Aircraft positioning method, apparatus and aircraft

Abstract

The embodiment of the application provides a kind of aircraft positioning method, device and aircraft, wherein, method includes: in first positioning process, according to the center position of target object frame in the image obtained and image center position, determine first position deviation amount;According to the first position deviation amount, determine the first flight speed of the aircraft;In the case where the first position deviation amount is less than or equal to first threshold, start second positioning process, the focal length of pod camera is adjusted to maximum focal length;According to the center position of target part frame in the image obtained and the center projection position of delivery device, determine second position deviation amount;According to the second position deviation amount, determine the second flight speed of the aircraft;In the case where the second position deviation amount is less than or equal to second threshold, determine that the aircraft reaches target position.

Description

Technical Field

[0001] This disclosure relates to the field of positioning technology, and more specifically, to a method, apparatus, and aircraft for positioning. Background Technology

[0002] Currently, aircraft-based targeted delivery of goods is widely used in logistics distribution and emergency rescue. There are two main methods for aircraft positioning: manual and automatic. In manual positioning, if the image transmission link between the operator and the aircraft is interfered with or delayed, the operator will be unable to control the aircraft in a timely manner, thus reducing positioning accuracy and making it impossible to accurately locate the target location. In automatic positioning, the aircraft's altitude and the field of view of the pod's camera are directly related to positioning accuracy. If either of these factors malfunctions during the positioning process—for example, if the aircraft's altitude is too high or the camera's field of view is too large—it will severely affect the positioning accuracy. Summary of the Invention

[0003] One objective of this disclosure is to provide a new technical solution for aircraft positioning.

[0004] According to a first aspect of this disclosure, an embodiment of an aircraft positioning method is provided, comprising:

[0005] In the first positioning process, the first position deviation is determined based on the center position of the target object frame in the acquired image and the center position of the image.

[0006] The first flight speed of the aircraft is determined based on the first position deviation.

[0007] If the first position deviation is less than or equal to the first threshold, the second positioning process is started to adjust the focal length of the pod camera to the maximum focal length.

[0008] The second position deviation is determined based on the center position of the target area frame in the acquired image and the center projection position of the projector.

[0009] The second flight speed of the aircraft is determined based on the second position deviation.

[0010] If the second position deviation is less than or equal to the second threshold, the aircraft is determined to have reached the target position.

[0011] Optionally, determining the second positional deviation based on the center position of the target region frame in the acquired image and the center projection position of the projector includes:

[0012] The projected position of the center of the dispenser is determined based on the maximum focal length and the deviation of the center of the dispenser from the installation position of the pod camera.

[0013] Identify the target region in the image to obtain the target region outline;

[0014] Extract the target part of a predetermined shape from the deployment area frame;

[0015] The second position deviation is determined based on the center projection position of the dispenser and the center position of the target part.

[0016] Optionally, the second position deviation includes a first width deviation corresponding to the width direction and a first height deviation corresponding to the height direction. Determining that the aircraft has reached the target position when the second position deviation is less than or equal to a second threshold includes:

[0017] If the squared difference between the first width deviation and the first height deviation is less than or equal to the third threshold, the first video stream to be determined is obtained.

[0018] For each image to be judged in the first video stream to be judged, the second height deviation in the height direction and the second width deviation in the width direction of the image to be judged are determined according to the center position of the target part in the image to be judged and the center projection position of the projector, so as to obtain multiple second width deviations and multiple second height deviations.

[0019] If the standard deviation of the plurality of second altitude deviations and the plurality of second width deviations is less than or equal to a fourth threshold, the aircraft is determined to have reached the target position.

[0020] Optionally, in the first positioning process, the method further includes:

[0021] Use the target object frame of the previous frame of the image to be recognized as the initial frame;

[0022] The initial frame is scaled according to multiple preset scaling ratios to obtain multiple candidate frames corresponding to the multiple scaling ratios.

[0023] The target object frame of the image to be identified is determined based on the response value of the target search image corresponding to each candidate frame in the image to be identified.

[0024] Optionally, determining the target object frame of the image to be identified based on the response value of the target search image corresponding to each candidate frame in the image to be identified includes:

[0025] For each candidate box, zoom in according to the set zoom factor to obtain multiple target search boxes;

[0026] Extract the target search image corresponding to each target search box from the image to be identified to obtain multiple target search images;

[0027] For each target search image, feature extraction and response value calculation are performed to determine the response value corresponding to the target search image, resulting in multiple response values.

[0028] The candidate frame corresponding to the largest response value among the multiple response values ​​is taken as the target object frame of the image to be recognized.

[0029] Optionally, before initiating the first location process, the method further includes:

[0030] The system identifies whether a target image exists in the acquired image; wherein, the target image is an image in which the pixel coordinates of the identified target object frame and the pixel coordinates of the identified target part frame satisfy a set positional relationship;

[0031] In the presence of a target image, the position coordinates of the target object frame in the geodetic coordinate system are determined based on the pixel coordinates and coordinate transformation relationship of the target object frame.

[0032] Based on the position coordinates of the target object frame in the geodetic coordinate system, predict the target area where the target object is located in each image to be judged in the second video stream to be judged.

[0033] To identify whether a target object exists within the target region of the image to be determined;

[0034] If the sum of the total probability of the first image corresponding to the first determination result and the total probability of the second image corresponding to the second determination result in the second video stream to be determined is greater than or equal to a set probability threshold, the target object is determined to be a real target object; wherein, the first determination result is that a target object exists in the target area of ​​the image to be determined, and the second determination result is that a target object does not exist in the target area of ​​the image to be determined.

[0035] Optionally, determining the position coordinates of the target object frame in the geodetic coordinate system based on the pixel coordinates and coordinate transformation relationship of the target object frame includes:

[0036] Based on the first coordinate transformation relationship, the pixel coordinates of the target object frame are transformed into position coordinates in the camera coordinate system;

[0037] According to the second coordinate transformation relationship, the coordinates of the target object frame in the camera coordinate system are converted to the coordinates in the body coordinate system;

[0038] Based on the third coordinate transformation relationship, the coordinates of the target object frame in the body coordinate system are converted into position coordinates in the geodetic coordinate system.

