Ground stacking determination method and device, electronic equipment and storage medium

Abstract

The invention provides a ground stacking determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a projection grid image in a target area, judging whether a ground model exists or not, if yes, updating the ground model according to the projection grid image, otherwise, generating the ground model according to the projection grid image, and determining at least one to-be-selected area according to the projection grid image, the ground model and a preset fault-tolerant threshold, determining a stacking area in the ground model based on a watershed algorithm according to each to-be-selected area, and determining a stacking area in the target area according to the stacking area in the ground model. The stacking range is finally determined by using the projection grid image of the target area, the application range is wide, multiplexing can be achieved, and interference caused by incomplete training samples and other problems is avoided. And the stacking range is determined in combination with the watershed algorithm, the adhesion phenomenon of the stacking range is avoided, and therefore the accuracy of the determined stacking range is high.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, electronic device and storage medium for determining ground stacking. Background Art

[0002] In factory areas and ports, it is necessary to monitor and extract the stacking range of goods or containers on the yard, so as to assist in cargo scheduling according to the stacking position.

[0003] In the prior art, there are three main strategies for extracting the stacking range in the yard. The first strategy is to design an algorithm for regular objects separately, such as designing a container training target detection algorithm, or using an instance segmentation algorithm to obtain the target object range and then determine the stacking range. The second strategy is to have the operator manually draw a single stacking area and calculate the approximate actual contour. The third strategy is to use a deep learning 3D segmentation model to segment and predict the point cloud data to obtain the final stacking contour range.

[0004] However, the first strategy in the prior art is suitable for stacks with fixed characteristics, and its application range is small. It has poor extraction effect on irregular objects such as coal piles. The second strategy is highly dependent on the experience of the operators, and the extracted stacking range may not fit the actual stacking range. This strategy requires a lot of time and cost, resulting in low efficiency. In the third strategy, the samples of the training model may have problems such as incomplete coverage, insufficient sample collection data, and difficulty in drawing sample labels, which may lead to the inability to reuse algorithm models between different yards. Summary of the invention

[0005] The purpose of the present application is to provide a ground stacking determination method, device, electronic device and storage medium to address the deficiencies in the above-mentioned prior art, so as to solve the problems of inaccurate segmentation of stacking areas, low efficiency and non-reusability in the prior art.

[0006] To achieve the above objectives, the technical solutions adopted in this application are as follows:

[0007] In a first aspect, the present application provides a method for determining a ground stack, the method comprising:

[0008] Acquire a projected grid image in the target area, wherein the projected grid image is obtained by projecting a point cloud in the target area, and the pixel value of each pixel point in the projected grid image is the height value of the point cloud corresponding to the pixel point;

[0009] Determine whether there is a ground model;

[0010] If yes, then update the ground model according to the projected raster image; otherwise, generate a ground model according to the projected raster image, wherein the pixel value of the pixel point corresponding to the non-ground pixel point in the projected raster image in the ground model is the pixel value corresponding to the ground pixel point;

[0011] Determine at least one area to be selected in the ground model according to the projected grid image, the ground model and a preset fault tolerance threshold, wherein the area to be selected is a partial stacking area;

[0012] According to each of the candidate areas, based on a watershed algorithm, a stacking area in the ground model is determined, and according to the stacking area in the ground model, a stacking area in the target area is determined.

[0013] Optionally, generating a ground model according to the projected raster image includes:

[0014] determining a height mode in the projected raster image;

[0015] Generate a water level estimate based on the height mode and a preset mode threshold;

[0016] The ground model is generated according to the pixel value of each pixel point in the projected raster image and the horizontal plane estimation value.

[0017] Optionally, generating the ground model according to the pixel value of each pixel point in the projected raster image and the horizontal plane estimation value includes:

[0018] Traverse each pixel point in the projected raster image, and for the first current pixel point traversed, determine whether the pixel value of the first current pixel point is greater than the horizontal plane estimation value; if so, replace the pixel value of the first current pixel point with the horizontal plane estimation value to obtain the pixel value of the pixel point corresponding to the first current pixel point in the ground model.

