Control method and device for movable platform

Abstract

A control method and device for a movable platform, the method comprising: determining whether a target object is in a stationary state (S301); when the target object is in a stationary state, running a multi-view geometry algorithm according to multiple frames of images collected by a shooting device to determine a first position of the target object, and controlling the movable platform to perform a work task on the target object according to the first position (S302); when the target object is in a moving state, determining a second position of the target object according to the size of an image area of ​​the target object in an image collected by the shooting device, and controlling the movable platform to perform a work task on the target object according to the second position (S303), thereby improving the accuracy of the position of the target object in different states. Moreover, the movable platform can be controlled to perform a work task on the target object according to the above position, and the execution effect of the work task is better.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of mobile platforms, and in particular, to a control method and device for a mobile platform. Background Art

[0002] After the drone selects a target object, it can fly with reference to the target object. For example, the drone can move along a fixed trajectory relative to the target object. Common scenarios include automatic surround shooting, automatic inspection, autonomous monitoring, etc.

[0003] Taking active surround shooting as an example, the drone needs to observe the position of the target and fly around the target according to the position of the target. The position of the observed target can be determined by the following method: the drone runs a multi-view geometry algorithm through multiple frames of images collected by the shooting device to determine the position of the target. However, this method is suitable for the target to be stationary. If the target is in motion, the above method is still used, and the position of the target determined is inaccurate. Summary of the invention

[0004] The embodiments of the present application provide a control method and device for a movable platform, which are used to accurately determine the position of a target object.

[0005] In a first aspect, an embodiment of the present application provides a control method for a movable platform, wherein the movable platform includes a photographing device, and the method includes:

[0006] Determine whether the target object is stationary;

[0007] When the target object is in a stationary state, a multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine a first position of the target object, and the movable platform is controlled to perform a work task on the target object according to the first position;

[0008] When the target object is in motion, the second position of the target object is determined according to the size of the image area of ​​the target object in the image captured by the shooting device, and the movable platform is controlled to perform the work task on the target object according to the second position.

[0009] In a second aspect, an embodiment of the present application provides a control device for a movable platform, the movable platform comprising a photographing device, the control device for the movable platform comprising: a memory and at least one processor;

[0010] The memory is used to store program code;

[0011] The at least one processor is configured to execute the program code to:

[0012] Determine whether the target object is stationary;

[0013] When the target object is in a stationary state, a multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine a first position of the target object, and the movable platform is controlled to perform a work task on the target object according to the first position;

[0014] When the target object is in motion, the second position of the target object is determined according to the size of the image area of ​​the target object in the image captured by the shooting device, and the movable platform is controlled to perform the work task on the target object according to the second position.

[0015] In a third aspect, an embodiment of the present application provides a movable platform, which includes a photographing device and a control device of the movable platform as described in the embodiment of the present application in the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon; when the computer program is executed, the control method of the movable platform as described in the embodiment of the present application in the first aspect is implemented.

[0017] In a sixth aspect, an embodiment of the present application provides a program product, which includes a computer program, wherein the computer program is stored in a readable storage medium, at least one processor can read the computer program from the readable storage medium, and the at least one processor executes the computer program to implement the control method of the movable platform as described in the embodiment of the present application in the first aspect.

[0018] In summary, the control method and device of the movable platform provided in the embodiment of the present application determines the first position of the target object by running a multi-view geometry algorithm based on the multiple frames of images captured by the shooting device when the target object is in a stationary state, and determines the second position of the target object based on the image area size of the target object in the image captured by the shooting device when the target object is in a moving state. The position of the target object is determined in different ways according to different states of the target object, thereby improving the accuracy of the determined position of the target object. Moreover, the movable platform can be controlled according to the above position to perform a work task on the target object, and the execution effect of the work task is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 is a schematic architecture diagram of an unmanned aerial system according to an embodiment of the present application;

[0021] Figure 2 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0022] Figure 3 A flow chart of a control method for a movable platform provided in one embodiment of the present application;

[0023] Figure 4 A schematic diagram of running a multi-view geometry algorithm based on multiple frames of images captured by a shooting device to determine the position of a target object in a stationary state provided by an embodiment of the present application;

[0024] Figure 5 A schematic diagram of running a multi-view geometry algorithm based on multiple frames of images captured by a shooting device to determine the position of a target object in motion provided by an embodiment of the present application;

[0025] Figure 6 A schematic diagram of determining that a target object is in a stationary state provided by an embodiment of the present application;

[0026] Figure 7 A schematic diagram of determining that a target object is in a moving state provided by an embodiment of the present application;

[0027] Figure 8 A schematic diagram of the structure of a control device for a movable platform provided in one embodiment of the present application;

[0028] Fig. 9 A schematic diagram of the structure of a movable platform provided in one embodiment of the present application;

[0029] Fig.10 A schematic structural diagram of a movable platform provided in another embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there can be a central component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there can be a central component at the same time.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0033] Embodiments of the present application provide control methods and devices for movable platforms. Among them, the movable platform can be a drone, an unmanned vehicle, an unmanned ship, a robot, a handheld gimbal, etc. The following description of the movable platform of the present application uses a drone as an example. It will be apparent to those skilled in the art that other types of drones can be used without restriction, and the embodiments of the present application can be applied to various types of drones. For example, the drone can be a small or large drone. In some embodiments, the drone can be a rotorcraft, for example, a multi-rotor drone propelled by a plurality of propulsion devices through the air, and the embodiments of the present application are not limited thereto.

[0034] Figure 1 1 is a schematic diagram of the architecture of an unmanned aerial system according to an embodiment of the present application. This embodiment is described by taking a rotary wing unmanned aerial vehicle as an example.

[0035] The unmanned aerial system 100 may include a drone 110, a display device 130, and a control terminal 140. The drone 110 may include a power system 150, a flight control system 160, a rack, and a gimbal 120 carried on the rack. The drone 110 may communicate wirelessly with the control terminal 140 and the display device 130. The drone 110 also includes a battery (not shown in the figure), which provides power to the power system 150. The drone 110 may be an agricultural drone or an industrial application drone, which has a demand for cyclic operation. Correspondingly, the battery also has a demand for cyclic operation.

[0036] The frame may include a fuselage and a foot frame (also called a landing gear). The fuselage may include a center frame and one or more arms connected to the center frame, and the one or more arms extend radially from the center frame. The foot frame is connected to the fuselage to provide support when the drone 110 lands.

[0037] The power system 150 may include one or more electronic speed regulators (referred to as ESCs) 151, one or more propellers 153, and one or more motors 152 corresponding to the one or more propellers 153, wherein the motor 152 is connected between the electronic speed regulator 151 and the propeller 153, and the motor 152 and the propeller 153 are arranged on the arm of the drone 110; the electronic speed regulator 151 is used to receive the drive signal generated by the flight control system 160, and provide a drive current to the motor 152 according to the drive signal to control the speed of the motor 152. The motor 152 is used to drive the propeller to rotate, thereby providing power for the flight of the drone 110, and the power enables the drone 110 to achieve one or more degrees of freedom. In some embodiments, the drone 110 can rotate around one or more rotation axes. For example, the above-mentioned rotation axes may include a roll axis (Roll), a yaw axis (Yaw), and a pitch axis (pitch). It should be understood that the motor 152 may be a DC motor or an AC motor. In addition, the motor 152 may be a brushless motor or a brushed motor.

