WO2020078217A1 - Unmanned aerial vehicle-based tracking method and system, unmanned aerial vehicle and terminal - Google Patents

Abstract

Provided are an unmanned aerial vehicle (20, 20')-based tracking method and system, an unmanned aerial vehicle (20, 20') and a terminal (10, 10'). The tracking method comprises: an unmanned aerial vehicle (20, 20') flying according to an acquired search instruction and acquiring real-time images (S101); the unmanned aerial vehicle (20, 20') extracting information of an object needing to be tracked from a currently acquired real-time image according to target information from the terminal (10, 10') and the currently acquired real-time image (S103); the unmanned aerial vehicle (20, 20') calculating a matching degree of the target information and the information of the object needing to be tracked (S105); if the calculated matching degree is greater than a preset matching degree, the unmanned aerial vehicle (20, 20') sending feedback information to the terminal (10, 10'), so that the terminal (10, 10') generates a tracking instruction according to the feedback information (S107); and if the tracking instruction from the terminal (10, 10') is received, the unmanned aerial vehicle (20, 20') sending the current tracking information of the object needing to be tracked to the terminal (10, 10') (S109). Accordingly, tracking target information can be directly sent to the unmanned aerial vehicle (20, 20') through the terminal (10, 10'), with no need to select a tracking target from real-time images returned by the unmanned aerial vehicle (20, 20'). The present invention can be applied to a wider range of scenarios.

Description

UAV-based tracking method, system, UAV and terminal

Related applications cross reference

This application requires the priority of the Chinese patent application filed on October 17, 2018, with the application number 201811211036.9 and the application name "Drone-based tracking method, system, drone and terminal", all of which are approved by The reference is incorporated in this application.

Technical field

The invention relates to the technical field of unmanned aerial vehicles, in particular to a tracking method, system, unmanned aerial vehicle and terminal based on an unmanned aerial vehicle.

Background technique

Many existing drones achieve target tracking by the user selecting the target area in the real-time image returned by the drone; then the drone or the terminal performs target recognition according to the area set by the user; and finally the drone Implement tracking. However, in many occasions, for example, the UAV cannot return real-time images in time due to poor communication transmission quality, and users cannot select targets based on the images returned by the UAV to enable the UAV to achieve target tracking.

Summary of the invention

Embodiments of the present invention provide a tracking method based on a drone, and a system and terminal applying the method, which can be applied in a wider range of occasions.

A first aspect of the present invention provides a drone-based tracking method. The method may include: the drone flies according to the obtained search instruction and obtains a real-time image;

The drone extracts the information of the object to be tracked from the currently acquired real-time image according to the target information from the terminal and the currently acquired real-time image;

The UAV calculates the matching degree between the target information and the object information to be tracked;

If the calculated matching degree is greater than the preset matching degree, the drone sends feedback information to the terminal for the terminal to generate a tracking instruction according to the feedback information;

If a tracking instruction from the terminal is received, the drone sends the current tracking information of the object to be tracked to the terminal.

A second aspect of the present invention provides a drone, which may include:

A first memory for storing a first computer-readable program; and

A first processor is configured to execute the first computer-readable program to implement a tracking method, and the method includes:

Fly according to the obtained search instruction and obtain real-time images;

According to the target information from the terminal and the currently acquired real-time image, extract the object information to be tracked from the currently acquired real-time image;

Calculating the matching degree between the target information and the information of the object to be tracked;

If the calculated matching degree is greater than the preset matching degree, sending feedback information to the terminal for the terminal to generate a tracking instruction according to the feedback information; and

If a tracking instruction from the terminal is received, the corresponding object is tracked, and corresponding tracking information is sent to the terminal.

A third aspect of the present invention also provides a terminal, the terminal includes:

A second memory for storing a second computer-readable program; and

A second processor, configured to execute the second computer-readable program to implement a tracking method, the method including:

Sending a search instruction to the drone to control the drone to fly according to the search instruction and obtain real-time images;

If the feedback information from the drone is received, identify whether to send a tracking instruction to the drone according to the feedback information;

If it is identified that the tracking instruction needs to be sent to the drone, the tracking instruction is sent to the drone to control the drone to return the current tracking information of the object to be tracked.

A fourth aspect of the present invention provides a drone-based tracking system including a drone and a terminal; the drone includes a first memory for storing a first computer-readable program; and

A first processor is configured to execute the first computer-readable program to implement a tracking method, and the method includes:

Fly according to the obtained search instruction and obtain real-time images;

According to the target information from the terminal and the currently acquired real-time image, extract the object information to be tracked from the currently acquired real-time image;

Calculating the matching degree between the target information and the information of the object to be tracked;

If the calculated matching degree is greater than the preset matching degree, sending feedback information to the terminal for the terminal to generate a tracking instruction according to the feedback information; and

If a tracking instruction from the terminal is received, track the corresponding object and send corresponding tracking information to the terminal;

The terminal includes:

A second memory for storing a second computer-readable program; and

A second processor, configured to execute the second computer-readable program to implement a tracking method, the method including:

Sending the search command to the drone to control the drone to fly according to the search command and obtain real-time images;

If the feedback information from the drone is received, determine whether to send the tracking instruction to the drone according to the feedback information;

If it is determined that the tracking instruction needs to be sent to the drone, the tracking instruction is sent to the drone.

As can be seen from the above, embodiments of the present invention provide a drone-based tracking method, and a system and terminal applying the method. A user can directly send tracking target information to the drone through the terminal, and the drone can use Target information can be identified and tracked, and there is no need to select the tracking target in the real-time image returned by the drone, and the application is wider.

BRIEF DESCRIPTION

FIG. 1 is a schematic flowchart of a first example of the tracking method according to the first embodiment of the present invention;

2 is a schematic diagram of a first example of the tracking system according to the first embodiment of the present invention;

3 is a schematic flowchart of a second example of the tracking method according to the first embodiment of the present invention;

4 is a schematic flowchart of a third example of the tracking method according to the first embodiment of the present invention;

5 is a schematic flowchart of a fourth example of the tracking method according to the first embodiment of the present invention;

6 is a schematic diagram of a third example of the tracking method according to the first embodiment of the present invention;

7 is a schematic flowchart of a fourth example of the tracking method according to the first embodiment of the present invention;

8 is a schematic flowchart of a fifth example of the tracking method according to the first embodiment of the present invention;

9 is a schematic flowchart of a first example of a tracking method according to a second embodiment of the invention;

10 is a schematic flowchart of a first example of a tracking system according to a second embodiment of the invention;

11 is a schematic flowchart of a second example of the tracking method according to the second embodiment of the present invention;