[0039] Optionally, predicting the target region where the target object frame is located in each image to be judged in the second video stream to be judged, based on the position coordinates of the target object frame in the geodetic coordinate system, includes:

[0040] For each image to be judged, the target area in the image to be judged is predicted based on the position coordinates of the target object frame in the geodetic coordinate system and the position coordinates of the aircraft corresponding to the image in the geodetic coordinate system.

[0041] According to a second aspect of this disclosure, one embodiment of an aircraft positioning device is provided, comprising:

[0042] The position deviation determination module is used to determine the first position deviation in the first positioning process based on the center position of the target object frame in the acquired image and the center position of the image.

[0043] A flight speed determination module is used to determine the first flight speed of the aircraft based on the first position deviation.

[0044] The focusing module is used to start a second positioning process when the first position deviation is less than or equal to a first threshold, and adjust the focal length of the pod camera to the maximum focal length.

[0045] The position deviation determination module is used to determine the second position deviation based on the center position of the target part frame in the acquired image and the center projection position of the projector.

[0046] The flight speed determination module is used to determine the second flight speed of the aircraft based on the second position deviation.

[0047] The target position determination module is used to determine that the aircraft has reached the target position if the second position deviation is less than or equal to the second threshold.

[0048] According to a third aspect of this disclosure, an embodiment of an aircraft positioning device is provided, including a processor and a memory, the memory being used to store a computer program for controlling the processor to perform any of the positioning methods described in the first aspect of this disclosure.

[0049] According to a fourth aspect of this disclosure, an embodiment of an aircraft is provided, comprising: a pod camera for acquiring images and transmitting the acquired images to an aircraft positioning device; and an aircraft positioning device as described in the second or third aspect.

[0050] According to an embodiment of this application, in the first positioning process, a first position deviation is determined based on the center position of the target object frame in the acquired image and the center position of the image; a first flight speed of the aircraft is determined based on the first position deviation; if the first position deviation is less than or equal to a first threshold, a second positioning process is initiated, and the focal length of the pod camera is adjusted to the maximum focal length; a second position deviation is determined based on the center position of the target part frame in the acquired image and the center projection position of the delivery device; a second flight speed of the aircraft is determined based on the second position deviation; if the second position deviation is less than or equal to a second threshold, it is determined that the aircraft has reached the target position. This improves the accuracy of aircraft positioning, thereby improving the delivery accuracy of rescue items, delivery items, etc.

[0051] Other features and advantages of this specification will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of this specification and, together with their description, serve to explain the principles of this specification.

[0053] Figure 1 This is a hardware configuration block diagram of an aircraft positioning system that can be used to implement the embodiments of this disclosure;

[0054] Figure 2 This is a flowchart illustrating an aircraft positioning method according to one embodiment;

[0055] Figure 3 This is a flowchart illustrating an aircraft positioning method according to another embodiment;

[0056] Figure 4 This is a flowchart illustrating an aircraft positioning method according to yet another embodiment;

[0057] Figure 5 This is a schematic diagram of the structure of an aircraft positioning device according to one embodiment;

[0058] Figure 6 This is a schematic diagram of the structure of an aircraft positioning device according to one embodiment;

[0059] Figure 7 This is a structural schematic diagram of an aircraft according to one embodiment. Detailed Implementation

[0060] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0061] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0062] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0063] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0064] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0065] <Hardware Configuration>

[0066] like Figure 1 As shown, the aircraft 100 includes a pod camera 1000 and an aircraft positioning device 2000. The pod camera 1000 is used to acquire real-time images and provide the acquired real-time images to the aircraft positioning device 2000. The pod camera 1000 can adjust its shooting direction at any time according to the gimbal.

[0067] The pod camera 1000 can be any imaging device capable of capturing images of objects, such as a camera.

[0068] The aircraft positioning device 2000 may include a processor 2100 and a memory 2200, etc.

[0069] In one embodiment, refer to Figure 1 As shown, the aircraft positioning device 2000 may include a processor 2100, a memory 2200, an interface device 2300, a communication device 2400, a display device 2500, an input device 2600, a speaker 2700, a microphone 2800, etc.

[0070] Processor 2100 may be a mobile processor. Memory 2200 includes, for example, ROM (Read-Only Memory), RAM (Random Access Memory), and non-volatile memory such as a hard disk. Interface device 2300 includes, for example, a USB interface and a headphone jack. Communication device 2400 is capable of wired or wireless communication. Communication device 2400 may include short-range communication devices, such as any device that performs short-range wireless communication based on short-range wireless communication protocols such as Hilink, WiFi (IEEE 802.11), Mesh, Bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, and LiFi. Communication device 2400 may also include long-range communication devices, such as any device that performs WLAN, GPRS, or 2G / 3G / 4G / 5G long-range communication. Display device 2500 is, for example, an LCD screen or a touch screen, used to display real-time images captured by the pod camera. Input device 2600 may include, for example, a touch screen or a keyboard. Users can input / output voice information through speaker 2700 and microphone 2800.

[0071] In this embodiment, the memory 2200 of the aircraft positioning device 2000 is used to store instructions for controlling the processor 2100 to operate in order to at least execute the aircraft positioning method according to any embodiment of the present invention. Those skilled in the art can design the instructions according to the disclosed scheme of the present invention. How the instructions control the processor to operate is well known in the art and will not be described in detail here.

[0072] Despite Figure 1 The invention illustrates multiple devices of the aircraft positioning device 2000; however, the invention may refer to only some of these devices. For example, the aircraft positioning device 2000 may refer only to the memory 2200 and the processor 2100.

[0073] In this embodiment, the pod camera 1000 is used to acquire real-time images and provide them to the aircraft positioning device 2000. The aircraft positioning device 2000 then implements the method according to any embodiment of the present invention based on the images to complete the positioning of the aircraft.

