An unmanned aerial vehicle parking lot identification method, an unmanned aerial vehicle system and a vehicle

Abstract

The application provides a UAV warehouse entry identification method, a UAV system and a vehicle. In the embodiment of the application, in the case that the target area of the hangar has a UAV, the actual UAV features and the actual UAV pose in the actual visual image information are combined with the preset UAV features and the preset UAV pose to further determine whether the UAV entering the hangar is the target UAV and whether the UAV is accurately stored in the hangar. Thus, the false appearance caused by the replacement of other objects can be effectively avoided, and the actual storage condition of the vehicle-mounted UAV can be effectively identified.

Description

Technical Field

[0001] This invention relates to the field of vehicle intelligent control technology, and in particular to a method for identifying unmanned aerial vehicles (UAVs) entering a parking area, an UAV system, and a vehicle. Background Technology

[0002] With the development of drone technology, the application of vehicle-mounted drones is becoming increasingly widespread.

[0003] The realization of vehicle-mounted drone functionality is closely related to its placement in the vehicle-mounted drone hangar.

[0004] In existing technologies, the presence and arrival status of drones are generally determined by limit switches or pressure sensors, which cannot distinguish the false entry caused by replacement by other objects, and can easily cause inconvenience to the identification of the entry status of vehicle-mounted drones. Summary of the Invention

[0005] This invention provides a method for identifying drone entry into a warehouse, a drone system, and a vehicle, to solve the problem that existing technologies cannot accurately identify the actual entry of vehicle-mounted drones into warehouses.

[0006] In a first aspect, embodiments of the present invention provide a method for identifying unmanned aerial vehicles (UAVs) entering a warehouse, wherein the method includes:

[0007] If it is determined that there is a drone in the target area of ​​the hangar, the actual visual image information of the target area is obtained, and the actual visual image information includes the actual drone features and the actual drone pose.

[0008] If the actual drone features are consistent with the preset drone features, and the actual drone pose is consistent with the preset drone pose, then the drone is successfully stored in the database.

[0009] Optionally, in the method, the preset drone features and the preset drone pose are visual image information of the target area obtained when the drone successfully enters the warehouse.

[0010] Optionally, the method further includes:

[0011] If the actual drone characteristics are inconsistent with the preset drone characteristics, or if the actual drone pose is inconsistent with the preset drone pose, then the drone's entry into the database is determined to have failed.

[0012] Optionally, the method further includes:

[0013] If the actual drone characteristics are inconsistent with the preset drone characteristics, then the drone is controlled to perform a first preset number of take-off and landing operations;

[0014] If, after the first preset number of attempts, the actual drone characteristics are inconsistent with the preset drone characteristics, then the drone's entry into the database is determined to have failed.

[0015] Optionally, the method further includes:

[0016] If, after the first preset number of times, the actual drone features are consistent with the preset drone features, then it is determined whether the actual drone pose is consistent with the preset drone pose.

[0017] If the actual drone pose is inconsistent with the preset drone pose, the drone is controlled to perform a second preset number of take-off and landing operations.

[0018] If the actual drone pose is inconsistent with the preset drone pose after the second preset number of attempts, then the drone is determined to have failed to be stored in the warehouse.

[0019] Optionally, the method further includes:

[0020] If the actual drone pose is inconsistent with the preset drone pose, the drone is controlled to perform a second preset number of take-off and landing operations.

[0021] If the actual drone pose is inconsistent with the preset drone pose after the second preset number of attempts, then the drone is determined to have failed to be stored in the warehouse.

[0022] Optionally, in the method, the situation where the actual UAV pose is consistent with the preset UAV pose includes:

[0023] If the deviation between the actual drone pose and the preset drone pose is less than a preset deviation threshold, the actual drone pose is determined to be consistent with the preset drone pose.

[0024] The situations where the actual drone pose differs from the preset drone pose include:

[0025] If the deviation between the actual drone pose and the preset drone pose is greater than or equal to a preset deviation threshold, the actual drone pose is determined to be consistent with the preset drone pose.

[0026] Optionally, in the method, determining that the drone has entered the hangar target area includes:

[0027] If a limit signal is received for the target area and the limit signal continues for a preset duration, it is determined that the drone has entered the target area.

[0028] Optionally, before receiving a limiting signal for the target area, the method further includes:

[0029] After the drone has landed, it will be moved to the target area.

[0030] Optionally, the hangar includes a centering mechanism for gathering drones into the target area; moving the drones to the target area includes:

[0031] The centering mechanism is controlled to bring the drone to the target area.

[0032] Optionally, the hangar further includes a limit switch disposed on the centering mechanism, the limit switch being used to limit the target area; determining that a drone exists in the target area of ​​the hangar includes:

[0033] If the limit switch receives a limit signal for the target area and the limit signal continues for a preset duration, it is determined that there is a drone in the target area of ​​the hangar.