[0019] Optionally, updating the ground model according to the projected raster image includes:

[0020] Determine whether there are pixels without data in the projected raster image;

[0021] If yes, then replace the pixel value of the pixel point without data in the projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, to obtain the updated projected raster image, and compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and take the lower pixel value as the pixel value of the corresponding pixel point in the ground model;

[0022] If not, then compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and use the lower pixel value as the pixel value of the corresponding pixel point in the ground model.

[0023] Optionally, determining the area to be selected according to the projected grid image, the ground model and a preset error tolerance threshold comprises:

[0024] Traversing the pixel points in the ground model, and for the traversed second current pixel point, calculating the difference between the pixel value of the pixel point corresponding to the second current pixel point in the projected raster image and the pixel value of the second current pixel point;

[0025] If the difference is greater than the preset error tolerance threshold, the second current pixel point is taken as a pixel point in a candidate area.

[0026] Optionally, determining the stacking area in the ground model based on each of the to-be-selected areas and a watershed algorithm includes:

[0027] Dilate and invert the selected area to obtain a background area;

[0028] Determine a plurality of first water filling points according to the distance between the edge pixel points in the background area and each pixel in each of the to-be-selected areas, and use the background area as the second water filling point;

[0029] Based on the plurality of the first water injection points and the second water injection points, a stacking area in the ground model is determined according to the watershed algorithm.

[0030] Optionally, before determining the stacking area in the target area according to the stacking area in the ground model, the method further comprises:

[0031] Traversing each stacking area, for the current stacking area traversed, inputting the pixel value of each pixel point in the current stacking area and the pixel value of the corresponding pixel point in the projected raster image into a pre-trained instance partitioning model, and outputting the repose angle parameter, area parameter and minimum bounding rectangle parameter of each stacking area;

[0032] Determine whether the current stacking area is an interference area according to the angle of repose threshold, the area threshold, the minimum bounding rectangle threshold, the angle of repose parameter, the area parameter and the minimum bounding rectangle parameter;

[0033] If so, the interference area is filtered out.

[0034] Optionally, the method further comprises:

[0035] Acquire local change parameters input by a user, wherein the local change parameters include a range of changed pixels and a changed pixel value of the changed pixels;

[0036] Determining the pixel points to be changed in the ground model according to the range of the changed pixel points;

[0037] The pixel value of the pixel to be changed is replaced by the changed pixel value.

[0038] In a second aspect, the present application provides a ground stack determination device, the device comprising:

[0039] An acquisition module is used to acquire a projected grid image in a target area, wherein the projected grid image is obtained by projecting a point cloud in the target area, and the pixel value of each pixel point in the projected grid image is a height value of the point cloud corresponding to the pixel point;

[0040] A judgment module, used to judge whether there is a ground model;

[0041] A generating and updating module is used for updating the ground model according to the projected raster image if yes, and otherwise generating a ground model according to the projected raster image, wherein the pixel value of the pixel point corresponding to the non-ground pixel point in the projected raster image in the ground model is the pixel value corresponding to the ground pixel point;

[0042] A first determination module is used to determine at least one to-be-selected area in the ground model according to the projected grid image, the ground model and a preset fault tolerance threshold, wherein the to-be-selected area is a partial stacking area;

[0043] The second determination module is used to determine the stacking area in the ground model according to each of the candidate areas based on a watershed algorithm, and determine the stacking area in the target area according to the stacking area in the ground model.

[0044] Optionally, the generation update module is specifically used for:

[0045] determining a height mode in the projected raster image;

[0046] Generate a water level estimate based on the height mode and a preset mode threshold;

[0047] The ground model is generated according to the pixel value of each pixel point in the projected raster image and the horizontal plane estimation value.

[0048] Optionally, the generation update module is specifically used for:

[0049] Traverse each pixel point in the projected raster image, and for the first current pixel point traversed, determine whether the pixel value of the first current pixel point is greater than the horizontal plane estimation value; if so, replace the pixel value of the first current pixel point with the horizontal plane estimation value to obtain the pixel value of the pixel point corresponding to the first current pixel point in the ground model.

[0050] Optionally, the generation update module is specifically used for:

[0051] Determine whether there are pixels without data in the projected raster image;

[0052] If yes, then replace the pixel value of the pixel point without data in the projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, to obtain the updated projected raster image, and compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and take the lower pixel value as the pixel value of the corresponding pixel point in the ground model;

[0053] If not, then compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and use the lower pixel value as the pixel value of the corresponding pixel point in the ground model.

