Unmanned aerial vehicle garage protection method and device and computer equipment

Abstract

The invention relates to the technical field of intelligent inspection, and discloses an unmanned aerial vehicle garage protection method and device and computer equipment, and the method comprises the steps: monitoring a to-be-confirmed object entering a protection region corresponding to an unmanned aerial vehicle garage; performing identification based on the to-be-confirmed object to obtain a target object meeting an execution condition; a protection program matched with the target object is executed, and the protection program is used for driving the target object. According to the invention, active monitoring and expelling of the invaded target object can be realized, and foreign matter invasion can be responded in time, so that the protection effect is optimized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent inspection technology, and in particular to a drone hangar protection method, device and computer equipment. Background Art

[0002] With the continuous development and application of drone technology, drones and drone hangars are increasingly set up in open, unmanned outdoor areas. These areas usually lack infrastructure such as protective measures and are vulnerable to damage from intruders such as wild animals and tourists, posing great risks to the safe storage and use of drones.

[0003] However, in the protection measures of related drone hangars, physical fences and other solutions are usually used to divide the protection area of ​​the drone hangar to prevent intruders, but physical fences often have problems such as limited protection effect, inability to respond to foreign object intrusion in a timely manner, and poor protection effect. Summary of the invention

[0004] In view of this, the present invention provides a drone hangar protection method, device and computer equipment to solve the problems of limited protection effect of physical fences, inability to respond to foreign body intrusion in a timely manner, and poor protection effect.

[0005] In a first aspect, the present invention provides a drone hangar protection method, the method comprising:

[0006] Monitor the objects to be confirmed that have entered the protection area corresponding to the drone hangar;

[0007] Based on the object to be confirmed, identification is performed to obtain the target object that meets the execution conditions;

[0008] A protection program matching the target object is executed, wherein the protection program is used to drive away the target object.

[0009] In the embodiment of the present invention, the objects to be confirmed that enter the protection area corresponding to the drone hangar can be monitored first, and the objects to be confirmed can be identified based on the objects to be confirmed to obtain the target objects that meet the execution conditions. Then, the protection program matching the target objects can be executed, wherein the protection program is used to drive away the target objects, thereby realizing active monitoring and expulsion of the invading target objects, and timely responding to the invasion of foreign objects, thereby optimizing the protection effect.

[0010] In some optional implementations, identifying the target object that meets the execution condition based on the object to be confirmed includes:

[0011] Obtain the video frame corresponding to the object to be confirmed;

[0012] Identifying an object type of the object to be confirmed based on the video frame, and acquiring sensor data of the object to be confirmed when the object type matches a preset type;

[0013] When it is determined based on the sensing data that the object to be confirmed is in the target state, the object to be confirmed is regarded as a target object that meets the execution condition.

[0014] In an embodiment of the present invention, image recognition technology and sensor fusion technology can be used to detect foreign body intrusion, wherein the image recognition technology can determine whether the object type of the object to be confirmed matches the preset type, and the sensor fusion technology further improves the accuracy and reliability of the detection, making up for the limitations of a single detection method.

[0015] In some optional implementations, determining that the object to be confirmed is in a target state based on the sensing data includes:

[0016] Based on the sensor data, determine the real-time temperature of the object to be confirmed;

[0017] When the real-time temperature matches the temperature interval of the preset type, it is determined that the object to be confirmed is in the target state.

[0018] In the disclosed embodiment, liveness detection can be performed on the object to be confirmed by matching the real-time temperature of the object with a preset type of temperature range. If the object to be confirmed passes the liveness detection, it is considered that the object to be confirmed is in the target state, thereby improving the confidence of the detection result and further compensating for the limitations of a single detection method.

[0019] In some optional implementations, identifying the object to be confirmed to obtain a target object that meets the execution condition further includes:

[0020] When the object type of the object to be confirmed does not match the preset type, identifying the object behavior and the object volume of the object to be confirmed;

[0021] When the behavior of the object matches the preset behavior, and / or the volume of the object exceeds the volume threshold, the object to be confirmed is determined to be a target object that meets the execution condition.

