UAV patrol control system and method

Abstract

The present application provides a drone patrol control system and method, relating to the field of warehouse management technology. By setting a photoluminescent area, the method can more conveniently determine the location of each information tag based on the current cargo image, thereby determining the shooting point, further reducing the difficulty of drone inspections. A photoluminescent area and a filter segment are set on the cargo information tag. The brightness of the filter segment at different angles under the illumination of a laser light source is adjusted to ensure that valid cargo information can be extracted from the image to be identified acquired by the drone camera. This can reduce the difficulty of collection and shorten the drone's hovering time, thereby solving the problem of insufficient drone endurance.

Description

Technical Field

[0001] The present application relates to the field of warehouse management technology, and specifically to a drone patrol control system and method. Background Art

[0002] Warehouse cargo management can use drones to inspect goods in logistics warehouses, realize unmanned warehouse management, improve inspection efficiency and reduce inspection costs.

[0003] The related drone patrol control method, based on the combination of drones, barcodes, and RFID technologies, can reduce the workload during inspections and inventory checks, improving the efficiency of automated storage management and the reliability and credibility of inventory data. However, in actual operational management, because the information tags on the goods are not on the same plane and have different inclination angles with the horizontal plane, if the angle between the camera's viewfinder and the information tag's orientation is too large, it increases the difficulty of data collection and can easily cause the drone to hover in front of a piece of goods for a long time, thereby reducing the drone's flight time and making it impossible to complete the inventory task. Summary of the Invention

[0004] The present application provides a drone patrol control system and method, which can reduce the difficulty of collecting cargo during drone inspection and improve the drone's endurance.

[0005] This application provides a method for controlling a drone patrol, including:

[0006] Obtain an image of the current cargo captured by the drone hovering at the starting point of the current collection area; the drone passes through multiple collection areas while inspecting along a preset patrol route, the current collection area including a shelf and at least one item placed on the shelf, an information tag disposed on the item, the information tag facing outward from the shelf, an annular photoluminescent region disposed around the information tag, and a filter segment disposed in any section of the photoluminescent region; the drone is provided with a laser light source and a camera module, and under illumination from the laser light source, the photoluminescent region appears as a bright area in the current cargo image;

[0007] Based on the position of the photoluminescent area on the information tag of each item in the current cargo image, multiple shooting points of the drone in the current collection area are determined, and the shooting points correspond to the information tags one by one;

[0008] Obtain the images to be identified taken by the drone at each shooting point;

[0009] Based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, the target hovering height and target camera angle of the drone are determined, and the target hovering height and target camera angle are sent to the drone, so that the drone obtains the image to be processed including the information label based on the target hovering height and target camera angle.

[0010] Optionally, determining a target hovering height and a target camera angle of the drone based on a brightness ratio of the filter segment and the photoluminescent region in the image to be identified includes:

[0011] If the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is greater than or equal to a preset threshold, performing information tag identification based on the image to be identified;

[0012] If the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is less than a preset threshold, the target hovering height and the target camera angle are determined based on the mapping relationship among the preset brightness ratio, the hovering height and the camera angle.

[0013] Optionally, the laser light source is an ultraviolet light source.

[0014] Optionally, the method further includes:

[0015] Determine the separation distance between the information tag and the drone camera;

[0016] The target frequency and target power of the laser light source are determined according to the separation distance.

[0017] Optionally, determining a target frequency and a target power of the laser light source according to the separation distance includes:

[0018] The target frequency and target power are determined according to the mapping relationship between the interval distance and the preset interval distance, frequency, and power.

[0019] Optionally, based on the position of the photoluminescent area on the information label of each cargo in the current cargo image, multiple shooting points of the drone in the current collection area are determined, including:

[0020] Compare the current cargo image with the cargo image at the previous moment to determine whether there is any change in the cargo in the current collection area;

[0021] If there is a change in the goods, the shooting point is determined based on the position of the photoluminescent area on the information label of each goods in the current goods image;

[0022] If the goods have not changed, a preset number of target photoluminescent areas are randomly selected from the photoluminescent areas of all goods based on the position of the photoluminescent areas on the information labels of each goods in the current goods image, and the shooting point is determined based on the position of each target photoluminescent area.

