Material delivery operation method, device, unmanned equipment and storage medium

Abstract

The embodiments of the present application disclose a material delivery operation method, device, unmanned equipment and storage medium. The technical solution provided by the embodiments of the present application obtains remote sensing image data of the operation area, determines the delivery target contained in the remote sensing image data; determines the target space corresponding to each delivery target, and determines the volume information of the corresponding delivery target based on each target space; determines the material delivery amount corresponding to the delivery target according to the volume information, and controls the unmanned equipment to deliver the corresponding material delivery amount to the delivery target. Through the above technical means, the technical problem of poor material delivery effect in the prior art is solved, and the operation quality of material delivery is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of unmanned equipment, and in particular to a material delivery operation method, device, unmanned equipment and storage medium. Background Art

[0002] Based on the automatic high-altitude flight characteristics of unmanned equipment, a large number of unmanned equipment have been used in the field of high-altitude material delivery, such as pesticide spraying and pollination in the agricultural field, the delivery of fire extinguishing agents in the fire fighting field, or the delivery of rescue materials in the rescue field.

[0003] When performing high-altitude material delivery operations, existing unmanned equipment will fly to a preset height and deliver a set amount of materials. However, this method is only suitable for delivery targets with uniform height, uniform volume and uniform distribution. For delivery targets with uneven height, uneven volume or uneven distribution, the delivery effect is poor and the delivery operation quality is low. Summary of the invention

[0004] The embodiments of the present application provide a material delivery operation method, device, unmanned equipment and storage medium, which solve the technical problem of poor material delivery effect in the prior art and improve the operation quality of material delivery.

[0005] In a first aspect, an embodiment of the present application provides a material delivery method, comprising:

[0006] Acquire remote sensing image data of the operation area, and determine the delivery target contained in the remote sensing image data;

[0007] Determine a target space corresponding to each delivery target, and determine volume information of the corresponding delivery target based on each target space;

[0008] The material delivery amount corresponding to the delivery target is determined according to the volume information, and the unmanned equipment is controlled to deliver the corresponding material delivery amount to the delivery target.

[0009] In a second aspect, an embodiment of the present application provides a material delivery operation device, including:

[0010] A delivery target identification module is configured to obtain remote sensing image data of the operation area and determine the delivery target contained in the remote sensing image data;

[0011] A volume determination module is configured to determine a target space corresponding to each delivery target, and determine volume information of the corresponding delivery target based on each target space;

[0012] The material delivery module is configured to determine the material delivery amount corresponding to the delivery target according to the volume information, and control the unmanned equipment to deliver the corresponding material delivery amount to the delivery target.

[0013] In a third aspect, an embodiment of the present application provides an unmanned device, including:

[0014] One or more processors; a storage device storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the material delivery operation method as described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the material delivery method as described in the first aspect.

[0016] The embodiment of the present application obtains remote sensing image data of the operation area, determines the delivery target contained in the remote sensing image data; determines the target space corresponding to each delivery target, and determines the volume information of the corresponding delivery target based on each target space; determines the material delivery amount corresponding to the delivery target according to the volume information, and controls the unmanned equipment to deliver the corresponding material delivery amount to the delivery target. The above technical means are adopted to significantly improve the operational efficiency of material delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a material delivery method provided in Example 1 of the present application;

[0018] Figure 2 is a schematic diagram of remote sensing image data of an operation area provided in an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of a delivery target provided in an embodiment of the present application;

[0020] Figure 4 is a schematic diagram of elevation information of a work area provided in an embodiment of the present application;

[0021] Figure 5 is a first schematic diagram of a target space provided in an embodiment of the present application;

[0022] Figure 6 is a second schematic diagram of the target space provided in an embodiment of the present application;

[0023] Figure 7 is a schematic diagram of a flight route of an unmanned device provided in an embodiment of the present application;

[0024] Figure 8This is a structural schematic diagram of a material delivery operation device provided in Example 2 of the present application;

[0025] Fig. 9 This is a structural diagram of an unmanned device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0027] The material delivery operation method provided in the present application is intended to obtain remote sensing image data of the operation area, determine the delivery target contained in the remote sensing image data; determine the target space corresponding to each delivery target, and determine the volume information of the corresponding delivery target based on each target space; determine the material delivery amount corresponding to the delivery target according to the volume information, and control the unmanned equipment to deliver the corresponding material delivery amount to the delivery target. At present, when unmanned equipment is performing high-altitude material delivery operations, most of them will fly to a preset height and deliver materials according to the set material quantity, but this method is suitable for delivery targets with average height, average volume and uniform distribution. For delivery targets with uneven height, uneven volume or uneven distribution, the delivery effect is poor and the delivery operation quality is low. Based on this, a material delivery operation method of an embodiment of the present application is provided to solve the technical problem of poor material delivery effect in the prior art.

[0028] Embodiment 1:

[0029] Figure 1 A flow chart of a material delivery method provided in Example 1 of the present application is given. The material delivery method provided in this embodiment can be executed by unmanned equipment, which can be implemented by software and / or hardware. The unmanned equipment can be composed of two or more physical entities, or it can be composed of one physical entity.

[0030] The following description is based on the unmanned equipment as the main body of the material delivery operation method. Figure 1 , the material delivery operation method specifically includes:

[0031] S110: Acquire remote sensing image data of the operation area, and determine the delivery target contained in the remote sensing image data.

[0032] Exemplarily, the operation area refers to an area where materials are delivered by unmanned equipment, and the area contains at least one delivery target. The delivery target refers to a target to which unmanned equipment needs to deliver materials. Unmanned equipment includes unmanned aerial vehicles, unmanned vehicles, unmanned ships and other equipment that can move independently based on preset routes. For example, unmanned equipment sprays pesticides or pollinates plants in farmland or forests; unmanned equipment delivers fire extinguishing agents to fire points in housing areas or suburbs; unmanned equipment delivers rescue materials to people in disaster areas. Existing unmanned equipment will deliver a fixed amount of materials to the delivery target during operation, so that the delivery targets of different volumes receive the same amount of material delivery, which causes some delivery targets to have less or more material delivery, and the material delivery effect is poor. In this regard, this embodiment proposes a material delivery operation method, according to the volume of the delivery target, to deliver a material delivery amount corresponding to the volume of the delivery target to the delivery target, to prevent the phenomenon of less or more material delivery to delivery targets of different volumes caused by quantitative delivery, and to improve the material delivery effect. In this embodiment, the high-altitude spraying of pesticides by drones on fruit trees in the mountains and forests is taken as an example. The mountains and forests are the operation areas, and the fruit trees are the delivery targets in the mountains and forests. Spraying pesticides on the fruit trees is to deliver materials to the delivery targets. Spraying pesticides on the fruit trees at high altitude by drones is to deliver materials to the delivery targets by unmanned equipment. The terrain in the mountains and forests is tortuous, and the growth of fruit trees is different, resulting in uneven height, volume and distribution of fruit trees in the mountains and forests. If the high-altitude material delivery method of the existing unmanned equipment is used, due to the different heights and volumes of fruit trees, it is easy for some fruit trees to be sprayed with more pesticides and / or some fruit trees to be sprayed with less pesticides. Spraying more pesticides will waste pesticides and cause soil compaction and fertility reduction, while spraying less pesticides will have no pesticide effect. The volume of the fruit trees can be determined by the material delivery operation method provided in this embodiment to control the drone to spray the fruit trees with pesticides in an amount corresponding to the volume.