[0038] The flight control system 160 may include a flight controller 161 and a sensor system 162. The sensor system 162 is used to measure the attitude information of the drone, that is, the position information and state information of the drone 110 in space, such as three-dimensional position, three-dimensional angle, three-dimensional velocity, three-dimensional acceleration and three-dimensional angular velocity. The sensor system 162 may include at least one of sensors such as a gyroscope, an ultrasonic sensor, an electronic compass, an inertial measurement unit (IMU), a visual sensor, a global navigation satellite system and a barometer. For example, the global navigation satellite system may be a global positioning system (GPS). The flight controller 161 is used to control the flight of the drone 110, for example, the flight of the drone 110 may be controlled according to the attitude information measured by the sensor system 162. It should be understood that the flight controller 161 may control the drone 110 according to pre-programmed instructions, or may control the drone 110 by responding to one or more remote control signals from the control terminal 140.

[0039] The gimbal 120 may include a motor 122. The gimbal is used to carry a load, and the load may be, for example, a shooting device 123. The flight controller 161 may control the movement of the gimbal 120 through the motor 122. Optionally, as another embodiment, the gimbal 120 may also include a controller for controlling the movement of the gimbal 120 by controlling the motor 122. It should be understood that the gimbal 120 may be independent of the drone 110 or may be a part of the drone 110. It should be understood that the motor 122 may be a DC motor or an AC motor. In addition, the motor 122 may be a brushless motor or a brushed motor. It should also be understood that the gimbal may be located at the top of the drone or at the bottom of the drone.

[0040] The shooting device 123 can be, for example, a device for capturing images, such as a camera or a video camera. The shooting device 123 can communicate with the flight controller and shoot under the control of the flight controller. The shooting device 123 of this embodiment includes at least a photosensitive element, such as a complementary metal oxide semiconductor (CMOS) sensor or a charge-coupled device (CCD) sensor. It can be understood that the shooting device 123 can also be directly fixed on the drone 110, so that the gimbal 120 can be omitted.

[0041] The display device 130 is located at the ground end of the unmanned aerial system 100, can communicate with the drone 110 in a wireless manner, and can be used to display the attitude information of the drone 110. In addition, the image captured by the camera 123 can also be displayed on the display device 130. It should be understood that the display device 130 can be an independent device or integrated in the control terminal 140.

[0042] The control terminal 140 is located at the ground end of the unmanned aerial system 100 and can communicate with the drone 110 in a wireless manner to remotely control the drone 110 .

[0043] It should be understood that the above-mentioned naming of the components of the unmanned aerial system is for identification purposes only and should not be construed as a limitation on the embodiments of the present application.

[0044] Figure 2 The following is a schematic diagram of an application scenario provided by an embodiment of the present application, such as Figure 2 As shown, Figure 2The figure shows a drone 201 and a control terminal 202 of the drone. The control terminal 202 of the drone 201 can be one or more of a remote control, a smart phone, a desktop computer, a laptop computer, and a wearable device (a watch, a bracelet). The embodiment of the present application takes the control terminal 202 as a remote control 2021 and a terminal device 2022 as an example for schematic illustration. The terminal device 2022 is, for example, a smart phone, a wearable device, a tablet computer, etc., but the embodiment of the present application is not limited thereto.

[0045] The drone 201 includes a fuselage 2011 and a gimbal 2012 connected to the fuselage 2011, and the gimbal 2012 is used to carry a load 2013. Among them, the load 2013 includes a shooting device, and the drone transmits the image captured by the shooting device to the control terminal 202, and the control terminal 202 displays the image captured by the shooting device. In the scene where the drone 201 tracks the target object or the drone 201 flies around the target object, the drone 201 needs to determine the position of the target object. Therefore, the present application proposes that the method of observing the position of the target object when the target object is in a stationary state is different from the method of observing the position of the target object when the target object is in a moving state. For example, when the target object is in a stationary state, the position of the target object is determined according to the multi-view geometry algorithm; when the target object is in a moving state, the position of the target object is determined according to the image area size of the target object in the collected image. So as to accurately determine the position of the target object when the target object is in different states.

[0046] Figure 3 This is a flow chart of a control method for a mobile platform provided in an embodiment of the present application. The method of this embodiment can be applied to a control device for a mobile platform. The control device for the mobile platform can be arranged on the mobile platform; or, a part of the control device for the mobile platform is arranged on the mobile platform, and another part is arranged on a control terminal of the mobile platform. This embodiment takes the control device for the mobile platform being arranged on the mobile platform as an example. Figure 3 As shown, the method of this embodiment may include:

[0047] S301: Determine whether the target object is in a stationary state.

[0048] In this embodiment, the movable platform includes a shooting device, which is used to shoot the target object so that the target object is located in the image captured by the shooting device. The movable platform can determine whether the target object shot by the shooting device is in a stationary state. If it is determined that the target object is in a stationary state, S302 is executed. If it is determined that the target object is not in a stationary state, for example, the target object is in a moving state, S303 is executed.

[0049] S302: When the target object is stationary, a multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine a first position of the target object, and the movable platform is controlled to perform a work task on the target object according to the first position.

[0050] In this embodiment, when the target object is stationary, the shooting device can shoot an image including the target object. The movable platform runs a multi-view geometry algorithm based on the multiple frames of images collected by the shooting device to determine the position of the target object, which is called the first position. The first position can be used to guide the movable platform to perform a corresponding work task. Then, the movable platform is controlled to perform the work task on the target object according to the first position.

[0051] Among them, one implementation method of determining the position of the target object by running multi-view geometry based on the multiple frames of images collected by the shooting device is: when the target object is stationary, according to the principle of epipolar geometry, such as Figure 4 As shown in A in FIG, a frame of image captured by the camera is taken as the first frame of image. The camera can determine the position of the target object on a ray connecting the camera and the target object by observing a single frame of image, and thus determine the direction of the target object. However, the distance between the camera and the target object cannot be determined based on the first frame of image. Figure 4 As shown in B in , the shooting device captures the next frame of image after the first frame of image, which is called the second frame of image. According to the second frame of image, a ray representing the direction of the target object can be determined. According to the intersection of the two determined rays, the position of the target object is obtained, that is, the position of the target object determined according to the first and second frames of image. The shooting device continues to shoot the third frame of image, and according to the position of the target object determined above, the target object is projected into the first frame of image, the second frame of image, and the third frame of image to obtain three projection positions respectively. According to the three projection positions (for example, the sum of the reprojection errors corresponding to the three projection positions is the smallest), the position of the target object is optimized to obtain the optimized position of the target object. The shooting device continues to shoot the fourth frame of image, and according to the optimized position of the target object, the target object is projected into the first frame of image, the second frame of image, the third frame of image, and the fourth frame of image to obtain four projection positions respectively. According to the four projection positions (for example, the sum of the reprojection errors corresponding to the four projection positions is the smallest), the position of the target object is optimized to obtain the optimized position of the target object again. By analogy, the position of the target object is optimized, so that the accurate position of the target object when it is in a stationary state can be obtained through multiple frames of images. Optionally, the above method can also be called a triangulation distance measurement method.

[0052] S303: When the target object is in motion, determine a second position of the target object according to the size of an image area of ​​the target object in an image captured by a shooting device, and control the movable platform to perform a work task on the target object according to the second position.

[0053] When the target object is in motion, if the multi-view geometry algorithm is run based on the multiple frames of images collected by the shooting device to determine the position of the target object, such as Figure 5 As shown, two rays are determined based on two frames of images captured by the shooting device, but the intersection of the two rays is not located at the position of the target object. Therefore, the position of the target object in motion cannot be obtained by the above method when the target object is in a stationary state.