[0034] Secondly, embodiments of the present invention provide a drone entry identification device, the device comprising:

[0035] The first acquisition module is used to acquire actual visual image information of the target area when it is determined that there is a drone in the target area of ​​the hangar. The actual visual image information includes actual drone features and actual drone pose.

[0036] The first determining module is used to determine that the drone has been successfully entered into the database if the actual drone features are consistent with the preset drone features and the actual drone pose is consistent with the preset drone pose.

[0037] Thirdly, embodiments of the present invention provide an electronic device, including: a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0038] Memory, used to store computer programs;

[0039] When the processor executes the program stored in the memory, it implements the steps in the drone entry identification method described in the first aspect above.

[0040] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the drone entry identification method described in the first aspect above.

[0041] Fifthly, embodiments of the present invention provide an unmanned aerial vehicle (UAV) system, including a UAV, a hangar, and electronic equipment as described above. The hangar is used to store the UAV, and the electronic equipment is used to identify the UAV upon entry into the hangar.

[0042] In a sixth aspect, embodiments of the present invention provide a vehicle that further includes an unmanned aerial vehicle system as described in the fifth aspect above, and the hangar is located on the roof, rear, or front compartment of the vehicle.

[0043] Compared with prior art, the present invention has the following advantages:

[0044] In this embodiment of the invention, when it is determined that a drone exists in the target area of ​​the hangar, actual visual image information of the target area is acquired. This actual visual image information includes the actual drone's features and its actual pose. If the actual drone's features match preset drone features, and its actual pose matches the preset drone pose, then the drone is determined to have successfully entered the hangar. In this embodiment of the invention, by combining the actual visual image with preset drone features and the preset drone pose when it is determined that a drone exists in the target area of ​​the hangar, it is possible to further determine whether the drone entering the hangar is the target drone and whether it has accurately entered the hangar. Therefore, it can effectively avoid the false impression of entry caused by substitution by other objects and effectively identify the actual entry status of vehicle-mounted drones.

[0045] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0047] Figure 1 A flowchart illustrating a drone entry identification method provided in an embodiment of the present invention;

[0048] Figure 2 To implement the hangar structure diagram provided in the embodiments of the present invention;

[0049] Figure 3 This is a schematic diagram of the drone arrival detection process in an embodiment of the present invention;

[0050] Figure 4 This is a schematic diagram of the in-situ detection process for unmanned aerial vehicles (UAVs) in an embodiment of the present invention.

[0051] Figure 5 This is a schematic diagram of the UAV attitude detection process in an embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram of a drone entry identification device provided in an embodiment of the present invention;

[0053] Figure 7 A block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0054] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.

[0055] Figure 1 This is a schematic diagram of a drone entry identification method provided by an embodiment of the present invention, including steps 101 to 103.

[0056] The drone parking identification method provided in this embodiment of the invention is applied to a vehicle, which is equipped with a hangar for drones to park, and the vehicle is communicatively connected to the drones, and can obtain signals such as drone landing requests and landing completion; wherein, the hangar can be set on the roof, rear or front of the vehicle, etc.

[0057] Step 101: If it is determined that there is a drone in the target area of ​​the hangar, obtain the actual visual image information of the target area, which includes the actual drone features and the actual drone pose.

[0058] In this step, the drone to be identified refers to the object parked in the target area of ​​the hangar. The drone to be identified can be a real drone or a fake drone; the target area is the desired location in the hangar where the drone is accurately parked.

[0059] In this step, when a drone is detected in the target area of ​​the hangar, that is, when the drone is confirmed to be in place, the actual visual image of the target area is obtained by means of methods such as taking a frontal shot of the target area with a camera. Then, a visual algorithm is used to search for the actual visual image information in the actual visual image. The actual visual image information includes at least the actual drone features and the actual drone pose. The actual drone features are the characteristics of the drone or drone-like objects that have entered the hangar, used to determine whether the drone has entered the hangar, that is, to determine whether the drone is in place. The actual drone features can be the drone outline, shape features, etc. The actual drone pose is the actual pose state of the drone after entering the hangar, used to determine whether the actual attitude of the drone is normal, that is, to determine whether the drone is correctly parked in place. The reference position parameters can be the drone's nose position, nose orientation, and the position of the marker, etc.

[0060] "In place" refers to the presence of a drone or drone-like object parked in the target area of ​​the hangar, meaning that a drone or drone-like object is parked in the target area of ​​the hangar; while "in position" refers to the drone being parked in the target area of ​​the hangar in the correct posture.

[0061] Optionally, a limit switch and / or pressure sensor are installed in the target area of ​​the hangar to determine the arrival of the drone. When the limit switch and / or pressure sensor are touched, it can be determined that there is a drone in the target area of ​​the hangar, that is, the drone is determined to be in place.

[0062] Optionally, the aforementioned camera is positioned at the end of the hangar facing the nose of the drone, capable of capturing visual images including the nose. It can not only capture images of the correct position of the drone after it has centered in the target area, serving as a reference map for the visual algorithm, but also capture real-time images of the target area after the drone has landed, and then compare them with the reference map. The presence of the drone and the correctness of its landing attitude can be determined by the nose tilt angle.