[0074] It should be understood that, despite Figure 1 Only one pod camera 1000 and one aircraft positioning device 2000 are shown, but this does not mean that the number of each is limited. The aircraft 100 may contain multiple pod cameras 1000 and / or aircraft positioning devices 2000.

[0075] <Method Implementation>

[0076] Figure 2This is a flowchart illustrating an aircraft positioning method according to one embodiment, which can be implemented by an aircraft positioning device.

[0077] like Figure 2 As shown, the aircraft positioning method in this embodiment may include steps 2100-2600.

[0078] Step 2100: In the first positioning process, the first position deviation is determined based on the center position of the target object frame in the acquired image and the center position of the image.

[0079] In this embodiment, during the flight of the aircraft, the pod camera captures a video stream and sends it to the aircraft's positioning device. If a target object frame is identified from the video stream, the first positioning process is initiated. The target object can be any object corresponding to the current positioning task. For example, if the current positioning task is to search for a specific vehicle, the target object can be that specific vehicle. If the current positioning task is to search for a fire in a mountainous area, the target object can be the fire itself; the specific target object is not limited here.

[0080] In some embodiments, a target recognition model can be used to identify targets in an image. If the image contains a target object, the model outputs the target object type and its location information. The location information can include the coordinates of the target object's bounding box and its dimensions within the image.

[0081] In some examples, the target recognition model can be a lightweight YoLoV5s target recognition model that has been optimized for inference.

[0082] In some embodiments, the method for obtaining a lightweight target recognition model includes:

[0083] The training sample dataset is input into the YoLoV5s detection network for model training to obtain an initial target recognition model; wherein, the sample data includes the bounding box of the target object and the bounding box of the target part. The initial target recognition model is optimized and inferred to obtain a lightweight target recognition model.

[0084] In the first positioning process, the aircraft moves guided by the center of the target frame in the real-time acquired image. Specifically, the aircraft positioning device can determine the first position deviation based on the coordinates of the target frame center in the acquired image and the coordinates of the image center.

[0085] The first position deviation can be calculated using formula (1):

[0086]

[0087] Where, Δu1k Δv 1k These represent the first positional deviations of the k-th frame image in the width and height directions, respectively, in the first positioning process. center1k v center1k These are the pixel width and height of the center of the target object frame in the k-th frame of the first positioning process, respectively, where width and height are the width and height of the image, respectively.

[0088] Step 2200: Determine the first flight speed of the aircraft based on the first position deviation.

[0089] In this embodiment, since the aircraft is in a state of continuous movement during the first positioning process, that is, the first position deviation will keep changing, and the first flight speed determined based on the first position deviation will also change accordingly.

[0090] In one example, the first flight speed of the aircraft can be calculated using formula (2);

[0091]

[0092] in, These are the first flight velocities of the aircraft in the east and north directions, determined in the k-th frame image during the first positioning process, respectively. P,vel K I,vel These are the proportional and integral parameters of the aircraft's flight control.

[0093] In some examples, after determining the first flight speed of the aircraft in the first positioning process, the first flight speed can be input into a low-pass filter for filtering and noise reduction to obtain a filtered first flight speed, and the movement of the aircraft can be controlled by the filtered first flight speed.

[0094] Step 2300: If the first position deviation is less than or equal to the first threshold, start the second positioning process and adjust the focal length of the pod camera to the maximum focal length.

[0095] In this embodiment, the first threshold is a set critical value for whether to initiate the second positioning process. If the first position deviation is less than or equal to the first threshold, it indicates that the aircraft has reached directly above the target object. At this point, the second positioning process is initiated to locate the target part. The target part is a specific location on the target object. For example, if the target object is a fire point, the target part is the part with the highest temperature within that fire point.

[0096] Since the target part is only a small part of the target object, the difficulty of locating the target part is higher than the difficulty of locating the target object. Therefore, the focal length of the pod camera needs to be adjusted to the maximum focal length to locate the target part with the smallest field of view.

[0097] If the first position deviation is greater than the first threshold, it means that the aircraft has not reached directly above the target object. The center of the target object frame in the image is still needed as a guide to instruct the aircraft to move.

[0098] Step 2400: Determine the second position deviation based on the center position of the target area frame in the acquired image and the center projection position of the projector.

[0099] In this embodiment, during the second positioning process, the acquired image is obtained, and the target is identified by the target recognition model to obtain the position coordinates of the target part frame.

[0100] Based on the position coordinates of the target area frame, determine the position coordinates of the center of the target area frame. Based on the position coordinates of the center of the target area frame and the projection position of the center of the dispenser, determine the second position deviation.

[0101] In some embodiments, step 2400, determining the second position deviation based on the center position of the target part frame in the acquired image and the center projection position of the projector, includes steps 2411 to 2414.

[0102] Step 2411: Determine the projected position of the center of the dispenser based on the maximum focal length and the deviation of the center of the dispenser from the installation position of the pod camera.

[0103] In this embodiment, the projection position of the center of the projector on the image can be calculated using formula (3).

[0104]

[0105] Among them, u p v p Δx and Δy are the projected pixel coordinates of the projector center in the width and height directions of the image, respectively; Δx and Δy are the installation deviations of the projector center relative to the pod camera on the horizontal plane, respectively; f yl is the longest focal length on the y-axis.

[0106] Step 2412: Identify the target part in the image and obtain the target part frame.

[0107] In this embodiment, a target region in an image is identified using a target recognition model, and the coordinates of the target region's bounding box are obtained. The target region's bounding box can be represented by these coordinates.

[0108] Step 2413: Extract the target part of the set shape from the target part frame.

[0109] In this embodiment, the target part can be a circle or any other shape besides a frame. After obtaining the target part frame, the corresponding circular or other shaped target part can be extracted from the target part frame.

[0110] In some examples, the Hough shape detection method can be used to extract target parts of a set shape from the target part frame.

[0111] Step 2414: Determine the second position deviation based on the center projection position of the dispenser and the center position of the target part.