[0054] In this embodiment, when the target object is in motion, the camera device may also capture an image including the target object, and the target object is located in the image captured by the camera device and occupies a portion of the image area in the image. The movable platform determines the position of the target object according to the size of the image area of ​​the target object in the image captured by the camera device, and this position is referred to as the second position. The second position can be used to guide the movable platform to perform a corresponding work task. Then, the movable platform is controlled to perform the work task on the target object according to the second position.

[0055] Among them, one implementation method of determining the position of the target object based on the image area size of the target object in the image captured by the shooting device is: the ray representing the direction of the target object can be determined through a single-frame image of the shooting device; based on the image area size of the target object in the image captured by the shooting device and prior information of the target object (such as prior size, for example, the prior size of the target object being a car is different from the prior size of the target object being a person), the distance between the target object and the shooting device is determined, and the position of the target object can be determined based on the distance and the direction of the target object.

[0056] In this embodiment, when the target object is in a stationary state, a multi-view geometry algorithm is run based on multiple frames of images captured by the shooting device to determine the first position of the target object, and when the target object is in a moving state, the second position of the target object is determined based on the size of the image area of ​​the target object in the image captured by the shooting device. By using different methods to determine the position of the target object according to different states of the target object, the accuracy of the determined position of the target object is improved. Moreover, the movable platform can be controlled to perform a work task on the target object according to the above position, and the execution effect of the work task is better.

[0057] In some embodiments, the work task is at least one of an circling flight task and a tracking task. If the work task is an circling flight task, the movable platform is controlled to fly around the target object according to the first position or the second position. The trajectory of the movable platform flying around the target object can be an involute, or a spiral, or a circular arc with a constant radius (or a circumferential line). This embodiment can accurately circle the target object and quickly follow the target object.

[0058] In some embodiments, when the target object is stationary, after the first position of the target object is obtained, the first position of the target object is no longer updated. That is, the multi-view geometry algorithm is no longer run based on the multiple frames of images captured by the shooting device to update the first position of the target object. Even if the shooting device continues to capture images, the first position of the target object is no longer optimized based on the image. This can save processing resources and avoid the influence of noise in a certain frame of image on the shooting effect. It can also ensure that when the target object is stationary, the movable platform is controlled to perform work tasks on the target object according to the same fixed first position, thereby improving the performance of the work tasks. For example, the movable platform is fixed around the center of the target object to ensure the smoothness of the surrounding path.

[0059] In some embodiments, when the target object is in motion, after obtaining the second position of the target object, the second position of the target object is updated to improve the accuracy of the position determined when the target object is in motion and improve the performance of the work task.

[0060] In some embodiments, a possible implementation of S302 is: running a multi-view geometry algorithm based on multiple frames of images captured by the shooting device to determine a first distance between the target object and the shooting device, and determining a first position of the target object based on the first distance.

[0061] In this embodiment, a multi-view geometry algorithm is run according to multiple frames of images captured by the shooting device to determine the distance between the target object and the shooting device, and this distance is referred to as a first distance.

[0062] Optionally, the first distance is determined as the first position of the target object, wherein the position can be represented by the distance. Alternatively, since the target object is photographed by the camera, the target object occupies an image area in the image photographed by the camera, and the direction of the target object can be determined based on the image area, and the first position is determined based on the direction of the target object and the first distance.

[0063] In addition, when the target object is stationary, the distance between the target object and the shooting device can also be determined based on the size of the image area of ​​the target object in the image captured by the shooting device, which is called the second distance. The specific implementation process can refer to the above description and will not be repeated here. Among them, for the same target object, if the image size of the target object in the image captured by the shooting device is smaller, it indicates that the distance between the target object and the shooting device is farther. Conversely, if the image size of the target object in the image captured by the shooting device is larger, it indicates that the distance between the target object and the shooting device is closer. In this embodiment, in determining the distance between the target object and the shooting device, since it is necessary to use the prior size of the target object, there may be a deviation between the prior size and the actual size of the target object. Compared with the second distance, the above-mentioned first distance is closer to the actual distance between the target object and the shooting device. Therefore, there is a distance deviation between the first distance and the second distance obtained in different ways.

[0064] Therefore, the movable platform of this embodiment can also obtain a distance correction deviation, where the distance correction deviation is used to characterize the distance deviation between the first distance and the second distance.

[0065] Correspondingly, a possible implementation of S303 is: determining a third distance between the target object and the shooting device according to the image area size of the target object in the image captured by the shooting device, and determining the second position of the target object according to the third distance and the distance correction deviation.

[0066] In this embodiment, when the target object is in motion, the distance between the target object and the shooting device is determined according to the size of the image area of ​​the target object in the image captured by the shooting device, and this distance is called the third distance. However, as mentioned above, the prior size of the target object needs to be referred to in the process of determining the third distance, so there is an error between the third distance and the distance between the target object and the shooting device. In addition, since the distance between the target object and the shooting device determined by running the multi-view geometry algorithm based on the multiple frames of images captured by the shooting device is closer to the distance between the target object and the shooting device, according to the above-mentioned distance correction deviation, the third distance is transformed into the distance between the target object and the shooting device determined by running the multi-view geometry algorithm based on the multiple frames of images captured by the shooting device when the target object is in motion, and this distance is called the corrected distance. The corrected distance is closer to the distance between the target object and the shooting device, and then the second position of the target object is determined according to the corrected distance. Since the deviation of the third distance is corrected in this embodiment, the correction accuracy is higher, so that the obtained second position is closer to the actual position of the target object, which improves the accuracy of the position of the target object determined when the target object is in motion.

[0067] Optionally, the corrected distance is determined as the second position of the target object, wherein the position can be represented by the distance. Alternatively, since the target object is photographed by the camera, the target object occupies an image area in the image photographed by the camera, and the direction of the target object can be determined based on the image area, and the second position is determined based on the direction of the target object and the corrected distance.

[0068] Several possible implementation methods of obtaining the distance correction deviation are described below with examples.

[0069] In a possible implementation, when the target object is stationary, the second distance between the target object and the shooting device is determined according to the size of the image area of ​​the target object in the image captured by the shooting device; and the distance correction deviation is determined according to the first distance and the second distance. When the target object is stationary, a multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine the first distance between the target object and the shooting device, and the first distance is closer to the distance between the target object and the shooting device when the target object is stationary. In order to obtain the distance between the target object and the shooting device determined by the multi-view geometry algorithm, relative to the distance between the target object and the shooting device determined according to the image area size, the distance deviation, in this embodiment, when the target object is stationary, determines the second distance between the target object and the shooting device according to the size of the image area of ​​the target object in the image captured by the shooting device. Then, according to the distance between the target object and the shooting device obtained according to different methods when the target object is in the same state, the above-mentioned distance correction deviation is determined according to the first distance and the second distance.

[0070] Optionally, the distance correction deviation is obtained by subtracting the second distance from the first distance. Accordingly, the distance after correction is, for example, equal to the sum of the third distance and the distance correction deviation.

[0071] Optionally, the distance correction deviation is obtained by dividing the first distance by the second distance. Accordingly, the distance after correction is, for example, equal to the product of the third distance and the distance correction deviation.

[0072] Optionally, the distance correction deviation is obtained by subtracting the second distance from the first distance and then dividing the first distance by the second distance. Accordingly, the distance after correction is, for example, equal to the sum of the third distance and (the product of the third distance and the distance correction deviation).

[0073] It should be noted that the manifestation of the distance correction deviation is not limited to this.