[0022] In the embodiment of the present invention, considering that the actual field environment for deploying the drone hangar is often more complicated, technical personnel are often unable to predict in advance and set all the preset types of intrusion objects in a comprehensive manner. Therefore, the non-preset intrusion objects can be further identified through the judgment process of object behavior and object volume, thereby improving the protection plan and enhancing the security of the protection plan.

[0023] In some optional implementations, executing a protection program that matches the target object includes:

[0024] Determine, in the audio to be played, a target audio that matches the object type of the target object;

[0025] Play the target audio based on the guard program.

[0026] In an embodiment of the present invention, corresponding target audio can be played according to the object type of the target object to achieve a better repelling effect, thereby coping with different types of intrusion objects to meet the safety requirements of the drone hangar in complex outdoor environments.

[0027] In some optional implementations, determining the target audio that matches the object type of the target object in the audio to be played includes:

[0028] When there are multiple target objects, determining the expulsion level of each target object based on the object type;

[0029] A target audio that matches the expulsion level is determined in the audio to be played.

[0030] In the embodiment of the present invention, considering that the outdoor environment is often more complex, multiple target objects invading the protection area may be detected at the same time. At this time, the corresponding target audio can be played based on the expulsion level, and the number of target audio played can be streamlined, thereby improving the expulsion efficiency of the target objects.

[0031] In some optional implementations, executing a protection program that matches the target object further includes:

[0032] Get the location information of the target object;

[0033] Based on the location information, the flight trajectory of the drone is determined, and based on the protection program, the drone is controlled to operate according to the flight trajectory, and intrusion information is generated based on the target object.

[0034] In an embodiment of the present invention, after detecting the target object, the location information of the target object can be monitored in real time while playing the target audio, and when it is determined based on the location information that the target object is in a warning position, the drone in the drone hangar is instructed to fly out of the cabin and fly according to the determined flight trajectory. At the same time, the management personnel are notified through the intrusion information to handle it in time, so as to reduce the possibility of damage to the drone and avoid the expansion of economic losses.

[0035] In some optional embodiments, the method further comprises:

[0036] When executing the protection program that matches the target object, the intrusion data of the target object is obtained and uploaded to the cloud server in real time.

[0037] In an embodiment of the present invention, the intrusion data of the target object can be recorded by the recording module, and the intrusion data can be uploaded to the cloud server in real time for storage, so that the administrator can view and trace the intrusion video at any time, so that the administrator can understand the security status of the drone hangar in time and take corresponding treatment measures quickly, thereby improving management efficiency and response speed.

[0038] In a second aspect, the present invention provides a drone hangar protection device, the device comprising:

[0039] A monitoring module, used to monitor the objects to be confirmed that enter the protection area corresponding to the drone hangar;

[0040] An identification module is used to identify the target object that meets the execution conditions based on the object to be confirmed;

[0041] The execution module is used to execute a protection program that matches the target object, wherein the protection program is used to drive away the target object.

[0042] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the drone hangar protection method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the drone hangar protection method of the first aspect or any corresponding embodiment thereof.

[0044] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the drone hangar protection method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 is a flow chart of a drone hangar protection method according to an embodiment of the present invention;

[0047] Figure 2 is a system architecture diagram of another intelligent protection device for a drone hangar according to an embodiment of the present invention;

[0048] Figure 3 is a flow chart of another method for intelligent protection of a drone hangar according to an embodiment of the present invention;

[0049] Figure 4 is a flow chart of another drone hangar protection method according to an embodiment of the present invention;

[0050] Figure 5 is a structural block diagram of a drone hangar protection device according to an embodiment of the present invention;

[0051] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0053] In conjunction with the application scenarios on which the execution of the drone hangar protection method depends, the application scenarios are described here.

[0054] With the continuous development and application of drone technology, drones and drone hangars are increasingly set up in open, unmanned outdoor areas. These areas usually lack infrastructure such as protective measures and are vulnerable to damage from intruders such as wild animals and tourists, posing great risks to the safe storage and use of drones.

