Unmanned aerial vehicle logistics control method and system based on image recognition and unmanned aerial vehicle

Abstract

The invention provides an unmanned aerial vehicle logistics control method and system based on image recognition and an unmanned aerial vehicle, and relates to the technical field of warehouse management, and the method comprises the steps: obtaining a current itinerant view image shot by the unmanned aerial vehicle at a current shooting point, carrying out the image comparison of the current itinerant view image and a previous itinerant view image, and if goods change, carrying out the logistics control of the unmanned aerial vehicle. If the goods change, a multi-point identification instruction is sent to the unmanned aerial vehicle, so that the unmanned aerial vehicle shoots auxiliary view images at all circumferential identification points corresponding to the current shooting point and then uploads the auxiliary view images to the cloud for dumping risk identification, and if the goods do not change, the next shooting point of the current shooting point in the itinerant path is sent to the unmanned aerial vehicle. The data processing amount of the cloud can be reduced, the time of single inspection of the unmanned aerial vehicle is reduced, and the cost of warehouse management is reduced.

Description

Technical Field

[0001] The present application relates to the field of warehouse management technology, and specifically to a drone logistics control method, system and drone based on image recognition. 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] In the related technology, there is a drone logistics control method based on image recognition. The drone flies according to a preset inspection route. After the drone flies to any shooting point, it first hovers at the shooting point to shoot the tour field of view image, and then flies to each circumferential identification point corresponding to the shooting point to sequentially shoot the auxiliary field of view image. After uploading the tour field of view image and the auxiliary field of view image to the cloud, the cloud determines whether the goods photographed by the drone have a risk of dumping. However, this method requires a lot of computing power support, which greatly increases management costs; on the other hand, the drone itself has limited endurance, and hovering at multiple points may increase the drone's power consumption, increasing the cost of drone inspections. Summary of the invention

[0004] The present application provides a drone logistics control method, system and drone based on image recognition, which can reduce the amount of data processing in the cloud, reduce the time of a single drone inspection, and thus reduce the cost of warehouse management.

[0005] The present application provides a drone logistics control method based on image recognition, comprising: Obtain the current patrol view image taken by the drone at the current shooting point; the drone is used to fly according to the preset patrol path and shoot the goods stored on the shelves in the logistics warehouse at the current shooting point; If there is a previous patrol field of view image corresponding to the current shooting point, then compare the current patrol field of view image with the previous patrol field of view image to determine whether there is any change in the cargo in the drone field of view corresponding to the current shooting point; If there is a change in the cargo, a multi-point identification command is sent to the drone, so that after receiving the multi-point identification command, the drone takes auxiliary field of view images at each circumferential identification point corresponding to the current shooting point and uploads them to the cloud for dumping risk identification; If there is no change in the goods, the next shooting point of the current shooting point in the patrol path is sent to the drone.

[0006] Optionally, if there is a change in the cargo, a multi-point identification command is sent to the drone, including: If there is any change in the goods, the vibration data uploaded to the cloud by the target vibration sensor corresponding to the current shooting point is obtained; If the vibration data meets the vibration judgment conditions, a multi-point recognition command is sent to the drone; If the vibration data does not meet the vibration judgment condition, the next shooting point of the current shooting point in the patrol path is sent to the drone.

[0007] Optionally, the vibration data includes acceleration, and the vibration judgment condition includes: The peak acceleration within the preset time is greater than a first threshold; and / or, The effective value of acceleration within the preset time is greater than the second threshold.

[0008] Optionally, the target threshold includes a first threshold or a second threshold, and the method further includes: Obtain the current load weight of the shelf and the preset load weight of the shelf; the preset load weight of the shelf represents the maximum load weight of the shelf; Determining a first adjustment coefficient based on a ratio of a current load weight of the shelf to a preset load weight of the shelf; Determine a second adjustment coefficient based on a mapping relationship between a preset shelf level and an adjustment coefficient at a shelf level where the goods are located; A target threshold is determined according to the first adjustment coefficient, the second adjustment coefficient and a preset initial value.

[0009] Optionally, if there is a change in the cargo, the vibration data uploaded to the cloud by the target vibration sensor corresponding to the current shooting point is obtained, including: If there is a change in the cargo, a high-frequency operation instruction is sent to the target vibration sensor to change the target vibration sensor from low-frequency operation to high-frequency operation, and run in the high-frequency operation state for a preset time. The frequency of the high-frequency operation is 1Hz~10Hz; Obtain vibration data of a target vibration sensor that runs for a preset time in a high-frequency operating state.