[0023] Optionally, the method further includes:

[0024] Obtain the quantity of goods in the current collection area;

[0025] determining a number of photoluminescent regions based on the current cargo image;

[0026] If the quantity of goods and the quantity of photoluminescent areas are inconsistent, a prompt message is generated.

[0027] To achieve the above objectives and other related objectives, the present application provides a drone patrol control system, comprising:

[0028] A first data acquisition module is configured to acquire an image of the current cargo captured by the drone while hovering at a starting point in a current collection area. The drone passes through multiple collection areas while inspecting along a preset patrol route. The current collection area includes a shelf and at least one item placed on the shelf. An information tag is disposed on the item, facing outward from the shelf. The information tag is surrounded by an annular photoluminescent region, and a filter segment is disposed in any section of the photoluminescent region. The drone is equipped with a laser light source and a camera module. Under illumination from the laser light source, the photoluminescent region appears as a bright area in the current cargo image.

[0029] The first processing module is configured to determine a plurality of shooting points of the drone in the current collection area based on the position of the photoluminescent area on the information tag of each item in the current item image, wherein the shooting points correspond to the information tags one by one;

[0030] The second data acquisition module is used to acquire the images to be identified taken by the drone at each shooting point;

[0031] The second processing module is used to determine the target hovering height and target camera angle of the drone based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, and send the target hovering height and target camera angle to the drone, so that the drone obtains the image to be processed including the information tag based on the target hovering height and target camera angle.

[0032] Optionally, the second processing module further includes:

[0033] a first determining unit, configured to perform information tag recognition based on the image to be recognized if a brightness ratio of the filter segment to the photoluminescent area in the image to be recognized is greater than or equal to a preset threshold;

[0034] A processing unit is configured to determine a target hovering height and a target camera angle based on a mapping relationship among a preset brightness ratio, a hovering height, and a camera angle if a brightness ratio between the filter segment and the photoluminescent area in the image to be identified is less than a preset threshold.

[0035] Optionally, the laser light source is an ultraviolet light source.

[0036] As described above, the drone patrol control system and method provided by this application have the following beneficial effects:

[0037] The present application discloses a drone patrol control method that, by setting a photoluminescent area, can more conveniently determine the location of each information tag based on the current cargo image, thereby determining the shooting point and further reducing the difficulty of drone inspections. By setting a photoluminescent area and a filter segment on the cargo information tag, and adjusting the brightness of the filter segment at different angles under laser illumination, the drone's hovering height and camera angle are adjusted to ensure that valid cargo information can be extracted from the image to be identified captured by the drone camera. This method can reduce the acquisition difficulty and the drone's hovering time, thereby resolving the problem of insufficient drone endurance.

[0038] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0040] Figure 1 is a schematic diagram of an information tag shown in an exemplary embodiment of the present application;

[0041] Figure 2 is a schematic structural diagram of a drone shown in an exemplary embodiment of the present application;

[0042] Figure 3 is a flow chart of a method for controlling a drone patrol according to an exemplary embodiment of the present application;

[0043] Figure 4 is a schematic diagram of a drone inspection shown in an exemplary embodiment of the present application;

[0044] Figure 5 is a schematic diagram of an information tag and a drone before adjustment, shown in an exemplary embodiment of the present application;

[0045] Figure 6 is a schematic diagram of an adjusted information tag and a drone shown in an exemplary embodiment of the present application;

[0046] Figure 7 It is a structural block diagram of a drone patrol control system shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will describe the embodiments of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0048] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0049] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0050] See also Figure 1 , which is a schematic diagram of an information tag shown as an exemplary embodiment of the present application.

[0051] The information label may include cargo information such as the type of cargo and the place of shipment. A photoluminescent area 110 may be provided around the information label. A filter segment 120 may be provided in any section of the photoluminescent area. The photoluminescent area 110 may include an upper section, a right section, a lower section, and a left section in a clockwise direction from the top. Figure 1 The middle filter segment 120 is disposed at the upper section.

[0052] See also Figure 2 , which is a schematic diagram of the structure of a drone according to an exemplary embodiment of the present application. The drone may be provided with a laser light source 210 and a camera 220.