[0063] It should be noted that the data acquisition process and related data involved in the embodiments of the present invention are carried out in compliance with the relevant data protection laws and policies of the country where the invention is located, and with the authorization of the owner of the corresponding device.

[0064] Step 102: If the actual drone features are consistent with the preset drone features, and the actual drone pose is consistent with the preset drone pose, then the drone is successfully stored in the warehouse.

[0065] In this step, the preset drone features and preset drone pose are visual image information of the target area obtained when the target drone successfully enters the warehouse. Specifically, it can be visual image data, which is pre-stored in the vehicle system. The target drone is the drone configured in the vehicle.

[0066] In this step, the preset drone features are the features used to determine whether the drone entering the hangar is a drone, that is, to determine whether the drone is in place. The preset drone features can be the drone outline, shape features, etc.; the preset drone pose is the reference pose state after the target drone is accurately placed in the hangar, used to determine whether the drone's attitude is normal, that is, to determine whether the drone is correctly parked in place. The preset drone pose can be the drone's nose position, nose direction, and the position of the marker, etc.

[0067] In this step, the visual algorithm determines that the actual drone features in the actual visual image are consistent with the preset drone features, which means that the drone parked in the target area of ​​the hangar is indeed the target drone. The visual algorithm also determines that the actual drone pose in the actual visual image matches the preset drone pose after the target drone has accurately entered the hangar, which means that the drone's attitude in the hangar is normal, and therefore it can be determined that the drone has been successfully entered the hangar.

[0068] Optionally, in one embodiment, step 102 specifically includes:

[0069] If the preset drone features are present in the actual visual image, and the actual drone pose is consistent with the preset drone pose, the drone is determined to have been successfully stored.

[0070] In this embodiment, after searching for actual drone features that match preset drone features from actual visual images using visual algorithms, that is, after confirming that the drone parked in the target area of ​​the hangar is indeed the target drone, the drone's pose in the actual visual image is further obtained through visual algorithms and used as the aforementioned actual drone pose.

[0071] In this implementation, if the drone pose in the actual visual image is determined to be consistent with the drone pose after the target drone has been accurately stored in the hangar by comparing the images using a visual algorithm, it indicates that the drone pose in the hangar is normal, and therefore it can be determined that the drone has been successfully stored.

[0072] In this embodiment of the invention, by combining the actual visual image with preset drone features and preset drone pose, it is possible to further determine whether the drone entering the hangar is the target drone, and whether it has entered the hangar accurately. Therefore, it can effectively avoid the false entry caused by other objects replacing the drone, and effectively identify the actual entry of the vehicle-mounted drone.

[0073] Optionally, in one implementation, determining that a drone exists in the target area of ​​the hangar includes step 112:

[0074] Step 112: Upon receiving a limit signal for the target area, and if the limit signal continues for a preset duration, determine that the drone has entered the target area.

[0075] In this step, the limit signal is issued by the limit switch when the drone arrives at the target area of ​​the hangar. The limit switch can be touched when the drone arrives at the target area to issue the limit signal. As long as the limit switch is continuously touched, the limit signal can be continuously generated. The preset duration is the duration of the limit signal used to determine that the drone has truly returned to the target area, which can prevent over-positioning misjudgment caused by failure to effectively limit clamping. The duration can be 1 to 10 seconds, for example, 1 second, 2 seconds, 3 seconds, 5 seconds, 8 seconds, or 10 seconds.

[0076] In this embodiment, by using limit signals and the duration of the limit signals, it is possible to accurately determine whether the drone to be identified has accurately entered the hangar, and then use visual images to determine whether the drone is a real and accurate drone, and whether its parking posture is correct.

[0077] Optionally, in one embodiment, the method provided by the present invention further includes step 111 before step 112:

[0078] Step 111: After the drone has landed, move the drone to the target area.

[0079] In this step, after the hangar receives the drone landing completion instruction, the centering mechanism, such as the centering lever, moves the drone to be identified to the target area, which triggers the determination that a drone exists in the target area, that is, triggers the execution of the above step 101. At the same time, it can achieve clamping and limiting of the drone, thus fixing the drone.

[0080] Optionally, in one specific embodiment, the method provided by the present invention is applied to a vehicle, the vehicle including a hangar for parking drones, the hangar including a centering mechanism for gathering drones to a target area;

[0081] Moving the drone to the target area includes step 1111:

[0082] Step 1111: Control the centering mechanism to bring the UAV to the target area;

[0083] In step 1111, after the drone lands in the hangar, the centering motor of the centering mechanism is controlled to automatically perform the centering operation and bring the drone to the target area.

[0084] Optionally, the upper hangar also includes a limit switch, which is disposed on the centering mechanism and is used to limit the target area; step 112 specifically includes step 1121:

[0085] If the limit switch receives a limit signal for the target area and the limit signal continues for a preset duration, it is determined that the drone has entered the target area.