[0055] However, in the protection measures of related drone hangars, physical fences and other solutions are usually used to divide the protection area of ​​the drone hangar to prevent intruders, but physical fences often have problems such as limited protection effect, inability to respond to foreign object intrusion in a timely manner, and poor protection effect.

[0056] Based on this, an embodiment of the present invention provides a drone hangar protection method, which can first monitor the unconfirmed objects entering the protection area corresponding to the drone hangar, and identify the unconfirmed objects based on the unconfirmed objects to obtain target objects that meet the execution conditions. Then, a protection program matching the target object can be executed, wherein the protection program is used to drive away the target object, thereby realizing active monitoring and expulsion of the invading target object, and timely responding to the invasion of foreign objects, thereby optimizing the protection effect.

[0057] According to an embodiment of the present invention, an embodiment of a drone hangar protection method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0058] In this embodiment, a drone hangar protection method is provided, which can be used for drone hangar intelligent protection equipment. Figure 1 is a flow chart of a drone hangar protection method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0059] Step S101, monitoring the objects to be confirmed that enter the protection area corresponding to the drone hangar.

[0060] In an embodiment of the present invention, a drone hangar in the wild is a facility specifically used for storing, automatically charging and dispatching drones. The drone hangar is usually deployed in the wild or in a specific area to achieve efficient management and automated operation of drones. Specifically, the drone hangar can provide a safe storage space for drones and automatically charge or replace batteries when necessary. This ensures that the drone is always in the best condition before performing a mission. Then, through the integrated scheduling system, the drone hangar can automatically release or recover the drone according to mission requirements, thereby achieving efficient utilization of drones. At the same time, the drone hangar is also responsible for collecting, storing and managing data collected by drones, providing support for subsequent data analysis and application.

[0061] In order to protect the drone hangar, the drone hangar can be equipped with a drone hangar intelligent protection device. Figure 2 The figure shows the system architecture diagram of the drone hangar intelligent protection device, wherein the drone hangar intelligent protection device may include a gimbal, a detection module, a driving module, a recording module, an uploading module, and a notification module.

[0062] Specifically, the protection area corresponding to the drone hangar can be pre-demarcated, wherein the protection area can be a three-dimensional range with a radius centered on the drone hangar, for example, a three-dimensional protection area with a radius of 2 meters. Then, the position of the pan / tilt can be set according to the protection area, and the monitoring device can be installed in the pan / tilt, so that the monitoring device can monitor the entire protection area in real time.

[0063] After the monitoring device is set up, it can be turned on in response to a protection start instruction, and the monitoring device can be used to monitor the unconfirmed objects in the protection area in real time. The unconfirmed objects can be people, objects, animals, machinery, etc. that were not originally in the protection area but were detected to suddenly enter the protection area.

[0064] Step S102: performing identification based on the object to be confirmed to obtain a target object that meets the execution condition.

[0065] In an embodiment of the present invention, the target object may be an intrusion object that may cause damage to the drone library, such as a tourist or an animal, etc. Here, the object to be confirmed can be identified by the above-mentioned detection module to determine whether the object to be confirmed poses a threat, and the object to be confirmed that poses a threat to the drone library is determined as the target object.

[0066] Specifically, after the object to be confirmed is detected, the object to be confirmed may be matched with an intrusion object and a non-intrusion object. If the object to be confirmed hits an intrusion object, it may be considered that the object to be confirmed meets the execution condition.

[0067] In addition, considering that the field environment where the drone hangar is set is often complex, there may be many intrusion objects, and the types of interference objects that will not pose a threat to the drone hangar are also complex. Therefore, while setting the intrusion objects in advance, common interference objects that are easily confused with intrusion objects can also be set as non-intrusion objects.

[0068] For example, if the intrusion target is a wild Siberian tiger, and the Siberian tiger is a common cultural product in local tourism, resulting in the common sight of industrial products with Siberian tigers printed on them in the wild, such as brand X packaging bags with Siberian tigers printed on them, then the packaging bag can be set as a non-intrusion target.