[0053] A laser light source is provided on the drone, and an annular photoluminescent area is provided around the information tag. The material of the photoluminescent area can be zinc sulfide, and a portion of the zinc sulfide is covered with a filter segment. During the drone inspection process, the laser light source 210 emits excitation light, and the camera 220 on the drone captures the excitation effect of the zinc sulfide on the information tag, thereby confirming the position of the information tag. Then, based on the difference in excitation effect between the filter segment and the uncovered filter segment, it is determined whether the framing direction of the camera 220 corresponds to the orientation of the information tag. The framing direction of the camera 220 is adjusted accordingly, thereby shortening the information tag collection time, improving statistical efficiency, and enhancing the energy efficiency of the drone.

[0054] It should be noted that the drone can be provided with a drive component to adjust the camera angle.

[0055] See also Figure 3 , Figure 3 This is a flow chart of a drone patrol control method shown in an exemplary embodiment of the present application. Figure 3 It can be seen that the UAV patrol control method may include:

[0056] Step S310: obtaining a current cargo image captured by the drone hovering at the starting point of the current collection area.

[0057] Among them, the drone passes through multiple collection areas when inspecting along a preset patrol route. The current collection area includes a shelf and at least one item placed on the shelf. The information tag is set on the item, and the information tag faces outside the shelf. A ring-shaped photoluminescent area is set around the information tag, and a filter segment is set in any section of the photoluminescent area. The drone is equipped with a laser light source and a camera module. Under the illumination of the laser light source, the photoluminescent area is displayed as a bright area in the current item image.

[0058] In one embodiment of the present application, when a drone hovers at a starting point, it can capture an image of all goods within the current collection area. Shelves in a logistics warehouse can be divided into multiple collection areas, each of which can include at least one shelf. The starting point can be located to the left or right of the collection area. When the drone hovers at the starting point, all goods within the collection area are within the drone's field of view.

[0059] The cloud can obtain the current cargo image uploaded by the drone and perform subsequent image recognition and other steps based on the current cargo image.

[0060] Optionally, the laser light source may be an ultraviolet light source or an infrared light source, or may be other light sources, which are not limited in the present embodiment.

[0061] Step S320 , based on the position of the photoluminescent area on the information label of each cargo in the current cargo image, a plurality of shooting points of the drone in the current collection area are determined.

[0062] Among them, the shooting points correspond to the information tags one by one.

[0063] In one embodiment of the present application, the cloud can determine multiple drone shooting points in the current collection area based on the location of the photoluminescent area on the information label of each item in the current cargo image. Because the laser light source is turned on when the drone captures the current cargo image, the photoluminescent area on each information label can be excited by the laser light source, and the brightness of the photoluminescent area is different from that of other areas in the current cargo image. The cloud can perform image recognition on the current cargo image based on the identification label point in the current cargo image (e.g., the bottom of the shelf, the top of the shelf, or other identification label point), preset shelf size information, a preset distance between the identification label point and the ground, and a preset coordinate system (e.g., with the identification label point as the origin, the direction parallel to the shelf end face as the x-axis, and the direction perpendicular to the ground as the y-axis), to determine the coordinates of each information label in the current cargo image (e.g., the coordinates of the center point of each information label).

[0064] The camera point can be at the same height as the center point of the information tag. The horizontal distance between each camera point and the edge of the shelf (shelf end face) can be a preset spacing. The preset spacing can be a preset value set by the designer. The preset spacing can be greater than 0.3m, which can ensure the safety of the drone and the goods and avoid collision between the drone and the goods.

[0065] For example, see Figure 4 , which is a schematic diagram of a drone inspection according to an exemplary embodiment of the present application. The dotted line with an arrow represents the direction of the drone inspection. Goods 420 can be placed on shelf 410, which corresponds to the current collection area. Based on the direction of the drone inspection, drone 200 flies to various shooting locations and hovers over each shooting location to capture an image to be identified, including an information tag 100.

[0066] Step S330: Obtain the images to be identified taken by the drone at each shooting point.