[0112] In this embodiment, the second position deviation can be calculated using the following formula (4):

[0113]

[0114] Where, Δu 2k Δv 2k These are the second positional deviation values ​​in the width and height directions of the k-th frame image during the second positioning process, u. center2k v center2k These are the pixel width and height of the center of the target region in the k-th frame of the image during the second positioning process.

[0115] According to the embodiments of this application, the second position deviation is determined by the center projection position of the dispenser and the center position of the target part. Compared with determining the second position deviation by the center projection position of the dispenser and the center position of the target part frame, the positioning failure caused by the large difference between the shape and frame of the target part is avoided, and the positioning accuracy can be further improved.

[0116] Step 2500: Determine the second flight speed of the aircraft based on the second position deviation.

[0117] In this embodiment, during the second positioning process, the aircraft is guided to move based on the center position of the target area frame. Specifically, the aircraft's second flight speed is adjusted based on the second positional deviation between the center position of the target area frame and the center projection position of the dispenser.

[0118] In one example, the second flight speed of the aircraft can be determined based on the second position deviation and the proportional and integral parameters of the feedback control. After determining the second flight speed, it is then filtered and noise-reduced using a low-pass filter to obtain the filtered second flight speed. The aircraft movement is then controlled based on this filtered second flight speed.

[0119] Step 2600: If the second position deviation is less than or equal to the second threshold, determine that the aircraft has reached the target position.

[0120] In this embodiment, the second positioning process is essentially the process by which the aircraft aligns its dispenser with the target part of the target object through movement. The second threshold can be a set critical value for determining whether the dispenser and the target part are aligned. If the second position deviation is less than or equal to the second threshold, it indicates that the center of the dispenser and the center of the target part have been aligned, and the aircraft has reached the target position. After reaching the target position, the aircraft can dispense items using the dispenser.

[0121] In some embodiments, the second position deviation includes a first width deviation corresponding to the width direction and a first height deviation corresponding to the height direction. Step 2600, which states that if the second position deviation is less than or equal to a second threshold, determines that the aircraft has reached the target position, includes steps 2611 to 2613.

[0122] Step 2611: If the squared difference between the first width deviation and the first height deviation is less than or equal to the third threshold, obtain the first video stream to be determined.

[0123] In this embodiment, the second position deviation includes a first width deviation corresponding to the width direction and a first height deviation corresponding to the height direction.

[0124] If the squared difference between the first height deviation and the first width deviation is less than or equal to the third threshold, it is considered that the delivery device may have reached the target position. At this time, the aircraft is not actively controlled to move, and the first video stream to be judged is acquired to determine whether the aircraft can remain at the target position, that is, to determine whether the ambient wind speed affects the aircraft's position at the target position.

[0125] Step 2612: For each image to be judged in the first video stream to be judged, based on the center position of the target part in the image to be judged and the center projection position of the projector, determine the second height deviation in the height direction and the second width deviation in the width direction of the image to be judged, and obtain multiple second width deviations and multiple second height deviations.

[0126] In one example, the first video stream to be judged may contain 10 frames of the first image to be judged. For each frame of the image to be judged, based on the center position of the target part frame in the image to be judged and the center projection position of the projector, a second height deviation in the height direction and a second width deviation in the width direction of the image to be judged are determined, resulting in 10 second width deviations and 10 second height deviations.

[0127] Step 2613: If the standard deviation of the plurality of second altitude deviations and the plurality of second width deviations is less than or equal to a fourth threshold, determine that the aircraft has reached the target position.

[0128] Continuing with the example above, if the standard deviations of the 10 second width deviations and the 10 second height deviations are less than or equal to the fourth threshold, it indicates that the ambient wind speed has little impact on the aircraft's positional movement, and the aircraft can maintain its target position.

[0129] According to an embodiment of this application, a first video stream to be judged is obtained when the square difference between the first width deviation and the first height deviation is less than or equal to a third threshold. For each image to be judged in the first video stream, a second height deviation in the height direction and a second width deviation in the width direction are determined based on the center position of the target part in the image to be judged and the center projection position of the projector, resulting in multiple second width deviations and multiple second height deviations. When the standard deviation of the multiple second height deviations and the multiple second width deviations is less than or equal to a fourth threshold, it is determined that the aircraft has reached the target position. This avoids the problem of reduced delivery accuracy caused by the aircraft deviating too much from the target position when the ambient wind speed is high, thus improving positioning accuracy.

[0130] Because the target object frame often exhibits jitter during the initial positioning process, using the center of the target object frame as the guide center will cause the aircraft to oscillate, thus reducing the positioning speed and prolonging the positioning time. Furthermore, lightweight target recognition models are prone to recognition discontinuities, leading to discontinuous aircraft control. Low-frequency control poses a significant safety risk to the aircraft.

[0131] To address the above problems, in some embodiments, such as Figure 3 As shown, in step 2100, during the first positioning process, the method further includes steps 3100 to 3300.

[0132] Step 3100: Use the target object frame of the previous frame of the recognized image of the current image to be recognized as the initial frame.

[0133] In this embodiment, for ease of description, the identified image that triggers the first positioning process is referred to as the first frame image. This first frame image includes the target object, and the bounding box of the target object in the first frame image is used as the initial bounding box of the current image to be identified (the second frame image). In the first positioning process, if the current image to be identified is the (i+1)th frame image, the corresponding previous identified image is the i-th frame image. The bounding box of the target object corresponding to the i-th frame image is used as the initial bounding box of the (i+1)-th frame image. Here, i is greater than or equal to 1.

[0134] It should be noted that the target object may or may not exist in the target object frame in the i-th frame image. The tracking method in this embodiment is to track the target object frame, that is, the target object frame always exists in the image regardless of whether the target object exists in the image.

[0135] Step 3200: Scale the initial frame according to multiple preset scaling ratios to obtain multiple candidate frames corresponding to the multiple scaling ratios.