12 is a schematic flowchart of a third example of the tracking method according to the second embodiment of the present invention;

13 is a schematic flowchart of a fourth example of the tracking method according to the second embodiment of the present invention;

14 is a schematic flowchart of a fifth example of the tracking method according to the second embodiment of the present invention;

15 is a schematic diagram of a first example of a sub-flow of a tracking method according to a second embodiment of the invention;

16 is a schematic diagram of a second example of the sub-flow of the tracking method according to the second embodiment of the present invention;

17 is a schematic diagram of a third example of the sub-flow of the tracking method according to the second embodiment of the present invention;

18 is a schematic flowchart of a sixth example of the tracking method according to the second embodiment of the present invention;

19 is a schematic flowchart of a seventh example of the tracking method according to the second embodiment of the present invention;

20 is a schematic diagram of functional modules of the tracking system according to the first embodiment of the present invention;

21 is a schematic diagram of functional modules of a tracking system according to a second embodiment of the invention;

22 is a schematic diagram of a first example of a sub-function module of a tracking system according to a second embodiment of the invention;

23 is a schematic diagram of a second example of the sub-function module of the tracking system according to the second embodiment of the present invention;

24 is a schematic structural diagram of a first embodiment of a terminal according to an embodiment of the present invention;

FIG. 25 is a schematic structural diagram of a second embodiment of a terminal according to an embodiment of the present invention.

detailed description

Embodiments of the present invention provide a tracking method based on a drone, and a system and terminal applying the method. A user can directly send tracking target information to the drone through the terminal, and the drone can be identified based on the tracking target information. And tracking, there is no need to select the tracking target in the real-time image returned by the drone, and the application is wider.

1 and 2 are respectively a schematic flowchart of a tracking method based on a drone and a schematic diagram of an operating environment of the tracking method according to an embodiment of the present invention. In this embodiment, the terminal 10 communicates with the drone 20 through the ground station 30. The user can control the drone 20 through the terminal 10 to realize the tracking method. As shown in Figure 1, the tracking method includes:

In step S101, the UAV 20 flies according to the obtained search instruction and obtains a real-time image. In this embodiment, the search command is sent from the terminal 10 to the drone 20. Specifically, the terminal 10 sends the search instruction to the drone 20 in response to user operation. For example, if the tracking target is a vehicle or a person, the user can set a corresponding search strategy according to the possible range or track of the tracking target. Search strategies include flight strategies, such as UAV search path, attitude, bearing, airspeed, etc. The search strategy also includes image acquisition strategies, such as shooting methods, shooting light, and framing strategies. The user sets a corresponding search strategy through the terminal to generate a search instruction and sends it to the drone. After the drone obtains the search instruction, it will fly according to the search instruction.

In step S103, the drone 20 extracts the information of the object to be tracked from the currently acquired real-time image according to the tracking target information from the terminal 10 and the currently acquired real-time image. The tracking target information may be text information or image information. Specifically, the user sends a picture of tracking target information to the drone through the terminal 10. For example, the tracking target is a vehicle, and the user sends the vehicle license plate number to the drone 20 through the terminal 10. For example, the tracking target is a person, and the user sends a face image of the tracking target to the drone 20 through the terminal 10. The face image may be extracted from a picture sent by a non-drone 20, or may be extracted from a picture sent by the drone 20. Specifically, the user can select the face contour of the tracking target in the picture through the terminal 10 or select the face area of the tracking target through the rectangular frame by the terminal 10 and send it to the drone 20. Or the image of the person included in the picture is only the tracking target, and the user can directly send the picture to the drone 20 through the terminal 10. After acquiring the tracking target information, the UAV 20 extracts the tracking target information according to the tracking target information. For example, the tracking target information acquired by the drone 20 is text information, and the drone 20 extracts text information from the currently acquired real-time image. For example, the tracking target information acquired by the drone 20 is face image information, and the drone 20 extracts face image information from the currently acquired real-time image.

In step S105, the UAV 20 calculates the matching degree of the tracking target information and the information of the tracking target. Specifically, the unmanned aerial vehicle 20 compares the acquired tracking target information and the extracted tracking target information to obtain a matching degree. In this embodiment, if it is text information, the matching degree can be set according to the proportion of the number of text matches, for example, 60% of the text is the same, and the matching degree is 60%. If it is image information, the matching degree can be compared according to the feature value of the image information. For example, the face contour is set as the feature value. If the feature values are 70% consistent, the matching degree is 70%.

In step S107, if the calculated matching degree is greater than the preset matching degree, the UAV 20 sends feedback information to the terminal 10 for the terminal 10 to generate a tracking instruction according to the feedback information. Specifically, in this embodiment, the preset matching degree of the text information is greater than the preset matching degree of the image information. Understandably, since the character information recognition technology has higher accuracy than the image information recognition technology, the matching degree is accordingly increased to further reduce errors. In this embodiment, the feedback information is a picture. The following will describe in detail how the terminal generates the tracking command based on the feedback information, which will not be repeated here.

In step S109, if a tracking instruction from the terminal 10 is received, the drone 20 sends corresponding tracking information to the terminal 10. Preferably, the drone 20 also tracks the object to be tracked and sends real-time tracking information to the terminal 10. The tracking information includes the GPS positioning information of the tracking target, the tracking path, time, matching degree, and the type of matching algorithm used. The UAV 20 starts tracking after receiving the tracking instruction from the terminal 10, that is, the UAV 20 initially determines that the object to be tracked is sent to the terminal 10 to further confirm whether the object to be tracked is accurate, and further avoids misjudgement of the tracking target The phenomenon. In addition, the UAV 20 only sends feedback information to the terminal 10 when the matching degree is high, which can reduce the probability of sending wrong feedback information to the terminal 10, avoid adding unnecessary data to the terminal 10, and greatly improve the efficiency and Processing speed.

In the above embodiment, the tracking target information (such as pictures or text information) sent by the terminal 10 to the drone or the terminal 10 receiving feedback information (such as pictures or text information) from the drone 20 need not be the drone 20 Real-time images returned. That is, the terminal 10 and the UAV 20 can use non-real-time information to achieve tracking of the tracking target, so the quality of communication transmission is not high. That is, when the communication transmission quality between the terminal 10 and the drone 20 is not good, the terminal 10 and the drone 20 can also successfully track the tracking target. Therefore, the tracking method of the above embodiment greatly reduces the dependence on the communication transmission quality, and can also be applied in occasions where the communication transmission quality is poor, and the application scenarios are more extensive.

Please refer to FIG. 3, the method further includes the following steps.