[0010] Optionally, the current tour view image taken by the drone at the current shooting point is obtained, including: In response to receiving the arrival information sent by the drone, the cloud sends a start command to the light source device, so that the light source device performs lighting compensation for the drone's field of view corresponding to the current shooting point after receiving the start command. The arrival information indicates that the drone has flown to the current shooting point.

[0011] Optionally, in response to receiving the arrival information sent by the drone, the cloud sends a start instruction to the light source device, including: In response to receiving the location information sent by the drone, the cloud obtains the natural light intensity; If the natural light intensity is less than the light threshold, the cloud sends a turn-on command to the light source device.

[0012] Another drone logistics control method based on image recognition provided by this application includes: In response to receiving the current shooting point sent by the cloud, the drone flies along the tour path to the current shooting point and then shoots the current tour field of view image; and uploads the current tour field of view image to the cloud; In response to receiving the multi-point recognition command sent by the cloud, the drone flies to each circumferential recognition point corresponding to the current shooting point to shoot the auxiliary field of view image, and uploads the auxiliary field of view image to the cloud; In response to receiving the next shooting point sent by the cloud, the drone flies along the tour path to the next shooting point to shoot the next tour field of view image; and uploads the next tour field of view image to the cloud.

[0013] To achieve the above-mentioned objectives and other related objectives, the present application also provides an image recognition-based drone logistics control system, including a cloud, a drone and one or more processors, the drone and the cloud are communicatively connected, the processor is arranged in the drone and / or the cloud, and the processor is used to execute one or more of the aforementioned image recognition-based drone logistics control methods.

[0014] To achieve the above objectives and other related objectives, the present application also provides a drone, including a processor, which is used to execute one or more of the aforementioned image recognition-based drone logistics control methods.

[0015] As described above, the drone logistics control method, system and drone based on image recognition provided by the present application have the following beneficial effects: The present application discloses a drone logistics control method based on image recognition. The method obtains the current patrol field image taken by the drone at the current shooting point, compares the current patrol field image with the previous patrol field image, and sends a multi-point recognition instruction to the drone if there is a change in the goods, so that the drone shoots auxiliary field images at each circumferential recognition point corresponding to the current shooting point and uploads them to the cloud for dumping risk identification. If there is no change in the goods, the next shooting point of the current shooting point in the patrol path is sent to the drone. This can reduce the amount of data processing in the cloud, reduce the time of a single drone inspection, and thus reduce the cost of warehouse management.

[0016] 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

[0017] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 is a schematic diagram of an implementation scenario of a drone logistics control method based on image recognition, shown in an exemplary embodiment of the present application; Figure 2 is a flow chart of a drone logistics control method based on image recognition shown in an exemplary embodiment of the present application; Figure 3 is a schematic diagram of an implementation scenario of a drone logistics control method based on image recognition according to another exemplary embodiment of the present application; Figure 4 It is a flow chart of a drone logistics control method based on image recognition shown in another embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand 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 implementation methods, 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 illustrating the present application, not for limiting the scope of protection of the present application.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0020] 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.

[0021] See also Figure 1 , which is a schematic diagram of an implementation scenario of a drone logistics control method based on image recognition as an exemplary embodiment of the present application.

[0022] The implementation scenario may include a drone 110, a vibration sensor 120, a light source device 130, and a cloud (not shown in the figure). The drone 110, the vibration sensor 120, and the light source device 130 may all be connected to the cloud in a wireless manner. Figure 1 The dotted line with an arrow in the figure represents the patrol path of the drone. The preset patrol path can be sent to the drone from the cloud. Multiple shooting points can be set on the patrol path.

[0023] A plurality of shelves may be provided in the logistics warehouse, and the goods may be placed on the shelves after entering the warehouse. For example, the first goods 200 may be placed on the rightmost side of the topmost layer of the shelf 300.

[0024] The drone 110 can fly in the logistics warehouse according to a preset patrol route and take images at various shooting points, and the shooting points can be sent to the drone from the cloud.

[0025] The vibration sensor 120 can be installed at the bottom of the shelf and upload the acquired vibration data to the cloud.

