Goods delivery method and related device
By obtaining and analyzing the overhead images of the target area in the mountainous area by drones, the problem of low safety in cargo delivery is solved, and precise airdrop of cargo in complex environments is achieved, ensuring the safety and efficiency of emergency repairs after the disaster.
Patent Information
- Application Number
- CN202411064394.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-22
AI Technical Summary
In complex natural environments such as mountainous areas, it is difficult to manually inspect the damage to power facilities after the disaster, resulting in missing the emergency repair window and the safety of goods being delivered is not high.
The drone obtains the top shot image of the target area and analyzes whether the open area to be tested is suitable for cargo delivery. If suitable, control the drone to be delivered vertically downward, and use pixel value threshold conversion and Gaussian blur processing to ensure delivery accuracy.
It has achieved accurate and safe delivery of goods in difficult-to-reach areas, ensured that the materials can reach the required locations quickly and accurately, and improved the safety and efficiency of post-disaster emergency repairs.
Smart Images

Figure CN119002510A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a cargo delivery method and related devices. Background Art
[0002] Mountainous areas have complex terrain and frequent geological disasters. Transmission lines often need to pass through uninhabited mountainous areas. When lines are interrupted by geological disasters, on the one hand, it is necessary to inspect power facilities and confirm potential safety hazards as soon as possible through various means. On the other hand, due to the complex natural environment, it is difficult to confirm the severity of geological disasters and the damage to power facilities by sending manpower after the disaster. At the same time, in complex natural environments such as mountainous areas, communication and transportation conditions are poor. Manual inspection of power equipment in disaster areas will miss the window period for post-disaster repairs, which also poses a great challenge to the safety assurance work of engineers.
[0003] Drones have been widely used in aerial photography, traffic monitoring, disaster monitoring and other fields. The flight of drones is remotely controlled by pilots on the ground. In areas affected by natural disasters, or in severe weather conditions, or in areas that are otherwise inaccessible by manpower, drones can be used to deliver goods, but how to deliver goods accurately and safely needs to be strengthened. Summary of the invention
[0004] The main purpose of the present invention is to provide a cargo delivery method, device, computer equipment and storage medium, which can solve the problem of low security of cargo delivery in the prior art.
[0005] To achieve the above object, the present invention provides a cargo delivery method in a first aspect, the method comprising:
[0006] Controlling a drone for delivering goods to be located above a to-be-tested area in a target area, wherein the target area is an area within a first preset range where goods need to be delivered; and the to-be-tested area is an area within a second preset range within the target area;
[0007] Acquire an overhead image of the area to be measured; analyze whether the open area of the area to be measured is suitable for cargo delivery based on the overhead image; if the open area of the area to be measured is suitable for cargo delivery, control the drone to drop the cargo vertically downward.
[0008] In combination with the first aspect, in a possible implementation method, the above-mentioned analysis of whether the open area of the area to be measured is suitable for the delivery of goods based on the overhead image includes: obtaining each pixel value of the overhead image, converting all pixel values greater than or equal to a first threshold into a first value, and converting all pixel values less than the first threshold into a second value, to obtain a converted segmented image; wherein the second value is less than the first value; and analyzing whether the open area of the area to be measured is suitable for the delivery of goods based on the segmented image.
[0009] In combination with the first aspect, in a possible implementation manner, the analyzing, based on the segmented image, whether the open area of the to-be-tested area is suitable for cargo placement includes:
[0010] Calculating the proportion of the blank space in the area to be measured based on the first value and the second value of the segmented image;
[0011] If the proportion of the blank space is greater than or equal to the second threshold, the open area of the area to be measured is suitable for goods placement; if the proportion of the blank space is less than the second threshold, the open area of the area to be measured is not suitable for goods placement.
[0012] In combination with the first aspect, in a possible implementation manner, the calculation formula for calculating the proportion of the blank space in the area to be measured based on the first value and the second value of the segmented image is as follows:
[0013]
[0014] Wherein, N represents the number of pixels in the overhead image, l is the number of rows, k is the number of columns, and p ij Represents the value of the i-th row and j-th column in the segmented image.
[0015] In combination with the first aspect, in a possible implementation manner, the method further includes:
[0016] If the open area of the area to be tested is not suitable for cargo delivery, the drone is controlled to move to the next area to be tested according to a preset rule, and the process returns to the step of acquiring an overhead image of the area to be tested.