[0054] Optionally, the first determining module is specifically configured to:

[0055] Traversing the pixel points in the ground model, and for the traversed second current pixel point, calculating the difference between the pixel value of the pixel point corresponding to the second current pixel point in the projected raster image and the pixel value of the second current pixel point;

[0056] If the difference is greater than the preset error tolerance threshold, the second current pixel point is taken as a pixel point in a candidate area.

[0057] Optionally, the second determining module is specifically configured to:

[0058] Dilate and invert the selected area to obtain a background area;

[0059] Determine a plurality of first water filling points according to the distance between the edge pixel points in the background area and each pixel in each of the to-be-selected areas, and use the background area as the second water filling point;

[0060] Based on the plurality of the first water injection points and the second water injection points, a stacking area in the ground model is determined according to the watershed algorithm.

[0061] Optionally, the second determining module is further used for:

[0062] Traversing each stacking area, for the current stacking area traversed, inputting the pixel value of each pixel point in the current stacking area and the pixel value of the corresponding pixel point in the projected raster image into a pre-trained instance partitioning model, and outputting the repose angle parameter, area parameter and minimum bounding rectangle parameter of each stacking area;

[0063] Determine whether the current stacking area is an interference area according to the angle of repose threshold, the area threshold, the minimum bounding rectangle threshold, the angle of repose parameter, the area parameter and the minimum bounding rectangle parameter;

[0064] If so, the interference area is filtered out.

[0065] Optionally, the generation update module is specifically used for:

[0066] Acquire local change parameters input by a user, wherein the local change parameters include a range of changed pixels and a changed pixel value of the changed pixels;

[0067] Determining the pixel points to be changed in the ground model according to the range of the changed pixel points;

[0068] The pixel value of the pixel to be changed is replaced by the changed pixel value.

[0069] In a third aspect, the present application provides an electronic device comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the ground stack determination method as described above.

[0070] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned ground stack determination method are executed.

[0071] The beneficial effects of the present application are: by acquiring the projected grid image in the target area, and then generating or updating the ground model according to the projected grid image, so as to provide ground height data for determining the stacking area. Then, at least one selected area in the ground model is determined according to the projected grid image, the ground model and the preset fault tolerance threshold, and the stacking area in the ground model is determined based on the watershed algorithm according to the selected area, so as to avoid the situation where multiple stacks are connected to form a tight stack, thereby improving the accuracy of the stacking area division. Then, the stacking area of ​​the target area is determined according to the stacking area in the ground model, which can avoid interference from houses and cars, and further improve the accuracy of the stacking area division. This embodiment obtains the projected grid image in the target area by iterative acquisition, so that the ground model is continuously updated and refined, and the timeliness and accuracy of the stacking area division are improved. In addition, since the present application has no restrictions on the target area and the projected grid image, it can segment stacks of different shapes and specifications, and has universal applicability. In addition, the present application does not require a large number of training samples, so the difficulty of label production is small, the labor cost is low, and the efficiency is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0073] Figure 1 It is a flowchart of a method for determining ground stacking provided in an embodiment of the present application;

[0074] Figure 2 It is a schematic diagram of a process of generating a ground model provided in an embodiment of the present application;

[0075] Figure 3 is a schematic diagram of a process of updating a ground model provided in an embodiment of the present application;

[0076] Figure 4 is a schematic diagram of a candidate area provided in an embodiment of the present application;

[0077] Figure 5 It is a schematic flow chart of a method for determining a stacking area provided in an embodiment of the present application;

[0078] Figure 6 It is a schematic flow chart of a method for filtering out interference areas provided in an embodiment of the present application;

[0079] Figure 7 It is a schematic flow chart of a method for locally changing the pixel value of a pixel point in a ground model provided by an embodiment of the present application;

[0080] Figure 8 It is a structural schematic diagram of a ground stack determination device provided in an embodiment of the present application;

[0081] Fig. 9 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0083] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0084] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0085] In the stacking range extraction strategy provided by the existing technology, the algorithm design for regular objects is only applicable to stacking with fixed characteristics and has a small scope of application. It takes a lot of time for operators to hand-draw the stacking area, and the extracted stacking range is inaccurate. When using deep learning three-dimensional segmentation model segmentation prediction, the samples used for model training may have problems such as incomplete coverage, insufficient sample collection data, and difficulty in drawing sample labels, resulting in the inability to reuse algorithm models between different yards.