[0067] In one embodiment of the present application, after determining each shooting point, the cloud can determine a shooting order based on each shooting point and send the shooting order to the drone, so that the drone can sequentially shoot the image to be identified at each shooting point based on the shooting order. When the drone shoots the image to be identified, the laser light source is turned on.

[0068] It should be noted that the laser light source is on when the drone is taking images. The drone can turn off the laser light source after taking the image and turn it on again when taking the next image. The laser light source can also be kept on and turned off after the drone inspection is completed.

[0069] In step S340, based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, the target hovering height and target camera angle of the drone are determined, and the target hovering height and target camera angle are sent to the drone, so that the drone obtains the image to be processed including the information tag based on the target hovering height and target camera angle.

[0070] In one embodiment of the present application, the cloud can perform image recognition on the image to be identified, and determine the target hovering height and target camera angle of the drone based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, and send the target hovering height and target camera angle to the drone.

[0071] After receiving the target hovering height and target camera angle, the drone can adjust the hovering height and camera angle of the drone to the target hovering height and target camera angle.

[0072] It should be noted that the drone can conduct inspections at a preset initial height. The coordinates of the starting point in the preset coordinate system are preset values, the y-axis coordinate value of the starting point is the preset initial height, and the x-axis coordinate of the starting point is the horizontal distance between the left end or the right end of the shelf and the identification label point.

[0073] In one possible implementation, the target hovering height and target camera angle of the drone are determined based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, including: if the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is greater than or equal to a preset threshold, information tag identification is performed based on the image to be identified; if the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is less than the preset threshold, the target hovering height and target camera angle are determined based on the mapping relationship between the preset brightness ratio, hovering height and camera angle.

[0074] In one embodiment of the present application, the preset threshold value may be 0.7. If the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is greater than or equal to the preset threshold value, information tag identification is performed based on the image to be identified to determine the cargo information of the information tag in the image to be identified. If the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is less than the preset threshold value, it indicates that the image to be identified obtained at the current hovering height and camera angle of the drone cannot be effectively recognized. The cloud can determine the target hovering height and target camera angle based on the mapping relationship between the preset brightness ratio, hovering height, and camera angle.

[0075] It should be noted that designers can pre-calibrate the mapping relationship between brightness ratio, hovering height, and camera angle. Regardless of the orientation of the photoluminescent area and the angle between the camera and the image, the brightness of the photoluminescent area remains unchanged under laser excitation in the image to be recognized. However, the orientation of the filter segment and the angle of the camera will affect the brightness of the filter segment in the image. Image recognition technology can be used to determine the brightness ratio of the filter segment in the image to be recognized to the brightness of the photoluminescent area.

[0076] In another possible implementation, if the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is greater than or equal to a preset threshold, information tag identification is performed based on the image to be identified. If the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is less than the preset threshold, the target hovering height, target camera angle, and target interval distance are determined based on a preset mapping relationship between the brightness ratio, interval distance, hovering height, and camera angle. When the drone first hovers at the shooting point to obtain the image to be identified during the current inspection process, the distance between the drone and the end face of the shelf is the preset spacing. When adjusting the drone's height, the higher the altitude, the more likely it is that the field of view is obstructed. In this case, the interval distance can be adjusted to reduce the height adjustment.

[0077] For example, see Figure 5 , which is a schematic diagram of an information tag and a drone before adjustment according to an exemplary embodiment of the present application. The cargo 420 is provided with an information tag 100, and the angle between the tag direction 510 of the information tag 100 and the camera direction 520 of the drone 200 is relatively large. Figure 6 , which is a schematic diagram of an adjusted information tag and drone according to an exemplary embodiment of the present application. After adjusting the drone's altitude and camera angle, the angle between the tag orientation 510 of the information tag 100 and the camera orientation 520 of the drone 200 is smaller.

[0078] Optionally, the drone patrol control method provided in the embodiment of the present application may further include: determining the interval distance between the information tag and the drone camera; and determining the target frequency and target power of the laser light source based on the interval distance.