[0033] Among them, the remote sensing image data of the operation area is the image data obtained by processing the pictures or videos collected by the surveying and mapping UAV in advance over the operation area. The remote sensing image data can be orthophoto image data or spectral image data. Take the remote sensing image data as orthophoto image data as an example for description. The orthophoto is a remote sensing image with the property of orthophoto projection. It is obtained by mosaicking the original image with an overlap of up to 60% collected by the monocular camera of the surveying and mapping UAV through the collinear equation. Furthermore, the point cloud data of the operation area is reconstructed according to the remote sensing image data, and a digital surface model of the operation area is generated based on the point cloud data and the remote sensing image data. Whether it is remote sensing image data, point cloud data or digital surface model, it contains digital information of the delivery target. The volume of the delivery target can be determined according to the digital information of the delivery target in the remote sensing image data, point cloud data or digital surface model.

[0034] However, before determining the volume of the delivery target, the delivery target in the operation area is first determined. In this embodiment, identifying the delivery target in the operation area through the neural network model includes two implementation methods:

[0035] The first implementation method is to identify the delivery targets contained in the remote sensing image data through the first preset network model to output each delivery target in the operation area. Exemplarily, the first preset network model is obtained by training the neural network model in advance through sample data marked with a first bounding box, wherein the first bounding box marks the delivery target. The remote sensing image data of the operation area is input into the first preset network model to obtain the remote sensing image data marked with the first bounding box output by the first preset network model. The first bounding box marks the delivery target from the remote sensing image data, and the area circled by the first bounding box is used as the target area corresponding to the delivery target, that is, the image in the first bounding box is determined as the image data of the overhead view of the target area corresponding to the delivery target. Among them, the first bounding box can be a circle, a square, etc., and the first bounding box can be selected according to the overhead view of the delivery target to select the first bounding box that fits the overhead view of the delivery target. Exemplarily, taking the first bounding box as a graphic as an example, Figure 2 Schematic diagram of remote sensing image data of the operation area provided in the embodiment of the present application. Figure 2 As shown, the delivery target 12 in the remote sensing image data of the operation area 11 is circled, and the image within the circle is determined as the image data of the target area 13 corresponding to the delivery target 12 .

[0036] The second implementation method is to reconstruct the point cloud data of the working area based on the remote sensing image data, and identify the delivery targets contained in the point cloud data through the second preset network model to output each delivery target in the working area. Exemplarily, the second preset network model is obtained by training the neural network model in advance through sample data marked with a second bounding box, wherein the first bounding box marks the delivery target. The point cloud data of the working area is input into the second preset network model to obtain the point cloud data marked with the second bounding box output by the second preset network model. The second bounding box marks the delivery target from the point cloud data, and the space circled by the second bounding box is used as the target space corresponding to the delivery target, that is, the point cloud data in the fourth bounding box is determined as a three-dimensional point cloud map of the delivery target. Among them, the second bounding box can be a cylinder, a cube, etc., and the second bounding box can be selected according to the shape of the delivery target to select a second bounding box that fits the shape of the delivery target.

[0037] In addition to the neural network model identifying the delivery target, the delivery target of the operation area can also be determined based on the user's selection operation on the control device. In this embodiment, determining the delivery target of the operation area based on the user's selection operation includes two implementation methods:

[0038] The first implementation method is to receive a first selection operation, and determine each delivery target in the remote sensing image data according to the first selection operation. The first selection operation refers to the operation input by the user on the control device to mark the delivery target in the remote sensing image data, and the first selection operation can be a click operation or a box selection operation. Exemplarily, based on the first selection operation of the user on the control device, a third bounding box corresponding to each delivery target is generated, and the corresponding delivery target in the remote sensing image data is marked by the third bounding box. If the first selection operation is a click operation, the pixel coordinates in the remote sensing image data clicked by the user are determined according to the touch position coordinates of the click operation, and the image around the pixel coordinates is circled based on the preset third bounding box. If the first selection operation is a box selection operation, the third bounding box is generated according to the touch position coordinates of the box selection operation, and the remote sensing image data is marked by the third bounding box. Regardless of whether it is a box selection operation or a click operation, the area circled by the third bounding box is used as the target area corresponding to the delivery target, that is, the image in the third bounding box is determined as the image data of the overhead view of the target area corresponding to the delivery target.

[0039] Furthermore, in order to improve the marking efficiency of the delivery target, the staff generally roughly encircles the delivery target with the third bounding box in the remote sensing image data. At this time, the third bounding box cannot fit the top view of the delivery target well. If the third bounding box is used to calculate the subsequent volume information of the delivery target, the calculation accuracy will be affected. Therefore, the range of the third bounding box can be adjusted according to the shape information of the delivery target in the third bounding box. The steps of adjusting the third bounding box specifically include S1101-S1102:

[0040] S1101. Identify the delivery targets in each target area through a third preset network model, and determine the target type and growth stage of the delivery targets in the target area.

[0041] Exemplarily, the third preset network model is obtained by training the neural network model in advance with sample data marked with target type information and growth stage information. The image data corresponding to each target area is input into the third preset network model to obtain the target type and growth stage of the target in the target area output by the third preset network model.

[0042] S1102: Adjust the bounding box corresponding to the target area according to the target type and growth stage of the delivery target.

[0043] Exemplarily, the size and shape of the enclosing box corresponding to the delivery target in the target area is determined based on the size and shape of the enclosing boxes corresponding to the various types of delivery targets at various growth stages that are pre-configured. The size and shape of the third enclosing box of the target area are adjusted based on the size and shape of the enclosing box. For example, different types of trees have different shapes in their top view, and their shapes are also different at different growth stages. Therefore, by matching an enclosing box that better fits the shape of the tree based on the type and growth stage of the tree in this embodiment, it is beneficial to improve the accuracy of subsequent volume calculations. In addition, a relatively regular enclosing box can also be matched based on the type and growth stage. Although the degree of fit is not as high as the enclosing box matched based on the outer contour of the tree, it is convenient for subsequent volume calculations and has higher calculation efficiency.