[0086] Based on this, the present application proposes a method for determining ground stacking, which creates and iterates a ground model based on an iteratively updated projection grid image, and determines the stacking area based on the projection grid image and the ground model based on the watershed algorithm. Since the present application uses the projection grid image of the target area to finally determine the stacking range, and the projection grid image has no restrictions on the area or stacking shape, the present method has a wide range of applications and can be reused, avoiding interference caused by problems such as incomplete training samples. In addition, since the present invention first uses the projection grid image to create and iterate the ground model, and then uses the ground model and the projection grid image in combination with the watershed algorithm to determine the stacking range, the stacking range adhesion phenomenon is avoided, so the determined stacking range has a high accuracy. The present method only needs to input the projection grid image to finally determine the stacking range, so the calculation efficiency is high and does not require a lot of time cost.

[0087] The ground stacking determination method of the present invention can be applied to scenes such as factories and ports. The ground stacking determination method is used to determine the stacking range of goods or containers during the process of moving and stacking goods, so as to assist in cargo scheduling according to the stacking position.

[0088] Figure 1 is a flow chart of a method for determining a ground stack provided in an embodiment of the present application. Figure 1 The ground stacking determination method is introduced in detail. Optionally, the ground stacking determination method can be applied in an electronic device with computing capability.

[0089] S101, obtaining a projected grid image in the target area, wherein the projected grid image is obtained by projecting a point cloud in the target area, and the pixel value of each pixel point in the projected grid image is the height value of the point cloud corresponding to the pixel point.

[0090] Specifically, a point cloud of the ground is obtained in advance by a scanner, etc., wherein the point cloud can indicate the coordinate position of each point in a coordinate system. The projected raster image is obtained by projecting the point cloud data from top to bottom onto a horizontal plane, wherein the pixel value of each pixel is the height value of the point cloud corresponding to the pixel.

[0091] It is worth mentioning that in the process of iteratively acquiring the projected raster image, the projected raster image can be an image of any local area in the target area. For example, if the target area is plant A, the currently acquired projected raster image can be an image of the southeast corner of plant A, and the next acquired projected raster image is an image of the middle position of plant A.

[0092] It is worth noting that the pixels in each projected raster image obtained are in the same coordinate system, and can be spliced ​​according to multiple projected raster images in the target area to form a projected raster image of the target area.

[0093] S102: Determine whether there is a ground model.

[0094] The pixel value of each pixel point in the ground model may include a height value corresponding to the pixel point.

[0095] Optionally, when the projected raster image in the target area is first acquired, there is no ground model, and a ground model needs to be generated based on the projected raster image. After the ground model is generated, when the projected raster image in the target area is acquired again, the existing ground model can be updated.

[0096] S103, if yes, update the ground model according to the projected raster image, otherwise, generate the ground model according to the projected raster image, wherein the pixel values ​​of the pixels corresponding to the non-ground pixels in the projected raster image in the ground model are the pixel values ​​corresponding to the ground pixels.

[0097] Specifically, if a ground model exists, the ground model is updated according to the position coordinates of each pixel point in the projected grid image. For example, if the currently acquired projected grid image is an image of the southeast corner of the A plant area, the model of the southeast corner position in the ground model is updated.

[0098] As an optional implementation, during the first iteration, a projection grid image of a first local area in the target area is obtained, and a ground model of the first local area is generated based on the projection grid image of the first local area. During the second iteration, a projection grid image of a second local area in the target area is obtained, wherein the second local area partially does not overlap with the first local area. A ground model is generated based on the portion where the projection grid image of the second local area does not overlap with the projection grid image of the first local area, and the ground model is updated based on the portion where the projection grid image of the second local area overlaps with the projection grid image of the first local area.

[0099] Optionally, the non-ground pixel points in the projected raster image are the pixel points of the area where the stack exists, and the ground pixel points are the pixel points of the area where the stack does not exist. The ground pixel points and the non-ground pixel points can be determined according to the pixel values ​​of each pixel point.