[0026] The light source device 130 can be installed at the edge of the shelf. The light source device 130 can receive the start-up command sent by the cloud to compensate for the illumination of the drone's field of view, thereby preventing the cloud from being unable to obtain sufficient information from the field of view image due to insufficient illumination.

[0027] It should be noted that each shelf in the logistics warehouse can be installed with a vibration sensor 120 and a light source device 130 ( Figure 1 not shown).

[0028] See also Figure 2 , Figure 2 FIG. 1 is a flowchart of an exemplary embodiment of the present application showing a method for controlling a drone logistics system based on image recognition. The method for controlling a drone logistics system based on image recognition can be applied to Figure 1 Implementation scenario shown. Figure 2 It can be seen that the drone logistics control method based on image recognition can include: Step S210, obtaining the current tour view image taken by the drone at the current shooting point.

[0029] Among them, the drone is used to fly according to the preset patrol route and photograph the goods stored on the shelves in the logistics warehouse at the current shooting point.

[0030] In one embodiment of the present application, a drone can perform a flight inspection in a logistics warehouse according to a preset patrol route, and after hovering at a current shooting point, capture an image of the current patrol field of view within the drone's field of view, and the drone's field of view may be the drone's camera field of view. When the drone hovers at the current shooting point, the drone's field of view may include part of the shelf and at least one item placed on the shelf, and the captured image of the current patrol field of view also includes part of the shelf and at least one item placed on the shelf. The current shooting point may be located to the side of the shelf, that is, in front of the item.

[0031] The cloud can send the current shooting point to the drone, and receive the current tour view image shot at the current shooting point from the drone. The current shooting point corresponds to the current tour view image.

[0032] It should be noted that the tour field of view images taken by the drone at all shooting points should include all the goods on the shelves in the logistics warehouse, that is, all the goods photographed by the drone in the logistics warehouse. When the drone hovers at the t-th shooting point, the t-th shooting point is the current shooting point. When the drone hovers at the t+1-th shooting point, the t-th shooting point is the previous shooting point, and the t+1-th shooting point is the current shooting point. The current shooting point and the previous shooting point are both shooting points.

[0033] In a possible implementation, step S210, the process of obtaining the current patrol field of view image taken by the drone at the current shooting point, may include: in response to receiving the location information sent by the drone, the cloud sends a start command to the light source device, so that the light source device performs lighting compensation for the drone field of view corresponding to the current shooting point after receiving the start command, and the location information indicates that the drone has flown to the current shooting point.

[0034] Among them, in response to receiving the location information sent by the drone, the cloud sends a start instruction to the light source device, including: in response to receiving the location information sent by the drone, the cloud obtains the natural light intensity; if the natural light intensity is less than the light threshold, the cloud sends a start instruction to the light source device.

[0035] In a possible implementation, the natural light intensity can be obtained by setting a photosensitive sensor or other device, and the photosensitive sensor or other device can be wirelessly connected to the cloud. The light threshold can be a preset value designed by an operator.

[0036] In one embodiment of the present application, the light source device can be installed at the edge of the shelf, the light source can be installed at the end of each layer of the shelf, the light source can be installed on the left and right sides of the shelf, and the installation position of each light source on a single shelf needs to meet the lighting compensation to cover all goods.

[0037] Optionally, if the natural light intensity is less than the light threshold, the cloud may send a start instruction to the light source device. The cloud may send a start instruction to all light source devices so that all light source devices are turned on.

[0038] Optionally, the cloud can store the installation shelves and positions of each light source. After receiving the location information sent by the drone, the cloud can determine the light source device to be turned on among multiple light sources based on the current shooting point in the location information, and turn on the light source device to be turned on.

[0039] For example, see Figure 3 , which is a schematic diagram of an implementation scenario of a drone logistics control method based on image recognition according to another exemplary embodiment of the present application. Figure 3 In the implementation scenario shown, the drone 110 is located between the first shelf 310 and the second shelf 320, and the drone 110 is located in the space on the top layer of the shelf. At this time, the light source device installed on the top layer of the first shelf 310 and the second shelf 320 can be turned on, while the light source device on the third shelf 330 is in the off state.

[0040] Step S220: If there is a previous patrol view image corresponding to the current shooting point, an image comparison is performed between the current patrol view image and the previous patrol view image to determine whether there is any change in the cargo in the drone view corresponding to the current shooting point.