[0017] In combination with the first aspect, in a possible implementation manner, before obtaining each pixel value of the overhead image, the method includes:
[0018] The overhead image is subjected to grayscale conversion and then Gaussian blur processing to obtain a processed overhead image.
[0019] To achieve the above object, the second aspect of the present invention provides a cargo delivery device, the device comprising:
[0020] Control module: control the drone for delivering goods to be located above the to-be-tested area of the target area; wherein the target area is an area of a first preset range to which goods need to be delivered, and the to-be-tested area is an area of a second preset range within the target area;
[0021] Delivery module: used to obtain the overhead image of the area to be tested; based on the overhead image, analyze whether the open area of the area to be tested is suitable for cargo delivery; if the open area of the area to be tested is suitable for cargo delivery, control the drone to drop the cargo vertically downward.
[0022] In conjunction with the second aspect, in a possible design, the delivery module includes a determination module;
[0023] The judgment module is used to obtain each pixel value of the overhead image, convert pixel values greater than or equal to a first threshold among all pixel values into a first value, and convert pixel values less than the first threshold among all pixel values into a second value, to obtain a converted segmented image; wherein the second value is less than the first value; and analyze whether the open area of the area to be tested is suitable for cargo delivery based on the segmented image.
[0024] In combination with the second aspect, in a possible design, the above-mentioned judgment module is also used to: calculate the proportion of the blank space in the area to be tested based on the first value and the second value of the segmented image; wherein the first value represents that the area is blank, and the second value represents that there are obstacles in the area; if the proportion of the blank space is greater than or equal to the second threshold, the open area of the area to be tested is suitable for the placement of goods, and if the proportion of the blank space is less than the second threshold, the open area of the area to be tested is not suitable for the placement of goods.
[0025] In conjunction with the second aspect, in a possible design, the calculation formula for calculating the proportion of the blank space in the test area based on the first value and the second value of the segmented image in the above-mentioned judgment module is as follows:
[0026]
[0027] Wherein, N represents the number of pixels in the overhead image, l is the number of rows, k is the number of columns, and p ij Represents the value of the i-th row and j-th column in the segmented image.
[0028] In combination with the second aspect, in a possible design, the above-mentioned delivery module is also used to: if the open area of the area to be tested is not suitable for cargo delivery, control the drone to move to the next area to be tested according to preset rules, and return to execute the step of obtaining an overhead image of the area to be tested.
[0029] In combination with the second aspect, in a possible design, the above-mentioned delivery module is also used to: perform grayscale conversion on the overhead image and then perform Gaussian blur processing to obtain a processed overhead image.
[0030] To achieve the above object, the third aspect of the present invention provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor performs the following steps:
[0031] Controlling a drone for delivering goods to be located above a to-be-tested area in a target area; wherein the target area is an area within a first preset range where goods need to be delivered, and the to-be-tested area is an area within a second preset range within the target area;
[0032] Acquire an overhead image of the area to be measured; analyze whether the open area of the area to be measured is suitable for cargo delivery based on the overhead image; if the open area of the area to be measured is suitable for cargo delivery, control the drone to drop the cargo vertically downward.
[0033] To achieve the above object, a fourth aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:
[0034] Controlling a drone for delivering goods to be located above a to-be-tested area in a target area; wherein the target area is an area within a first preset range where goods need to be delivered, and the to-be-tested area is an area within a second preset range within the target area;
[0035] Acquire an overhead image of the area to be measured; analyze whether the open area of the area to be measured is suitable for cargo delivery based on the overhead image; if the open area of the area to be measured is suitable for cargo delivery, control the drone to drop the cargo vertically downward.