[0044] The second implementation method is to receive a second selection operation, and determine each delivery target in the point cloud data according to the second selection operation. The second selection operation refers to an operation input by the user on the control device side to mark the delivery target in the point cloud data, and the second selection operation can be a click operation or a box selection operation. If the second selection operation is a click operation, the point cloud coordinates clicked by the user are determined according to the touch position coordinates of the click operation, and the point cloud data around the point cloud coordinates are circled based on the preset fourth bounding box. If the second selection operation is a box selection operation, a fourth bounding box is generated according to the touch position coordinates of the box selection operation, and the fourth bounding box is marked in the point cloud data of the operating area. Regardless of whether it is a click operation or a box selection operation, the space circled by the fourth bounding box is used as the target space corresponding to the delivery target, that is, the point cloud data in the fourth bounding box is determined as the three-dimensional point cloud map of the delivery target.

[0045] Further, the minimum bounding box corresponding to each delivery target in the point cloud data is determined, and the corresponding delivery target in the first point cloud data is marked by the minimum bounding box. Exemplarily, if the selection range of the manually selected bounding box is too large, it will affect the volume calculation accuracy of the subsequent delivery target. Therefore, after determining the fourth bounding box of the delivery target according to the user's second selection operation, the fourth bounding box is adjusted to the minimum bounding box of the three-dimensional point cloud map that just surrounds the delivery target according to the distribution range of the three-dimensional point cloud map of the delivery target in the fourth bounding box. Calculating the volume information of the subsequent delivery target through the minimum bounding box is conducive to improving the subsequent volume calculation accuracy. However, the minimum bounding box that fits the three-dimensional point cloud map of the delivery target is often an irregular bounding box, and the calculation of the volume of the irregular bounding box is relatively complicated and the calculation efficiency is low. In order to improve the volume calculation efficiency, the regular circumscribed bounding box of the minimum bounding box is determined according to the shape of the minimum bounding box. Although the degree of fit between the circumscribed bounding box and the three-dimensional point cloud map of the delivery target is lower than that of the minimum bounding box, the circumscribed bounding box is a regular shape, and its volume calculation is simple and the calculation efficiency is higher.

[0046] It can be understood that the bounding box in the remote sensing image data is a two-dimensional bounding box, and the bounding box in the point cloud data is a three-dimensional bounding box.

[0047] S120: Determine a target space corresponding to each delivery target, and determine volume information of the corresponding delivery target based on each target space.

[0048] Exemplarily, since the shapes of most delivery targets are difficult to determine directly, it is relatively complicated to calculate the precise volume of the delivery target. In this regard, the present embodiment identifies the delivery targets in the remote sensing image data of the operation area, determines the target space corresponding to the delivery target, and characterizes the volume of the corresponding delivery target with the volume of the target space. The target space has a fixed shape, and it is relatively simple to calculate the volume of the target space. As can be seen from step S110, the delivery targets are marked by corresponding bounding boxes in the remote sensing image data and point cloud data of the operation area. In this embodiment, since the point cloud data is three-dimensional space data, the space encircled by the bounding box in the point cloud data can be directly used as the target space of the corresponding delivery target. For example, based on the minimum bounding box, the target space corresponding to each delivery target is generated, and the space encircled by the minimum bounding box is used as the target space of the corresponding delivery target. The remote sensing image data is two-dimensional plane data. After the area encircled by the bounding box in the remote sensing image data is used as the target area of ​​the corresponding delivery target, it is also necessary to form the target space of the delivery target based on the height information of the target area in the height dimension. Exemplarily, the step of determining the corresponding target space based on the target area of ​​the delivery target specifically includes S1201-S1202:

[0049] S1201. Obtain a digital surface model corresponding to the operation area, and determine elevation information corresponding to each target area based on the digital surface model.

[0050] Among them, the digital surface model (DSM) refers to a ground elevation model that includes the heights of surface buildings, bridges, and trees. Exemplarily, when the orthophoto data of the operating area is generated based on the original image collected by the surveying and mapping drone, it is also necessary to determine the geographical location coordinates of each pixel in the orthophoto data in the world coordinate system based on the position coordinates of the surveying and mapping unmanned equipment in the world coordinate system when flying over the operating area to collect the original image and the internal and external parameters of the monocular camera. It can be understood that each pixel in the orthophoto data corresponds to a position point in the real world, and the geographical location coordinates corresponding to the pixel point are the geographical location coordinates of the position point in the world coordinate system. The orthophoto data of the operating area contains the mapping relationship between the pixel coordinates of the pixel point and the geographical location coordinates of the corresponding position point, that is, a certain pixel in the orthophoto data of the operating area can uniquely determine the position point in the operating area. It should be noted that the geographical location coordinates can be two-dimensional coordinates that do not contain height information in the world coordinate system, that is, X-axis coordinates and Y-axis coordinates, or longitude and latitude coordinates.

[0051] Furthermore, the orthophoto data of the operation area is processed to obtain a digital surface model corresponding to the operation area. After the digital surface model is generated, each pixel in the orthophoto data corresponds to an elevation information and a geographic location coordinate. The elevation information refers to the surface altitude at the location point corresponding to the pixel point. The digital surface model of the operation area contains the elevation information at each location point in the operation area. For example, Figure 3 Schematic diagram of the delivery target provided in the embodiment of the present application. Figure 3 As shown, each position point in the working area can be regarded as a two-dimensional coordinate point projected onto the horizontal plane formed by the X-axis and the Y-axis. Position point A and position point B are position points in the working area, and the two-dimensional coordinates (x1, y1) and (x2, y2) of position point A and position point B in the horizontal plane are the geographical location information of position point A and position point B. The elevation information of position point A is the altitude of the corresponding ground, and the elevation information of position point B is the altitude of the top of the corresponding delivery target. Since the position points included in the target area overlap with some of the position points in the working area, if the position points included in the target area can be determined, the elevation information corresponding to the target area can be determined based on the elevation information at the position point in the working area. Exemplarily, the steps of determining the elevation information corresponding to the target area specifically include S12011-S12012:

[0052] S12011. Determine the elevation information corresponding to each location point in the operation area according to the digital surface model corresponding to the operation area.

[0053] Exemplarily, based on the elevation information corresponding to each pixel point in the digital surface model, the elevation information at the position point corresponding to the pixel point is determined.

[0054] S12012. Determine the elevation information of each location point in the target area according to the image position coordinates of the target area in the remote sensing image data.

[0055] Exemplarily, the target area is the image data enclosed by the corresponding bounding box, and the pixel coordinates of each pixel point in the image data of the target area can be determined according to the pixel coordinates of the bounding box in the orthophoto image data. The geographical location coordinates of the location points in the target area are determined according to the pixel coordinates of the pixel points in the target area, and the elevation information of each location point in the target area is determined based on the corresponding elevation information of each location point in the digital surface model of the operation area.