[0136] For example, the scaling ratio can be 0.98, 0.99, 1.00, 1.01, 1.02, etc. If the current image to be identified is the second frame image, the initial frame can be scaled using the initial frame of the second frame image and the five scaling ratios to obtain five candidate frames for the second frame image.

[0137] Step 3300: Determine the target object frame of the image to be identified based on the response values ​​of the multiple target search images corresponding to the multiple candidate frames in the image to be identified.

[0138] Continuing with the example above, using these 5 candidate frames, 5 target search images corresponding to these 5 candidate frames are determined in the second frame image. Based on the response values ​​of these 5 target search images, the target object frame of the second frame image is determined.

[0139] In one embodiment, step 3300, which involves determining the target object frame of the image to be identified based on the response value of the target search image corresponding to each candidate frame in the image to be identified, includes steps 3311 to 3314.

[0140] Step 3311: For each candidate frame, magnify it according to the set magnification factor to obtain multiple target search frames.

[0141] Continuing with the example above, the five candidate boxes are magnified by a set magnification factor, such as 2.5, to obtain five target search boxes.

[0142] Step 3312: Extract the target search image corresponding to each target search box from the image to be identified to obtain multiple target search images.

[0143] Continuing with the example above, the target search images are extracted from the second frame image to be identified based on the five target search boxes, resulting in five target search images.

[0144] Step 3313: Perform feature extraction and response value calculation on each target search image to determine the response value corresponding to the target search image and obtain multiple response values;

[0145] Continuing with the example above, feature extraction and response value calculation are performed on each of the five target search images to determine the corresponding response value for each target search image, resulting in five response values.

[0146] Step 3314: Select the candidate frame corresponding to the largest response value among the multiple response values ​​as the target object frame of the image to be recognized.

[0147] Continuing with the example above, select the maximum response value from the five response values ​​corresponding to the five target search images, and use the candidate frame corresponding to the maximum response value as the target object frame of the second frame image.

[0148] According to the embodiments of this application, by tracking the target object frame in the first positioning process, the aircraft oscillation caused by using the center of the target object frame as the guide center can be avoided, thus improving the positioning speed. At the same time, the problem of discontinuous aircraft control caused by discontinuous identification can also be avoided.

[0149] In some embodiments, such as Figure 4 As shown, before starting the first positioning process, the method further includes steps 4100 to 4500.

[0150] Step 4100: Identify whether the acquired image contains the target image.

[0151] In this embodiment, the target image is an image in which the pixel coordinates of the identified target object frame and the pixel coordinates of the identified target part frame satisfy a predetermined positional relationship. The predetermined positional relationship is that the target part frame is contained within the target object frame. The pixel coordinates of the target object frame can be represented by the position coordinates of its upper left and lower right corners on the image.

[0152] When recognizing an image based on a target recognition model, the recognition result information can be identified and output in one go. This recognition result information is then used to determine whether a target object frame or a target part frame exists in the image. If a target object frame or a target part frame exists, it is determined whether the target object frame and the target part frame satisfy a predetermined positional relationship. If the predetermined positional relationship is satisfied, the image is determined to be a target image.

[0153] Step 4200: If a target image exists, determine the position coordinates of the target object frame in the geodetic coordinate system based on the pixel coordinates and coordinate transformation relationship of the target object frame.

[0154] In some embodiments, the step 4200 of determining the position coordinates of the target object frame in the geodetic coordinate system based on the pixel coordinates and coordinate transformation relationship of the target object frame includes steps 4211 to 4213.

[0155] Step 4211: Based on the first coordinate transformation relationship, the pixel coordinates of the target object frame are transformed into position coordinates in the camera coordinate system.

[0156] The position coordinates of the upper left and lower right corners of the target object frame in the camera coordinate system can be calculated using formulas (5) and (6) respectively:

[0157]

[0158]

[0159] in, f x f y c x c y Here, represents the camera intrinsic parameters corresponding to the target image, `altitude` represents the flight altitude of the target image, and `u` represents the altitude of the target image. topleft v topleft Let x and x represent the pixel coordinates of the top-left corner of the target object's bounding box in the target image, along the width and height directions, respectively. ctopleft y ctopleft z ctopleft This represents the position coordinates of the top-left corner of the target object's bounding box in the camera coordinate system, u. rightbottom v rightbottim Let x and x represent the pixel coordinates of the bottom right corner of the target object frame in the target image along the width and height directions, respectively. croghtbottom y crightbottom z crightbottom This indicates the position coordinates of the lower right corner of the target object's frame in the camera coordinate system.

[0160] Step 4212: Based on the second coordinate transformation relationship, convert the coordinates of the target object frame in the camera coordinate system to the coordinates in the body coordinate system.

[0161] In this embodiment, the second coordinate transformation relationship is determined based on the installation deviations of the aircraft's flight control system and the pod camera. This second coordinate transformation relationship can be expressed as:

[0162]

[0163] Where, x e y e z e This refers to the installation deviation between the aircraft's flight control system and the pod camera.

[0164] Step 4213: Based on the third coordinate transformation relationship, convert the coordinates of the target object frame in the body coordinate system to the position coordinates in the geodetic coordinate system.

[0165] In this embodiment, the third coordinate transformation relationship can be determined based on the position coordinates of the aircraft in the geodetic coordinate system corresponding to the target image.

[0166] The third coordinate transformation relationship can be expressed as:

[0167]

[0168] Where, x i y i z i This represents the position of the aircraft in the target image.

[0169] The position coordinates of the target object frame in the geodetic coordinate system can be expressed by formula (7):

[0170]

[0171] Among them, P topleft P represents the position coordinates of the top left corner of the target object frame in the geodetic coordinate system. rightbottom The coordinates of the lower left corner of the target object frame in the geodetic coordinate system.

[0172] Step 4300: Based on the position coordinates of the target object frame in the geodetic coordinate system, predict the target area where the target object is located in each image to be judged in the second video stream to be judged.

[0173] In this embodiment, if the existence of a target image is determined, the k consecutive frames following the target image are used as the second video stream to be determined. k can be 30 frames, 100 frames, etc., and is not limited here.