[0041] In one embodiment of the present application, if there is a previous tour field of view image corresponding to the current shooting point, an image comparison is performed between the current tour field of view image and the previous tour field of view image to determine whether there is a change in the cargo in the drone field of view corresponding to the current shooting point. The change in cargo may include at least one of an increase in cargo, a decrease in cargo, or a change in the location of cargo. The previous tour field of view image may be stored in a historical database in the cloud, and the tour field of view images taken by the drone at each shooting point and at each time may be stored in the historical database in the cloud after being uploaded to the cloud.

[0042] It should be noted that the previous patrol vision image is the patrol vision image taken by the drone at the previous moment of the current shooting point.

[0043] In a possible implementation, the Mask R-CNN or YOLOv8-Seg model can be used to perform instance segmentation on the previous tour field of view image and the current tour field of view image respectively to obtain the location, category and pixel-level mask of each item; the IoU (Intersection over Union) of the bounding boxes of the items in the two images is calculated. If IoU>threshold, they are considered to be the same object; the deep features of the item ROI (Region of Interest) are extracted through ResNet-50, and the cosine similarity is calculated to associate the same item in the two images; the existence of unmatched instances in the current tour field of view image indicates that new items are added; the existence of unmatched instances in the previous tour field of view image indicates that items are removed; the instance matching is successful but the position offset is greater than the offset threshold, indicating that the position of the item has changed.

[0044] In step S230, if there is a change in the cargo, a multi-point recognition command is sent to the drone, so that after receiving the multi-point recognition command, the drone takes auxiliary field of view images at each circumferential recognition point corresponding to the current shooting point and uploads them to the cloud for dumping risk identification.

[0045] In one embodiment of the present application, if there is a change in the cargo, the cloud can send a multi-point identification instruction to the drone. The multi-point identification instruction may include at least one circumferential identification point corresponding to the current shooting point, so that the drone can fly to each circumferential identification point and shoot an auxiliary field of view image at each circumferential identification point. The cloud can determine whether there is a risk of dumping the cargo within the drone's field of view at the current shooting point based on the auxiliary field of view image.

[0046] It should be noted that the circumferential identification points can be located above, behind, on the left or on the right side of the cargo.

[0047] In one embodiment, if there is a change in the cargo during execution of step S230, after sending a multi-point identification instruction to the drone, the drone logistics control method based on image recognition may also include: obtaining an auxiliary field of view image uploaded by the drone; performing auxiliary dumping identification on the cargo in the field of view based on the current patrol field of view image and each auxiliary field of view image to determine whether there is a risk of dumping of the cargo in the field of view of the drone; the auxiliary field of view image is an image captured by the drone at each circumferential identification point corresponding to the current shooting point.

[0048] In one embodiment of the present application, the cloud can perform three-dimensional construction based on the current patrol field of view image and each auxiliary field of view image, analyze the center of gravity of the cargo in the drone's field of view, and determine whether the cargo is at risk of dumping.

[0049] Step S240: If there is no change in the cargo, the next shooting point of the current shooting point in the patrol path is sent to the drone.

[0050] In one embodiment of the present application, if there is no change in the cargo, the cloud can send the next shooting point of the current shooting point in the patrol path to the drone, so that the drone can fly to the next shooting point and take an image at the next shooting point.

[0051] In the drone logistics control strategy of related technologies, when a drone conducts inspections in a logistics warehouse, it will generally shoot at the current shooting point, and then shoot at the circumferential identification points corresponding to the current shooting point. It also shoots at multiple points when the goods have not changed. On the one hand, the drone needs to hover for a period of time when shooting at each point, which increases the drone's working time and consumes more power. On the other hand, the cloud needs to perform image recognition on the image of each point to determine whether there is a risk of dumping of goods on the shelves within the drone's field of view, which requires high computing power on the cloud, resulting in higher costs.

[0052] In the drone logistics control method based on image recognition provided in the embodiment of the present application, the cloud can determine whether there is any change in the goods within the drone's field of view based on the current patrol field of view image and the previous patrol field of view image uploaded by the drone, and perform multi-point identification when there is a change in the goods. When there is no change in the goods, the drone flies to the next shooting point for inspection. This can reduce the amount of data processing on the cloud, and thus reduce the processing cost of the cloud. In addition, the number of images taken by the drone is reduced, that is, the drone's hovering time is reduced, which can reduce the drone's working time and allow the drone to complete cargo inspections with lower power consumption.