In step S301, the drone 20 detects whether an adjustment instruction from the terminal 10 is received, where the adjustment instruction is sent to the drone 20 when the terminal 10 does not receive feedback information from the drone 20 within a preset time. If the adjustment instruction is received, the drone executes step S302, otherwise executes step S103.

Step S302, the drone is flying according to the adjustment instruction.

Since the feedback information is not received within the preset time, the terminal 10 can determine that the search strategy of the drone 20 needs to be adjusted, and thus send an adjustment instruction to the corresponding drone to adjust the search path, thereby improving the efficiency of tracking.

Referring to FIG. 4, after the UAV 20 sends the feedback information, the method further includes the following steps.

In step S401, the drone 20 tracks the object to be tracked.

In step S402, the UAV 20 determines whether the tracking instruction is received within a preset time. If the tracking instruction is received, step S109 is executed; otherwise, step S103 is executed.

Since the UAV 20 initially recognizes the object to be tracked and tracks it in time, it can quickly track the suspicious tracking target and avoid missing the tracking target. In addition, since the UAV 20 has not received the tracking command for a long time after sending the feedback information, it indicates that the feedback information is not the information of the tracking target, but is invalid feedback information, so the search is repeated and the flexibility is strong.

Please refer to FIG. 5, which shows the specific steps of the terminal 10 controlling the UAV 20. Specifically, the tracking method further includes the following steps.

In step S500, the terminal 10 sends a search instruction and tracking target information to the drone 20. The search command and tracking target information can be sent at the same time or in a certain order.

In step S502, if feedback information is received, the terminal 10 displays the received feedback information for the user to identify whether the drone 20 needs the tracking instruction and for the user to input a tracking request based on the feedback information. Specifically, the feedback information includes a picture or feature information including the object to be tracked. In this embodiment, the feedback information is used as an example for illustration. If the picture contains an image of the tracking target, the user can recognize that the drone 20 needs the tracking instruction. The terminal 10 also displays a corresponding confirmation button. If the user recognizes the image containing the tracking target in the picture, the user clicks the corresponding confirmation button to generate the tracking request. In some other feasible embodiments, the feedback information may also require feature information of the tracking object. If the tracking target is a vehicle, the feature information such as vehicle damage information and vehicle license plate is blocked information. If the tracking target is a person, the feature information may be the person's height, body shape, age, human body defects, face contour information, and so on.

In step S504, if the terminal 10 receives the tracking request input by the user, the tracking instruction is generated.

In step S506, the terminal 10 sends the tracking instruction to the drone 20.

In this embodiment, the user can identify and track the target according to the picture sent by the drone 20, to avoid tracking the wrong target, and improve the tracking efficiency and success rate.

In some feasible embodiments, the method further includes step S508: The terminal 10 does not receive the feedback information within a preset time, and generates an adjustment instruction to control the drone 10 to adjust the flight path according to the adjustment instruction.

The above embodiments are described in terms of the corresponding steps in the UAV 20 and the terminal 10 executing the tracking method, respectively, to show the processing procedure of the UAV 20 or the terminal 10 alone executing the tracking method. The following will describe the corresponding steps in the UAV 20 and the terminal 10 cooperating with each other to execute the tracking method, to show the interaction process of the UAV 20 and the terminal 10 when performing the tracking method.

Please refer to FIG. 6, the tracking method includes the following steps.

In step S500, the terminal 10 sends a search instruction and tracking target information to the drone 20.

In step S101, the UAV 20 flies according to the obtained search instruction and obtains a real-time image.

In step S103, the drone 20 extracts the information of the object to be tracked based on the acquired tracking target information and the currently acquired real-time image.

In step S105, the drone 20 calculates the degree of matching between the tracking target information and the information of the target to be tracked.

In step S107, if the calculated matching degree is greater than the preset matching degree, the drone 20 sends feedback information to the terminal 10. Among them, the feedback information is a picture.

In step S502, the terminal 10 displays the received feedback information for the user to identify whether the drone needs a tracking instruction, and for the user to input a tracking request according to the picture.

Step S504, if a tracking instruction input by the user is received, the terminal 10 generates a tracking instruction.

In step S506, the terminal 10 sends the tracking instruction to the drone 20.

In step S109, in response to the tracking instruction, the UAV 20 sends tracking information to the terminal 10 to be tracked.

Please refer to FIG. 7. In some feasible embodiments, the tracking method further includes the following steps. Step S508, if the feedback information of the drone 20 is not received within the preset time, the terminal 10 sends an adjustment instruction.

In step S301, the drone 20 flies according to the adjustment instruction.

Please refer to FIG. 8. In some feasible embodiments, after the UAV 20 sends feedback information, the tracking method further includes the following steps.

In step S401, the drone 20 tracks the object to be tracked.

In step S403, if the tracking instruction is not received within the preset time, the drone 20 executes step S103 and the steps after step S103 again.

Please refer to FIG. 9 and FIG. 10, which are schematic flowcharts of another drone-based tracking method and an operating environment diagram of the tracking method according to an embodiment of the present invention. In this embodiment, the terminal 10 'communicates with several drones 20' through the ground station 30 '. The user can control several drones 20 'through the terminal 10' to realize the tracking method. As shown in FIG. 6, the tracking method includes the following steps.

In step S601, a number of unmanned 20 'aircrafts respectively fly according to the obtained search instructions and obtain real-time images, wherein the search instructions obtained by each UAV 20' are different to control each UAV 20 'to fly according to different search paths. The search command is sent from the terminal 10 'to several drones 20'.

Specifically, the terminal 10 'sends the search instruction to several drones 20' in response to user operations. For example, if the tracking target is a vehicle or a person, the user can set a corresponding search strategy according to the possible range or track of the tracking target. Search strategies include flight strategies, such as UAV search path, attitude, bearing, airspeed, etc. The search strategy also includes image acquisition strategies, such as shooting methods, shooting light, and framing strategies. The user sets a corresponding search strategy through the terminal to generate a search instruction and sends it to the drone 20 '. After acquiring the search command, the UAV 20 'flies according to the search command. Since the exact position of the target is uncertain, in order to speed up the search, the user can set a variety of possible search strategies, thereby generating a variety of different search commands to control the several drones 20 'to search simultaneously to achieve fast positioning tracking The effect of the goal.

In step S603, several drones 20 'extract the information of the object to be tracked from the currently acquired real-time image based on the tracking target information from the terminal 10' and the currently acquired real-time image, respectively. For a detailed description of this step, please refer to step S103, which will not be repeated here.

In step S605, several drones 20 'calculate the matching degree of the tracking target information and the tracking target information, respectively. For a detailed description of this step, please refer to S105, which will not be repeated here.