[0074] Optionally, when the target object is stationary, multiple frames of images captured by the shooting device are obtained, and the second distance between the target object and the shooting device is determined according to the size of the image area of ​​the target object in each frame of the image captured by the shooting device, and the above-mentioned distance correction deviation is determined according to the first distance and multiple second distances. For example: determine the mean of multiple second positions, and then determine the above-mentioned distance correction deviation according to the first distance and the mean. Alternatively, determine the distance correction deviation according to the first distance and each second distance, and then determine the mean of the multiple distance correction deviations as the final distance correction deviation.

[0075] In this embodiment, when the target object is in a stationary state, the distance correction deviation is calculated to more accurately reflect the deviation between the target object and the shooting device obtained in different ways under the same state of the target object. Then, when the target object is in a moving state, a more accurate position of the target object is obtained based on the distance correction deviation.

[0076] In another possible implementation, one or more reference distance correction deviations are pre-stored in the local storage device of the movable platform. The movable platform of this embodiment can obtain at least one reference distance correction deviation from the local storage device of the movable platform, and then determine the above-mentioned distance correction deviation based on the at least one reference distance correction deviation obtained. If a reference distance correction deviation is obtained from the local storage device of the movable platform, the reference distance correction deviation is determined as the above-mentioned distance correction deviation. If multiple reference distance correction deviations are obtained from the local storage device of the movable platform, the mean, maximum value, minimum value, or median of the multiple reference distance correction deviations is determined as the above-mentioned distance correction deviation.

[0077] Since the distance correction deviation of this embodiment is pre-stored in the local storage device of the movable platform, the distance correction deviation can be obtained from the local storage device without having to be calculated and obtained when the target object is in a stationary state, thus saving processing resources.

[0078] Several implementations of obtaining at least one reference distance correction deviation from a local storage device of a movable platform and determining a distance correction deviation according to the at least one reference distance correction deviation are described below by way of example.

[0079] In a possible implementation, a local storage device of a movable platform pre-stores reference distance correction deviations corresponding to multiple object types, and the multiple object types include: cars, people, etc. Each object type corresponds to a reference distance correction deviation, and optionally, each object type may correspond to multiple reference distance correction deviations. The reference distance correction deviations corresponding to different object types may be different. In this embodiment, the movable platform determines the object type of the target object according to the image captured by the shooting device, obtains the reference distance correction deviation matching the object type of the target object from the local storage device of the movable platform according to the object type of the target object, and determines the reference distance correction deviation as the above-mentioned distance correction deviation. Here, taking the object type of the target object as an example, in this embodiment, the reference distance correction deviation corresponding to the car is obtained from the multiple reference distance correction deviations corresponding to the car, people, etc. pre-stored in the local storage device of the movable platform. If the reference distance correction deviation corresponding to the car obtained from the local storage device of the movable platform is one, the reference distance correction deviation is determined as the above-mentioned distance correction deviation. If there are multiple reference distance correction deviations corresponding to the car obtained from the local storage device of the movable platform, the mean, maximum, minimum or median of the multiple reference distance correction deviations is determined as the above-mentioned distance correction deviation.

[0080] In another possible implementation, a local storage device of the movable platform pre-stores reference distance correction deviations corresponding to a plurality of reference distances. Each reference distance corresponds to a reference distance correction deviation, and optionally, each reference distance may correspond to a plurality of reference distance correction deviations. The reference distance correction deviations corresponding to different reference distances may be different.

[0081] Optionally, when the target object is stationary, the movable platform determines the first distance between the target object and the shooting device through the above-mentioned schemes. Then, according to the first distance, a reference distance correction deviation corresponding to at least one reference distance is obtained from the local storage device of the movable platform, and the distance correction deviation is determined according to the reference distance correction deviation. If the first distance is included in multiple reference distances, one or more pre-stored reference distance correction deviations corresponding to the first distance are obtained from the local storage device of the movable platform. If the first distance is not included in the multiple reference distances, one or more pre-stored reference distance correction deviations corresponding to the reference distance closest to the first distance are obtained from the local storage device of the movable platform in this embodiment. Alternatively, if the first distance is not included in the multiple reference distances, one or more pre-stored reference distance correction deviations corresponding to two reference distances adjacent to the first distance are obtained from the local storage device of the movable platform in this embodiment.

[0082] If there is one reference distance correction deviation obtained from the local storage device of the movable platform according to the first distance, the reference distance correction deviation is determined as the above-mentioned distance correction deviation. If there are multiple reference distance correction deviations corresponding to the car obtained from the local storage device of the movable platform according to the first distance, the mean, maximum, minimum or median of the multiple reference distance correction deviations is determined as the above-mentioned distance correction deviation.

[0083] Optionally, in this embodiment, when the target object is stationary, the movable platform determines the second distance between the target object and the shooting device according to the size of the image area of ​​the target object in the image captured by the shooting device. According to the second distance, a reference distance correction deviation corresponding to at least one reference distance is obtained from a local storage device of the movable platform, and a distance correction deviation is determined according to the reference distance correction deviation. For the specific implementation process, please refer to the above description of determining the distance correction deviation for the first distance, which will not be repeated here.

[0084] Optionally, in this embodiment, the movable platform determines the third distance between the target object and the shooting device in the above manner when the target object is in motion. Then, according to the third distance, a reference distance correction deviation corresponding to at least one reference distance is obtained from the local storage device of the movable platform, and the distance correction deviation is determined according to the reference distance correction deviation. The specific implementation process can refer to the above description of determining the distance correction deviation based on the first distance, which will not be repeated here.

[0085] In any of the above embodiments, a possible implementation method for determining whether the target object is in a stationary state is to obtain multiple frames of images containing the target object captured by the shooting device, and determine whether the target object is in a stationary state based on the multiple frames of images. In this embodiment, the shooting device can capture multiple frames of images, and the multiple frames of images include the target object. Then, it is determined whether the target object is in a stationary state based on the multiple frames. In this way, it is possible to quickly and stably detect whether the target object is in a stationary state or in a moving state, and at the same time, it is possible to avoid the influence of noise of a certain frame of image on the result.

[0086] The following is an example of how to determine whether the target is in a stationary state based on the multiple frames of images.

[0087] In one possible implementation, a multi-view geometry algorithm is run based on multiple frames of images to determine a fourth position of the target object at multiple moments; it is determined whether the multiple fourth positions satisfy a preset position convergence condition; if so, the target object is determined to be in a stationary state, otherwise, the target object is determined to be in a moving state.

[0088] Optionally, each frame of image may correspond to a moment, and a possible implementation method of running a multi-view geometry algorithm based on multiple frames of image to determine the fourth position of the target object at multiple moments is: the shooting device sequentially captures multiple frames of image, and when the shooting device captures the second frame of image at the second moment, the fourth position of the target object at the second moment can be determined based on the first frame of image and the second frame of image. When the shooting device captures the third frame of image at the third moment, the fourth position of the target object at the third moment can be determined based on the first frame of image, the second frame of image, and the third frame of image. When the shooting device captures the fourth frame of image at the fourth moment, the fourth position of the target object at the fourth moment can be determined based on the first frame of image, the second frame of image, the third frame of image, and the fourth frame of image. And so on, the fourth position of the target object at multiple moments can be obtained. For details on how to obtain the above-mentioned fourth position, please refer to Figure 3 The relevant description of S302 in the illustrated embodiment will not be repeated here. Then determine whether the multiple fourth positions meet the preset position convergence condition, such as whether the multiple fourth positions converge to the same position, for example, determine that the multiple fourth positions are within a preset range area, and the preset range area can represent the covariance of the convergence of the fourth positions. When the multiple fourth positions meet the preset position convergence condition, it means that the position of the target object has basically not changed at these moments, and it is determined that the target object is in a stationary state. When the multiple fourth positions do not meet the preset position convergence condition, it means that the position of the target object is changing, and it is determined that the target object is in a moving state.