[0086] In step 1121, because the centering mechanism is equipped with a limit switch, and the limit switch can be touched when the drone returns to the target area to generate a limit signal, and as long as the limit switch is continuously touched, the limit signal can be continuously generated; and the preset duration is the duration of the limit signal used to determine that the drone has truly returned to the target area, so when the limit signal is received and the limit signal continues for the preset duration, it indicates that the drone has indeed entered the target area of ​​the hangar.

[0087] For example, when not touched, the limit switch's level signal is 0; when touched, the limit switch's level signal will switch to 1; if the level signal becomes 1, it means that the centering rod of the centering mechanism has reached the limit position; if the level signal does not change back from 1 to 0 within a preset time, it can be determined that the drone has entered the target area of ​​the hangar.

[0088] Optionally, in one embodiment, the method provided by the present invention further includes step 1112 after step 1111:

[0089] If no limit signal is received when the drone is moved to the target area, the drone is controlled to perform a third preset number of take-off and landing operations; if no limit signal is received after the third preset number of operations, the drone is determined to have failed to enter the warehouse.

[0090] In this embodiment, after the drone lands and performs the centering operation, if the limit signal is not detected, the centering mechanism returns to the zero position and sends a re-landing signal to the drone to control it to take off and land again, avoiding limit switch recognition failure due to drone landing attitude issues. If, after re-taking off and landing and moving to the target area, the limit signal is still not received, the drone continues to be controlled to take off and land again until the number of re-taking off and landing reaches a third preset number, at which point the drone is determined to have failed to enter the warehouse. The third preset number can be three times.

[0091] Optionally, please refer to Figure 2 The diagram shows a schematic representation of the hangar structure in an embodiment of the present invention.

[0092] like Figure 2 As shown, the hangar includes a frame 21, a centering mechanism 22, and a camera 23. Both the centering mechanism 22 and the camera 23 are mounted on the frame 21. The centering mechanism 22 is used to center the drone 10 to the target area of ​​the frame 21. The centering mechanism 22 includes a centering rod 221 and a centering motor 222. The centering motor 222 is used to drive the centering rod 221 to perform a centering operation, thus centering the drone 10 to the target area. The centering rod 221 is equipped with a limit switch 223, which is used to contact the feet of the drone 1020 to limit the target area.

[0093] Optionally, the aforementioned camera 23 is positioned at one end of the frame 21 facing the nose of the drone 10.

[0094] Optionally, in one embodiment, the process of acquiring the preset UAV features and preset UAV pose includes steps 121 to 122:

[0095] Step 121: Obtain the reference image of the target area when the target drone is successfully put into storage.

[0096] In this step, the camera inside the hangar is used to capture an image of the target area when the target drone has successfully and accurately entered the hangar. This image serves as a reference image, which reflects the visual state of the target area after the target drone has correctly entered the hangar.

[0097] Step 122: Determine the preset UAV features and the preset UAV pose based on the reference image.

[0098] In this step, since the reference image can reflect the visual state of the target area after the target UAV is correctly placed in the warehouse, visual information is extracted through the reference image to obtain the preset UAV features and preset UAV pose.

[0099] In practical applications, the above-mentioned reference images are captured by hangar cameras that acquire actual visual images, ensuring that the shooting parameters are consistent and avoiding recognition errors caused by equipment differences.

[0100] Optionally, in one embodiment, the method provided by the present invention further includes step 103:

[0101] Step 103: If the actual drone features are inconsistent with the preset drone features, or the actual drone pose is inconsistent with the preset drone pose, then the drone is determined to have failed to be stored.

[0102] In this step, a visual algorithm is used to search the actual visual image. If no actual drone feature matches the preset drone feature, it means that the drone parked in the target area of ​​the hangar is not the target drone, or even a drone. Therefore, it can be directly determined that the drone failed to enter the hangar. If a visual algorithm determines that a drone exists in the actual visual image, but the actual pose of the drone is inconsistent with the pose after the drone is accurately entered into the hangar, it means that the drone's attitude in the current hangar is abnormal. Therefore, it can also be determined that the drone failed to enter the hangar.

[0103] In this embodiment, the reference visual image information composed of preset drone features and preset drone pose is compared with the actual visual image information. This allows it to identify whether the actual visual image information is consistent with the reference visual image information. When the actual visual image information is consistent with the reference visual image information, it indicates that the current state of the hangar is the same as the visual state after the drone is correctly stored, and it is determined that the drone has been successfully stored. When the actual visual image information is inconsistent with the reference visual image information, it indicates that the current state of the hangar is different from the visual state after the drone is correctly stored, and it is determined that the drone has not been successfully stored.

[0104] Optionally, in one embodiment, the method provided by the present invention further includes steps 104 to 105:

[0105] Step 104: If the actual drone characteristics are inconsistent with the preset drone characteristics, then control the drone to perform the first preset number of take-off and landing operations.