[0069] In specific implementation, when the object to be confirmed is identified, here we take the video frame of the object to be confirmed as an example. First, the intrusion object matching process can be executed. If it is detected that the object to be confirmed contains an intrusion object, the object to be confirmed can be further matched with the non-intrusion object. If the non-intrusion object is matched, the object to be confirmed is determined to be a non-target object. If it is not matched, the object to be confirmed is determined to be a target object.

[0070] In addition, when identifying the object to be confirmed, liveness recognition can also be performed through multimodal fusion. For example, when it is determined through the video frame that the object to be confirmed matches the intruding object, the RGB image of the video frame can be determined and fused with thermal imaging data to utilize information from different modalities to determine whether the intruding object is a living body. If so, it is the target object, otherwise it is a non-intrusive object.

[0071] Step S103, executing a protection program that matches the target object, wherein the protection program is used to drive away the target object.

[0072] In an embodiment of the present invention, the protection program may be a driving away program that matches the object type of the target object. The protection program may drive away the target object by emitting sound or light, etc., to prevent the target object from damaging the drone hangar.

[0073] Specifically, the protection program may be executed by the driving away module. For example, when the object type of the target object is a bird, the driving away module may execute the protection program to play the calls of the natural enemies of the birds, thereby driving away the birds.

[0074] It can be seen from the above description that in the embodiment of the present invention, the objects to be confirmed that enter the protection area corresponding to the drone hangar can be monitored first, and the objects to be confirmed can be identified to obtain the target objects that meet the execution conditions. Then, the protection program matching the target object can be executed, wherein the protection program is used to drive away the target object, thereby realizing active monitoring and expulsion of the invading target object, and timely responding to the invasion of foreign objects, thereby optimizing the protection effect.

[0075] In this embodiment, another drone hangar protection method is provided, which can be used for drone hangar intelligent protection equipment. Figure 3 FIG. 1 is a flow chart of another drone hangar protection method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0076] Step S201: monitor the objects to be confirmed that have entered the protection area corresponding to the drone hangar. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0077] Step S202: performing identification based on the object to be confirmed to obtain a target object that meets the execution condition.

[0078] Specifically, the above step S202 includes:

[0079] Step S2021, obtaining the video frame corresponding to the object to be confirmed.

[0080] Step S2022: Identify the object type of the object to be confirmed based on the video frame, and when the object type matches a preset type, obtain sensor data of the object to be confirmed.

[0081] Step S2023: when it is determined based on the sensing data that the object to be confirmed is in the target state, the object to be confirmed is regarded as a target object that meets the execution condition.

[0082] In an embodiment of the present invention, the preset type may be a pre-set type of an intrusion object. Here, a camera device may be installed in the above-mentioned pan / tilt head to collect video frames containing the object to be confirmed, and the object to be confirmed in the video frame is identified through a pre-trained network model to output the matching degree between the object to be confirmed and each preset type, so as to determine whether the target object is an intrusion object.

[0083] For example, the network model is a Siamese Network model. It should be understood that the network model may also be other network models suitable for image matching tasks, which is subject to what can be implemented, and the present invention does not make specific limitations on this.

[0084] When determining the degree of match between the object to be confirmed and each preset type, an image dataset can be first established based on the acquired video frames, and the image dataset can be preprocessed, for example, by scaling, cropping, normalization, etc., so that the image dataset meets the input requirements of the model.

[0085] Then, the network model can be used to extract the feature vectors of the image frames in the image data set, and the matching degree between the feature vectors of each preset type of intrusion object can be calculated. For example, the similarity or distance between the feature vectors can be calculated to obtain the matching degree between the object to be determined and the preset type of intrusion object. Here, the cosine similarity, Euclidean distance and other measurement methods can be used to measure the matching degree.

[0086] Next, it can be determined whether the object to be confirmed in the image frame matches the preset type of intrusion object according to the matching threshold. For example, if the preset type of intrusion object is a wild Siberian tiger, the matching degree between the object to be confirmed and the wild Siberian tiger is 90%, and the matching threshold is 80%, then it is considered that the object type of the object to be confirmed matches the preset type.