[0089] Optionally, each frame image may correspond to a moment, and another possible implementation method for determining the fourth position of the target object at multiple moments is: a cyclic triangulation scheme is proposed in this implementation method, that is, multiple triangulation rangefinders are instantiated at one time, updated over time, the oldest triangulation rangefinder is deleted in real time, and the latest triangulation rangefinder is added. Specifically, a triangulation rangefinder is instantiated according to two adjacent frames of images.

[0090] For example, a position is obtained by running a multi-view geometry algorithm based on at least two frames of images, and multiple positions can be obtained in the same manner. The following takes obtaining a position from two frames of images as an example, but this embodiment is not limited to two frames of images.

[0091] The camera captures multiple frames of images in sequence. For example, 8 frames of images captured by the camera at 8 moments are taken. After the camera captures the first frame of image at the first moment and the second frame of image at the second moment, a fourth position of the target object can be determined based on the first frame of image and the second frame of image (for example, see Figure 4After the 3rd frame of image is acquired at the 3rd moment and the 4th frame of image is acquired at the 4th moment, a fourth position of the target object can be determined according to the 3rd frame of image and the 4th frame of image. After the 5th frame of image is acquired at the 5th moment and the 6th frame of image is acquired at the 6th moment, a fourth position of the target object can be determined according to the 5th frame of image and the 6th frame of image. After the 7th frame of image is acquired at the 7th moment and the 8th frame of image is acquired at the 8th moment, a fourth position of the target object can be determined according to the 7th frame of image and the 8th frame of image.

[0092] When the target object is stationary, the position of the target object remains basically unchanged. Figure 6 As shown, it can be determined that the above four fourth positions of the target object converge within the same preset range area, indicating that the target object is in a stationary state.

[0093] When the target object is in motion, the position of the target object changes. Figure 7 As shown, it can be determined that the fourth positions of the target object at the above four moments cannot converge into the same preset range area, indicating that the target object is in a moving state.

[0094] In another possible implementation, after acquiring multiple frames of images, the target object may be included in each frame of the image, and the target object occupies an image area in each frame of the image. In this embodiment, whether the target object is in a stationary state may be determined based on the size of the image area of ​​the target object in each frame of the image. For example, if the target object is moving, the image size of the target object in the image is different. Therefore, it can be determined whether the difference between the image area sizes of the target object in each frame of the image is less than a preset difference. If so, it is determined that the target object is in a stationary state, otherwise it is determined that the target object is in a moving state.

[0095] In any of the above embodiments, the movable platform determines whether the target object switches from a stationary state to a moving state during the process of controlling the movable platform to perform a work task on the target object according to the first position.

[0096] In this embodiment, when the target object is in a stationary state, after determining the first position, the movable platform is controlled to perform a work task on the target object according to the first position. Since the first position is used for the movable platform to perform a work task when the target object is in a stationary state. If the target object is in a moving state, the first position cannot be used to control the movable platform to perform the work task, otherwise the movable platform cannot perform the above-mentioned work task on the target object. Therefore, in the process of controlling the movable platform to perform the work task on the target object according to the first position, it is determined whether the target object switches from a stationary state to a moving state. If it is determined that the target object has not switched from a stationary state to a moving state, it means that the target object is still in a stationary state, and the movable platform continues to be controlled to perform the work task on the target object according to the first position. If it is determined that the target object switches from a stationary state to a moving state, it means that the target object is in a moving state, then the second position of the target object is determined according to the image area size of the target object in the image captured by the shooting device, and the movable platform is controlled to perform the work task on the target object according to the second position.

[0097] Among them, a possible implementation method for determining whether the target object switches from a static state to a moving state is: obtaining multiple frames of images acquired by a shooting device; and identifying the position of the target object in the multiple frames of images; projecting the target object into the multiple frames of images according to a first position to obtain the projection position of the target object in the image; and determining whether the target object switches from a static state to a moving state according to the identified position and the projection position.

[0098] In this embodiment, in the process of controlling the movable platform to perform a work task on the target object according to the first position, multiple frames of images captured by the shooting device are obtained, and then the position of the target object in each frame of the image is identified (wherein, how to identify the position of the target object in the image can be referred to the description in the neural network model or image tracking and other related technologies, which will not be repeated here), and the target object is projected into each frame of the image according to the above-mentioned first position to obtain the projection position of the target object in each frame of the image. For each frame of the image, the deviation between the identified position and the projection position is determined, which can be called a reprojection error. Based on the reprojection errors corresponding to the multiple frames of images (i.e., multiple reprojection errors), it is determined whether the target object has switched from a static state to a moving state.

[0099] For example, it is determined whether multiple reprojection errors meet the preset error convergence conditions, that is, whether these multiple reprojection errors converge to the same error. For example, it is determined that these multiple reprojection errors are within the preset error range. If multiple reprojection errors meet the preset error convergence conditions, it means that the position of the target object has basically not changed, and it is determined that the target object is still in a static state. When multiple reprojection errors do not meet the preset error convergence conditions, it means that the position of the target object begins to change, and it is determined that the target object begins to move, and the target object switches from a static state to a moving state.

[0100] For example, if it is determined based on multiple reprojection errors that the reprojection errors are getting larger, it is determined that the target object starts to move. Or, if some of the multiple reprojection errors are small and some are large, it is determined that the target object starts to move. Thus, it is determined that the target object switches from a static state to a moving state.

[0101] Therefore, through the above-mentioned methods of this embodiment, it is possible to detect in real time and quickly that the target object switches from a static state to a moving state. Then, it can be seamlessly switched to: determining the second position of the target object according to the size of the image area of ​​the target object in the image captured by the shooting device, and controlling the movable platform to perform the work task on the target object according to the second position. This avoids a sudden change in the determined position when switching from a static state to a moving state. Therefore, the path is smooth during the process of the movable platform performing the work task on the target object, and no sudden jitter occurs.

[0102] Optionally, the photographing device in the above embodiments may be a monocular camera.

[0103] A computer storage medium is also provided in an embodiment of the present application. The computer storage medium stores program instructions. When the program is executed, it may include some or all steps of the control method of the movable platform in any of the above embodiments.

[0104] Figure 8 This is a schematic diagram of the structure of a control device for a movable platform provided in an embodiment of the present application, wherein the movable platform includes a photographing device, such as Figure 8 As shown, the control device 800 of the movable platform includes: at least one processor 801, and one processor 801 is shown as an example in the figure.

[0105] The at least one processor 801 is configured to:

[0106] Determine whether the target object is stationary;

[0107] When the target object is in a stationary state, a multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine a first position of the target object, and the movable platform is controlled to perform a work task on the target object according to the first position;

[0108] When the target object is in motion, the second position of the target object is determined according to the size of the image area of ​​the target object in the image captured by the shooting device, and the movable platform is controlled to perform the work task on the target object according to the second position.

[0109] Optionally, when the target object is in a stationary state, the first position of the target object is no longer updated.

[0110] Optionally, when the at least one processor 801 runs a multi-view geometry algorithm according to the multiple frames of images captured by the shooting device to determine the first position of the target object, it is specifically configured to:

[0111] A multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine a first distance between the target object and the shooting device, and a first position of the target object is determined according to the first distance.