[0100] As an optional implementation, the mode of each pixel value may be determined and used as a dividing point, where pixels with values ​​lower than or equal to the mode are ground pixels, and the others are non-ground pixels.

[0101] After determining the non-ground pixel points and ground pixel points in the projected raster image using the above method, the pixel values ​​of the non-ground pixel points are replaced with the pixel values ​​of the ground pixel points, thereby generating or updating the ground model.

[0102] S104: Determine at least one area to be selected in the ground model according to the projected grid image, the ground model and a preset fault tolerance threshold, where the area to be selected is a partial stacking area.

[0103] Optionally, the preset error tolerance threshold is used to determine the area to be selected based on the projected raster image and the ground model, and the area to be selected is a local range of the stacking area. In the case of the same projected raster image and the ground model, the larger the preset error tolerance threshold, the smaller the area to be selected, and the smaller the preset error tolerance threshold, the larger the area to be selected.

[0104] S105 . Determine the stacking area in the ground model according to each candidate area based on a watershed algorithm, and determine the stacking area in the target area according to the stacking area in the ground model.

[0105] Optionally, the watershed algorithm is a morphological segmentation method based on topological theory, and the present application uses the watershed algorithm to determine the stacking area in the ground model. As an optional implementation, the stacking area in the ground model can be determined based on each selected area in the ground model and the pixel points in the ground model corresponding to the ground pixel points in the projected raster image.

[0106] After the stacking area in the ground model is determined by the watershed algorithm, there may be areas in the stacking area that are not actually stacking, such as interference areas such as cranes and houses. Therefore, it is necessary to filter the stacking area in the ground model and convert the coordinate system of the filtered stacking area in the ground model into the coordinate system of the target area, so as to generate the stacking area of ​​the target area.

[0107] In this embodiment, by acquiring the projected grid image in the target area, and then generating or updating the ground model according to the projected grid image, the ground height data is provided for determining the stacking area. Then, at least one selected area in the ground model is determined according to the projected grid image, the ground model and the preset fault tolerance threshold, and the stacking area in the ground model is determined based on the watershed algorithm according to the selected area, so as to avoid the situation that multiple stacks are connected to form a tight stack, and improve the accuracy of the stacking area division. Then, the stacking area of ​​the target area is determined according to the stacking area in the ground model, which can avoid interference from houses and cars, and further improve the accuracy of the stacking area division. This embodiment obtains the projected grid image in the target area by iteration, so that the ground model is continuously updated and refined, and the timeliness and accuracy of the stacking area division are improved. In addition, since the present application has no restrictions on the target area and the projected grid image, it can segment stacks of different shapes and specifications, and has universal applicability. In addition, the present application does not require a large number of training samples, so the difficulty of label production is small, the labor cost is small, and the efficiency is high.

[0108] Figure 2is a schematic diagram of a process for generating a ground model provided in an embodiment of the present application. Figure 2 This paper introduces a method of generating a ground model based on a projected raster image.

[0109] S201, determining the height mode in the projected raster image.

[0110] As an optional implementation, the pixel value that appears most frequently in each pixel point in the projected raster image can be used as the height mode. For example, if there are 10 pixels in the projected raster image, and the pixel values ​​of each pixel point are 1, 3.1, 1.1, 3.5, 1.3, 1.1, 1.2, 1.1, 1.3 and 1.1 respectively, then the height mode is 1.1.

[0111] As another optional implementation, the pixel values ​​of each pixel point in the projected raster image can be divided into intervals according to a preset interval division standard, and the interval set with the largest number of pixel points in multiple interval sets is determined, and the highest value of the pixel values ​​of the pixel points in the interval set is used as the height mode. If there are 5 pixel points in the projected raster image, and the pixel values ​​of each pixel point are 0.001, 0.002, 0.321, 0.821 and 1.0 respectively, the interval is divided according to the minimum and maximum values ​​of the pixel values ​​of each pixel point, for example, the interval of 0.001 to 1.0 is divided into 20 equal parts, then the number of pixel points whose pixel values ​​fall into the interval of 0.001 to 0.05 is the largest, and the maximum value of this interval, that is, 0.05, is used as the height mode in the projected raster image.

[0112] It is worth noting that before determining the height mode, it is necessary to filter out pixels with negative or 0 values.