[0053] In one embodiment, if there is a change in the cargo in step S230, the process of sending a multi-point position identification instruction to the drone may include: Step S231: If there is any change in the cargo, the vibration data uploaded to the cloud by the target vibration sensor corresponding to the current shooting point is obtained.

[0054] In one embodiment of the present application, if there is a change in the goods, the vibration data uploaded to the cloud by the target vibration sensor corresponding to the current shooting point can be obtained. The vibration data of each vibration sensor installed on each shelf can be uploaded to the cloud in real time, and the vibration data uploaded to the cloud by each vibration sensor can be associated with the shelf number of the shelf where each vibration sensor is located. The current shooting point can correspond to a shelf number. According to the shelf number corresponding to the current shooting point, the cloud can determine the target vibration sensor among multiple vibration sensors based on the shelf number corresponding to the current shooting point and obtain the vibration data corresponding to the target vibration sensor.

[0055] In one embodiment, if there is a change in the cargo in step S231, the process of obtaining the vibration data uploaded to the cloud by the target vibration sensor corresponding to the current shooting point may include: Step S231A, if there is a change in the cargo, a high-frequency operation instruction is sent to the target vibration sensor to change the target vibration sensor from low-frequency operation to high-frequency operation, and operate in the high-frequency operation state for a preset time.

[0056] Among them, the frequency of high-frequency operation is 1Hz~10Hz.

[0057] In one embodiment of the present application, if there is a change in the cargo, the cloud can send a high-frequency operation instruction to the target vibration sensor. Under normal conditions (that is, when no high-frequency operation instruction is received), each vibration sensor can operate at a low frequency, and the range of the low-frequency operation can be (10Hz, 50Hz], that is, the range of the low-frequency operation can be greater than 10Hz and less than or equal to 50Hz. After the target vibration sensor receives the high-frequency operation instruction, the target vibration sensor can be converted from low-frequency operation to high-frequency operation.

[0058] When the vibration sensor operates at a low frequency, the sampling rate is low, the energy consumption is low, and the burden of data storage and transmission can be reduced. When the target vibration sensor operates at a high frequency, the target vibration sensor can obtain more data so that the cloud can accurately identify whether the shelf is vibrating.

[0059] Step S231B, obtaining vibration data of the target vibration sensor running in a high frequency operating state for a preset time.

[0060] In one embodiment of the present application, the cloud can obtain vibration data of the target vibration sensor running in a high-frequency operation state for a preset time. The target vibration sensor runs in a high-frequency operation state for a preset time, during which the target vibration sensor can upload the vibration data to the cloud in real time.

[0061] It should be noted that after the target vibration sensor uploads the vibration data of the preset time in the high-frequency operation state to the cloud, the target vibration sensor can be converted from high-frequency operation to low-frequency operation to avoid continuous high energy consumption.

[0062] Step S232: If the vibration data meets the vibration judgment condition, a multi-point position recognition instruction is sent to the drone.

[0063] In one embodiment of the present application, if the vibration data meets the vibration judgment condition, the cloud can send a multi-point recognition instruction to the drone. If the vibration data meets the vibration judgment condition, it can be determined that the shelf photographed by the drone at the current shooting point is vibrating. When the shelf vibrates, the cloud can send a multi-point recognition instruction to the drone, so that the drone can perform three-dimensional reconstruction based on the auxiliary field of view image uploaded by the drone to determine whether the goods on the shelf are vibrating.

[0064] In a possible implementation manner, the vibration data includes acceleration, and the vibration determination condition includes: The peak acceleration within the preset time is greater than the first threshold; and / or the effective value of the acceleration within the preset time is greater than the second threshold.

[0065] It should be noted that the first threshold and the second threshold may be preset values ​​set by designers based on historical experience. When the peak acceleration within the preset time is greater than the first threshold, it indicates shelf vibration. When the effective value of the acceleration within the preset time is greater than the second threshold, it indicates shelf vibration.

[0066] Exemplarily, the preset time is 30 seconds.