[0112] The at least one processor 801 is also used to: obtain a distance correction deviation, wherein the distance correction deviation is used to characterize a distance deviation between the first distance and a second distance, the second distance being the distance between the target object and the shooting device determined according to an image area size of the target object in an image captured by the shooting device when the target object is in a stationary state.

[0113] The at least one processor 801, when determining the second position of the target object according to the size of the image area of ​​the target object in the image captured by the shooting device, is specifically configured to:

[0114] A third distance between the target object and the shooting device is determined according to an image area size of the target object in the image captured by the shooting device, and a second position of the target object is determined according to the third distance and the distance correction deviation.

[0115] Optionally, the at least one processor 801 is specifically used to: when the target object is stationary, determine a second distance between the target object and the shooting device according to the size of an image area of ​​the target object in the image captured by the shooting device; and determine the distance correction deviation according to the first distance and the second distance.

[0116] Optionally, one or more reference distance correction deviations are pre-stored in a local storage device of the movable platform, and the at least one processor 801 is specifically configured to:

[0117] At least one reference distance correction deviation is obtained from a local storage device of the movable platform, and the distance correction deviation is determined according to the at least one reference distance correction deviation.

[0118] Optionally, reference distance correction deviations corresponding to a plurality of object types are pre-stored in a local storage device of the movable platform, and the at least one processor 801 is further used to determine the object type of the target object according to the image captured by the shooting device.

[0119] The at least one processor 801, when acquiring at least one reference distance correction deviation from the local storage device of the movable platform and determining the distance correction deviation according to the at least one reference distance correction deviation, is specifically configured to:

[0120] A reference distance correction deviation matching the object type of the target object is acquired from a local storage device of the movable platform according to the object type of the target object, and the reference distance correction deviation is determined as the distance correction deviation.

[0121] Optionally, a reference distance correction deviation corresponding to a plurality of reference distances is pre-stored in a local storage device of the movable platform. The at least one processor 801 is specifically configured to: obtain a reference distance correction deviation corresponding to at least one reference distance from the local storage device of the movable platform according to the first distance, and determine the distance correction deviation according to the reference distance correction deviation.

[0122] Optionally, the distance correction deviation corresponding to multiple reference distances pre-stored in a local storage device of the movable platform is obtained. The at least one processor 801 is further used to: when the target object is stationary, determine a second distance between the target object and the shooting device according to the image area size of the target object in the image captured by the shooting device.

[0123] The at least one processor 801, when acquiring at least one reference distance correction deviation from the local storage device of the movable platform and determining the distance correction deviation according to the at least one reference distance correction deviation, is specifically configured to:

[0124] A reference distance correction deviation corresponding to at least one reference distance is acquired from a local storage device of the movable platform according to the second distance, and the distance correction deviation is determined according to the reference distance correction deviation.

[0125] Optionally, the distance correction deviation corresponding to a plurality of pre-stored reference distances is obtained from a local storage device of the movable platform.

[0126] The at least one processor 801 is specifically configured to: obtain a reference distance correction deviation corresponding to at least one reference distance from a local storage device of the movable platform according to the third distance, and determine the distance correction deviation according to the reference distance correction deviation.

[0127] Optionally, the at least one processor 801 is specifically used to: acquire a plurality of frames of images containing a target object captured by the shooting device; and determine whether the target is in a stationary state based on the plurality of frames of images.

[0128] Optionally, the at least one processor 801 is specifically used to: run a multi-view geometry algorithm based on the multiple frame images to determine the fourth position of the target object at multiple moments; determine whether the multiple fourth positions meet a preset position convergence condition; when satisfied, determine that the target object is in a stationary state, otherwise, determine that the target object is in a moving state.

[0129] Optionally, the at least one processor 801 is further configured to:

[0130] In the process of controlling the movable platform to perform a work task on the target object according to the first position, it is determined whether the target object switches from a stationary state to a moving state.

[0131] Optionally, the at least one processor 801 is specifically used to: acquire multiple frames of images captured by a shooting device; identify the position of a target object in the multiple frames of images; project the target object into the multiple frames of images according to the first position to obtain the projection position of the target object in the image; and determine whether the target object switches from a static state to a moving state according to the identified position and the projection position.

[0132] Optionally, the work task is at least one of an circling mission and a tracking mission.

[0133] Optionally, the control device 800 of the mobile platform of this embodiment may further include a memory 802. The memory 802 is used to store program codes. The at least one processor 801 calls the program codes, and when the program codes are executed, they are used to implement the above methods.

[0134] The control device of the movable platform of this embodiment can be used to execute the technical solutions of the above-mentioned method embodiments of this application. Its implementation principles and technical effects are similar and will not be repeated here.

[0135] Fig. 9This is a schematic diagram of the structure of a movable platform provided in an embodiment of the present application. The movable platform 900 includes a shooting device 901 and at least one processor 902. The figure shows one processor 902 as an example.

[0136] The at least one processor 902 is used to: determine whether the target object is in a stationary state; when the target object is in a stationary state, run a multi-view geometry algorithm based on the multiple frames of images captured by the shooting device 901 to determine a first position of the target object, and control the movable platform 900 to perform a work task on the target object based on the first position; when the target object is in a moving state, determine the second position of the target object based on the size of the image area of ​​the target object in the image captured by the shooting device 901, and control the movable platform 900 to perform the work task on the target object based on the second position.

[0137] Optionally, when the target object is in a stationary state, the first position of the target object is no longer updated.

[0138] Optionally, when the at least one processor 902 runs a multi-view geometry algorithm according to the multiple frames of images captured by the shooting device 901 to determine the first position of the target object, it is specifically configured to:

[0139] A multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device 901 to determine a first distance between the target object and the shooting device 901, and a first position of the target object is determined according to the first distance.

[0140] The at least one processor 902 is also used to: obtain a distance correction deviation, wherein the distance correction deviation is used to characterize a distance deviation between the first distance and a second distance, the second distance being the distance between the target object and the shooting device 901 determined according to an image area size of the target object in an image captured by the shooting device 901 when the target object is in a stationary state.

[0141] The at least one processor 902, when determining the second position of the target object according to the image area size of the target object in the image captured by the shooting device 901, is specifically configured to:

[0142] A third distance between the target object and the shooting device 901 is determined according to the image area size of the target object in the image captured by the shooting device 901, and a second position of the target object is determined according to the third distance and the distance correction deviation.

[0143] Optionally, the at least one processor 902 is specifically used to: when the target object is stationary, determine a second distance between the target object and the shooting device 901 according to the size of an image area of ​​the target object in the image captured by the shooting device 901; and determine the distance correction deviation according to the first distance and the second distance.

[0144] Optionally, the mobile platform 900 of this embodiment further includes a local storage device 903. The local storage device 903 of the mobile platform 900 pre-stores one or more reference distance correction deviations, and the at least one processor 902 is specifically configured to:

[0145] At least one reference distance correction deviation is obtained from the local storage device 903 of the movable platform 900, and the distance correction deviation is determined according to the at least one reference distance correction deviation.

[0146] Optionally, reference distance correction deviations corresponding to a plurality of object types are pre-stored in the local storage device 903 of the movable platform 900 , and the at least one processor 902 is further used to determine the object type of the target object according to the image captured by the shooting device 901 .