[0106] In this step, a visual algorithm is first used to search for preset drone features in the actual visual image. If no actual drone features matching the preset drone features are found, it indicates that the drone parked in the target area of ​​the hangar is likely not the target drone, or even not a drone at all. However, this identification result may be due to a drone landing attitude problem. Therefore, the centering mechanism is controlled to return to zero, and a re-landing signal is sent to the drone to control it to take off and land again, avoiding search failure caused by the drone's landing attitude problem. If, after taking off and landing again and moving to the target area, the limit signal is still not received, the drone is controlled to take off and land again until the number of takeoffs and landings reaches a first preset number. The first preset number can be 3 times.

[0107] Step 105: If, after the first preset number of attempts, the actual drone characteristics are inconsistent with the preset drone characteristics, then the drone is determined to have failed to be stored in the database.

[0108] In this step, if the drone fails to find the preset drone features in the actual visual image after performing the first preset number of take-off and landing operations and moving to the target area, the search failure caused by the drone's landing attitude problem can be ruled out, and the drone can be determined to have failed to be stored.

[0109] Optionally, in one specific embodiment, the method provided by the present invention further includes steps 106 to 108:

[0110] Step 106: If, after the first preset number of times, the actual drone features are consistent with the preset drone features, then determine whether the actual drone pose is consistent with the preset drone pose.

[0111] In this step, after searching for the actual drone features that match the preset drone features from the actual visual image using a visual algorithm, that is, after confirming that the drone parked in the target area of ​​the hangar is indeed the target drone, the visual algorithm is then used to further determine the matching between the actual pose of the drone in the actual visual image and the preset drone pose.

[0112] Step 107: If the actual drone pose is inconsistent with the preset drone pose, control the drone to perform a second preset number of take-off and landing operations.

[0113] In this step, if the visual algorithm compares the actual drone pose in the visual image with the preset drone pose after the target drone has accurately entered the hangar, it indicates an abnormal drone pose in the hangar. Therefore, the centering mechanism is reset to zero, and a re-landing signal is sent to the drone to control its re-takeoff and landing, correcting the hangar failure caused by the drone's landing attitude. If, after re-taking off and landing and moving to the target area, a limit signal is received and the actual drone features matching the preset drone features are found in the actual visual image information, but the actual drone pose in the actual visual image information still does not match the preset drone pose after the target drone has accurately entered the hangar, the drone's re-takeoff and landing operation continues until the number of re-takeoffs and landings reaches a second preset number. This second preset number can be three times.

[0114] Step 108: If the actual drone pose is inconsistent with the preset drone pose after the second preset number of attempts, then the drone is determined to have failed to be stored.

[0115] In this step, if after the drone performs the second preset number of take-offs and landings and moves to the target area, it still fails to overcome the inconsistency between the actual pose of the drone in the actual visual image and the preset pose of the drone after the target drone is accurately placed in the warehouse, then the abnormal placement attitude caused by the drone's landing attitude problem can be ruled out, and the drone can be determined to have failed to place in the warehouse.

[0116] In this embodiment, if the preset drone features cannot be found in the actual visual image or the actual drone pose is inconsistent with the preset drone pose, the drone is controlled to perform multiple take-off and landing operations, which can effectively avoid misjudgment caused by landing attitude problems.

[0117] Optionally, in another embodiment, the method provided by the present invention further includes steps 109 to 110:

[0118] Step 109: If the actual drone pose is inconsistent with the preset drone pose, control the drone to perform a second preset number of take-off and landing operations.

[0119] In this step, after confirming the presence of a drone in the target area and acquiring actual visual image information of the target area, a visual algorithm directly determines whether the actual drone pose in the actual visual image information is inconsistent with the preset drone pose. If inconsistent, the centering mechanism is controlled to return to zero, and a re-landing signal is sent to the drone to control it to take off and land again, correcting the parking failure caused by the drone's landing attitude. If, after re-taking off and landing and moving to the target area, a limit signal is received and the actual drone pose in the actual visual image information is still inconsistent with the preset drone pose after the target drone has accurately entered the parking area, the drone is controlled to take off and land again until the number of re-takeoffs and landings reaches a second preset number. The second preset number can be three times.

[0120] Step 110: If the actual drone pose is inconsistent with the preset drone pose after the second preset number of attempts, then the drone is determined to have failed to be stored in the warehouse.

[0121] For details of step 110 above, please refer to step 108, which will not be repeated here.

[0122] In this embodiment, when the actual drone pose in the actual visual image information is inconsistent with the preset drone pose, the drone is directly controlled to perform multiple take-off and landing operations, which can effectively avoid misjudgment caused by landing attitude problems.

[0123] Optionally, in one specific embodiment, the case where the actual UAV pose is consistent with the preset UAV pose includes step 1021; the case where the actual UAV pose is inconsistent with the preset UAV pose includes step 1031.