[0056] In one embodiment, in addition to being obtained based on orthophoto data, the digital surface model can also be calculated based on sensor data collected by unmanned equipment when flying over the operation area. Exemplarily, the calculation method of the height information of each location point in the operation area includes S12013-S12015:

[0057] S12013. Obtain altitude data and collected sensor data of the unmanned equipment when it flies over various locations in the operation area, where the sensor data includes point cloud data or image data.

[0058] For example, Figure 4 Schematic diagram of elevation information of the working area provided in the embodiment of the present application. Figure 4 As shown, the surface altitude H of each position point in the operation area can be obtained by subtracting the altitude H1 of the unmanned device 14 when it is flying and the distance H2 between the unmanned device 14 and the surface of each position point in the operation area when it is flying. In this embodiment, the altitude H1 of the unmanned device 14 when it is flying can be collected by the positioning device of the unmanned device. The distance data H2 between the unmanned device 14 and the surface of each position point in the operation area when it is flying can be obtained based on the image data collected by the binocular camera or the point cloud data collected by the laser sensor.

[0059] S12014. Determine the distance data from each location point to the unmanned equipment based on the sensor data.

[0060] For example, the distance between the unmanned device and the surface of each location point can be obtained by analyzing and processing the point cloud data or remote sensing image data. In addition, the image data collected by the monocular camera can be processed by aerial image processing to obtain the distance data between the unmanned device and the surface of each location point.

[0061] S12025. Subtract the altitude data and distance data corresponding to each location point to obtain the elevation information of the corresponding location point.

[0062] For example, whether it is the altitude data of the unmanned equipment or the distance data between the unmanned equipment and the ground at each location point, it will correspond to a two-dimensional coordinate in the XY coordinate system when it is collected. By subtracting the altitude data and distance data with the same two-dimensional coordinates, the elevation information of the location point corresponding to the two-dimensional coordinate can be obtained. Figure 4 , the distance between the unmanned equipment and the surface of the location point C is H2. According to the positioning data of the unmanned equipment during the surveying flight, the flight altitude of the unmanned equipment when the location coordinates are (x3, y3) is determined to be H1. Subtract H1-H2 to obtain the elevation information H at the location point C.

[0063] S1202: Determine a target space corresponding to each delivery target based on the target area and corresponding elevation information.

[0064] In this embodiment, since the elevation information in the target area can characterize the shape of the upper surface of the corresponding delivery target, a target three-dimensional model can be constructed based on the elevation information of all target areas. The upper surface of the target three-dimensional model fits the upper surface of the delivery target, and the target space corresponding to the delivery target can be constructed according to the target three-dimensional model. Figure 5 is a first schematic diagram of the target space provided in the embodiment of the present application. Figure 5 As shown, the surface altitude corresponding to each position point can be determined according to the elevation information in the target area, and a target three-dimensional model 15 ( Figure 5 Since the surface altitude of the delivery target is significantly different from the surface altitude of the ground, the elevation information outside the target area will suddenly decrease. The ground and the delivery target in the target area can be determined based on the change in elevation information. The elevation information corresponding to the delivery target is selected from the target three-dimensional model 15 to reconstruct the delivery target three-dimensional model 16 ( Figure 5 The triangle and the combination of the two rectangles in the delivery target three-dimensional model 16 include the elevation information of the ground. Therefore, the minimum elevation information can be selected from the target area as the elevation information of the ground. The altitude of each position point of the delivery target three-dimensional model 16 is subtracted from the altitude of the ground to obtain the relative height of the target space of the delivery target. According to the relative height of the target space and the delivery target in the target area, the target space 13 of the delivery target is constructed ( Figure 5 The triangle in the middle and the first rectangle below).

[0065] In one embodiment, the upper surface of the target space constructed based on the target three-dimensional model 15 is often an irregular curved surface, and its volume calculation process is relatively complicated. Therefore, the corresponding target space can be constructed based on the maximum elevation information and the minimum elevation information in the target area. Exemplarily, the top elevation of the delivery target is the maximum elevation information in its corresponding target area. Therefore, the elevation information of each position point in the target area is compared to determine the maximum elevation information as the top elevation of the delivery target. The target area includes not only the delivery target, but also the ground where the delivery target is located. The ground elevation of the delivery target is the minimum elevation information in its corresponding target area. Therefore, the elevation information of each position point in the target area is compared to determine the minimum elevation information as the ground elevation of the delivery target. The maximum elevation information and the minimum elevation information are used to obtain the relative height of the delivery target, and the relative height is used as the height of the target space. The area of ​​the target area is used as the bottom area of ​​the target space to construct a target space with a regular shape. Figure 6 is a second schematic diagram of the target space provided in the embodiment of the present application. Figure 6As shown, the elevation information of each position point in the target area is sorted from small to large, and the position point D and the position point E are determined to be the minimum elevation information H4 and the maximum elevation information H5 respectively. The relative height H3 of the delivery target 12 can be obtained by subtracting the minimum elevation information H3 from the maximum elevation information H5. According to the relative heights of the target area and the delivery target, the target space 13 of the delivery target is constructed, and the relative height H3 of the delivery target is the relative height of the target space.

[0066] Further, after determining the target space corresponding to the delivery target, the volume of the target space is calculated, and the volume of the target space is used as the volume of the corresponding delivery target. The target area can be regarded as the bottom surface of the corresponding target space. From the volume calculation formula of the bottom area multiplied by the height, it can be known that the volume can be calculated according to the bottom area and height of the target space. Exemplarily, the steps of determining the volume of the target space specifically include S1203-S1204:

[0067] S1203: Determine the geographical area of ​​the target area according to the geographical location coordinates of the operation area and the image location coordinates of the target area corresponding to the target space in the remote sensing image data.

[0068] For example, although the target area is image data marked by a bounding box in remote sensing image data, in the real world, the target area can be regarded as a fence surrounding the delivery target, and the actual area of ​​the target area needs to be calculated, that is, the geographic area of ​​the target area in the world coordinate system. The volume information of the target space refers to the geographic volume in the world coordinate system.