In step S607, one or more drones 20 'send feedback information to the terminal 10 for the terminal 10 to generate a tracking instruction according to the feedback information, wherein the drones 20' sending the feedback information are calculated that the matching degree is greater than the preset Match the degree of UAV 20 '. For a detailed description of this step, please refer to S107.

In step S609, if one or more UAVs 20 'receive a tracking instruction from the terminal 10', the UAV 20 'that received the tracking instruction sends corresponding tracking information to the terminal 10'. In some feasible embodiments, if one or more drones 20 'receive the tracking instruction from the terminal 10', they also track the object to be tracked. The tracking information includes position information and tracking path information of the tracking object.

In step S611, if one or more drones 20 'receive a return instruction from the terminal 10', one or more drones 20 'return in response to the return instruction. If the drone that needs to track the command is identified, it can be understood that the rest of the unmanned aerial vehicles 20 'still do not need to continue searching, so the terminal 10' generates a return command to control the remaining unmanned Drone 20 'ends the search.

In the above embodiment, the tracking target information (such as pictures or text information) sent by the terminal 10 'to the drone 20' or the terminal 10 'receiving feedback information (such as pictures or text information) from the drone 20' does not require It is a real-time image returned by the UAV 20 ', that is, the terminal 10' and the UAV 20 'can use non-real-time information to achieve tracking of the tracking target, so the quality of communication transmission is not high. That is, when the communication transmission quality between the terminal 10 'and the drone 20' is not good, the terminal 10 'and the drone 20' can also successfully complete the tracking of the tracking target. Therefore, the tracking method of the above embodiment greatly reduces the dependence on the communication transmission quality, and can also be applied in occasions where the communication transmission quality is poor, and the application scenarios are more extensive.

Referring to FIG. 11, after the method executes step S601, the method further includes the following steps.

Step S801, each drone 20 'detects whether an adjustment instruction from the terminal 10' is received, where the adjustment instruction is when the terminal 10 'does not receive feedback information from one or more drones within a preset time Generated and sent to the corresponding UAV 20 '. If the adjustment instruction is received, step S802 is executed, otherwise, step S603 is executed.

In step S802, the drone 20 'that has received the adjustment instruction flies according to the adjustment instruction. Since the feedback information is not received within the preset time, the terminal 10 'can recognize that the search strategy of the drone 20' needs to be adjusted, so as to send an adjustment instruction to the corresponding drone 20 'to adjust the search path, which can improve tracking effectiveness.

Referring to FIG. 12, after one or more drones 20 'send feedback information, the method further includes the following steps.

In step S901, the unmanned aerial vehicles 20 'that send feedback information track their respective tracking objects.

In step S902, the unmanned aerial vehicle 20 'sending feedback information judges whether the tracking instruction is received within a preset time. If the tracking instruction is received, step S609 is executed; otherwise, S603 is executed. Since the UAV sends the feedback information but has not received the tracking instruction for a long time, it indicates that the feedback information is not the information of the tracking target, but is invalid feedback information, so the search is restarted. Understandably, in this embodiment, suspicious tracking targets can be quickly tracked, and missed tracking targets can be avoided. In addition, if the tracking instruction is not received within the preset time, it can be determined that the suspicious object is not the tracking target, and the search is performed again according to the original search strategy, which has greater flexibility.

Please refer to FIG. 13 and FIG. 5 to show the specific steps of the terminal 10 ’controlling the drone 20’. Specifically, the tracking method further includes the following steps.

In step S1000, the terminal 10 'sends several search instructions and tracking target information to several drones 20'. The terminal 10 'may simultaneously search for commands and track target information to the drones 20', or send search commands and track target information to each drone 20 'in a certain order. Several search instructions are different.

In step S1002, if the terminal 10 'receives the feedback information, the drone 20' that needs the tracking instruction is identified based on the feedback information.

In step S1004, the terminal 10 'sends the tracking instruction to the drone 20' that needs the tracking instruction.

In step S1006, the terminal 10 'also generates a return instruction according to the drone that needs the tracking instruction to control the drone 20' that does not need to send the tracking instruction to return. Specifically, if a drone that needs a tracking instruction is identified, it is understandable that the remaining unmanned aerial vehicles 20 'are not considered to continue searching. Therefore, the terminal 10' generates a return instruction to control the remaining unmanned The searching UAV 20 'ends the search.

Referring to FIG. 14, the identification of the drone 20 'that needs to be tracked according to the feedback information specifically includes the following steps.

In step S10021, the terminal 10 'displays the received feedback information for the user to identify the drone 20' requiring the tracking instruction, and the user to input the corresponding tracking request according to the picture. In this embodiment, the feedback information is a picture containing the object to be tracked. Specifically, if the user identifies the tracking target from the picture, the user can recognize that the drone 20 'needs the tracking instruction. In some other feasible embodiments, the feedback information may also be characteristic information of the object to be tracked. For example, if the tracking target is a vehicle, the feature information such as vehicle damage information and vehicle license plate information is blocked. For example, if the tracking target is a person, the characteristic information may be the person's height, body shape, age, and human body defect information. Specifically, the method further includes the following steps.

Step S10022, if the terminal 10 'receives the tracking request input by the user, it identifies the drone 20' that needs the tracking instruction according to the tracking request, and generates a corresponding tracking instruction. Specifically, the terminal 10 'also displays a confirmation button corresponding to the pictures one-to-one. If the user recognizes that there is a tracking target image in the picture displayed on the terminal 10 ', the user clicks the corresponding confirmation button to generate the tracking request. In some other feasible embodiments, if the user recognizes that there is a tracking target image in the picture displayed by the terminal 10 ', the terminal 10' may also input a unique identification code corresponding to the drone 20 'to generate the tracking request. The identification code may be the number of the drone or the IP address.

Referring to FIG. 15, a method flowchart of a second embodiment in which the terminal provides the tracking instruction to the drone according to the feedback information according to an embodiment of the present invention. In this embodiment, the feedback information includes the matching degree and / or the type of matching algorithm used. The following uses feedback information as an example of matching. Specifically, the method further includes the following steps.

In step S1101, the terminal 10 'identifies the unmanned aerial vehicle 20' requiring the tracking instruction according to the received matching degree and the preset condition.

Step S1103, if the terminal recognizes the drone that needs the tracking instruction, generates the tracking instruction and sends it to the drone that needs the tracking instruction.

In this embodiment, it is possible to identify whether a drone that needs a tracking instruction according to the matching degree and send the tracking instruction to the drone that needs a tracking instruction, which reduces the target of tracking errors and improves the efficiency and success rate of tracking.