[0067] In one embodiment, the target threshold includes a first threshold or a second threshold, and the method further includes: obtaining the current load weight of the shelf and the preset load weight of the shelf; the preset load weight of the shelf represents the maximum load weight of the shelf; determining a first adjustment coefficient based on the ratio of the current load weight of the shelf and the preset load weight of the shelf; determining a second adjustment coefficient based on a mapping relationship between a preset shelf level and an adjustment coefficient of the shelf level where the goods are located; and determining the target threshold according to the first adjustment coefficient, the second adjustment coefficient and the preset initial value.

[0068] In one embodiment of the present application, the cloud can store the current load weight of the shelf and the preset load weight of the shelf. When the goods are put into storage, the current load weight of the shelf can be stored in the cloud in advance. The current load weight of the shelf represents the total weight of the goods currently stored on the shelf. The ratio of the current load weight of the shelf to the preset load weight of the shelf can be determined as the first adjustment coefficient. Generally, the current load weight of the shelf is less than or equal to the preset load weight of the shelf. Based on the mapping relationship between the preset shelf level and the adjustment coefficient of the shelf level where the goods are located, the second adjustment coefficient is determined. When the drone acquires the current patrol field image of the image, the drone height can be sent to the cloud accordingly, and the shelf level where the goods are located can be determined based on the drone height and the preset heights of each shelf level, and the second adjustment coefficient can be determined in the mapping relationship between the preset shelf level and the adjustment coefficient. The product of the first adjustment coefficient, the second adjustment coefficient and the preset initial value can be determined as the target threshold.

[0069] It should be noted that as the shelf level increases, the second adjustment coefficient gradually decreases. For example, when the shelf level is the first level (that is, the bottom level), the second adjustment coefficient may be 1. When the shelf level is the second level, the second adjustment coefficient may be 0.8. This setting can associate the target threshold with the shelf level. The higher the shelf level, the more likely it is to vibrate, and the smaller the target threshold.

[0070] Exemplarily, when the target threshold is the first threshold, the preset initial value may be 0.5, and when the target threshold is the second threshold, the preset initial value may be 0.2.

[0071] Step S233: if the vibration data does not meet the vibration judgment condition, the next shooting point of the current shooting point in the patrol path is sent to the drone.

[0072] In one embodiment of the present application, if the vibration data does not meet the vibration judgment conditions, it can be indicated that the shelf corresponding to the current shooting point of the drone has not vibrated. When the shelf is not vibrating and the goods have not changed, there is generally no risk of dumping of the goods. At this time, the cloud can send the next shooting point of the current shooting point in the patrol path to the drone.

[0073] See also Figure 4 , which is a flow chart of a drone logistics control method based on image recognition according to another embodiment of the present application. Figure 4 It can be seen that the drone logistics control method based on image recognition can include: Step S410, in response to receiving the current shooting point sent by the cloud, the drone flies along the tour path to the current shooting point and shoots the current tour field of view image; and uploads the current tour field of view image to the cloud.

[0074] Step S420, in response to receiving the multi-point recognition instruction sent by the cloud, the drone flies to each circumferential recognition point corresponding to the current shooting point to shoot auxiliary field of view images, and uploads the auxiliary field of view images to the cloud.

[0075] Step S430, in response to receiving the next shooting point sent by the cloud, the drone flies along the tour path to the next shooting point to shoot the next tour field of view image; and uploads the next tour field of view image to the cloud.

[0076] An embodiment of the present application also provides a drone logistics control system, including: a cloud, a drone and one or more processors, the drone and the cloud are communicatively connected, the processor is arranged in the drone and / or the cloud, and the processor is used to execute the image recognition-based drone logistics control method provided in the above-mentioned embodiments.

[0077] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the drone logistics control method based on image recognition provided in the above embodiments. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being assembled into the electronic device.

[0078] Another aspect of the present application also provides a computer program product or a 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 the processor executes the computer instructions, so that the computer device executes the drone logistics control method based on image recognition provided in each of the above embodiments.

[0079] Another aspect of the present application provides a drone, which includes a processor, and the processor is used to execute the drone logistics control method based on image recognition provided in the above-mentioned embodiments.

[0080] In the embodiments of the present application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. "Including" and "comprising" mentioned throughout the specification and claims are open-ended terms and should be interpreted as "including but not limited to".