[0069] In this embodiment, determining the geographic area of ​​the target area includes two implementation methods, one of which is to convert the image area of ​​the target area into the geographic area according to the imaging ratio. Exemplarily, the distances between the target areas at different altitudes and the unmanned equipment are different, and the imaging ratios are different. Therefore, it is necessary to determine the imaging ratio of the image data of the target area according to the distance between the target area and the unmanned equipment, and then convert the image area of ​​the image data of the target area into the geographic area according to the imaging ratio. Another implementation method is to determine its geographic area according to the geographic coordinate position of the target area. Among them, the image position coordinates of the target area in the remote sensing image data refer to the pixel coordinates of each pixel point of the target area in the orthophoto data of the operating area. When the delivery target in the orthophoto data is identified and the target area is determined, only the pixel coordinates of the target area in the orthophoto data are obtained. If you want to calculate the geographic area of ​​the target area through the geographic location coordinates, you need to determine the geographic location coordinates of the target area from the geographic location coordinates of the operating area according to the pixel coordinates of the target area. Exemplarily, the orthophoto data contains the mapping relationship between each pixel point in the operating area and each position point, and the geographic location coordinates of the corresponding position point can be deduced according to the pixel coordinates of the pixel points in the operating area. According to the pixel coordinates of the target area in the working area, the geographical coordinates of the target area can be determined, and the geographical area of ​​the target area can be calculated based on the geographical coordinates of the target area. If the target area is a regular shape such as a square or a circle, the geographical area of ​​the target area can be determined based on the conventional calculation formula. If the target area is an irregular shape, the target area can be divided into multiple sub-areas based on the principle of calculus, and the areas of the sub-areas are calculated and summed to obtain the total area of ​​the target area.

[0070] In this embodiment, reference Figure 2 , the bounding box of the target area in the orthophoto data is a circle, and the target area 13 is a circular area. To obtain the true bottom area of ​​the circular area, it is only necessary to substitute the true radius of the circular area into the circular area calculation formula. Exemplarily, the calculation steps of calculating the true bottom area of ​​the target area according to the true radius of the circular area include S12301-S12033:

[0071] S12031. Determine the image center coordinates and image edge coordinates of the target area according to the image position coordinates of the target area in the remote sensing image data.

[0072] Exemplarily, the image center coordinates refer to the pixel coordinates of the pixel point that is the center of the image data of the target area. The image edge coordinates refer to the pixel coordinates of any pixel point of the bounding box that marks the image data of the target area. When marking the bounding box in the orthophoto data, the pixel coordinates of each pixel point in the image data of the target area are obtained, and the image center coordinates and image edge coordinates of the target area are determined from the pixel coordinates of these pixel points.

[0073] S12032. Determine the geographic center coordinates and geographic radius of the target area according to the geographic location coordinates, the image center coordinates, and the image outer edge coordinates.

[0074] Exemplarily, the geographic center coordinates refer to the position coordinates of the center of the target area in the world coordinate system. The pixel points of the image data of the target area correspond to the various position points of the target area. According to the correspondence between the pixel points of the image data and the position points, the position coordinates of the position points corresponding to the center of the image are determined, and the position coordinates are determined as the geographic center coordinates of the target area. According to the correspondence between the pixel points of the image data and the position points, the position coordinates of the position points corresponding to the pixel points of the bounding box are determined, and the position coordinates are determined as the geographic outer edge coordinates of the target area. The geographic radius can be obtained by calculating the straight-line distance between the geographic outer edge coordinates and the geographic center coordinates. It should be noted that for a circle, the straight line between the center and the outer edge can be regarded as the radius, so the position coordinates of the position point corresponding to any pixel point of the first bounding box can be obtained to calculate the geographic radius.

[0075] S12033. Calculate the geographic area of ​​the target area based on the geographic radius.

[0076] For example, the geographic radius is substituted into the circular area calculation formula πr 2 , and obtain the actual geographical area of ​​the target area.

[0077] S1204: Determine the volume information of the delivery target corresponding to the target space according to the geographical area and elevation information of the target area.

[0078] For a target space with a regular shape, the volume of the target space can be calculated based on a conventional calculation formula. Figure 6 , assuming Figure 6 If the target space in is a cylinder, substitute the bottom area and relative height of the target space into the cylinder volume calculation formula to obtain the volume of the target space. From the above content, it can be seen that the relative height of the target space has been calculated through the elevation information of the target area during construction.

[0079] For an irregularly shaped target space, the target space is divided into multiple subspaces based on the principle of calculus, and the total volume of the target space is determined by calculating the volume of each subspace. In this embodiment, the step of calculating the irregularly shaped target space specifically includes S12041-S12044:

[0080] S12041. Divide the target area into multiple sub-areas according to a preset segmentation rule, and determine the area of ​​each sub-area.

[0081] Exemplarily, the upper surface of the target space constructed by the target three-dimensional model is a curved surface, but the lower surface is a plane, so the lower surface, that is, the target area, is used as the bottom surface of the target space. The target area is divided into multiple sub-areas by evenly distributed grid lines, and the area of ​​the sub-area is calculated based on the side length of each grid. The area of ​​the sub-area whose edge of the target area is less than one grid is also calculated based on the side length of the grid. It should be noted that the area of ​​the sub-area refers to the geographical area in the world coordinate system.

[0082] S12042. Determine the area height of each sub-area according to the elevation information of each location point in the target area.

[0083] Exemplarily, the position point in the sub-region is determined according to the position of the sub-region in the target region. According to the relative height of each position point in the target space, the height of the position point with the largest relative height in the sub-region is determined as the region height of the sub-region.

[0084] S12043. Multiply the area of ​​each sub-region by the corresponding region height to determine the region volume of each sub-region.

[0085] S12044. Add up the area volumes of all sub-areas to determine the volume information of the delivery target.

[0086] Exemplarily, the area of ​​each sub-region is multiplied by the corresponding region height, and the region volumes of all sub-regions are added together to estimate the volume information of the target space, and the volume information of the target space is used as the volume information of the delivery target.

[0087] S130. Determine the material delivery amount corresponding to the delivery target according to the volume information, and control the unmanned equipment to deliver the corresponding material delivery amount to the delivery target.

[0088] Exemplarily, the amount of material required for delivery targets of different volumes is different. This embodiment determines the volume-material mapping relationship and determines the amount of material corresponding to the volume information according to the volume-material mapping relationship. In this embodiment, the amount of material required for delivery targets of different volumes can be tested in advance to establish a volume-material mapping relationship between the volume of the delivery target and the corresponding required amount of material, so that after calculating the volume of the delivery target, a pre-set volume-material mapping relationship is obtained, and the amount of material required for the delivery target is determined according to the volume-material mapping relationship. Taking the delivery target as a fruit tree as an example, assuming that a 15-cubic-meter fruit tree needs to be sprayed with 100 milliliters of pesticide, then the volume-material mapping relationship for spraying 6.667 milliliters of pesticide on a 1-cubic-meter fruit tree can be determined. According to the volume-material mapping relationship, after determining that the volume of the fruit tree to be sprayed is 10 cubic meters, it can be determined that the fruit tree needs to be sprayed with 66.67 milliliters of pesticide.