[0087] When it is determined that the object type of the object to be confirmed matches the preset type, the sensor data of the object to be confirmed can be obtained to further confirm the state of the object to be confirmed, so as to determine whether the object to be confirmed is in a target state where it can or will destroy the drone hangar. Specifically, the sensor data can be infrared data collected by a temperature sensor, etc.

[0088] In an embodiment of the present invention, image recognition technology and sensor fusion technology can be used to detect foreign body intrusion, wherein the image recognition technology can determine whether the object type of the object to be confirmed matches the preset type, and the sensor fusion technology further improves the accuracy and reliability of the detection, making up for the limitations of a single detection method.

[0089] Step S203, executing a protection program that matches the target object, wherein the protection program is used to drive away the target object. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0090] In an embodiment of the present invention, image recognition technology and sensor fusion technology can be used to detect foreign body intrusion, wherein the image recognition technology can determine whether the object type of the object to be confirmed matches the preset type, and the sensor fusion technology further improves the accuracy and reliability of the detection, making up for the limitations of a single detection method.

[0091] In some optional implementations, the above step S2023, determining that the object to be confirmed is in the target state based on the sensing data, includes:

[0092] Step a1, determining the real-time temperature of the object to be confirmed based on the sensing data.

[0093] Step a2: when the real-time temperature matches the temperature interval of the preset type, it is determined that the object to be confirmed is in the target state.

[0094] In the disclosed embodiment, the sensing data may be heat distribution data in the protection area fed back by a temperature sensor. Specifically, the temperature sensor may include an infrared thermal imager, and the sensing data may be a thermal radiation image in the protection area, which reflects the temperature distribution in the protection area.

[0095] Here, the object to be confirmed in the thermal radiation image may be marked in combination with the object to be confirmed marked in the video frame captured by the camera device to obtain the real-time temperature of the object to be confirmed.

[0096] Then, a temperature interval matching the preset type corresponding to the object to be confirmed can be determined. Here, if the object to be confirmed is an animal or a person with temperature, the temperature interval can be the body temperature interval of the object to be confirmed.

[0097] It should be understood that if the real-time temperature of the object to be confirmed is within the temperature range corresponding to the preset type, it is determined that the object to be confirmed has passed the liveness detection and is in a target state that may pose a threat to the drone hangar.

[0098] In the disclosed embodiment, liveness detection can be performed on the object to be confirmed by matching the real-time temperature of the object with a preset type of temperature range. If the object to be confirmed passes the liveness detection, it is considered that the object to be confirmed is in the target state, thereby improving the confidence of the detection result and further compensating for the limitations of a single detection method.

[0099] In some optional implementations, the above step S102, identifying the target object that meets the execution condition based on the object to be confirmed, further includes:

[0100] Step S11 : when the object type of the object to be confirmed does not match the preset type, identifying the object behavior and the object volume of the object to be confirmed.

[0101] Step S12: when the behavior of the object matches the preset behavior and / or the volume of the object exceeds the volume threshold, the object to be confirmed is determined to be a target object that meets the execution condition.

[0102] In the disclosed embodiment, when the object type of the object to be confirmed does not match the preset type, it means that the object to be confirmed is not a preset intrusion object. At this time, further intrusion determination can be performed on the object to be confirmed, and when the object to be confirmed has the possibility of threatening the drone hangar, the object to be confirmed is identified as a target object. Here, the object behavior and object volume of the object to be confirmed can be obtained, and the determination of whether the execution condition is met can be made based on the object behavior and the object volume.

[0103] When executing the object behavior determination process, a preset behavior that may damage the drone hangar can be obtained. For example, the preset behavior can be moving toward the drone hangar at a certain moving speed. Based on this, when executing the determination process, if it is detected that the object behavior is that the object to be confirmed moves toward the drone hangar at a certain speed, it can be determined whether the moving speed of the object to be confirmed exceeds the moving speed corresponding to the preset behavior. If so, it is determined that the object behavior matches the preset behavior.