[0124] Step 1031: If the deviation between the actual UAV pose and the preset UAV pose is less than a preset deviation threshold, determine that the actual UAV pose is consistent with the preset UAV pose.

[0125] In this step, the preset deviation threshold is the deviation value used to determine whether the actual drone pose is consistent with the preset drone pose. After comparing the actual drone pose extracted from the actual visual image with the preset drone pose after the target drone is successfully stored using a visual algorithm, if the deviation value between the two does not reach the preset deviation threshold, it means that the deviation between the two is small. It can be determined that the current drone pose is consistent with the reference pose after the drone is successfully stored, which means that the current drone pose is normal.

[0126] Optionally, the above pose parameters can be tilt angles, and the above deviation values ​​can specifically be 0.1%, 0.5%, 1%, 1.5%, or 2%.

[0127] Step 1041: If the deviation between the actual UAV pose and the preset UAV pose is greater than or equal to a preset deviation threshold, determine that the actual UAV pose is consistent with the preset UAV pose.

[0128] In this step, after comparing the actual drone pose extracted from the actual visual image with the preset drone pose after the target drone successfully enters the warehouse using a visual algorithm, if the deviation between the two reaches the preset deviation threshold, it indicates that the deviation between the two is large. This means that the current drone pose is inconsistent with the reference pose after the drone successfully enters the warehouse, which means that the current drone pose is abnormal.

[0129] Please see Figure 3 The diagram illustrates the process of UAV arrival detection in an embodiment of the present invention.

[0130] like Figure 3 As shown, in step 301, after the hangar receives the drone landing request, the limit switch used for the drone landing centering limit starts detection;

[0131] In step 302, after the hangar receives the flag indicating that the drone has successfully landed, the return motor starts.

[0132] In step 303, the centering motor drives the actuator to return the drone to the target area, such as the center of the hangar.

[0133] In step 304, the hangar determines whether the signal of the limit switch is set to 1 and lasts for 5 seconds. If so, the limit switch is determined to be valid and the process proceeds to step 305; otherwise, the limit switch is determined to be invalid and the process proceeds to step 306.

[0134] In step 305, the limit switch will continuously set the signal to 1 because it will be continuously touched by the drone's feet. Therefore, when the limit switch is active, it is assumed that the drone has landed in place. Thus, subsequent visual recognition can be performed to determine the drone's position and attitude.

[0135] In step 306, it is determined whether the number of times the drone has re-executed take-off and landing exceeds 3. If it does not exceed 3, the process proceeds to step 307, where the centering mechanism is opened, and then to step 308, where the drone re-executes take-off and landing. If the number of times the drone re-executes take-off and landing exceeds 3, the process proceeds to step 309.

[0136] In step 309, it is determined that the drone failed to reach its destination, that is, the drone failed to successfully center and clamp itself in the target area.

[0137] Please see Figure 4 The diagram illustrates a flowchart of the in-situ detection process for unmanned aerial vehicles (UAVs) in an embodiment of the present invention.

[0138] like Figure 4 As shown, in step 401, a front view of the drone is taken beforehand when it is correctly stored in the warehouse, which will serve as the reference image for subsequent comparison.

[0139] In step 402, after the drone is successfully detected to be in place, the camera is controlled to capture images of the centering area to obtain a real-time front view of the drone's parking position.

[0140] In step 403, visual information is extracted and image search is performed using the feature points of the drone. The captured image is compared and identified with the reference image to determine whether there is a drone at the center position in the captured image. If there is, proceed to step 404; otherwise, proceed to step 405.

[0141] In step 404, it is determined that the drone is in place, but this does not mean that the attitude is correct, so attitude detection is required.

[0142] In step 405, it is determined whether the number of times the drone has re-executed take-off and landing exceeds 3. If it does not exceed 3, the process proceeds to step 406, where the centering mechanism is opened, then to step 407, where the drone re-executes take-off and landing, and then to step 408, where the drone's arrival detection process is executed. If the number of times the drone has re-executed take-off and landing exceeds 3, the process proceeds to step 409.

[0143] In step 409, it is determined that the drone is not in place, that is, the one that landed in the hangar is not a drone.

[0144] Please see Figure 5 The diagram illustrates a flowchart of UAV attitude detection in an embodiment of the present invention.

[0145] like Figure 5 As shown, in step 501, a front view of the drone is taken beforehand when it is correctly stored in the warehouse, which will serve as the reference image for subsequent comparison.

[0146] In step 502, after the drone is successfully detected to be in place, the camera is controlled to capture images of the returned center area to obtain a real-time front view of the drone's parking position.

[0147] In step 503, the captured image is compared and identified with the reference image. After determining that the drone exists at the center position in the captured image, the angle between the reference image and the real-time image is calculated. It is determined whether the real-time image exceeds the left side of the reference image by 1%. If so, the drone is considered to be tilted to the left, and then the process proceeds to step 504; otherwise, the process proceeds to step 509.