Please refer to FIG. 16, which is a flowchart of steps in the first implementation example of step S1101.

In step S1202, the terminal 10 'counts the degree of matching received within a preset time. If the count is 1, execute step S1204; if the count is greater than 1, execute step S1206.

In step S1204, if the terminal 10 'receives the matching degree sent by only one drone within a preset time, it is recognized that the drone sending the matching degree needs the tracking instruction.

In step S1206, if the terminal 10 'receives the matching degree sent by the multiple drones 20' within the preset time, the terminal 10 'compares the received matching degree to obtain the highest matching degree.

In step S1208, the terminal 10 'recognizes that the UAV that sends the highest matching degree needs the tracking instruction.

Please refer to FIG. 17, which is a method flowchart of steps in the second implementation example of step S1101.

In step S1302, the terminal 10 'counts the matching degree received within a preset time. If the count is 1, execute step S1304; if the count is greater than 1, execute step 1306.

In step S1304, if the terminal 10 'receives the matching degree sent by only one drone 20' within a preset time, it is recognized that the drone 20 'sending the matching degree needs the tracking instruction.

In step S1306, if the terminal 10 'receives the matching degrees sent by multiple drones 20' within a preset time, the terminal 10 'compares the received matching degrees to obtain the highest number of matching degrees.

In step S1308, the terminal 10 'recognizes that sending the preset number of drones 20' with the highest matching degree requires the tracking instruction.

In some feasible embodiments, if each UAV 20 'uses a different matching algorithm type, the analysis unit compares the matching degrees of the same type when analyzing the highest matching degree. The comparison process refers to the above steps. No longer.

The above embodiments are described in terms of the respective steps in the tracking method performed by the UAV 20 'and the terminal 10', respectively, to show the processing procedure of the UAV 20 'or the terminal 10' performing the tracking method alone. The following will describe the corresponding steps in the UAV 20 'and the terminal 10' cooperating with each other to execute the tracking method to show the interaction process between the UAV 20 'and the terminal 10' when performing the tracking method.

Please refer to FIG. 18, the tracking method includes the following steps.

Step S1000: The terminal 10 'sends several search instructions and tracking target information to several drones 20'.

Step S601: Several drones 10 'fly according to the obtained search instruction and obtain real-time images.

In step S603, a number of drones 20 'extract the information of the object to be tracked from the currently acquired real-time image based on the tracking target information from the terminal 10' and the currently acquired real-time image, respectively.

In step S605, several drones 20 'calculate the matching degree of the tracking target information and the tracking target information, respectively.

In step S607, one or more drones 20 'send feedback information to the terminal 10 for the terminal 10 to generate a tracking instruction according to the feedback information, wherein the drones 20' sending the feedback information are calculated that the matching degree is greater than the preset Match the degree of UAV 20 '.

In step S1002, the terminal 10 'identifies the unmanned aerial vehicle 20' requiring the tracking instruction based on the feedback information.

In step S1004, the terminal 10 'sends the tracking instruction to the drone 20' that needs the tracking instruction.

In step S1006, the terminal 10 'also generates a return instruction according to the drone that needs the tracking instruction to control the drone 20' that does not need to send the tracking instruction to return. Specifically, if the user identifies the drone that needs to track the command, it can be understood that the remaining unmanned drone 20 'is still not required to continue the search, so the terminal 10' generates a return command to control the remaining The search is completed at the UAV 20 'performing the search.

In step S609, the drone 20 'that has received the tracking instruction sends corresponding tracking information to the terminal 10'.

In step S609, the drone 20 'that has received the tracking instruction sends corresponding tracking information to the terminal 10'.

Step S1008: The terminal 10 'generates a return instruction according to the drone that needs the tracking instruction.

In step S611, the drone 20 'that has received the return instruction returns in response to the return instruction.

Referring to FIG. 19, in some feasible embodiments, the tracking method further includes the following steps.

In step S901, the unmanned aerial vehicles 20 'that send feedback information track their respective tracking objects.

In step S403, if the tracking instruction is not received within the preset time, the UAV 20 'sending the feedback information re-executes steps S603 and the steps after step S603.

Please refer to FIG. 2 and FIG. 20, which are schematic diagrams of the tracking system 100 and the terminal 10 of the first embodiment, respectively. The tracking system 100 includes a terminal 10, a drone 20, and a ground station 30. The terminal 10 communicates with the drone 20 through the ground station 30 to control the drone 20 to track the tracking target.

The terminal 10 includes a setting unit 11, a first communication unit 13, and a tracking management unit 14.

The setting unit 11 is used to set a search strategy in response to user operation. Specifically, for example, if the tracking target is a vehicle or a person, the user may set a corresponding search strategy according to the possible range or track of the tracking target. Search strategies include flight strategies, such as UAV search path, attitude, bearing, airspeed, etc. The search strategy also includes image acquisition strategies, such as shooting methods, shooting light, and framing strategies. The user sets the corresponding search strategy through the setting unit 11 and generates a search instruction. The setting unit 11 is also used to send the search instruction to the drone 20 through the first communication unit 13 to control the drone 20 to fly according to the search strategy and obtain real-time images.

The setting unit 11 is further configured to set tracking target information in response to the user's operation, and send the tracking target information to the drone 20 through the first communication unit 13. For example, the tracking target is a vehicle, and the user sets the vehicle license plate number as the tracking target information through the setting unit 11. For example, the tracking target is a person, and the user sets the face image of the tracking target as tracking target information through the setting unit 11. The face image may be extracted from a picture sent by a non-drone 20, or may be extracted from a picture sent by the drone 20. Specifically, the user may select the face contour of the tracking target in the picture through the setting unit 11 or use the rectangular frame to select the face area of the tracking target through the setting unit 11 and set it as tracking target information. Or the image of the person included in the picture is only the tracking target, and the user can directly send the picture to the drone 20 through the setting unit 11.

The tracking management 14 is also used to receive feedback information from the UAV 20 through the first communication unit 13 and identify whether tracking instructions need to be generated according to the feedback information. The tracking management 14 is also used to receive tracking information from the UAV 20 through the first communication unit 13. The feedback information includes picture information, and the picture information includes feature information or pictures. In this embodiment, the feedback information is taken as an example for description. See below for the detailed description of the generation and sending of the feedback information and tracking information. The tracking management 14 specifically includes a display unit 140, an interface providing unit 142, and an instruction generating unit 144.

The display unit 140 is used to display the received picture on the terminal 10 for the user to recognize whether the drone 20 needs the tracking instruction. Specifically, if the picture contains an image of the tracking target, the user can recognize that the drone needs the tracking instruction.