[0089] In one embodiment, the material delivery amount of subsequent delivery targets is adjusted based on the first delivery target of each operation as an anchor point. Exemplarily, the volume material mapping relationship used in this operation is determined based on the material delivery amount of the first delivery target selected by the user and the volume of the first delivery target, so that the unmanned equipment determines the material delivery amount of the subsequent delivery target based on the volume material mapping relationship and the volume of the subsequent delivery target. Taking the delivery target as a fruit tree as an example, assuming that the user chooses to spray 100 milliliters of pesticide on the first fruit tree, and the volume of the first fruit tree is 10 cubic meters, then it can be determined that the volume material mapping relationship used in this operation is to spray 10 milliliters of pesticide per 1 cubic meter of fruit tree. If the volume of the second fruit tree is 15 cubic meters, according to the volume material mapping relationship, it is determined that the second fruit tree is sprayed with 150 milliliters of pesticide. In addition, the physical delivery amount of the delivery target can also be determined through big data analysis. For example, taking fruit trees as the target of administration, the volume-material mapping relationship of fruit trees in different regions, seasons, growth trends and types can be determined by analyzing data such as the regional characteristics, environmental characteristics, growth characteristics and biological characteristics of various fruit trees and the corresponding dosage of medicine.

[0090] Furthermore, there are different delivery methods for different delivery targets. The unmanned equipment can deliver materials while sailing, or it can deliver materials by hovering when sailing to the working position. In this embodiment, the unmanned equipment is controlled to deliver a delivery amount of materials to the delivery target when sailing to the working position. Taking the delivery target as fruit trees as an example, when spraying pesticides on fruit trees, it is necessary to spray pesticides on the heart of the fruit trees to ensure that the fruit trees have sufficient nutrients. Therefore, the unmanned equipment can be controlled to hover above the heart of the fruit tree and spray pesticides on the fruit tree. The working position is the position where the unmanned equipment hovers to spray pesticides. Exemplarily, the steps for the unmanned equipment to perform material delivery operations specifically include S1301-S1304:

[0091] S1301. Determine the target area center corresponding to each target space, and obtain the operation position corresponding to each delivery target according to the geographical location coordinates of the position point corresponding to the target area center.

[0092] For example, the center of the target area refers to the central pixel point of the image data of the target area. For example, since the image data of the target area is obtained by identifying the top view of the fruit tree, the position of the heart of the fruit tree is close to the center of the target area, so the geographical coordinates of the position point corresponding to the central pixel point of the target area are determined as the geographical coordinates of the operation position to ensure that the heart of the fruit tree is within the spraying range of the unmanned equipment.

[0093] S1302: Obtain the elevation information of each position point in the target space, and determine the maximum elevation value as the elevation information of the delivery target.

[0094] Exemplarily, the geographic location coordinates of the location point are two-dimensional coordinates that do not contain altitude information. Therefore, it is also necessary to determine the flight altitude of the unmanned equipment based on the elevation information of each location point in the target area, that is, the surface altitude. The maximum elevation information in the target space can be regarded as the altitude of the top of the corresponding delivery target. Specifically, since the pesticides are easily disturbed by wind factors when the unmanned equipment is spraying pesticides, the spraying direction of the pesticides deviates, causing the pesticides to be sprayed on the ground or on the leaves, affecting the quality of the pesticide spraying. Therefore, according to the altitude of the top of the fruit tree, the unmanned equipment can be controlled to spray pesticides on the fruit trees as close to the top of the tree as possible, so as to reduce the degree of interference of environmental factors on the spraying direction of the pesticides when the distance between the unmanned equipment and the fruit trees is large.

[0095] S1303. Determine the flight altitude corresponding to each operating position according to the elevation information of each delivery target.

[0096] Exemplarily, the treetop altitude of each fruit tree is matched with the corresponding operation position to obtain the three-dimensional geographic coordinates of the unmanned equipment when spraying the fruit trees.

[0097] S1304: Control the unmanned equipment to fly to each operating position at a corresponding flight altitude, and deliver the material delivery amount to the corresponding delivery target.

[0098] For example, according to the three-dimensional geographic coordinates of each fruit tree during the spraying operation, the unmanned device is controlled to fly to the location and spray the corresponding amount of pesticide on the fruit tree. Since the altitude of the top of the fruit tree is the highest altitude of the fruit tree, the unmanned device is controlled to fly at the altitude of the tree top, which can also prevent the fruit tree from affecting the navigation of the unmanned device.

[0099] In one embodiment, the unmanned equipment is controlled to navigate in a straight line between the determined operating positions. For example, the unmanned equipment needs to hover and drop materials at the three-dimensional geographic coordinates during the spraying operation. Based on the principle that the straight-line distance between two points is the shortest, the straight line between the operating positions of the delivery targets of adjacent operations can be used as the flight route of the unmanned equipment. According to the flight route, the unmanned equipment is controlled to navigate in a straight line between the operating positions of the delivery targets of adjacent operations, effectively shortening the route distance of the unmanned equipment, improving the efficiency of the unmanned equipment, and reducing the battery consumption of the unmanned equipment. Figure 7 Schematic diagram of the flight route of the unmanned equipment provided in the embodiment of the present application. Figure 7 As shown, the position coordinates of the position point corresponding to the center point of the target area are determined as the position coordinates of the operation position 17, and the maximum elevation information among the elevation information of each position point in the target area is used as the flight altitude of the operation position 17. The straight line between the three-dimensional geographic coordinates of the delivery targets of adjacent operations is used as the flight route 18 of the unmanned equipment. It can be understood that the delivery targets of adjacent operations refer to the delivery targets that are adjacent in the operation sequence, and the operation sequence is set in advance by the staff according to the distribution position and other parameters of the delivery targets in the operation area.

[0100] In summary, by acquiring the remote sensing image data of the operation area, the delivery targets contained in the remote sensing image data are determined; the target space corresponding to each delivery target is determined, and the volume information of the corresponding delivery target is determined based on each target space; the material delivery amount corresponding to the delivery target is determined according to the volume information, and the unmanned equipment is controlled to deliver the corresponding material delivery amount to the delivery target. By adopting the above technical means, the delivery targets in the remote sensing image data of the operation area are identified, and each delivery target in the operation area is marked by the target space in the remote sensing image data of the operation area. The volume of the corresponding delivery target is represented by the volume of the target space, so that the unmanned equipment delivers the material delivery amount corresponding to the volume of the delivery target to the delivery target, meets the material needs of each delivery target, avoids the phenomenon of too much or too little delivery of materials in the delivery target, and ensures the material delivery effect and delivery operation quality. In addition, according to the altitude of the top of the delivery target and the center position of the target area, the working position of the unmanned equipment is determined, so that the unmanned equipment can deliver materials close to each delivery target to avoid environmental factors affecting the material delivery effect.