[0174] In some embodiments, step 4300, predicting the target region where the target object frame is located in each image to be judged in the second video stream to be judged, based on the position coordinates of the target object frame in the geodetic coordinate system, includes:

[0175] For each image to be judged, the target area in the image to be judged is predicted based on the position coordinates of the target object frame in the geodetic coordinate system and the position coordinates of the aircraft corresponding to the image in the geodetic coordinate system.

[0176] In this embodiment, for each image to be judged in the second video stream to be judged, the target area where the target object is located in the image to be judged is predicted based on the position coordinates and flight altitude of the aircraft corresponding to the image to be judged, and the position coordinates of the target object frame in the geodetic coordinate system.

[0177] The target area can be represented by the pixel coordinates of its top-left and bottom-right corners. The formula (8) for calculating the pixel coordinates of the top-left and bottom-right corners of the target area is as follows:

[0178]

[0179]

[0180] in, middle The altitude represents the position coordinates of the aircraft corresponding to the image to be determined in the k-th frame. k Let the flight altitude be the corresponding flight altitude of the k-th frame of the image to be determined. This represents the coordinates of the top-left corner of the target region in the k-th frame of the image to be judged. The coordinates are the lower right corner coordinates of the target region in the k-th frame of the image to be judged.

[0181] As can be seen from formula (8), when predicting the target area of ​​the image to be determined, the position and altitude of the aircraft corresponding to the image to be determined are variables, while other parameters are constants.

[0182] Step 4400: Identify whether a target object exists within the target region of the image to be determined.

[0183] In this embodiment, for each frame of the image to be judged, it is determined whether a target object exists in its target region.

[0184] Step 4500: If the sum of the total probability of the first image corresponding to the first determination result and the total probability of the second image corresponding to the second determination result in the second video stream to be determined is greater than or equal to a set probability threshold, the target object is determined to be a real target object.

[0185] In this embodiment, the first determination result is the determination result that a target object exists in the target area of ​​the image to be determined, and the second determination result is the determination result that a target object does not exist in the target area of ​​the image to be determined. For each frame of the video stream to be determined, the presence of a target object in its target area is identified. If a target object exists in the target area of ​​the image to be determined, the determination result corresponding to that image is the first determination result, and the image to be determined is recorded as the first image. If no target object exists in the target area of ​​the image to be determined, the determination result corresponding to that image is the second determination result, and the image to be determined is recorded as the second image. After determining the second video stream to be determined, the probability of the video stream is calculated based on the first image probability corresponding to the first image and the second image probability corresponding to the second image, to obtain the total image probability of the second video stream to be determined. The total image probability of the second video stream to be determined is the sum of the total first image probability of all first images and the total second image probability of all second images in the video stream. If the total image probability of the video stream to be determined is greater than or equal to a set probability threshold, the target object is determined to be a real target object.

[0186] In one example, the second video stream to be judged may include k frames of images to be judged, which can be represented as:

[0187] List target ={S1,S2,…,S K}

[0188] Where S1, S2, ..., S K This represents the observed state value for each frame in the K frames.

[0189] If a target object exists in the target region of the image to be determined, the image is denoted as hit (first image). If no target object exists in the target region of the image to be determined, the image is denoted as miss (second image).

[0190] The probability of the first image corresponding to the first image The probability of the second image corresponding to the second image Where, p hit Let p be the probability of observing the first image once. miss Let p be the probability of observing a second image once. hit +p miss =1, p hit >p miss In other words, the probabilities of the first and second images are both set constants.

[0191] The total image probability of the second video stream to be determined can be expressed as:

[0192]

[0193] If Result target ≥ Threshold, then the target object is a real target object.

[0194] If S init < Result target < Threshold, then the target object is a non-real target object.

[0195] If Result target = S init , then it is uncertain whether the target object is a real target object. Wherein, S init and Threshold are set probability determination thresholds.

[0196] In some embodiments, after determining that the target object is a real target object in step 4500, start the first positioning process, and execute steps 2100 to 2600 for positioning, so that the aircraft reaches the target position.

[0197] The above has described steps 2100 to 2600 in detail, and will not be elaborated here.

[0198] In some embodiments, after determining that the target object is a real target object in step 4500, trigger and start the tracking process for the target object frame according to the image with the largest number of frames in the second video stream to be determined and the determination result as the first determination result. In these embodiments, the image with the largest number of frames and the determination result as the first determination result is the first frame image in the tracking process. The target object frame recognized through this first frame image can be used as the initial frame of the second frame image to be recognized, and then steps 3100 to 3300 can be executed to determine the target object frame of the second frame image, so as to realize the tracking of the target object frame.

[0199] According to the embodiments of the present application, in the first positioning process, according to the center position of the target object frame and the center position of the image obtained in the image, determine the first position deviation amount; according to the first position deviation amount, determine the first flight speed of the aircraft; in the case where the first position deviation amount is less than or equal to the first threshold, start the second positioning process, and adjust the focal length of the pod camera to the maximum focal length; according to the center position of the target part frame and the center projection position of the dispenser in the obtained image, determine the second position deviation amount; according to the second position deviation amount, determine the second flight speed of the aircraft; in the case where the second position deviation amount is less than or equal to the second threshold, determine that the aircraft reaches the target position, which can improve the positioning accuracy of the aircraft, and further improve the delivery accuracy of rescue items, delivery items, etc.

[0200] <Device Example 1>

[0201] Figure 5 This is a structural block diagram of an aircraft positioning device according to one embodiment. Figure 5 As shown, the aircraft positioning device 5000 may include:

[0202] The position deviation determination module 5100 is used to determine the first position deviation in the first positioning process based on the center position of the target object frame in the acquired image and the center position of the image.

[0203] The flight speed determination module 5200 is used to determine the first flight speed of the aircraft based on the first position deviation.

[0204] The focusing module 5300 is used to start a second positioning process and adjust the focal length of the pod camera to the maximum focal length when the first position deviation is less than or equal to the first threshold.