[0036] The embodiments of the present invention have the following beneficial effects:
[0037] The present invention provides a cargo delivery method, which controls a drone for cargo delivery to be located above a target area to be tested, obtains an overhead image of the target area, analyzes whether the open area of the target area is suitable for cargo delivery based on the overhead image, and controls the drone to drop the cargo vertically downward if the open area of the target area is suitable for cargo delivery. The present invention determines the area that can be safely dropped by the ratio of the blank space in the target area, and realizes accurate airdrop of cargo in inaccessible areas by drones, and the drones accurately and safely drop necessary materials to the required locations. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0039] in:
[0040] Figure 1 A schematic diagram of a flow chart of a cargo delivery method in an embodiment of the present invention;
[0041] Figure 2 is a schematic diagram of a target area and an area to be measured in an embodiment of the present invention;
[0042] Figure 3 A schematic diagram of a process of image preprocessing in an embodiment of the present invention;
[0043] Figure 4 This is a structural block diagram of a cargo delivery device in an embodiment of the present invention;
[0044] Figure 5 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION
[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0046] The embodiment of the present invention provides a cargo delivery method, which can be applied to any scenario where a drone delivers cargo, so as to achieve accurate cargo delivery using a drone. Figure 1 , Figure 1 A flow chart of a cargo delivery method provided by an embodiment of the present invention is shown as follows: Figure 1 As shown, the method is as follows:
[0047] Step S101: Control a drone for delivering goods to be located above a to-be-tested area of a target area.
[0048] The target area is an area within a first preset range where goods need to be delivered, and the area to be tested is an area within a second preset range within the target area.
[0049] Step S102, obtaining an overhead image of the area to be measured; analyzing whether the open area of the area to be measured is suitable for cargo delivery based on the overhead image, and if the open area of the area to be measured is suitable for cargo delivery, controlling the drone to drop the cargo vertically downward.
[0050] The drone can be controlled and moved through positioning to the target area where goods need to be delivered. For example, if the place where the goods need to be delivered is a school, then the target area can be the entire school area, so that the goods can be delivered to the people who need them nearby.
[0051] Among them, since the target area is very large, the drone used to deliver goods is controlled to be located above the area to be tested in the target area. The area to be tested is an area within the target area that is within the second preset range. For example, the target area can be the entire school area, and the area to be tested can be the school playground; or the target area can be the school playground, and the area to be tested can be a part of the playground. This method can be used in scenarios where materials are delivered to uninhabited mountainous areas when geological disasters occur in uninhabited mountainous areas. The target area can be the target mountainous area, and the target mountainous area is the mountainous area where materials need to be delivered, and the area to be tested can be the area within the target area close to maintenance personnel. Figure 2 As shown, Figure 2 A schematic diagram of a target area and an area to be tested provided by an embodiment of the present invention, Figure 2 The largest square area in is the area to be delivered, i.e. the target area. Figure 2 The diamond and triangle areas can be obstacles within the target area. Figure 2 The small and medium square areas are the areas to be tested.
[0052] The onboard camera is installed on the drone and oriented vertically downward. When the drone reaches the destination using GPS information, the camera will begin to shoot the area directly below the drone. The area to be tested is photographed from above to obtain an overhead image of the area to be tested. After obtaining the overhead image, the overhead image is used to analyze whether the open area of the area to be tested is suitable for cargo delivery. If the open area of the area to be tested is suitable for cargo delivery, the drone is controlled to drop the cargo vertically downward. Figure 3 , Figure 3 A schematic diagram of an image preprocessing process provided by an embodiment of the present invention is shown in FIG. Figure 3As shown, after obtaining the overhead image, in order to improve the accuracy of the placement, the image range can be further reduced. A smaller image area can be located on the original overhead image (original image), that is, the overhead image is cropped and dragged to obtain an overhead image of a smaller target placement area, and then the overhead image is gray-converted and Gaussian blurred to obtain a processed overhead image (processed image). After the above pre-processing operation is performed on the overhead image, it can be used to clear and remove any distortion in the image and convert the image to a lower level of abstraction. In each frame, a bounding box is defined and cropped to match the position and size of the preset target placement area, and then gray-conversion is used to simplify the calculation requirements. Finally, Gaussian blur transformation is performed on each pixel value to smooth the image and reduce image noise.
[0053] How to determine whether the goods are suitable for delivery is as shown in the following steps S201-S202:
[0054] Step S201, obtaining each pixel value of the overhead image, converting pixel values greater than or equal to a first threshold among all pixel values into first values, and converting pixel values less than the first threshold among all pixel values into second values, to obtain a converted segmented image.
[0055] The second value is smaller than the first value.
[0056] Step S202: Analyze whether the open area of the area to be tested is suitable for cargo delivery based on the segmented image.
