black rectangle is concatenated from top to bottom to obtain concatenated data , using the series data as the semantic information contained in the semantic icon, comparing the semantic information represented by the series data with the semantic information of each semantic icon stored in the semantic icon database, and when the comparison results are consistent , then determine that the black rectangle corresponding to the above concatenated data is the correct semantic icon; The center position information of the landing target is calculated according to the semantic information contained in all the semantic icons on the landing target. 5. The method according to claim 4, characterized in that, according to the center position information of the landing target, the attitude and relative positional relationship between the airborne camera and the unmanned aerial vehicle are used to calculate the ground coordinate system. The location and dynamics of the landing target, including: The target coordinate system is established according to the center position information of the landing target, and the coordinate position of the vertex and center of the semantic icon in the target coordinate system is obtained according to the semantic information contained in each semantic icon; The rotation and translation matrix from the target plane to the camera imaging plane is obtained through the one-to-one correspondence between the semantic icon in the target coordinate system and the image pixel coordinates, and the semantic icon is placed on the target according to the rotation and translation matrix from the target plane to the camera imaging plane. The coordinates in the coordinate system are transformed into the coordinates of the semantic icon in the camera coordinate system. According to the conversion formula from the camera coordinate system to the earth coordinate system, the spatial coordinates of the semantic icon in the camera coordinate system are transformed into the coordinates of the semantic icon in the earth coordinate system. coordinate; Taking the geodetic coordinates of the east and north directions of the semantic icon as input, the position and velocity of the landing target in the geodetic coordinate system are calculated by Kalman filtering, and the state vector X=[x , y, v _x , v _y ] ^T and the output vector Y=[x, y] ^T , the state equation of the landing target under the geodetic coordinate system is shown in formula (1): in, Δt is the sampling time interval; W represents system noise with zero mean, which is a Gaussian variable with covariance Q; V represents measurement noise with zero mean, which is a Gaussian variable with covariance R; The rotation and translation matrix from the target plane to the camera imaging plane is shown in formula (2): Among them, (u, v) is the image pixel coordinates, (x, y) is the coordinates of the semantic icon in the target coordinate system, is the internal reference matrix, R is a 3×3 rotation matrix, and T is a 3×1 translation vector; The conversion formula of the camera coordinate system to the earth coordinate system is as shown in formula (3): X _g ＝R _p X _p +X _g0 ＝R _p R _c X _c +X _g0 (3) Among them, X _g , X _p , and X _c are the coordinates of the landing target in the earth coordinate system, the UAV coordinate system, and the camera coordinate system; X _g0 is the current coordinate of the UAV in the earth coordinate system, which is positioned by GNSS The coordinate transformation is obtained; R _p and R _c are the rotation matrices from the UAV system to the earth coordinate system, and from the camera to the UAV coordinate system, respectively. The calculation formula is shown in formula (4), where α is the roll angle and β is the pitch angle, and γ is the yaw angle. 6. The method according to claim 5, wherein the relative position and relative velocity of the unmanned aerial vehicle and the landing target under the geodetic coordinate system are continuously calculated based on the position and dynamic characteristics of the landing target, The drone is controlled to land at the center of the landing target through a triple PID control algorithm, including: Continuously calculate the relative position and relative velocity of the UAV and the landing target in the geodetic coordinate system based on the position and dynamic characteristics of the landing target; Taking the relative position of the UAV and the landing target as input, the UAV is controlled to move to the target through the PID control algorithm; The relative speed of the UAV and the landing target is used as input, superimposed on the speed obtained by the position control, and the dynamic landing target is tracked through the PID control algorithm; Taking the relative height of the UAV and the landing target as input, the UAV is controlled to land on the target through the PID control algorithm.