[0113] S202: Generate a horizontal plane estimation value according to the height mode and a preset mode threshold.

[0114] Since there is a certain error in taking the height mode of the pixel values ​​of each pixel point in the projected raster image as the height value of the horizontal plane, a preset mode threshold can be set in advance. Specifically, the sum of the height mode and the preset mode threshold is taken as the estimated value of the horizontal plane.

[0115] Exemplarily, the preset mode threshold may be 0.5, in meters.

[0116] S203: Generate a ground model according to the pixel value of each pixel point in the projected raster image and the estimated value of the horizontal plane.

[0117] As an optional implementation, the pixel values ​​of each pixel point in the projected raster image whose pixel values ​​are greater than the estimated horizontal plane value are replaced with the estimated horizontal plane value, and the replaced pixel points are combined with the pixel points whose pixel values ​​are greater than the estimated horizontal plane value to generate a ground model.

[0118] As an optional implementation, after replacing the pixel values ​​of the pixels in the projected raster image whose pixel values ​​are greater than the estimated horizontal plane value with the estimated horizontal plane value, the following steps may be performed: the pixel values ​​are replaced with the estimated horizontal plane value and the pixel values ​​are combined with the pixel values ​​greater than the estimated horizontal plane value to generate a candidate ground model, and it is determined whether the pixel values ​​of the pixels in the projected raster image have abnormal pixel values ​​or missing pixel values, wherein the abnormal pixel values ​​include pixel values ​​exceeding a preset range threshold. If so, the pixel value of the pixel is replaced with the height mode to reduce the interference of the abnormal pixel points in the projected raster image. Then, the pixel value of each pixel in the replaced projected raster image is compared with the pixel value of the corresponding pixel in the candidate ground model, and the lower pixel value of the two is used as the pixel value of the corresponding pixel of the ground model, thereby obtaining the ground model. The above process of obtaining the ground model can be expressed by formula (1):

[0119]

[0120] Among them, D i is the pixel value of the i-th pixel in the ground model, a i is the pixel value of the i-th pixel in the replaced projected raster image, tolerance a Estimated value for the water level.

[0121] In this embodiment, the height mode in the projected raster image is first determined, and then a horizontal plane estimation value is generated based on the height mode and a preset mode threshold. Compared with directly generating a ground model using the height mode, the pixel values ​​of pixel points in the ground model are more accurate when the ground model is generated using the horizontal plane estimation value.

[0122] Furthermore, the specific steps of generating the ground model according to the pixel value of each pixel point in the projected raster image and the estimated value of the horizontal plane in the above step S203 are introduced:

[0123] Optionally, traverse each pixel point in the projected raster image, and for the first current pixel point traversed, determine whether the pixel value of the first current pixel point is greater than the horizontal plane estimation value. If so, replace the pixel value of the first current pixel point with the horizontal plane estimation value to obtain the pixel value of the pixel point corresponding to the first current pixel point in the ground model.

[0124] Among them, if the pixel value of the first current pixel point is greater than the horizontal plane estimation value, it means that the first current pixel point is a non-ground pixel point. If the pixel value of the first current pixel point is less than or equal to the horizontal plane estimation value, it means that the first current pixel point is a ground pixel point.

[0125] In this embodiment, by traversing each pixel point in the projected raster image and replacing the pixel value of each pixel point whose pixel value is greater than the horizontal plane estimation value with the horizontal plane estimation value, the pixel value of the corresponding pixel point in the ground model is obtained.

[0126] The above explains how to generate a ground model based on a projected raster image. Next, we will introduce how to update the ground model based on a projected raster image. Figure 3 This is a schematic diagram of a process for updating a ground model provided in an embodiment of the present application. Figure 3 This section describes the steps for updating the ground model.

[0127] S301, determining whether there are pixels without data in the projected raster image.

[0128] The pixel value of the pixel without data is missing, or an abnormal situation occurs. The abnormal situation is that the pixel value exceeds the preset range threshold.

[0129] S302. If so, replace the pixel value of the data-free pixel in the projected raster image with the pixel value of the corresponding pixel in the ground model before updating to obtain the updated projected raster image, and compare the pixel value of each pixel in the updated projected raster image with the pixel value of the corresponding pixel in the ground model before updating, and take the lower pixel value as the pixel value of the corresponding pixel in the ground model.