[0079] In one embodiment of the present application, distance recognition can be performed based on the image to be recognized to determine the separation distance between the information tag and the drone camera. Laser ranging can also be performed on the drone using a laser light source to determine the separation distance between the information tag and the drone camera. After determining the separation distance, the target frequency and target power of the laser light source can be determined based on the preset separation distance, so that the frequency gradually increases as the separation distance decreases, while the power gradually decreases as the separation distance decreases, thereby improving the drone's endurance.

[0080] Optionally, determining the target frequency and target power of the laser light source based on the separation distance may include determining the target frequency and target power based on the separation distance and a preset mapping relationship between separation distance, frequency, and power. The ultraviolet light source on the drone emits pulsed light at intervals, and the power and frequency are divided into three levels, as shown in Table 1.

[0081] Table 1 Correspondence between laser light source parameters and separation distance

[0082] Separation distance Interval time (ms) Frequency (Hz) Power (W) Duty cycle (%) Long distance (>1.5m) 100 10 5 50% Medium distance (0.8-1.5m) 50 20 3 33% Close range (0.3-0.8m) 20 50 1 10%

[0083] High power at long distances ensures signal penetration, while low power at close distances reduces redundant energy consumption. The coordinated adjustment of pulse interval and frequency gradually reduces the duty cycle from 50% to 10%, significantly reducing average power consumption. Pulse operation reduces continuous heating of LEDs, reduces heat dissipation requirements, and further improves power efficiency. Compared with continuous high-power, high-frequency generation of ultraviolet light, the drone's flight time is significantly improved.

[0084] Optionally, the process of determining the multiple shooting points of the drone in the current collection area based on the position of the photoluminescent area on the information label of each cargo in the current cargo image in step S320 may include:

[0085] Step S321 : performing image comparison between the current cargo image and the cargo image at the previous moment to determine whether there is any change in the cargo in the current collection area.

[0086] In one embodiment of the present application, an image of the current cargo captured by the drone at the starting point of the current collection area can be compared with an image of the cargo captured at a previous moment to determine whether there has been any change in the cargo within the current collection area. Changes in cargo may include at least one of a decrease in cargo, an increase in cargo, and a change in cargo location.

[0087] Step S322 : If there is a change in the goods, the shooting point is determined based on the position of the photoluminescent area on the information label of each goods in the current goods image.

[0088] In one embodiment of the present application, if the cargo has changed, the location of the photoluminescent area on the information label of each cargo item in the current cargo image is used to determine the capture point. In other words, the drone needs to capture the information label corresponding to each photoluminescent area.

[0089] In step S323, if the goods have not changed, a preset number of target photoluminescent areas are randomly selected from the photoluminescent areas of all goods based on the positions of the photoluminescent areas on the information labels of the goods in the current goods image, and a shooting point is determined based on the position of each target photoluminescent area.

[0090] In one embodiment of the present application, if the goods remain unchanged, a preset number of target photoluminescent areas are randomly selected from all the photoluminescent areas of the goods based on the positions of the photoluminescent areas on the information labels of each item in the current goods image. The capture point is then determined based on the position of each target photoluminescent area. In other words, if the goods in the current capture area remain unchanged, a few target photoluminescent areas can be randomly selected for spot checks, which can improve inventory efficiency.

[0091] Exemplarily, the preset number may be 3.

[0092] Optionally, the drone patrol control method provided in the embodiment of the present application may also include: obtaining the quantity of goods in the current collection area; determining the number of photoluminescent areas based on the current cargo image; and generating a prompt message if the quantity of goods is inconsistent with the number of photoluminescent areas.

[0093] In one embodiment of the present application, the quantity of goods in the current collection area can be obtained. When goods are put into storage, the quantity can be synchronized to a remote device. Quantity recognition can also be performed based on the current goods image to determine the quantity of goods in the current collection area. The number of photoluminescent areas is determined based on the current goods image. If the quantity of goods and the number of photoluminescent areas are inconsistent, a prompt message can be generated to prompt the user to review. If the quantity of goods and the number of photoluminescent areas are consistent, step S320 can be executed.

[0094] For example, the cloud can send the prompt information to the buzzer corresponding to the current collection area to issue an alarm prompt through the buzzer.