[0101] Embodiment 2:

[0102] Based on the above embodiments, Figure 8 This is a schematic diagram of the structure of a material delivery device provided in Example 2 of the present application. Figure 8 The material delivery operation device provided in this embodiment specifically includes: a delivery target identification module 21, a volume determination module 22 and a material delivery module 23.

[0103] The delivery target identification module 21 is configured to obtain remote sensing image data of the operation area and determine the delivery target contained in the remote sensing image data;

[0104] The volume determination module 22 is configured to determine a target space corresponding to each delivery target, and determine volume information of the corresponding delivery target based on each target space;

[0105] The material delivery module 23 is configured to determine the material delivery amount corresponding to the delivery target according to the volume information, and control the unmanned equipment to deliver the corresponding material delivery amount to the delivery target.

[0106] Based on the above embodiment, the delivery target identification module includes: a first model identification submodule, which is configured to identify the delivery targets contained in the remote sensing image data through a first preset network model to output each delivery target in the working area; or, a second model identification submodule, which is configured to reconstruct point cloud data of the working area based on the remote sensing image data, and identify the delivery targets contained in the point cloud data through a second preset network model to output each delivery target in the working area.

[0107] Based on the above embodiments, the delivery target identification module includes: a first selection submodule, configured to receive a first selection operation, and determine each delivery target in the remote sensing image data according to the first selection operation; or, a second selection submodule, configured to receive a second selection operation, and determine each delivery target in the point cloud data according to the second selection operation.

[0108] On the basis of the above embodiment, the first selection submodule includes: a first frame selection unit, configured to generate a bounding box corresponding to each delivery target based on the first selection operation of the user on the control device, and mark the corresponding delivery target in the remote sensing image data through the bounding box; accordingly, the volume determination module includes a target space construction submodule including: a target area determination unit, configured to generate a target area corresponding to the delivery target according to each bounding box; an elevation information determination unit, configured to obtain a digital surface model corresponding to the operating area, and determine the elevation information corresponding to each target area based on the digital surface model; a first target space construction unit, configured to determine the target space corresponding to each delivery target based on the target area and the corresponding elevation information.

[0109] Based on the above embodiment, the first selection submodule also includes: a frame selection adjustment unit, which is configured to determine the target type and growth stage of the delivery target in the target area, and adjust the enclosing frame corresponding to the target area according to the target type and growth stage of the delivery target.

[0110] Based on the above embodiment, the elevation information determination unit includes: an elevation information matching subunit, which is configured to determine the elevation information corresponding to each position point in the working area according to the digital surface model corresponding to the working area; and an elevation information determination subunit, which is configured to determine the elevation information of each position point in the target area according to the image position coordinates of the target area in the remote sensing image data.

[0111] Based on the above embodiment, the second selection submodule includes: a second frame selection unit, configured to determine the minimum bounding box corresponding to each delivery target in the point cloud data, and mark the corresponding delivery target in the point cloud data through the minimum bounding box; accordingly, a second target space construction unit, configured to generate a target space corresponding to each delivery target based on the minimum bounding box.

[0112] On the basis of the above embodiment, the volume determination module includes: an area determination submodule, which is configured to determine the geographical area of ​​the target area according to the geographical location coordinates of the operating area and the image position coordinates of the target area corresponding to the target space in the remote sensing image data; and a volume determination submodule, which is configured to determine the volume information of the delivery target corresponding to the target space according to the geographical area and elevation information of the target area.

[0113] On the basis of the above embodiment, the target area is a circular area, and the area determination submodule includes: an image coordinate determination unit, configured to determine the image center coordinates and image outer edge coordinates of the target area according to the image position coordinates of the target area in the remote sensing image data; a geographic coordinate determination unit, configured to determine the geographic center coordinates and geographic radius of the target area according to the geographic location coordinates, the image center coordinates and the image outer edge coordinates; a geographic area calculation unit, configured to calculate the geographic area of ​​the target area according to the geographic radius.

[0114] On the basis of the above embodiment, the volume determination submodule includes: a sub-area area determination unit, configured to divide the target area into multiple sub-areas according to a preset segmentation rule, and determine the area of ​​each sub-area; a sub-area height determination unit, configured to determine the area height of each sub-area according to the elevation information of each position point in the target area; a sub-area volume determination unit, configured to multiply the area of ​​each sub-area by the corresponding area height to determine the area volume of each sub-area; and a volume determination unit, configured to add the area volumes of all sub-areas to determine the volume information of the delivery target.

[0115] Based on the above embodiment, the material delivery module includes: a delivery quantity determination submodule, which is configured to determine the volume-material mapping relationship, and determine the material delivery quantity corresponding to the volume information according to the volume-material mapping relationship; a delivery operation submodule, which is configured to control the unmanned equipment to deliver the material delivery quantity to the delivery target when navigating to the operation position.

[0116] On the basis of the above embodiment, the delivery operation submodule includes: an operation position determination unit, configured to determine the target area center corresponding to each target space, and obtain the operation position corresponding to each delivery target according to the geographical location coordinates of the position point corresponding to the target area center; a target height determination unit, configured to obtain the elevation information of each position point in the target space, and determine the maximum elevation value as the elevation information of the delivery target; a flight height determination unit, configured to determine the flight height corresponding to each operation position according to the elevation information of each delivery target; a delivery operation unit, configured to control the unmanned equipment to fly to each operation position at the corresponding flight height, and deliver the material delivery amount to the corresponding delivery target.

[0117] In the above, by acquiring the remote sensing image data of the operation area, the delivery target contained in the remote sensing image data is determined; the target space corresponding to each delivery target is determined, and the volume information of the corresponding delivery target is determined based on each target space; the material delivery amount corresponding to the delivery target is determined according to the volume information, and the unmanned equipment is controlled to deliver the corresponding material delivery amount to the delivery target. By adopting the above technical means, the delivery target in the remote sensing image data of the operation area is identified, and each delivery target in the operation area is marked by the target space in the remote sensing image data of the operation area. The volume of the corresponding delivery target is represented by the volume of the target space, so that the unmanned equipment delivers the material delivery amount corresponding to the volume of the delivery target to the delivery target, meets the material demand of each delivery target, avoids the phenomenon of too much or too little delivery of the delivery target, and ensures the material delivery effect and delivery operation quality. In addition, according to the altitude of the top of the delivery target and the center position of the target area, the operation position of the unmanned equipment is determined, so that the unmanned equipment can deliver materials close to each delivery target to avoid environmental factors affecting the material delivery effect.

[0118] The material placing operation device provided in the second embodiment of the present application can be used to execute the material placing operation method provided in the above-mentioned first embodiment, and has corresponding functions and beneficial effects.