[0104] When executing the object volume determination process, the volume data of the execution object can be obtained, for example, a model of the execution object can be established through the collected 3D point cloud data, so as to extract the feature vector of the 3D point cloud data through the network model, and output the prediction result of the object volume for the object to be confirmed. Here, the object whose object volume exceeds the volume threshold can be determined as a target object that may cause damage to the drone hangar.

[0105] In the embodiment of the present invention, considering that the actual field environment for deploying the drone hangar is often more complicated, technical personnel are often unable to predict in advance and set all the preset types of intrusion objects in a comprehensive manner. Therefore, the non-preset intrusion objects can be further identified through the judgment process of object behavior and object volume, thereby improving the protection plan and enhancing the security of the protection plan.

[0106] In this embodiment, another drone hangar protection method is provided, which can be used for drone hangar intelligent protection equipment. Figure 4 FIG. 4 is a flowchart of another drone hangar protection method according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0107] Step S401: monitor the objects to be confirmed that have entered the protection area corresponding to the drone hangar. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0108] Step S402: Identify the target object that meets the execution condition based on the object to be confirmed. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0109] Step S403: executing a protection program that matches the target object, wherein the protection program is used to drive away the target object.

[0110] Specifically, the above step S403 includes:

[0111] Step S4031: determine the target audio that matches the object type of the target object in the audio to be played.

[0112] Step S4032, playing the target audio based on the protection program.

[0113] In an embodiment of the present invention, the audio to be played may include a driving audio set for each preset type of intrusion object. For example, if the preset type is birds, the corresponding driving audio may be the call of the natural enemy of birds, and if the preset type is humans, the corresponding driving audio may be a warning of property damage, and at the same time ordering the intruder to stop the damage and leave the protection area.

[0114] Here, an association relationship between a preset type and a corresponding audio to be played may be preset to obtain association information, and after determining the object type of the target object, the target audio matching the object type may be searched based on the association information.

[0115] After the target audio is determined, the play mode of the target audio can be set through the protection program, and the target audio is played according to the play mode until the target object is detected to leave the protection area. For example, the play mode can be loop play.

[0116] In an embodiment of the present invention, corresponding target audio can be played according to the object type of the target object to achieve a better repelling effect, thereby coping with different types of intrusion objects to meet the safety requirements of the drone hangar in complex outdoor environments.

[0117] In some optional implementations, the above step S4031, determining the target audio that matches the object type of the target object in the audio to be played, includes:

[0118] Step b1: when there are multiple target objects, determine the expulsion level of each target object based on the object type.

[0119] Step b2: determining the target audio that matches the driving-away level in the audio to be played.

[0120] In the embodiment of the present invention, considering that the outdoor environment is often more complex, multiple target objects invading the protection area may be detected at the same time. At this time, the corresponding target audio can be played based on the expulsion level to streamline the number of target audios played.

[0121] Specifically, multiple expulsion levels can be pre-set, and corresponding audio to be played can be set for each expulsion level. Based on this, after multiple target objects are detected, the expulsion level corresponding to each target object can be identified to play the target audio corresponding to the expulsion level.

[0122] For example, if the target objects include bird 1, bird 2 and bird 3, and the repelling levels corresponding to bird 1-bird 3 are all the first repelling level, then the audio to be played that is pre-set for the first repelling level can be determined as the target audio.

[0123] In addition, when multiple target audios are determined, each target audio can be played in sequence. Specifically, the play order of the target audios can be determined based on the expulsion level, and the target audios can be played in sequence according to the play order. For example, the play order can be from high to low in terms of expulsion level.

[0124] In the embodiment of the present invention, considering that the outdoor environment is often more complex, multiple target objects invading the protection area may be detected at the same time. At this time, the corresponding target audio can be played based on the expulsion level, and the number of target audio played can be streamlined, thereby improving the expulsion efficiency of the target objects.

[0125] In some optional implementations, the above step S103, executing a protection program matching the target object, further includes:

[0126] Step S21, obtaining the location information of the target object.

[0127] Step S22, based on the location information, determine the flight trajectory of the UAV, control the UAV to operate according to the flight trajectory based on the protection program, and generate intrusion information based on the target object.