[0081] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A drone logistics control method based on image recognition, characterized in that: include: Get the current tour view image taken by the drone at the current shooting point; The drone is used to fly along a preset patrol route and take photos of the goods stored on the shelves in the logistics warehouse at the current shooting point; If there is a previous patrol field of view image corresponding to the current shooting point, then compare the current patrol field of view image with the previous patrol field of view image to determine whether there is any change in the cargo in the drone field of view corresponding to the current shooting point; If there is a change in the cargo, a multi-point identification command is sent to the drone, so that after receiving the multi-point identification command, the drone takes auxiliary field of view images at each circumferential identification point corresponding to the current shooting point and uploads them to the cloud for dumping risk identification; If there is no change in the goods, the next shooting point of the current shooting point in the patrol path is sent to the drone.

2. The drone logistics control method based on image recognition according to claim 1 is characterized in that: If there is any change in the cargo, a multi-point identification command will be sent to the drone, including: If there is any change in the goods, the vibration data uploaded to the cloud by the target vibration sensor corresponding to the current shooting point is obtained; If the vibration data meets the vibration judgment conditions, a multi-point recognition command is sent to the drone; If the vibration data does not meet the vibration judgment condition, the next shooting point of the current shooting point in the patrol path is sent to the drone.

3. The drone logistics control method based on image recognition according to claim 2 is characterized in that: The vibration data includes acceleration, and the vibration judgment conditions include: The peak acceleration within the preset time is greater than a first threshold; and / or, The effective value of acceleration within the preset time is greater than the second threshold.

4. The drone logistics control method based on image recognition according to claim 3 is characterized in that: The target threshold includes a first threshold or a second threshold, and the method further includes: Obtain the current load weight of the shelf and the preset load weight of the shelf; the preset load weight of the shelf represents the maximum load weight of the shelf; Determining a first adjustment coefficient based on a ratio of a current load weight of the shelf to a preset load weight of the shelf; Determine a second adjustment coefficient based on a mapping relationship between a preset shelf level and an adjustment coefficient at a shelf level where the goods are located; A target threshold is determined according to the first adjustment coefficient, the second adjustment coefficient and a preset initial value.

5. The drone logistics control method based on image recognition according to claim 2 is characterized in that: If there is any change in the cargo, the vibration data uploaded to the cloud by the target vibration sensor corresponding to the current shooting point is obtained, including: If there is a change in the cargo, a high-frequency operation instruction is sent to the target vibration sensor to change the target vibration sensor from low-frequency operation to high-frequency operation, and run in the high-frequency operation state for a preset time. The frequency of the high-frequency operation is 1Hz~10Hz; Obtain vibration data of a target vibration sensor that runs for a preset time in a high-frequency operating state.

6. The drone logistics control method based on image recognition according to any one of claims 1 to 5, characterized in that: Get the current tour view image taken by the drone at the current shooting point, including: In response to receiving the arrival information sent by the drone, the cloud sends a start command to the light source device, so that the light source device performs lighting compensation for the drone's field of view corresponding to the current shooting point after receiving the start command. The arrival information indicates that the drone has flown to the current shooting point.

7. The drone logistics control method based on image recognition according to claim 6 is characterized in that: In response to receiving the arrival information sent by the drone, the cloud sends a start instruction to the light source device, including: In response to receiving the location information sent by the drone, the cloud obtains the natural light intensity; If the natural light intensity is less than the light threshold, the cloud sends a turn-on command to the light source device.

8. A drone logistics control method based on image recognition, characterized in that: include: In response to receiving the current shooting point sent by the cloud, the drone flies along the tour path to the current shooting point and then shoots the current tour field of view image; And upload the current patrol vision image to the cloud; In response to receiving the multi-point recognition command sent by the cloud, the drone flies to each circumferential recognition point corresponding to the current shooting point to shoot the auxiliary field of view image, and uploads the auxiliary field of view image to the cloud; In response to receiving the next shooting point sent by the cloud, the drone flies along the tour path to the next shooting point to shoot the next tour field of view image; and uploads the next tour field of view image to the cloud.

9. A drone logistics control system based on image recognition, characterized in that: It includes a cloud, a drone and one or more processors, the drone and the cloud are communicatively connected, the processor is arranged on the drone and / or the cloud, and the processor is used to execute the drone logistics control method based on image recognition as described in any one of claims 1-8.

10. A drone, characterized in that: It includes a processor, which is used to execute the drone logistics control method based on image recognition as described in claim 9.

Images