The interface providing unit 142 is used to provide a key and display the key through the display unit 140 for the user to select to generate a tracking request. Specifically, the user can select the key through an input device, such as a mouse, a keyboard, or the like.

The instruction generating unit 144 is used to generate the tracking instruction and send it to the drone 20 through the first communication unit 13 if a tracking request input by the user is received.

The display unit 140 is also used to display the received tracking information.

Referring to FIG. 20, the UAV 20 includes a second communication unit 22, a shooting unit 23, a search unit 24, a feedback unit 26, and a tracking unit 27.

The shooting unit 23 is used to acquire an image. A camera device on the shooting unit 23, such as a camera.

The search unit 24 obtains the search instruction and tracking target information sent by the terminal 10 through the second communication unit 22, and controls the drone 20 to fly and obtain real-time images according to the search instruction. The searching unit 24 is also used to track the target information and the currently acquired real-time image to determine whether it is necessary to send feedback information to the terminal 10. Specifically, the search unit 24 includes a flight control unit 240, a shooting control unit 242, and an image processing unit 244.

The flight control unit 240 is used to control the UAV 20 to fly according to the search instruction according to the search instruction. Specifically, the search instructions include flight strategies, such as the UAV search path, attitude, bearing, and airspeed.

The shooting control unit 242 is used to control the shooting unit 23 to acquire a real-time image according to the search instruction according to the search instruction. Specifically, the search instruction also includes image acquisition strategies such as shooting mode, shooting light, and framing strategy.

The image processing unit 244 is used to extract the information of the object to be tracked from the currently acquired real-time image according to the tracking target information from the terminal and the currently acquired real-time image by the drone, for example, the tracking acquired by the drone The target information is text information, and the drone extracts text information from the currently acquired real-time image. For example, the tracking target information acquired by the drone is a face image, and the drone extracts face information from the currently acquired real-time image.

The image processing unit 242 is also used to calculate the matching degree according to the tracking target information and the tracking target information. Specifically, the image processing unit 242 compares the tracking target information and the tracking target information to calculate a matching degree. In this embodiment, if it is text information, the matching degree can be set according to the proportion of the number of text matches, for example, 60% of the text is the same, and the matching degree is 60%. If it is image information, the matching degree can be compared according to the feature value of the image information. For example, the face contour is set as the feature value. If the feature values are 70% consistent, the matching degree is 70%.

The feedback unit 26 is used to determine whether the calculated matching degree is greater than the preset matching degree, and if the calculated matching degree is greater than the preset matching degree, send feedback information to the terminal 10 for the terminal 10 to generate a tracking instruction according to the feedback information . Specifically, in this embodiment, the preset matching degree of the text information is greater than the preset matching degree of the image information. Understandably, since the character recognition technology has higher accuracy than the image recognition technology, the matching degree is accordingly increased to further reduce errors. In this embodiment, the feedback information is preferably picture information.

The tracking unit 27 is configured to send the information of the object to be tracked in response to the tracking instruction sent from the terminal 10. The tracking unit 27 is also used to track the object to be tracked and send real-time tracking information to the terminal 10. The tracking information includes the GPS positioning information of the tracking target, the tracking path, time, matching degree, and the type of matching algorithm used.

In some feasible embodiments, the flight control unit 240 is also used to adjust the flight strategy of the drone 20 in response to the adjustment instruction sent from the terminal 10.

Please refer to FIG. 7 and FIG. 21 together, which is a schematic diagram of a second embodiment of the tracking system 200 provided by the present invention. The tracking system 200 includes a terminal 10 ', a ground station 30' and a number of drones 20 '. The terminal 10 'is connected to a number of unmanned aerial vehicles 20' through a ground station 30 '.

The terminal 10 'includes a setting unit 11', an instruction generating unit 12 ', a first communication unit 13', and a tracking management unit 14 '.

The setting unit 11 'is used to set a search strategy in response to user operation. Specifically, for example, if the tracking target is a vehicle or a person, the user may set a corresponding search strategy according to the possible range or track of the tracking target. Search strategies include flight strategies, such as UAV search path, attitude, bearing, airspeed, etc. The search strategy also includes image acquisition strategies, such as shooting methods, shooting light, and framing strategies. The user sets a corresponding search strategy through the terminal to generate several different search instructions and sends them to several drones 20 'to control several drones 20' to fly and acquire real-time images according to different search strategies. The setting unit 11 'is different from the setting 11 in that the setting unit 11' is used to set different search strategies for the unmanned aerial vehicles 20 'one by one.

The setting unit 11 'is also used for setting tracking target information in response to the user's operation, and sending the tracking target information to a plurality of drones 20' through the first communication unit 13 '. Among them, the tracking target information sent to several UAVs 20 'is the same. The function of the setting unit 11 'is basically the same as that of the setting unit 11 and will not be repeated here.

The tracking management unit 14 'is also used to receive feedback information from the unmanned aerial vehicle 20' through the first communication unit 13 ', and identify whether a tracking instruction needs to be generated based on the feedback information. The tracking management 14 'is also used to receive tracking information from the drone 20' through the first communication unit 13. Among them, the feedback information includes pictures. See the above for the detailed description of the generation and sending of the feedback information and tracking information.

Please refer to FIG. 22, which is a functional block diagram of the tracking management unit 14 'according to the first embodiment. The tracking management unit 14 'specifically includes a display unit 14001, an interface providing unit 14002, and an instruction generating unit 14004. Among them, each functional module of the tracking management 14 'is basically the same as the tracking management unit 14. The difference is that the interface providing unit 14002 is used to provide several buttons for the user to select to generate a tracking request. The several keys correspond to the displayed pictures one by one, so that a tracking request corresponding to the pictures can be generated. In this embodiment, each picture is associated with the unique identification code of the drone 20 'to distinguish the drone 20' that sent the picture. Further, the interface providing unit 14002 generates the tracking request according to the unique identification code, that is, the tracking request includes the unique identification code of the drone 20 '. Specifically, in some other feasible embodiments, the user may also input the unique identification code of the drone 20 'requiring the tracking instruction through the interface providing unit 14002 to generate the tracking request.

The instruction generating unit 14004 is used to generate a corresponding tracking instruction according to the tracking request input by the user, and send it to the drone 20 'through the first communication unit 13'. Accordingly, the tracking instruction includes the unique identification code of the drone 20 'for the corresponding drone 20' to obtain. The instruction generating unit 14004 is also used to generate a return instruction according to the drone 20 'that needs the tracking instruction to control the return of the drone 20' that does not need to send the tracking instruction. Accordingly, the return instruction contains the unique identification code of the drone 20 '. Understandably, if the user identifies the drone that needs to track the command, the rest of the drones that are still searching are considered to not need to continue searching. Therefore, the command generation unit 14004 sends a return command to the first communication unit 13 ' The corresponding unmanned aerial vehicle 20 'ends the search by controlling the remaining unmanned aerial vehicles.