[0128] In an embodiment of the present invention, after detecting the target object, the position information of the target object can be monitored in real time while playing the target audio, and when it is determined based on the position information that the target object is in a warning position, the drones in the drone hangar are instructed to fly out of the cabin, so as to further warn the target object while avoiding the destruction of the drone hangar, resulting in damage to the drones and expanding economic losses.

[0129] Specifically, the flight trajectory of the drone can be formulated based on the location information of the target object, so that the drone can avoid the attack range of the target object when flying according to the flight trajectory, reducing the possibility of damage to the drone.

[0130] At the same time, intrusion information can also be generated based on the target object and sent to the management personnel so that the protection personnel can handle the security incident in time. For example, the intrusion information can include the intrusion time of the target object, the warning level, and the coordinates or number of the drone hangar. Specifically, a text message containing the intrusion information can be generated by the above notification module and sent to the terminal device of the management personnel.

[0131] In an embodiment of the present invention, after detecting the target object, the location information of the target object can be monitored in real time while playing the target audio, and when it is determined based on the location information that the target object is in a warning position, the drone in the drone hangar is instructed to fly out of the cabin and fly according to the determined flight trajectory. At the same time, the management personnel are notified through the intrusion information to handle it in time, so as to reduce the possibility of damage to the drone and avoid the expansion of economic losses.

[0132] In some optional embodiments, the above Figure 1 The corresponding implementations also include:

[0133] When executing the protection program that matches the target object, the intrusion data of the target object is obtained and uploaded to the cloud server in real time.

[0134] In the embodiment of the present invention, the intrusion data may include a video of the complete intrusion process of the target object. Specifically, when the expelling module expel the target object, the recording module may automatically start the recording function of the picture to collect the complete intrusion data.

[0135] Then, the collected intrusion data can be uploaded to the cloud server in real time through the above upload module for storage, so that the administrator can view and trace it at any time. Specifically, the cloud server can store the intrusion data in the storage location set for the drone library, so that the administrator can call the intrusion data based on the storage location.

[0136] In an embodiment of the present invention, the intrusion data of the target object can be recorded by the recording module, and the intrusion data can be uploaded to the cloud server in real time for storage, so that the administrator can view and trace the intrusion video at any time, so that the administrator can understand the security status of the drone hangar in time and take corresponding treatment measures quickly, thereby improving management efficiency and response speed.

[0137] In summary, in the embodiment of the present invention, the objects to be confirmed that enter the protection area corresponding to the drone hangar can be monitored first, and the objects to be confirmed can be identified based on the objects to be confirmed to obtain the target objects that meet the execution conditions. Then, the protection program that matches the target object can be executed, wherein the protection program is used to drive away the target object, thereby realizing active monitoring and expulsion of the invading target object, and timely responding to the intrusion of foreign objects, thereby optimizing the protection effect.

[0138] In this embodiment, a drone hangar protection device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0139] This embodiment provides a drone hangar protection device, such as Figure 5 As shown, including:

[0140] Monitoring module 501, used to monitor the objects to be confirmed that enter the protection area corresponding to the drone hangar;

[0141] An identification module 502 is used to identify the target object that meets the execution condition based on the object to be confirmed;

[0142] The execution module 503 is used to execute a protection program that matches the target object, wherein the protection program is used to drive away the target object.

[0143] In some optional implementations, the identification module 502 is further configured to:

[0144] Obtain the video frame corresponding to the object to be confirmed;

[0145] Identifying an object type of the object to be confirmed based on the video frame, and acquiring sensor data of the object to be confirmed when the object type matches a preset type;

[0146] When it is determined based on the sensing data that the object to be confirmed is in the target state, the object to be confirmed is regarded as a target object that meets the execution condition.

[0147] In some optional implementations, the identification module 502 is further configured to:

[0148] Based on the sensor data, determine the real-time temperature of the object to be confirmed;

[0149] When the real-time temperature matches the temperature interval of the preset type, it is determined that the object to be confirmed is in the target state.