[0148] In step 504, it is determined whether the number of times the drone has re-executed take-off and landing exceeds 3. If it does not exceed 3, the process proceeds to step 505, where the centering mechanism is opened, then to step 506, where the drone re-executes take-off and landing, and then to step 507, where the drone's arrival detection process is executed. If the number of times the drone has re-executed take-off and landing exceeds 3, the process proceeds to step 508.

[0149] In step 508, it is determined that the attitude of the drone that landed in the hangar is abnormal, that is, the drone attitude detection failed.

[0150] In step 509, it is further determined whether the real-time image exceeds the right side of the reference image by 1%. If so, the UAV is considered to be tilted to the right, and then proceed to step 504; otherwise, proceed to step 510.

[0151] In step 510, since the left and right tilt deviation between images is within an acceptable range of 1%, the drone is considered to be in position and in the correct attitude.

[0152] This invention also provides a drone entry identification device. Figure 6 This is a schematic diagram of a device provided in an embodiment of the present invention, the device comprising:

[0153] The first acquisition module 61 is used to acquire actual visual image information of the target area when it is determined that there is a drone in the target area of ​​the hangar. The actual visual image information includes actual drone features and actual drone pose.

[0154] The first determining module 62 is used to determine that the drone has been successfully entered into the database if the actual drone features are consistent with the preset drone features and the actual drone pose is consistent with the preset drone pose.

[0155] Optionally, in the device, the preset drone features and the preset drone pose are visual image information of the target area obtained when the drone successfully enters the warehouse.

[0156] Optionally, the device further includes:

[0157] The second determining module is used to determine that the drone fails to be stored if the actual drone features are inconsistent with the preset drone features, or if the actual drone pose is inconsistent with the preset drone pose.

[0158] Optionally, in the device, the second determining module includes:

[0159] The first control unit is configured to control the drone to perform a first preset number of take-off and landing operations if the actual drone characteristics are inconsistent with the preset drone characteristics.

[0160] The first determining unit is configured to determine that the drone entry into the warehouse has failed if, after a first preset number of times, the actual drone characteristics are inconsistent with the preset drone characteristics.

[0161] Optionally, in the device, the second determining module includes:

[0162] The second determining unit is used to determine whether the actual drone pose is consistent with the preset drone pose if, after a first preset number of times, the actual drone features are consistent with the preset drone features.

[0163] The second control unit is used to control the drone to perform a second preset number of take-off and landing operations if the actual drone pose is inconsistent with the preset drone pose.

[0164] The third determining unit is used to determine that the drone storage has failed if the actual drone pose is inconsistent with the preset drone pose after a second preset number of times.

[0165] Optionally, in the device, the second determining module includes:

[0166] The third control unit is used to control the drone to perform a second preset number of take-off and landing operations if the actual drone pose is inconsistent with the preset drone pose.

[0167] The third determining unit is used to determine that the drone storage has failed if the actual drone pose is inconsistent with the preset drone pose after a second preset number of times.

[0168] Optionally, the device further includes:

[0169] The third determining module is used to determine that there is a drone in the target area of ​​the hangar when a limit signal for the target area is received and the limit signal continues for a preset duration.

[0170] Optionally, the device further includes:

[0171] The first control module is used to move the drone to the target area after the drone to be identified has landed, before receiving a limit signal for the target area.

[0172] Optionally, the hangar includes a centering mechanism for bringing drones to the target area;

[0173] The first control module is specifically used to control the centering mechanism to bring the UAV to the target area.

[0174] Optionally, the hangar further includes a limit switch, which is disposed on the centering mechanism and is used to limit the target area;

[0175] The third determining module is specifically used to determine that there is a drone in the target area of ​​the hangar when the limit switch receives a limit signal for the target area and the limit signal continues for a preset duration.

[0176] Optionally, the second determining module includes:

[0177] The fourth determining unit is used to determine that the actual drone pose is consistent with the preset drone pose when the deviation between the actual drone pose and the preset drone pose is less than a preset deviation threshold.

[0178] Optionally, the second determining module includes:

[0179] The fifth determining unit is used to determine that the actual drone pose is consistent with the preset drone pose when the deviation between the actual drone pose and the preset drone pose is greater than or equal to a preset deviation threshold.

[0180] This invention also provides a vehicle, wherein the vehicle further includes the drone entry identification device as described above.

[0181] For the above-described device and vehicle embodiments, since they are basically similar to the drone entry and identification method embodiments, the relevant parts can be referred to in the description of the method embodiments.

[0182] The drone entry identification device and vehicle provided in this embodiment of the invention, by combining actual visual images with preset drone features and preset drone poses when a drone is found in the target area of ​​the hangar, can further determine whether the drone entering the hangar is the target drone and whether it has entered the hangar accurately. Therefore, it can effectively avoid the false entry caused by other objects replacing the drone and effectively identify the actual entry of the vehicle-mounted drone.

[0183] This invention also provides an electronic device, such as... Figure 7 As shown, it includes a processor 701, a communication interface 702, a memory 703, and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704.