[0057] Each pixel value of the overhead image is obtained, pixel values greater than or equal to a first threshold among all pixel values are converted into first values, and pixel values less than the first threshold among all pixel values are converted into second values, to obtain a converted segmented image.
[0058] Specifically, each pixel value of the overhead image is obtained, and the pixel values greater than or equal to the first threshold β among all pixel values are converted into the first value H1, and the pixel values less than the first threshold β among all pixel values are converted into the second value H2, so as to obtain the converted segmented image. Among them, the second value H2 is less than the first value H1, the first value H1 can be 1, and the second value H2 can be 0. The specific conversion method can be as follows:
[0059]
[0060] Among them, A ij represents the value of the pixel at position (i, j) in the overhead image, p ij Represents the converted value of the pixel at position (i, j) in the overhead image.
[0061] Based on the segmented image, the open area of the area to be tested is analyzed to determine whether it is suitable for cargo delivery, as shown in steps S301 and S302:
[0062] Step S301: Calculate the proportion of the blank space in the area to be measured based on the first value and the second value of the segmented image.
[0063] Step S302: If the proportion of the blank space is greater than or equal to a second threshold, the open area of the area to be tested is suitable for goods placement; if the proportion of the blank space is less than the second threshold, the open area of the area to be tested is not suitable for goods placement.
[0064] The first value represents that the area is blank, and the second value represents that there are obstacles in the area. The proportion of the blank space in the area to be tested is calculated based on the first and second values of the segmented image. This proportion value specifies the proportion of all objects that may appear in the target placement area, thereby specifying the proportion of blank space that may be used for falling. The specific calculation formula is as follows:
[0065]
[0066] Where N is the number of pixels in the top-view image, l is the number of rows, k is the number of columns, and p is the number of pixels in the top-view image. ij Represents the value of the i-th row and j-th column in the segmented image.
[0067] The proportion of blank space can represent the open area of the region. The larger the proportion of blank space, the larger the open area. A critical value α is set. If the proportion of blank space is greater than or equal to the second threshold α, it means that the open area is large enough, and the open area of the area to be tested is suitable for the placement of goods. If the proportion of blank space is less than the second threshold, the open area is not large enough, and the open area of the area to be tested is not suitable for the placement of goods.
[0068] In this embodiment, a threshold function may be applied to classify the drop area in the frame as safe or unsafe, as shown in the following formula:
[0069]
[0070] Among them, α is the minimum acceptable empty load ratio of the delivery area, and α can be determined according to the cargo and the area of the delivery area.
[0071] If the open area of the test area is not suitable for cargo delivery, it is necessary to re-detect the area where cargo delivery can be performed, control the drone to move to the next test area according to the preset rules, and re-execute the step of photographing the test area from above the test area to obtain an overhead image of the test area. In a possible implementation, the preset rule can be to control the drone to move a preset distance in a preset direction.
[0072] In order to reduce redundant safety assessments and multiple detections of the same image, in this embodiment, only when a change in the image is detected, the step of analyzing whether the open area of the area to be tested is suitable for cargo delivery based on the overhead image is performed on the image. When the drone is hovering, motion can be detected by simply detecting the change between every two consecutive frames. The method used is the sum of absolute difference (SAD), where SAD is a measure of the similarity between two images.
[0073] The absolute value of each pixel P at position (i, j) in the image is subtracted from the pixel P′ at the corresponding position in the other image, in the form of |P ij -P′ ij |. The sum of absolute differences (SAD) of two consecutive frames of the drone is determined by the following formula:
[0074]
[0075] Among them, m and m+1 are the consecutive frame numbers, l is the number of rows in each frame, and k is the number of columns in each frame.
[0076] Generally, in the case of the same frame, SAD is equal to zero, which means that no motion is detected. However, a small value can be tolerated as a difference between frames due to the vibration of the camera installed when the drone is hovering. Therefore, in this embodiment, when SAD is less than or equal to the preset third threshold, it is determined that the image has not changed, and when SAD is greater than the preset third threshold, it is determined that the image has changed.
[0077] Based on the above method, the safe delivery area can be determined by the proportion of blank space in the tested area, so that the drone can accurately and safely airdrop goods in inaccessible areas. The drone can accurately and safely deliver the necessary materials to the required location. And by judging whether the image has changed, it can avoid multiple detections of the same image, improve detection efficiency and save detection resources.