[0147] The at least one processor 902, when acquiring at least one reference distance correction deviation from the local storage device 903 of the movable platform 900 and determining the distance correction deviation according to the at least one reference distance correction deviation, is specifically configured to:

[0148] According to the object type of the target object, a reference distance correction deviation matching the object type of the target object is acquired from the local storage device 903 of the movable platform 900 , and the reference distance correction deviation is determined as the distance correction deviation.

[0149] Optionally, reference distance correction deviations corresponding to a plurality of reference distances are pre-stored in the local storage device 903 of the movable platform 900 .

[0150] The at least one processor 902 is specifically configured to: obtain a reference distance correction deviation corresponding to at least one reference distance from a local storage device 903 of the movable platform 900 according to the first distance, and determine the distance correction deviation according to the reference distance correction deviation.

[0151] Optionally, the local storage device 903 of the movable platform 900 acquires the distance correction deviation corresponding to the plurality of pre-stored reference distances, and the at least one processor 902 is further configured to:

[0152] When the target object is stationary, the second distance between the target object and the shooting device 901 is determined according to the size of the image region of the target object in the image captured by the shooting device 901 .

[0153] The at least one processor 902, when acquiring at least one reference distance correction deviation from the local storage device 903 of the movable platform 900 and determining the distance correction deviation according to the at least one reference distance correction deviation, is specifically configured to:

[0154] According to the second distance, a reference distance correction deviation corresponding to at least one reference distance is obtained from the local storage device 903 of the movable platform 900, and the distance correction deviation is determined according to the reference distance correction deviation.

[0155] Optionally, the distance correction deviation corresponding to multiple pre-stored reference distances is obtained from the local storage device 903 of the movable platform 900. The at least one processor 902 is specifically configured to: obtain a reference distance correction deviation corresponding to at least one reference distance from the local storage device 903 of the movable platform 900 according to the third distance, and determine the distance correction deviation according to the reference distance correction deviation.

[0156] Optionally, the at least one processor 902 is specifically used to: acquire a plurality of frames of images containing a target object captured by the shooting device 901; and determine whether the target is in a stationary state based on the plurality of frames of images.

[0157] Optionally, the at least one processor 902 is specifically used to: run a multi-view geometry algorithm based on the multiple frame images to determine a fourth position of the target object at multiple moments; determine whether the multiple fourth positions satisfy a preset position convergence condition; when satisfied, determine that the target object is in a stationary state, otherwise, determine that the target object is in a moving state.

[0158] Optionally, the at least one processor 902 is further configured to:

[0159] In the process of controlling the movable platform 900 to perform a work task on the target object according to the first position, it is determined whether the target object switches from a stationary state to a moving state.

[0160] Optionally, the at least one processor 902 is specifically used to: acquire multiple frames of images captured by the shooting device 901; identify the position of the target object in the multiple frames of images; project the target object into the multiple frames of images according to the first position to obtain the projection position of the target object in the image; and determine whether the target object switches from a static state to a moving state according to the identified position and the projection position.

[0161] Optionally, the work task is at least one of an circling mission and a tracking mission.

[0162] Optionally, the mobile platform 900 of this embodiment may further include a memory (not shown in the figure). The memory is used to store program codes. The at least one processor 902 calls the program codes, and when the program codes are executed, they are used to implement the above methods.

[0163] The memory and the storage device 903 may be the same component or different components.

[0164] The movable platform of this embodiment can be used to execute the technical solutions of the above-mentioned method embodiments of this application. The implementation principles and technical effects are similar and will not be repeated here.

[0165] Fig.10 This is a schematic diagram of the structure of a movable platform provided in another embodiment of the present application, wherein the movable platform 1000 includes a photographing device 1001 and a control device 1002 of the movable platform.

[0166] The control device 1002 of the movable platform can be used Figure 8 The structure of the device embodiment shown can correspondingly execute the technical solution provided by any of the above-mentioned method embodiments, which will not be repeated here.

[0167] Optionally, the movable platform 1000 further includes a storage device 1003. The storage device 1003 is used to pre-store one or more reference distance correction deviations.

[0168] Those skilled in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc. Various media that can store program codes.

[0169] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A control method for a movable platform, characterized in that: The movable platform includes a photographing device, and the method includes: Determine the state of the target object; In response to the target object being in a stationary state, a multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine a first position of the target object, and the movable platform is controlled to perform a work task on the target object according to the first position; In response to the target object being in motion, a second position of the target object is determined according to an image area size of the target object in an image captured by the shooting device, and the movable platform is controlled to perform the work task on the target object according to the second position.

2. The method according to claim 1, characterized in that When the target object is in a stationary state, the first position of the target object is no longer updated.

3. The method according to claim 1 or 2, characterized in that: The step of running a multi-view geometry algorithm according to the multiple frames of images captured by the shooting device to determine the first position of the target object includes: Running a multi-view geometry algorithm according to the multiple frames of images captured by the shooting device to determine a first distance between the target object and the shooting device, and determining a first position of the target object according to the first distance; The method further includes: acquiring a distance correction deviation, wherein the distance correction deviation is used to characterize a distance deviation between the first distance and a second distance, wherein the second distance is a distance between the target object and the shooting device determined according to an image area size of the target object in an image captured by the shooting device when the target object is stationary; The determining the second position of the target object according to the size of the image area of ​​the target object in the image captured by the shooting device includes: A third distance between the target object and the shooting device is determined according to an image area size of the target object in the image captured by the shooting device, and a second position of the target object is determined according to the third distance and the distance correction deviation.

4. The method according to claim 3, characterized in that The obtaining of the distance correction deviation comprises: When the target object is stationary, determining a second distance between the target object and the shooting device according to the size of an image area of ​​the target object in the image captured by the shooting device; The distance correction deviation is determined based on the first distance and the second distance.

5. The method according to claim 3, characterized in that: One or more reference distance correction deviations are pre-stored in the local storage device of the movable platform, and obtaining the distance correction deviation includes: At least one reference distance correction deviation is obtained from a local storage device of the movable platform, and the distance correction deviation is determined according to the at least one reference distance correction deviation.

6. The method according to claim 5, characterized in that The local storage device of the movable platform pre-stores reference distance correction deviations corresponding to a plurality of object types, and the method further includes: determining the object type of the target object according to the image captured by the photographing device; The acquiring at least one reference distance correction deviation from a local storage device of the movable platform, and determining the distance correction deviation according to the at least one reference distance correction deviation, comprises: According to the object type of the target object, a reference distance correction deviation matching the object type of the target object is acquired from a local storage device of the movable platform, and the reference distance correction deviation is determined as the distance correction deviation.

7. The method according to claim 5, characterized in that The local storage device of the movable platform pre-stores reference distance correction deviations corresponding to a plurality of reference distances; Acquiring at least one reference distance correction deviation from a local storage device of the movable platform, and determining the distance correction deviation according to the at least one reference distance correction deviation, comprising: A reference distance correction deviation corresponding to at least one reference distance is acquired from a local storage device of the movable platform according to the first distance, and the distance correction deviation is determined according to the reference distance correction deviation.

8. The method according to claim 5, characterized in that The distance correction deviation corresponding to a plurality of pre-stored reference distances is obtained from a local storage device of the movable platform, and the method further comprises: When the target object is in a stationary state, determining a second distance between the target object and the shooting device according to the size of an image area of ​​the target object in the image captured by the shooting device; Acquiring at least one reference distance correction deviation from a local storage device of the movable platform, and determining the distance correction deviation according to the at least one reference distance correction deviation, comprising: A reference distance correction deviation corresponding to at least one reference distance is acquired from a local storage device of the movable platform according to the second distance, and the distance correction deviation is determined according to the reference distance correction deviation.