[0095] Figure 7 FIG is a block diagram of a drone patrol control system according to an exemplary embodiment of the present application. Figure 7 As shown, the exemplary drone patrol control system 700 includes:

[0096] The first data acquisition module 710 is used to obtain an image of the current cargo captured by the drone while hovering at the starting point of the current collection area. The drone passes through multiple collection areas while inspecting along a preset patrol route. The current collection area includes a shelf and at least one cargo item placed on the shelf. An information tag is set on the cargo, and the information tag faces outward from the shelf. The information tag is surrounded by an annular photoluminescent area, and any section of the photoluminescent area is provided with a filter segment. The drone is equipped with a laser light source and a camera module. Under the illumination of the laser light source, the photoluminescent area appears as a bright area in the current cargo image.

[0097] The first processing module 720 is configured to determine a plurality of shooting points of the drone in the current acquisition area based on the position of the photoluminescent area on the information tag of each item in the current item image, wherein the shooting points correspond to the information tags one by one.

[0098] The second data acquisition module 730 is used to acquire the images to be identified taken by the drone at various shooting points.

[0099] The second processing module 740 is used to determine the target hovering height and target camera angle of the drone based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, and send the target hovering height and target camera angle to the drone, so that the drone can obtain the image to be processed including the information tag based on the target hovering height and target camera angle.

[0100] In one embodiment of the present application, the second processing module further includes:

[0101] a first determining unit, configured to perform information tag recognition based on the image to be recognized if a brightness ratio of the filter segment to the photoluminescent area in the image to be recognized is greater than or equal to a preset threshold;

[0102] A processing unit is configured to determine a target hovering height and a target camera angle based on a mapping relationship among a preset brightness ratio, a hovering height, and a camera angle if a brightness ratio between the filter segment and the photoluminescent area in the image to be identified is less than a preset threshold.

[0103] In one embodiment of the present application, the laser light source is an ultraviolet light source.

[0104] It should be noted that the drone patrol control device provided in the above embodiment and the drone patrol control method provided in the above embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the drone patrol control device provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0105] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the electronic device implements the drone patrol control method provided in the above-mentioned embodiments.

[0106] Another aspect of the present application provides a computer-readable storage medium storing a computer program. When executed by a computer processor, the computer program causes the computer to execute the drone patrol control methods provided in the aforementioned embodiments. The computer-readable storage medium may be included in the electronic device described in the aforementioned embodiments, or may exist independently and not be incorporated into the electronic device.

[0107] Another aspect of the present application provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the drone patrol control method provided in each of the above embodiments.

[0108] In the embodiments of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance. Throughout the specification and claims, the terms "including" and "comprising" are open-ended terms and should be interpreted as "including but not limited to."

[0109] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, any equivalent modifications or alterations accomplished by a person of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A method for controlling a drone patrol, characterized in that: include: Get the current cargo image taken by the drone hovering at the starting point of the current collection area; The drone passes through multiple collection areas while inspecting along a preset patrol route. The current collection area includes a shelf and at least one item placed on the shelf. An information tag is set on the item, with the information tag facing outward from the shelf. The information tag is surrounded by a ring-shaped photoluminescent area, and any section of the photoluminescent area is provided with a filter segment. The drone is equipped with a laser light source and a camera module. Under the illumination of the laser light source, the photoluminescent area appears as a bright area in the current image of the item. Based on the location of the photoluminescent area on the information label of each item in the current cargo image, multiple shooting points of the drone in the current collection area are determined, and the shooting points correspond one-to-one with the information labels. Based on the identification label point in the current cargo image, the preset shelf size information, the preset distance between the identification label point and the ground, and the preset coordinate system, the current cargo image is image recognized to determine the coordinates of each information label in the current cargo image; Obtain images to be identified, taken by the drone at various shooting locations. Regardless of the orientation of the photoluminescent region and the angle between the camera and the image, the brightness of the photoluminescent region remains unchanged under the excitation of the laser. However, the orientation of the filter segment and the angle of the camera affect the brightness of the filter segment in the image. Based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, the target hovering height and target camera angle of the drone are determined, and the target hovering height and target camera angle are sent to the drone, so that the drone obtains the image to be processed including the information label based on the target hovering height and target camera angle.