[0205] The position deviation determination module 5100 is used to determine the second position deviation based on the center position of the target part frame in the acquired image and the center projection position of the projector.

[0206] The flight speed determination module 5200 is used to determine the second flight speed of the aircraft based on the second position deviation.

[0207] The target position determination module 5400 is used to determine that the aircraft has reached the target position if the second position deviation is less than or equal to the second threshold.

[0208] In some embodiments, the position deviation determination module 5100 is used to determine the projected position of the center of the dispenser based on the maximum focal length and the installation position deviation of the center of the dispenser relative to the pod camera; identify the target part in the image and obtain the target part frame; extract the target part of a set shape from the delivery part frame; and determine the second position deviation based on the projected position of the center of the dispenser and the center position of the target part.

[0209] In some embodiments, the second position deviation includes a first width deviation corresponding to the width direction and a first height deviation corresponding to the height direction. The target position determination module 5400 is used to acquire a first video stream to be determined when the square difference between the first width deviation and the first height deviation is less than or equal to a third threshold. For each image to be determined in the first video stream to be determined, a second height deviation in the height direction and a second width deviation in the width direction are determined based on the center position of the target part in the image to be determined and the center projection position of the projector, resulting in a plurality of second width deviations and a plurality of second height deviations. When the standard deviation of the plurality of second height deviations and the plurality of second width deviations is less than or equal to a fourth threshold, it is determined that the aircraft has reached the target position.

[0210] In some embodiments, the aircraft positioning device 5000 further includes a tracking module 5500, which is used in the first positioning process to take the target object frame of the previous frame of the identified image of the current image to be identified as the initial frame; to scale the initial frame according to a preset multiple scaling ratios to obtain a plurality of candidate frames corresponding to the multiple scaling ratios; and to determine the target object frame of the image to be identified according to the response value of the target search image corresponding to each candidate frame in the image to be identified.

[0211] In some embodiments, the tracking module 5500 is configured to magnify each candidate frame by a set magnification factor to obtain multiple target search frames; extract target search images corresponding to each target search frame from the image to be identified to obtain multiple target search images; perform feature extraction and response value calculation on each target search image to determine the response value corresponding to the target search image to obtain multiple response values; and use the candidate frame corresponding to the maximum response value among the multiple response values ​​as the target object frame of the image to be identified.

[0212] In some embodiments, the aircraft positioning device 5000 further includes an identification module 5600, which is used to identify whether a target image exists in the acquired image before starting the first positioning process; wherein, the target image is an image in which the pixel coordinates of the identified target object frame and the pixel coordinates of the identified target part frame satisfy a set positional relationship; if a target image exists, the device determines the position coordinates of the target object frame in the geodetic coordinate system according to the pixel coordinates of the target object frame and the coordinate transformation relationship; predicts the target area where the target object is located in each image to be judged in the second video stream to be judged according to the position coordinates of the target object frame in the geodetic coordinate system; identifies whether a target object exists in the target area of ​​the image to be judged; and determines that the target object is a real target object when the sum of the total probability of the first image corresponding to the first judgment result and the total probability of the second image corresponding to the second judgment result in the second video stream to be judged is greater than or equal to a set probability threshold; wherein, the first judgment result is that a target object exists in the target area of ​​the image to be judged, and the second judgment result is that a target object does not exist in the target area of ​​the image to be judged.

[0213] In some embodiments, the recognition module 5600 is configured to convert the pixel coordinates of the target object frame into position coordinates in the camera coordinate system according to a first coordinate transformation relationship; convert the coordinates of the target object frame in the camera coordinate system into coordinates in the body coordinate system according to a second coordinate transformation relationship; and convert the coordinates of the target object frame in the body coordinate system into position coordinates in the geodetic coordinate system according to a third coordinate transformation relationship.

[0214] In some embodiments, the recognition module 5600 is used to predict the target area of ​​the target object in the image to be judged based on the position coordinates of the target object frame in the geodetic coordinate system and the position coordinates of the aircraft corresponding to the image to be judged in the geodetic coordinate system for each image to be judged.

[0215] <Device Embodiment Two>

[0216] Figure 6 This is a structural schematic diagram of an aircraft positioning device according to one embodiment.

[0217] like Figure 6 As shown, the aircraft positioning device 6000 includes a processor 6100 and a memory 6200. The memory 6200 is used to store a computer program, which is used to control the processor 6100 to execute the method as described in any of the above method embodiments.

[0218] <Aircraft Implementation Examples>

[0219] like Figure 7 As shown, this disclosure provides an embodiment of an aircraft 7000, including a pod camera 7100 and an aircraft positioning device 7200.

[0220] The pod camera 7100 is used to collect real-time images and provide them to the aircraft positioning device 7200.

[0221] In one embodiment, the aircraft positioning device 7200 is as follows: Figure 5 As shown or as Figure 6 The aircraft positioning device shown.

[0222] One or more embodiments of this specification may be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this specification.

[0223] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0224] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0225] Computer program instructions used to perform the operations of the embodiments described herein may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of this specification.

[0226] Various aspects of this specification are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0227] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0228] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0229] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this specification. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are equivalent.

[0230] The various embodiments of this specification have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this application is defined by the appended claims.