[0184] Memory 703 is used to store computer programs.

[0185] When processor 701 executes a program stored in memory 703, it performs the following steps:

[0186] If it is determined that there is a drone in the target area of ​​the hangar, the actual visual image information of the target area is obtained, and the actual visual image information includes the actual drone features and the actual drone pose.

[0187] If the actual drone features are consistent with the preset drone features, and the actual drone pose is consistent with the preset drone pose, then the drone is successfully stored in the database.

[0188] The processor 701 can also implement other steps in the above-mentioned drone entry identification method, which will not be elaborated here.

[0189] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0190] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0191] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0192] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0193] In another embodiment of the present invention, a drone system is also provided, including a drone, a hangar, and the aforementioned electronic equipment, wherein the hangar is used to park the drone, and the electronic equipment is used to identify the drone upon entry into the hangar.

[0194] In another embodiment of the present invention, a vehicle is also provided, the vehicle including the above-described unmanned aerial vehicle system, the hangar being disposed on the roof, rear or front of the vehicle.

[0195] In another embodiment of the present invention, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the drone entry identification method described in the above embodiments.

[0196] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the drone entry identification method described in the above embodiments.

[0197] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0198] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0199] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. For embodiments of systems, electronic devices, computer-readable storage media, and computer program products containing instructions, the descriptions are relatively simple because they are fundamentally similar to the method embodiments; relevant parts can be referred to in the descriptions of the method embodiments.

[0200] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A method for identifying drone entry into a warehouse, characterized in that, The method includes: If it is determined that there is a drone in the target area of ​​the hangar, the actual visual image information of the target area is acquired. The actual visual image information includes the actual drone features and the actual drone pose. The hangar includes a centering mechanism for gathering drones into the target area and a limit switch. The limit switch is disposed on the centering mechanism and is used to limit the target area. If the actual drone features are consistent with the preset drone features, and the actual drone pose is consistent with the preset drone pose, then the drone is determined to have been successfully stored. If the actual drone characteristics are inconsistent with the preset drone characteristics, then the drone is controlled to perform a first preset number of take-off and landing operations; If, after the first preset number of attempts, the actual drone characteristics are inconsistent with the preset drone characteristics, then the drone is determined to have failed to be stored in the database. The determination that a drone exists in the target area of ​​the hangar includes: If no limit signal is received when the drone is moved to the target area, the drone is controlled to perform a third preset number of take-off and landing operations. If no limit signal is received after the third preset number of operations, the drone is determined to have failed to enter the hangar. If a limit signal is received from the limit switch for the target area and the limit signal lasts for a preset duration, the drone is determined to be present in the target area of ​​the hangar.

2. The method according to claim 1, characterized in that, The preset drone features and the preset drone pose are visual image information of the target area obtained when the drone is successfully stored.

3. The method according to claim 1, characterized in that, include: If the actual drone features are inconsistent with the preset drone features, or if the actual drone pose is inconsistent with the preset drone pose, then the drone is determined to have failed to be stored.

4. The method according to claim 1, characterized in that, include: If, after the first preset number of times, the actual drone features are consistent with the preset drone features, then it is determined whether the actual drone pose is consistent with the preset drone pose. If the actual drone pose is inconsistent with the preset drone pose, the drone is controlled to perform a second preset number of take-off and landing operations. If the actual drone pose is inconsistent with the preset drone pose after the second preset number of attempts, then the drone is determined to have failed to be stored in the warehouse.

5. The method according to claim 1, characterized in that, include: If the actual drone pose is inconsistent with the preset drone pose, the drone is controlled to perform a second preset number of take-off and landing operations. If the actual drone pose is inconsistent with the preset drone pose after the second preset number of attempts, then the drone is determined to have failed to be stored in the warehouse.

6. The method according to claim 1, characterized in that, The presence of drones in the target area of ​​the hangar has been confirmed, including: If a limit signal is received for the target area and the limit signal continues for a preset duration, it is determined that a drone exists in the target area of ​​the hangar.

7. The method according to claim 6, characterized in that, Before receiving a limiting signal for the target area, the method further includes: After the drone has landed, it will be moved to the target area.

8. The method according to claim 7, characterized in that, Moving the drone to the target area includes: The centering mechanism is controlled to bring the drone to the target area.

9. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus; the processor, communication interface, and memory communicate with each other via the communication bus. Memory, used to store computer programs; The processor, when executing a program stored in memory, implements the steps in the drone entry identification method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the steps in the drone entry identification method as described in any one of claims 1 to 8.

11. An unmanned aerial vehicle (UAV) system, comprising a UAV, a hangar, and electronic equipment as described in claim 9, wherein the hangar is used to park the UAV, and the electronic equipment is used to identify the UAV upon entry into the hangar.

12. A vehicle, characterized in that, Including the unmanned aerial vehicle system as described in claim 11, wherein the hangar is located on the roof, rear, or front compartment of the vehicle.

Images