[0078] In order to better implement the above method, the embodiment of the present invention provides a cargo delivery device, referring to Figure 4 , Figure 4 A structural block diagram of a cargo delivery device provided by an embodiment of the present invention, such as Figure 4 As shown, the device 40 specifically includes the following:
[0079] Control module 401: Control a drone for delivering goods to be located above a target area to be tested; wherein the target area is an area within a first preset range where goods need to be delivered, and the test area is an area within a second preset range within the target area.
[0080] The drone can be controlled and moved through positioning to the target area where goods need to be delivered. For example, if the place where the goods need to be delivered is a school, then the target area can be the entire school area, so that the goods can be delivered to the people who need them nearby.
[0081] Among them, since the target area is very large, the drone used to deliver the goods is controlled to be located above the test area of the target area. The test area is an area within the target area that is a second preset range. For example, the target area can be the entire school area, and the test area can be the school playground; or the target area can be the school playground, and the test area can be an area of the playground.
[0082] Delivery module 402: used to obtain an overhead image of the area to be tested; analyze whether the open area of the area to be tested is suitable for cargo delivery based on the overhead image; if the open area of the area to be tested is suitable for cargo delivery, control the drone to drop the cargo vertically downward.
[0083] The onboard camera is installed on the drone and oriented vertically downward. When the drone reaches the destination using GPS information, the camera will start to shoot the area directly below the drone. The area to be tested is photographed from above to obtain an overhead image of the area to be tested. Based on the overhead image, it is analyzed whether the open area of the area to be tested is suitable for cargo delivery. If the open area of the area to be tested is suitable for cargo delivery, the drone is controlled to drop the cargo vertically downward.
[0084] In a possible design, the delivery module 402 is specifically used to: perform grayscale conversion on the overhead image and then perform Gaussian blur processing to obtain a processed overhead image.
[0085] After obtaining the overhead image, in order to improve the accuracy of the placement, the image range can be further reduced. A smaller image area can be located on the original overhead image (original image), that is, the overhead image is cropped and dragged to obtain an overhead image of a smaller target placement area, and then the overhead image is gray-converted and Gaussian blurred to obtain a processed overhead image (processed image). After the above pre-processing operation is performed on the overhead image, it can be used to clear and remove any distortion in the image and convert the image to a lower level of abstraction. In each frame, a bounding box is defined and cropped to match the position and size of the preset target placement area, and then gray-conversion is used to simplify the calculation requirements. Finally, each pixel value is Gaussian blurred to smooth the image and reduce image noise.
[0086] In one possible design, the delivery module 402 includes a judgment module, which is specifically used to: obtain each pixel value of the overhead image, convert all pixel values greater than or equal to a first threshold into a first value, and convert all pixel values less than the first threshold into a second value, to obtain a converted segmented image; wherein the second value is less than the first value; and analyze whether the open area of the test area is suitable for cargo delivery based on the segmented image.
[0087] Specifically, each pixel value of the overhead image is obtained, and the pixel values greater than or equal to the first threshold β among all pixel values are converted into the first value H1, and the pixel values less than the first threshold β among all pixel values are converted into the second value H2, so as to obtain the converted segmented image. Among them, the second value H2 is less than the first value H1, the first value H1 can be 1, and the second value H2 can be 0. The specific conversion method can be as follows:
[0088]
[0089] Among them, A ij represents the value of the pixel at position (i, j) in the overhead image, p ij Represents the converted value of the pixel at position (i, j) in the overhead image.
[0090] In a possible design, the judgment module is specifically used to: calculate the proportion of the blank space in the area to be tested based on the first value and the second value of the segmented image; wherein the first value represents that the area is blank, and the second value represents that there are obstacles in the area; if the proportion of the blank space is greater than or equal to a second threshold, the open area of the area to be tested is suitable for the placement of goods, and if the proportion of the blank space is less than the second threshold, the open area of the area to be tested is not suitable for the placement of goods.
[0091] The proportion of blank space can represent the open area of the region. The larger the proportion of blank space, the larger the open area. A critical value α is set. If the proportion of blank space is greater than or equal to the second threshold α, it means that the open area is large enough, and the open area of the area to be tested is suitable for the placement of goods. If the proportion of blank space is less than the second threshold, the open area is not large enough, and the open area of the area to be tested is not suitable for the placement of goods.