Please refer to Fig. 23, which is a functional block diagram of the tracking management unit 14 'according to the second embodiment. The tracking management unit 14 'is used to receive feedback information from the unmanned aerial vehicle 20' through the first communication unit 13 ', and identify whether a tracking instruction needs to be generated based on the feedback information. In this embodiment, the feedback information includes the matching degree. Specifically, the tracking management unit 14 'includes an identification unit 14011, and an instruction generation unit 14012.

The recognizing unit 14011 is used to recognize the drone 20 'requiring the tracking instruction according to the received matching degree and preset conditions. The identification unit 14011 includes a counting unit 14013 and an analysis unit 14015.

The counting unit 14013 is used to count the matching degree received within a preset time.

The analysis unit 14015 is used to recognize that the matching degree sent by only one drone 20 'within a preset time, that is, a count of 1, recognizes that the drone needs the tracking instruction. The analysis unit 14015 is also used to receive the matching degree sent by multiple drones 20 'within a preset time, that is, the count is greater than 1, compare the received matching degree to obtain the highest matching degree, and identify the sending The highest matching degree UAV 20 'needs this tracking instruction. In some other feasible embodiments, the analysis unit 14013 is configured to receive the matching degrees sent by multiple drones 20 'within a preset time, and compare the received matching degrees to obtain the highest preset number. Matching degree, and recognizes that the UAV 20 'sending the preset number of highest matching degree needs the tracking instruction.

The instruction generating unit 14012 is used to generate a corresponding tracking instruction according to the tracking request input by the user, and send it to the drone 20 through the first communication unit 13 '. Accordingly, the tracking instruction includes the unique identification code of the drone 20 'for the corresponding drone 20' to obtain. The instruction generating unit 14012 is also used to generate a return instruction according to the drone 20 'that needs the tracking instruction to control the return of the drone 20' that does not need to send the tracking instruction. Accordingly, the return instruction contains the unique identification code of the drone 20 '. Understandably, if the user identifies the drone that needs to track the command, the rest of the drones that are still searching are considered not to need to continue searching. Therefore, the command generation unit 14012 sends a return command to the first communication unit 13 ' The corresponding unmanned aerial vehicle 20 'ends the search by controlling the remaining unmanned aerial vehicles.

In this embodiment, it is possible to identify whether a drone that needs a tracking instruction according to the matching degree and send the tracking instruction to the drone that needs a tracking instruction, which reduces the tracking error target and improves the tracking efficiency and success rate.

In this embodiment, the functions of the UAV 20 'and the UAV 20 are basically the same, the difference is that the UAV 20' is also used to return in response to a return instruction. For the specific function module of the UAV 20 ', please refer to the UAV 20, which will not be repeated here.

24 is a schematic structural composition diagram of another embodiment of a terminal of the present invention. As shown in FIG. 18, the terminal 1000 may include: a first memory 1005 and a first processor 1006, where:

The first memory 1005 is used to store a first computer-readable program. In a specific implementation, the first memory 105 of the embodiment of the present invention may be a system memory, for example, volatile (such as RAM), non-volatile (such as ROM, flash memory, etc.), or a combination of both. In a specific implementation, the first memory 105 in this embodiment of the present invention may also be an external memory outside the system, such as a magnetic disk, an optical disk, or a magnetic tape.

The first processor 1006 is configured to call the first computer-readable program stored in the first memory 1005 and perform the following operations:

Send search commands to the drone;

Send tracking target information to the drone;

If the feedback information of the drone is received, it is recognized whether the drone needs to track the instruction according to the feedback information.

Preferably, the first processor 1006 also performs the following operations:

The received picture is displayed for the user to identify whether the drone needs the tracking instruction. Specifically, if the picture contains an image of the tracking target, the user can recognize that the drone needs the tracking instruction.

If the tracking request input by the user is received, the tracking instruction is generated. Specifically, the terminal also displays a corresponding confirmation button. If the user recognizes that there is a tracking target in the picture displayed on the terminal, the user clicks the corresponding confirmation button to generate the tracking request.

Send the tracking instruction to the drone.

In some other feasible embodiments, the first processor 1006 performs the following operations:

Send some search commands to some drones;

Send tracking target information to several drones;

If the feedback information of the drone is received, it is recognized whether the drone needs to track the instruction according to the feedback information.

In some feasible embodiments, the first processor 1006 also performs the following operations:

Display the received picture within a preset time for the user to identify the drone that needs the tracking instruction, and for the user to input the corresponding tracking request according to the picture;

If a tracking request input by the user is received, the tracking instruction is generated according to the tracking request;

Send the tracking instruction to the drone that needs the tracking instruction;

The unmanned aerial vehicle that needs the tracking instruction generates a return instruction to control the unmanned aerial vehicle that does not need to send the tracking instruction to return.

In some feasible embodiments, the first processor 1006 also performs the following operations:

According to the received matching degree and the preset condition, the drone that needs the tracking instruction is identified.

If a drone that needs to send a tracking instruction is identified, the tracking instruction is generated and sent to the drone that needs the tracking instruction.

In some feasible embodiments, the first processor 1006 also performs the following operations:

Count the matching degree received within the preset time;

If the terminal receives the matching degree sent by only one drone within a preset time, it is recognized that the drone sending the matching degree needs to follow the instruction;

If a matching degree sent by multiple drones is received within a preset time, the terminal compares the received matching degree to obtain the highest matching degree;

It is recognized that the drone sending the highest matching degree needs the tracking instruction.

In some feasible embodiments, the first processor 1006 also performs the following operations:

Count the matching degree received within the preset time;

If the matching degree sent by only one drone is received within a preset time, it is recognized that the drone sending the matching degree needs the tracking instruction;

If the matching degree sent by multiple drones is received within a preset time, the received matching degree is compared to obtain the highest number of matching degrees;

It is recognized that the UAV that sends the preset number of highest matching degrees needs the tracking instruction.

FIG. 25 is a schematic structural composition diagram of another embodiment of the drone of the present invention. As shown in FIG. 19, the drone 2000 may include: a second memory 2005 and a second processor 2006, where:

The second memory 2005 is used to store the first computer readable program. In a specific implementation, the second memory 2005 of the embodiment of the present invention may be a system memory, for example, volatile (such as RAM), non-volatile (such as ROM, flash memory, etc.), or a combination of both. In a specific implementation, the second memory 2005 in this embodiment of the present invention may also be an external memory outside the system, such as a magnetic disk, an optical disk, or a magnetic tape.