Claims

1. A method of positioning an aircraft, characterized in that, include: In the first positioning process, the first position deviation is determined based on the center position of the target object frame in the acquired image and the center position of the image. The first flight speed of the aircraft is determined based on the first position deviation. If the first position deviation is less than or equal to the first threshold, the second positioning process is started to adjust the focal length of the pod camera to the maximum focal length. The second position deviation is determined based on the center position of the target area frame in the acquired image and the center projection position of the projector. The second flight speed of the aircraft is determined based on the second position deviation. If the second position deviation is less than or equal to the second threshold, it is determined that the aircraft has reached the target position; The step of determining the second position deviation based on the center position of the target area frame in the acquired image and the center projection position of the projector includes: The projected position of the center of the dispenser is determined based on the maximum focal length and the deviation of the center of the dispenser from the installation position of the pod camera. Identify the target region in the image to obtain the target region outline; Extract the target part of a predetermined shape from the target part frame; The second position deviation is determined based on the center projection position of the dispenser and the center position of the target part; The second position deviation includes a first width deviation corresponding to the width direction and a first height deviation corresponding to the height direction. Determining that the aircraft has reached the target position when the second position deviation is less than or equal to a second threshold includes: If the squared difference between the first width deviation and the first height deviation is less than or equal to the third threshold, the first video stream to be determined is obtained. For each image to be judged in the first video stream to be judged, the second height deviation in the height direction and the second width deviation in the width direction of the image to be judged are determined according to the center position of the target part in the image to be judged and the center projection position of the projector, so as to obtain multiple second width deviations and multiple second height deviations. If the standard deviation of the plurality of second altitude deviations and the plurality of second width deviations is less than or equal to a fourth threshold, the aircraft is determined to have reached the target position.

2. The method of claim 1, wherein, In the first positioning process, the method further includes: Use the target object frame of the previous frame of the image to be recognized as the initial frame; The initial frame is scaled according to multiple preset scaling ratios to obtain multiple candidate frames corresponding to the multiple scaling ratios. The target object frame of the image to be identified is determined based on the response value of the target search image corresponding to each candidate frame in the image to be identified.

3. The method according to claim 2, characterized in that, Determining the target object frame of the image to be identified based on the response value of the target search image corresponding to each candidate frame in the image to be identified includes: For each candidate box, zoom in according to the set zoom factor to obtain multiple target search boxes; Extract the target search image corresponding to each target search box from the image to be identified to obtain multiple target search images; For each target search image, feature extraction and response value calculation are performed to determine the response value corresponding to the target search image, resulting in multiple response values. The candidate frame corresponding to the largest response value among the multiple response values ​​is taken as the target object frame of the image to be recognized.

4. The method of claim 1, wherein, Before initiating the first location process, the method further includes: The system identifies whether a target image exists in the acquired image; wherein, the target image is an image in which the pixel coordinates of the identified target object frame and the pixel coordinates of the identified target part frame satisfy a set positional relationship; In the presence of a target image, the position coordinates of the target object frame in the geodetic coordinate system are determined based on the pixel coordinates and coordinate transformation relationship of the target object frame. Based on the position coordinates of the target object frame in the geodetic coordinate system, predict the target area where the target object is located in each image to be judged in the second video stream to be judged. To identify whether a target object exists within the target region of the image to be judged; If the sum of the total probability of the first image corresponding to the first determination result and the total probability of the second image corresponding to the second determination result in the second video stream to be determined is greater than or equal to a set probability threshold, the target object is determined to be a real target object; wherein, the first determination result is that a target object exists in the target area of ​​the image to be determined, the first image total probability is the sum of the first image probabilities corresponding to all images in the second video stream to be determined that are determined to have a target object in the target area, the second determination result is that a target object does not exist in the target area of ​​the image to be determined, the second image total probability is the sum of the second image probabilities corresponding to all images in the second video stream to be determined that are determined to not have a target object in the target area.

5. The method of claim 4, wherein, The step of determining the position coordinates of the target object frame in the geodetic coordinate system based on the pixel coordinates and coordinate transformation relationship of the target object frame includes: Based on the first coordinate transformation relationship, the pixel coordinates of the target object frame are transformed into position coordinates in the camera coordinate system; According to the second coordinate transformation relationship, the coordinates of the target object frame in the camera coordinate system are converted to the coordinates in the body coordinate system; Based on the third coordinate transformation relationship, the coordinates of the target object frame in the body coordinate system are converted into position coordinates in the geodetic coordinate system.

6. The method of claim 4, wherein, The step of predicting the target region where the target object frame is located in each image to be judged in the second video stream to be judged, based on the position coordinates of the target object frame in the geodetic coordinate system, includes: For each image to be judged, the target area in the image to be judged is predicted based on the position coordinates of the target object frame in the geodetic coordinate system and the position coordinates of the aircraft corresponding to the image in the geodetic coordinate system.

7. An aircraft positioning device, characterized in that, include: The determination module is used to determine a first position deviation based on the center position of the target object frame in the acquired image and the center position of the image during the first positioning process; and to determine a first flight speed of the aircraft based on the first position deviation. The focusing module is used to start a second positioning process when the first position deviation is less than or equal to a first threshold, and adjust the focal length of the pod camera to the maximum focal length. The determining module is used to determine a second position deviation based on the center position of the target area frame in the acquired image and the center projection position of the dispenser; determine a second flight speed of the aircraft based on the second position deviation; and determine that the aircraft has reached the target position if the second position deviation is less than or equal to a second threshold. The determining module is further configured to: determine the projected position of the center of the dispenser based on the maximum focal length and the deviation of the center of the dispenser relative to the installation position of the pod camera; identify the target part in the image and obtain the target part frame; extract the target part of a predetermined shape from the target part frame; and determine the second position deviation based on the projected position of the center of the dispenser and the center position of the target part. The second position deviation includes a first width deviation corresponding to the width direction and a first height deviation corresponding to the height direction. The determining module is further configured to acquire a first video stream to be judged when the square difference between the first width deviation and the first height deviation is less than or equal to a third threshold. For each image to be judged in the first video stream to be judged, a second height deviation in the height direction and a second width deviation in the width direction are determined based on the center position of the target part in the image to be judged and the center projection position of the projector, resulting in a plurality of second width deviations and a plurality of second height deviations. When the standard deviation of the plurality of second height deviations and the plurality of second width deviations is less than or equal to a fourth threshold, it is determined that the aircraft has reached the target position.

8. An aircraft positioning apparatus, characterized by It includes a processor and a memory, the memory being used to store a computer program, the computer program being used to control the processor to perform the method according to any one of claims 1-6.

9. An aircraft comprising: The pod camera and the aircraft positioning device according to claim 7 or 8, wherein the pod camera is used to acquire real-time images and provide them to the aircraft positioning device.

Images