2. The UAV patrol control method according to claim 1, characterized in that: Based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, the target hovering height and target camera angle of the drone are determined, including: If the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is greater than or equal to a preset threshold, performing information tag identification based on the image to be identified; If the brightness ratio of the filter segment and the photoluminescent area in the image to be identified is less than a preset threshold, the target hovering height and the target camera angle are determined based on the mapping relationship among the preset brightness ratio, the hovering height and the camera angle.

3. The UAV patrol control method according to claim 1, characterized in that: The laser light source is an ultraviolet light source.

4. The UAV patrol control method according to claim 1, characterized in that: The method further comprises: Determine the separation distance between the information tag and the drone camera; The target frequency and target power of the laser light source are determined according to the separation distance.

5. The UAV patrol control method according to claim 4, characterized in that: Determine the target frequency and target power of the laser light source based on the separation distance, including: The target frequency and target power are determined according to the mapping relationship between the interval distance and the preset interval distance, frequency, and power.

6. The UAV patrol control method according to claim 1, characterized in that: Based on the location of the photoluminescent area on the information label of each cargo in the current cargo image, multiple shooting points of the drone in the current collection area are determined, including: Compare the current cargo image with the cargo image at the previous moment to determine whether there is any change in the cargo in the current collection area; If there is a change in the goods, the shooting point is determined based on the position of the photoluminescent area on the information label of each goods in the current goods image; If the goods have not changed, a preset number of target photoluminescent areas are randomly selected from the photoluminescent areas of all goods based on the position of the photoluminescent areas on the information labels of each goods in the current goods image, and the shooting point is determined based on the position of each target photoluminescent area.

7. The UAV patrol control method according to claim 1, characterized in that: The method further comprises: Obtain the quantity of goods in the current collection area; determining a number of photoluminescent regions based on the current cargo image; If the quantity of goods and the quantity of photoluminescent areas are inconsistent, a prompt message is generated.

8. A drone patrol control system, characterized in that: include: The first data acquisition module is used to obtain the current cargo image taken by the drone hovering at the starting point of the current collection area; The drone passes through multiple collection areas while inspecting along a preset patrol route. The current collection area includes a shelf and at least one item placed on the shelf. An information tag is set on the item, with the information tag facing outward from the shelf. The information tag is surrounded by a ring-shaped photoluminescent area, and any section of the photoluminescent area is provided with a filter segment. The drone is equipped with a laser light source and a camera module. Under the illumination of the laser light source, the photoluminescent area appears as a bright area in the current image of the item. The first processing module is configured to determine multiple shooting points of the drone in the current collection area based on the location of the photoluminescent area on the information tag of each item in the current item image, wherein the shooting points correspond one-to-one with the information tags; and perform image recognition on the current item image based on the identification tag point in the current item image, preset shelf size information, a preset distance between the identification tag point and the ground, and a preset coordinate system to determine the coordinates of each information tag in the current item image; The second data acquisition module is used to acquire the image to be identified taken by the drone at each shooting point. Regardless of the orientation of the photoluminescent area and the angle between the camera and the image, the brightness of the photoluminescent area under the excitation of the laser does not change in the image to be identified, while the orientation of the filter segment and the angle of the camera will affect the brightness of the filter segment in the image. The second processing module is used to determine the target hovering height and target camera angle of the drone based on the brightness ratio of the filter segment and the photoluminescent area in the image to be identified, and send the target hovering height and target camera angle to the drone, so that the drone obtains the image to be processed including the information tag based on the target hovering height and target camera angle.

9. The UAV patrol control system according to claim 8, characterized in that: The second processing module also includes: a first determining unit, configured to perform information tag recognition based on the image to be recognized if a brightness ratio of the filter segment to the photoluminescent area in the image to be recognized is greater than or equal to a preset threshold; A processing unit is configured to determine a target hovering height and a target camera angle based on a mapping relationship among a preset brightness ratio, a hovering height, and a camera angle if a brightness ratio between the filter segment and the photoluminescent area in the image to be identified is less than a preset threshold.

10. The UAV patrol control system according to claim 8, characterized in that: The laser light source is an ultraviolet light source.

Images