The second processor 2006 is configured to call the first computer-readable program stored in the second memory 2005 and perform the following operations:

Fly and obtain real-time images according to the obtained search instructions from the terminal;

Extract the information of the object to be tracked from the currently acquired real-time image according to the tracking target information from the terminal and the currently acquired real-time image;

Calculate the matching degree between the tracking target information and the information of the tracking object;

If the calculated matching degree is greater than the preset matching degree, feedback information is sent to the terminal for the terminal to generate a tracking instruction according to the feedback information;

If a tracking instruction from the terminal is received, the object to be tracked is tracked, and corresponding tracking information is sent to the terminal.

Preferably, the second processor 2006 also performs the following steps:

Check whether the adjustment instruction from the terminal is received;

If an adjustment instruction is detected, the aircraft flies according to the adjustment instruction.

Preferably, the second processor 2006 can also perform the following steps:

Track the object that needs to be tracked;

Determine whether the tracking instruction is received;

If a tracking instruction is received, track the object to be tracked and send the corresponding tracking information to the terminal;

If no tracking command is received, re-flight according to the received search command to continue searching for the tracking target.

In addition, an embodiment of the present invention further provides a computer storage medium. The computer storage medium may store a program, and when the program is executed, part or all of the steps of the method described in the embodiment of the present invention may be executed. In a specific implementation, the computer storage medium in the embodiments of the present invention includes: RAM, ROM, EEPROM, flash memory, CD-ROM, DVD, or other optical storage, magnetic tape, magnetic disk, or other magnetic storage, or any other storage medium that can be used to store required information Media that can be accessed by computer equipment.

Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. In this way, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and equivalent technologies thereof, the present invention is also intended to include these modifications and variations.

The above list is only preferred embodiments of the present invention. Of course, it 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 (10)

1. A drone-based tracking method, characterized in that the method includes:

   The drone flies according to the obtained search instruction and obtains real-time images;

   The drone extracts the information of the object to be tracked from the currently acquired real-time image according to the target information from the terminal and the currently acquired real-time image;

   The UAV calculates the matching degree between the target information and the object information to be tracked;

   If the calculated matching degree is greater than the preset matching degree, the drone sends feedback information to the terminal for the terminal to generate a tracking instruction according to the feedback information;

   If a tracking instruction from the terminal is received, the drone sends the current tracking information of the object to be tracked to the terminal.
2. The tracking method according to claim 1, wherein the feedback information includes a picture including the object to be tracked, and the method further includes:

   The terminal displays the picture for the user to identify whether a tracking request needs to be sent;

   If the terminal receives the tracking request input by the user and determines that the tracking instruction needs to be sent, and generates the tracking instruction;

   The terminal sends the tracking instruction to the drone.
3. The tracking method according to claim 1, wherein the method further comprises:

   If the drone receives an adjustment instruction from the terminal, the drone flies according to the adjustment instruction, wherein the adjustment instruction is that the terminal does not receive feedback information within a preset time and sends Give the drone.
4. The tracking method according to claim 3, wherein:

   If the drone does not receive the tracking instruction or the adjustment instruction within a preset time after sending the matching degree, re-execute the drone according to the target information from the terminal and the currently acquired real-time image The object information to be tracked is extracted from the currently acquired real-time image.
5. The tracking method according to claim 1, wherein if the drone sends the feedback information, the method further comprises:

   The UAV tracking needs to track objects;

   If the tracking instruction is not received within a preset time, the drone re-executes the object information to be tracked from the currently acquired real-time image according to the target information from the terminal and the currently acquired real-time image.
6. A drone, characterized in that the drone includes:

   A first memory for storing a first computer-readable program; and

   A first processor is configured to execute the first computer-readable program to implement a tracking method, and the method includes:

   Fly according to the obtained search instruction and obtain real-time images;

   According to the target information from the terminal and the currently acquired real-time image, extract the object information to be tracked from the currently acquired real-time image;

   Calculating the matching degree between the target information and the information of the object to be tracked;

   If the calculated matching degree is greater than the preset matching degree, sending feedback information to the terminal for the terminal to generate a tracking instruction according to the feedback information; and

   If a tracking instruction from the terminal is received, the corresponding object is tracked, and corresponding tracking information is sent to the terminal.
7. The drone according to claim 6, wherein if the feedback information is sent, the tracking method further includes:

   Track the object that needs to be tracked;

   If the tracking instruction is not received within a preset time, the target information from the terminal and the currently acquired real-time image are re-executed to extract the information of the object to be tracked from the currently acquired real-time image.
8. The drone according to claim 7, characterized in that

   If the drone does not receive the tracking instruction or the adjustment instruction within a preset time after sending the matching degree, re-execute the drone according to the target information from the terminal and the currently acquired real-time image The object information to be tracked is extracted from the currently acquired real-time image.
9. A terminal is characterized in that the terminal includes:

   A second memory for storing a second computer-readable program; and

   A second processor, configured to execute the second computer-readable program to implement a tracking method, the method including:

   Sending a search instruction to the drone to control the drone to fly according to the search instruction and obtain real-time images;

   If the feedback information from the drone is received, identify whether to send a tracking instruction to the drone according to the feedback information;

   If it is identified that the tracking instruction needs to be sent to the drone, the tracking instruction is sent to the drone to control the drone to return the current tracking information of the object to be tracked.
10. A tracking system based on a drone, the tracking system includes a drone and a terminal, characterized in that the drone includes:

    A first memory for storing a first computer-readable program; and

    A first processor is configured to execute the first computer-readable program to implement a tracking method, and the method includes:

    Fly according to the obtained search instruction and obtain real-time images;

    According to the target information from the terminal and the currently acquired real-time image, extract the object information to be tracked from the currently acquired real-time image;

    Calculating the matching degree between the target information and the information of the object to be tracked;

    If the calculated matching degree is greater than the preset matching degree, sending feedback information to the terminal for the terminal to generate a tracking instruction according to the feedback information; and

    If a tracking instruction from the terminal is received, track the corresponding object and send corresponding tracking information to the terminal;

    The terminal includes:

    A second memory for storing a second computer-readable program; and

    A second processor, configured to execute the second computer-readable program to implement a tracking method, the method including:

    Sending the search command to the drone to control the drone to fly according to the search command and obtain real-time images;

    If the feedback information from the drone is received, determine whether to send the tracking instruction to the drone according to the feedback information;

    If it is determined that the tracking instruction needs to be sent to the drone, the tracking instruction is sent to the drone.

Images