9. The method according to claim 5, characterized in that Acquiring the distance correction deviations corresponding to a plurality of pre-stored reference distances from a local storage device of the movable platform; Acquiring at least one reference distance correction deviation from a local storage device of the movable platform, and determining the distance correction deviation according to the at least one reference distance correction deviation, comprising: A reference distance correction deviation corresponding to at least one reference distance is acquired from a local storage device of the movable platform according to the third distance, and the distance correction deviation is determined according to the reference distance correction deviation.

10. The method according to claim 1, characterized in that The step of determining whether the target object is in a stationary state comprises: Acquire multiple frames of images containing the target object captured by the shooting device; Determine whether the target is in a stationary state according to the multiple frames of images.

11. The method according to claim 10, characterized in that The step of determining whether the target is in a stationary state according to the multiple frames of images comprises: Running a multi-view geometry algorithm based on the multiple frames of images to determine a fourth position of the target object at multiple moments; Determining whether the plurality of fourth positions satisfy a preset position convergence condition; If the condition is satisfied, it is determined that the target object is in a stationary state; otherwise, it is determined that the target object is in a moving state.

12. The method according to claim 1, characterized in that The method further comprises: In the process of controlling the movable platform to perform a work task on the target object according to the first position, it is determined whether the target object switches from a stationary state to a moving state.

13. The method according to claim 12, characterized in that The determining whether the target object switches from a stationary state to a moving state comprises: Acquire multiple frames of images captured by a shooting device; Identify the location of the target object in the multiple frames of images; Projecting the target object into the multiple frames of images according to the first position to obtain a projection position of the target object in the image; It is determined whether the target object switches from a stationary state to a moving state according to the identified position and the projection position.

14. The method according to claim 1, characterized in that The work task is at least one of an circling mission and a tracking mission.

15. A control device for a movable platform, characterized in that: The movable platform includes a photographing device, and the control device of the movable platform includes: a memory and at least one processor; The memory is used to store program codes; The at least one processor is configured to execute the program code to: Determine the state of the target object; In response to the target object being in a stationary state, a multi-view geometry algorithm is run according to the multiple frames of images captured by the shooting device to determine a first position of the target object, and the movable platform is controlled to perform a work task on the target object according to the first position; In response to the target object being in motion, a second position of the target object is determined according to an image area size of the target object in an image captured by the shooting device, and the movable platform is controlled to perform the work task on the target object according to the second position.

16. The control device according to claim 15, characterized in that: When the target object is in a stationary state, the first position of the target object is no longer updated.

17. The control device according to claim 15 or 16, characterized in that: The at least one processor, when running a multi-view geometry algorithm according to the multiple frames of images acquired by the shooting device to determine the first position of the target object, is specifically used to: Running a multi-view geometry algorithm according to the multiple frames of images captured by the shooting device to determine a first distance between the target object and the shooting device, and determining a first position of the target object according to the first distance; The at least one processor is further configured to: obtain a distance correction deviation, wherein the distance correction deviation is used to characterize a distance deviation between the first distance and a second distance, wherein the second distance is a distance between the target object and the shooting device determined according to an image area size of the target object in an image captured by the shooting device when the target object is stationary; The at least one processor, when determining the second position of the target object according to the size of the image area of ​​the target object in the image captured by the shooting device, is specifically configured to: A third distance between the target object and the shooting device is determined according to an image area size of the target object in the image captured by the shooting device, and a second position of the target object is determined according to the third distance and the distance correction deviation.

18. The control device according to claim 17, characterized in that: The at least one processor is specifically configured to: When the target object is stationary, determining a second distance between the target object and the shooting device according to the size of an image area of ​​the target object in the image captured by the shooting device; The distance correction deviation is determined based on the first distance and the second distance.

19. The control device according to claim 17, characterized in that: One or more reference distance correction deviations are pre-stored in the local storage device of the movable platform, and the at least one processor is specifically configured to: At least one reference distance correction deviation is obtained from a local storage device of the movable platform, and the distance correction deviation is determined according to the at least one reference distance correction deviation.

20. The control device according to claim 19, characterized in that The local storage device of the movable platform pre-stores reference distance correction deviations corresponding to a plurality of object types, and the at least one processor is further configured to: determining the object type of the target object according to the image captured by the photographing device; The at least one processor, when acquiring at least one reference distance correction deviation from the local storage device of the movable platform and determining the distance correction deviation according to the at least one reference distance correction deviation, is specifically configured to: According to the object type of the target object, a reference distance correction deviation matching the object type of the target object is acquired from a local storage device of the movable platform, and the reference distance correction deviation is determined as the distance correction deviation.

21. The control device according to claim 19, characterized in that The local storage device of the movable platform pre-stores reference distance correction deviations corresponding to a plurality of reference distances; The at least one processor is specifically configured to: obtain a reference distance correction deviation corresponding to at least one reference distance from a local storage device of the movable platform according to the first distance, and determine the distance correction deviation according to the reference distance correction deviation.

22. The control device according to claim 19, characterized in that The local storage device of the movable platform acquires the distance correction deviation corresponding to a plurality of pre-stored reference distances, and the at least one processor is further configured to: When the target object is in a stationary state, determining a second distance between the target object and the shooting device according to the size of an image area of ​​the target object in the image captured by the shooting device; The at least one processor, when acquiring at least one reference distance correction deviation from the local storage device of the movable platform and determining the distance correction deviation according to the at least one reference distance correction deviation, is specifically configured to: A reference distance correction deviation corresponding to at least one reference distance is acquired from a local storage device of the movable platform according to the second distance, and the distance correction deviation is determined according to the reference distance correction deviation.

23. The control device according to claim 19, characterized in that Acquiring the distance correction deviations corresponding to a plurality of pre-stored reference distances from a local storage device of the movable platform; The at least one processor is specifically configured to: obtain a reference distance correction deviation corresponding to at least one reference distance from a local storage device of the movable platform according to the third distance, and determine the distance correction deviation according to the reference distance correction deviation.

24. The control device according to claim 15, characterized in that The at least one processor is specifically configured to: Acquire multiple frames of images containing the target object captured by the shooting device; Determine whether the target is in a stationary state according to the multiple frames of images.

25. The control device according to claim 24, characterized in that The at least one processor is specifically configured to: Running a multi-view geometry algorithm based on the multiple frames of images to determine a fourth position of the target object at multiple moments; Determining whether the plurality of fourth positions satisfy a preset position convergence condition; If the condition is satisfied, it is determined that the target object is in a stationary state; otherwise, it is determined that the target object is in a moving state.

26. The control device according to claim 15, characterized in that The at least one processor is further configured to: In the process of controlling the movable platform to perform a work task on the target object according to the first position, it is determined whether the target object switches from a stationary state to a moving state.

27. The control device according to claim 26, characterized in that The at least one processor is specifically configured to: Acquire multiple frames of images captured by a shooting device; Identify the location of the target object in the multiple frames of images; Projecting the target object into the multiple frames of images according to the first position to obtain a projection position of the target object in the image; It is determined whether the target object switches from a stationary state to a moving state according to the identified position and the projection position.

28. The control device according to claim 15, characterized in that The work task is at least one of an circling mission and a tracking mission.

29. A movable platform, characterized in that: The movable platform comprises a photographing device and a control device of the movable platform as described in any one of claims 15-28.

30. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program; when the computer program is executed, it implements the control method of the movable platform according to any one of claims 1 to 14.

Images