[0119] Embodiment three:

[0120] Fig. 9 This is a schematic diagram of the structure of an unmanned device provided in Example 3 of the present application, with reference to Fig. 9 The unmanned device includes: a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The number of processors 31 in the unmanned device can be one or more, and the number of memories 32 in the unmanned device can be one or more. The processor 31, memory 32, communication module 33, input device 34, and output device 35 of the unmanned device can be connected via a bus or other means.

[0121] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the material delivery operation method of any embodiment of the present application (for example, the delivery target identification module 21, the volume determination module 22 and the material delivery module 23 in the material delivery operation device). The memory 32 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to the use of the device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0122] The communication module 33 is used for data transmission.

[0123] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 32, that is, realizes the above-mentioned material delivery operation method.

[0124] The input device 34 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 35 may include a display device such as a display screen.

[0125] The unmanned equipment provided above can be used to execute the material delivery operation method provided in the above embodiment 1, and has corresponding functions and beneficial effects.

[0126] Embodiment 4:

[0127] An embodiment of the present application also provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute a material delivery operation method, the material delivery operation method comprising: acquiring remote sensing image data of an operation area, and determining delivery targets contained in the remote sensing image data; determining a target space corresponding to each delivery target, and determining volume information of the corresponding delivery target based on each target space; determining a material delivery amount corresponding to the delivery target based on the volume information, and controlling unmanned equipment to deliver the corresponding material delivery amount to the delivery target.

[0128] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system, which is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0129] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application, whose computer executable instructions are not limited to the above material delivery operation method, can also execute related operations in the material delivery operation method provided in any embodiment of the present application.

[0130] The material delivery operation device, storage medium and unmanned equipment provided in the above embodiments can execute the material delivery operation method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the material delivery operation method provided in any embodiment of the present application.

[0131] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the protection scope of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A material delivery method, characterized in that: include: Acquire remote sensing image data of the operation area, and determine the delivery target contained in the remote sensing image data; The method includes: generating a bounding box corresponding to each delivery target based on a first selection operation of a user on a control device, marking the delivery target corresponding to the remote sensing image data by the bounding box; identifying the delivery target in the bounding box, determining the target type and growth stage of the delivery target in the bounding box; adjusting the bounding box corresponding to the delivery target according to the target type and growth stage of the delivery target; Determining the target space corresponding to each delivery target, including: generating a target area corresponding to the delivery target according to each bounding box; obtaining a digital surface model corresponding to the operation area, and determining the elevation information corresponding to each target area based on the digital surface model; determining the target space corresponding to each delivery target based on the target area and the corresponding elevation information; Determining volume information of a corresponding delivery target based on each of the target spaces; The material delivery amount corresponding to the delivery target is determined according to the volume information, and the unmanned equipment is controlled to deliver the corresponding material delivery amount to the delivery target.

2. The material delivery method according to claim 1, characterized in that: The step of determining the elevation information corresponding to each target area based on the digital surface model includes: Determining elevation information corresponding to each location point in the operation area according to a digital surface model corresponding to the operation area; The elevation information of each position point in the target area is determined according to the image position coordinates of the target area in the remote sensing image data.

3. The material delivery method according to claim 1, characterized in that: The determining the volume information of the corresponding delivery target based on each target space includes: Determine the geographical area of ​​the target area according to the geographical location coordinates of the operation area and the image location coordinates of the target area corresponding to the target space in the remote sensing image data; The volume information of the delivery target corresponding to the target space is determined according to the geographical area and elevation information of the target area.

4. The material delivery method according to claim 1, characterized in that: The target area is a circular area, and determining the geographical area of ​​the target area according to the geographical location coordinates of the operation area and the image location coordinates of the target area corresponding to the target space in the remote sensing image data includes: Determine the image center coordinates and image edge coordinates of the target area according to the image position coordinates of the target area in the remote sensing image data; Determine the geographic center coordinates and geographic radius of the target area according to the geographic location coordinates, the image center coordinates and the image outer edge coordinates; The geographical area of ​​the target area is calculated according to the geographical radius.

5. The material delivery method according to claim 3, characterized in that: Determining the volume information of the delivery target corresponding to the target space according to the geographical area and elevation information of the target area includes: Divide the target area into multiple sub-areas according to a preset segmentation rule, and determine the area of ​​each sub-area; Determine the height of each sub-area according to the elevation information of each location point in the target area; Multiplying the area of ​​each sub-region by the corresponding region height to determine the region volume of each sub-region; The area volumes of all the sub-areas are added together to determine the volume information of the delivery target.

6. The material delivery method according to claim 1, characterized in that: The step of determining the material delivery amount corresponding to the delivery target according to the volume information, and controlling the unmanned equipment to deliver the material of the corresponding material delivery amount to the delivery target includes: Determine a volume-material mapping relationship, and determine a material delivery amount corresponding to the volume information according to the volume-material mapping relationship; The unmanned equipment is controlled to deliver the material delivery amount to the delivery target when navigating to the operation position.

7. The material delivery method according to claim 6, characterized in that: The controlling the unmanned equipment to deliver the material delivery amount to the delivery target when navigating to the operation position includes: Determine the target area center corresponding to each target space, and obtain the operation position corresponding to each delivery target according to the geographical location coordinates of the location point corresponding to the target area center; Acquire the elevation information of each position point in the target space, and determine the maximum elevation value as the elevation information of the delivery target; Determine the flight altitude corresponding to each operation position according to the elevation information of each delivery target; When the unmanned equipment is controlled to fly to each operating position at a corresponding flight altitude, the material delivery amount is delivered to the corresponding delivery target.

8. A material delivery device, characterized in that: include: The delivery target recognition module is configured to obtain remote sensing image data of the operation area and determine the delivery target contained in the remote sensing image data; wherein the delivery target recognition module is specifically configured to generate a bounding box corresponding to each delivery target based on the first selection operation of the user on the control device, and mark the corresponding delivery target in the remote sensing image data by the bounding box; identify the delivery target in the bounding box, determine the target type and growth stage of the delivery target in the bounding box; and adjust the bounding box corresponding to the delivery target according to the target type and generation stage of the delivery target; The volume determination module is configured to determine the target space corresponding to each delivery target, and determine the volume information of the corresponding delivery target based on each target space; wherein the volume determination module includes: a target area determination unit, configured to generate a target area corresponding to the delivery target according to each bounding box; an elevation information determination unit, configured to obtain a digital surface model corresponding to the operation area, and determine the elevation information corresponding to each target area based on the digital surface model; a first target space construction unit, configured to determine the target space corresponding to each delivery target based on the target area and the corresponding elevation information; The material delivery module is configured to determine the material delivery amount corresponding to the delivery target according to the volume information, and control the unmanned equipment to deliver the corresponding material delivery amount to the delivery target.

9. An unmanned device, characterized in that: include: one or more processors; A storage device stores one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the material delivery operation method as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the material delivery method as described in any one of claims 1-7.

Images