[0092] In a possible design, the calculation formula for calculating the proportion of the blank space in the to-be-tested area based on the first value and the second value of the segmented image in the judgment module is as follows:
[0093]
[0094] Wherein, N represents the number of pixels in the overhead image, l is the number of rows, k is the number of columns, and p ij Represents the value of the i-th row and j-th column in the segmented image.
[0095] In one possible design, the delivery module 402 is specifically used to control the drone to move to the next area to be tested according to preset rules if the open area of the area to be tested is not suitable for cargo delivery, and return to execute the step of obtaining an overhead image of the area to be tested.
[0096] Based on the above device, it is possible to achieve precise airdrop of cargo in inaccessible areas by drones, with the drones delivering necessary supplies accurately and safely to the required locations.
[0097] Figure 5 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 5 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement all the steps of the above method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement all the steps of the above method. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0098] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes each step of the aforementioned method.
[0099] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor executes each step of the aforementioned method.
[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0101] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0102] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for delivering goods, It is characterized in that The method comprises: Controlling a drone for delivering goods to be located above a to-be-tested area in a target area, wherein the target area is an area within a first preset range where goods need to be delivered; and the to-be-tested area is an area within a second preset range within the target area; Acquire an overhead image of the area to be measured; analyze whether the open area of the area to be measured is suitable for cargo delivery based on the overhead image; if the open area of the area to be measured is suitable for cargo delivery, control the drone to drop the cargo vertically downward.
2. The method according to claim 1, It is characterized in that The analyzing, based on the overhead image, whether the open area of the area to be tested is suitable for cargo delivery includes: Obtaining each pixel value of the overhead image, converting pixel values greater than or equal to a first threshold among all pixel values into a first value, and converting pixel values less than the first threshold among all pixel values into a second value, to obtain a converted segmented image; wherein the second value is less than the first value; Based on the segmented image, it is analyzed whether the open area of the area to be tested is suitable for cargo delivery.
3. The method according to claim 2, It is characterized in that The analyzing, based on the segmented image, whether the open area of the to-be-tested area is suitable for cargo delivery comprises: Calculate the proportion of the blank space in the area to be measured based on the first value and the second value of the segmented image; wherein the first value represents that the area is blank, and the second value represents that there are obstacles in the area; If the proportion of the blank space is greater than or equal to the second threshold, the open area of the area to be measured is suitable for goods placement; if the proportion of the blank space is less than the second threshold, the open area of the area to be measured is not suitable for goods placement.
4. The method according to claim 3, It is characterized in that The calculation formula for calculating the ratio of the blank space in the area to be measured based on the first value and the second value of the segmented image is as follows: Wherein, N represents the number of pixels in the overhead image, l is the number of rows, k is the number of columns, and p ij Represents the value of the i-th row and j-th column in the segmented image.
5. The method according to claim 1, It is characterized in that The method further comprises: If the open area of the area to be tested is not suitable for cargo delivery, the drone is controlled to move to the next area to be tested according to a preset rule, and the process returns to the step of acquiring an overhead image of the area to be tested.
6. The method according to claim 2, It is characterized in that Before obtaining each pixel value of the overhead image, the method includes: The overhead image is subjected to grayscale conversion and then Gaussian blur processing to obtain a processed overhead image.
7. A cargo delivery device, It is characterized in that The device comprises: Control module: control the drone for delivering goods to be located above the to-be-tested area of the target area; wherein the target area is an area of a first preset range to which goods need to be delivered, and the to-be-tested area is an area of a second preset range within the target area; Delivery module: used to obtain the overhead image of the area to be tested; based on the overhead image, analyze whether the open area of the area to be tested is suitable for cargo delivery; if the open area of the area to be tested is suitable for cargo delivery, control the drone to drop the cargo vertically downward.
8. The device according to claim 7, It is characterized in that The delivery module includes a judgment module; The judgment module is used to obtain each pixel value of the overhead image, convert pixel values greater than or equal to a first threshold among all pixel values into a first value, and convert pixel values less than the first threshold among all pixel values into a second value, to obtain a converted segmented image; wherein the second value is less than the first value; and analyze whether the open area of the area to be tested is suitable for cargo delivery based on the segmented image.
9. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 6.
10. A computer device comprising a memory and a processor, It is characterized in that The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 6.