[0150] In some optional implementations, the identification module 502 is further configured to:

[0151] When the object type of the object to be confirmed does not match the preset type, identifying the object behavior and the object volume of the object to be confirmed;

[0152] When the behavior of the object matches the preset behavior, and / or the volume of the object exceeds the volume threshold, the object to be confirmed is determined to be a target object that meets the execution condition.

[0153] In some optional implementations, the execution module 503 is further configured to:

[0154] Determine, in the audio to be played, a target audio that matches the object type of the target object;

[0155] Play the target audio based on the guard program.

[0156] In some optional implementations, the execution module 503 is further configured to:

[0157] When there are multiple target objects, determining the expulsion level of each target object based on the object type;

[0158] A target audio that matches the expulsion level is determined in the audio to be played.

[0159] In some optional implementations, the execution module 503 is further configured to:

[0160] Get the location information of the target object;

[0161] Based on the location information, the flight trajectory of the drone is determined, and based on the protection program, the drone is controlled to operate according to the flight trajectory, and intrusion information is generated based on the target object.

[0162] In some optional embodiments, the device is also used for:

[0163] When executing the protection program that matches the target object, the intrusion data of the target object is obtained and uploaded to the cloud server in real time.

[0164] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0165] The drone hangar protection device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0166] The embodiment of the present invention also provides a computer device having the above Figure 5The drone hangar guard shown.

[0167] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0168] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0169] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0170] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0171] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0172] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0173] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0174] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0175] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the accompanying description.

Claims

1. A drone hangar protection method, characterized in that: The method comprises: Monitor the objects to be confirmed that have entered the protection area corresponding to the drone hangar; Identify the target object based on the object to be confirmed to obtain the target object that meets the execution condition; A protection program matching the target object is executed, wherein the protection program is used to drive away the target object.

2. The method according to claim 1, characterized in that The identifying based on the object to be confirmed to obtain a target object that meets the execution condition includes: Obtaining a video frame corresponding to the object to be confirmed; Identifying an object type of the object to be confirmed based on the video frame, and acquiring sensor data of the object to be confirmed when the object type matches a preset type; When it is determined based on the sensing data that the object to be confirmed is in the target state, the object to be confirmed is a target object that meets the execution condition.

3. The method according to claim 2, characterized in that The determining, based on the sensing data, that the object to be confirmed is in a target state comprises: Based on the sensor data, determining the real-time temperature of the object to be confirmed; When the real-time temperature matches the temperature interval of the preset type, it is determined that the object to be confirmed is in the target state.

4. The method according to claim 1, characterized in that: The identifying based on the object to be confirmed to obtain a target object that meets the execution condition also includes: When the object type of the object to be confirmed does not match the preset type, identifying the object behavior and the object volume of the object to be confirmed; When the object behavior matches a preset behavior and / or the object volume exceeds a volume threshold, it is determined that the object to be confirmed is a target object that meets the execution condition.

5. The method according to claim 1, characterized in that The executing a protection program matching the target object includes: Determining a target audio that matches the object type of the target object in the audio to be played; The target audio is played based on the protection program.

6. The method according to claim 5, characterized in that The step of determining the target audio that matches the object type of the target object in the audio to be played includes: When there are multiple target objects, determining the expulsion level of each target object based on the object type; A target audio that matches the driving-away level is determined in the audio to be played.

7. The method according to claim 1, characterized in that The executing a protection program matching the target object further includes: Acquire location information of the target object; Based on the location information, the flight trajectory of the UAV is determined, and based on the protection program, the UAV is controlled to operate according to the flight trajectory, and intrusion information is generated based on the target object.

8. The method according to claim 1, characterized in that The method further comprises: When executing a protection program that matches the target object, the intrusion data of the target object is obtained, and the intrusion data is uploaded to the cloud server in real time.

9. A drone hangar protection device, characterized in that: The device comprises: A monitoring module, used to monitor the objects to be confirmed that enter the protection area corresponding to the drone hangar; An identification module, used to identify the target object that meets the execution condition based on the object to be confirmed; An execution module is used to execute a protection program that matches the target object, wherein the protection program is used to drive away the target object.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the drone hangar protection method according to any one of claims 1 to 8 by executing the computer instructions.

Images