[0130] If there are pixels without data in the projected raster image, in order to ensure that there will be no anomalies in the subsequent pixel value comparison, it is necessary to replace the pixel values ​​of the pixels without data in the projected raster image with the pixel values ​​of the corresponding pixels in the ground model before the update. The ground model before the update is the ground model that already existed before the current projected raster image was obtained.

[0131] S303, if not, compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and use the lower pixel value as the pixel value of the corresponding pixel point in the ground model.

[0132] Among them, using the low pixel value as the pixel value of the corresponding pixel point in the ground model will not interfere with the subsequently determined stacking area.

[0133] It is worth noting that the projected raster images at different positions in the target area can be iteratively obtained, and then the pixel points at the corresponding positions in the ground model are updated according to the coordinate positions of each pixel point in the projected raster image obtained each time, so as to obtain the overall ground model in the target area. By iteratively updating the ground model at the local position in the target area, the amount of calculation of the electronic equipment can be reduced, and the pressure of collecting the projected raster images can be reduced.

[0134] In this embodiment, by determining whether there are data-free pixels in the projected raster image and updating the projected raster image, interference of data-free pixels on the comparison results is avoided, and the lower pixel value of the pixel in the updated projected raster image and the pixel in the ground model before the update is selected as the pixel value of the corresponding pixel in the ground model. This can eliminate the tolerance in estimating the pixel value of the ground model pixel, retain a more realistic height value of the ground, and thereby improve the accuracy of the stacking area division.

[0135] It should be understood that if the area where the pixel value of each pixel point in the ground model is lower than the pixel value of each pixel point in the projected raster image is directly divided into a stacking area, the stacking area division may be inaccurate because multiple stacks are connected to form a tight stack. Therefore, it is necessary to obtain a candidate area where there must be a stack by calculation, and determine the stacking area in the ground model based on the candidate area.

[0136] Therefore, after determining the ground model, the specific steps of how to determine the area to be selected according to the projected grid image, the ground model and the preset error tolerance threshold in the above step S104 are introduced next.

[0137] Optionally, the pixel points in the ground model are traversed, and for the traversed second current pixel point, the difference between the pixel value of the pixel point corresponding to the second current pixel point in the projected raster image and the pixel value of the second current pixel point is calculated.

[0138] Optionally, if the difference between the pixel value of the pixel point corresponding to the second current pixel point in the projected raster image and the pixel value of the second current pixel point is greater than 0, it means that the second current pixel point can correspond to a non-ground pixel point in the projected raster image. If the difference between the pixel value of the pixel point corresponding to the second current pixel point in the projected raster image and the pixel value of the second current pixel point is less than or equal to 0, it means that the second current pixel point can correspond to a ground pixel point in the projected raster image.

[0139] As an optional implementation, the boundary of the pixel points whose difference is greater than 0 is the outer contour of the stack.

[0140] Optionally, if the difference is greater than a preset error tolerance threshold, the second current pixel point is taken as a pixel point in a to-be-selected area.

[0141] Optionally, in the same projected raster image, the larger the preset error tolerance threshold, the fewer pixels in the area to be selected, and the smaller the preset error tolerance threshold, the more pixels in the area to be selected. Setting the preset error tolerance threshold can filter out pixels that are stuck together due to close stacking.

[0142] As an optional implementation, the electronic device can start traversing from the first pixel point to the last pixel point of the ground model. When there is a pixel point whose corresponding difference is greater than a preset fault tolerance threshold, it is used as a pixel point in the selected area. If there is a pixel point whose corresponding difference is less than or equal to the preset fault tolerance threshold, it is used as a pixel point in the non-selected area. The boundary line of the selected area is the line connecting the boundaries between the pixel points in the selected area and the pixel points in the non-selected area. It is determined whether multiple pixel points whose corresponding difference is greater than the preset fault tolerance threshold are connected. If so, the multiple pixel points belong to the same selected area.

[0143] Figure 4 is a schematic diagram of a candidate area provided in an embodiment of the present application. Figure 4 , the pixels in the dotted line part are the pixels to be selected, and it can be seen that the selected area is a partial stacking area. The difference between the pixel value of the pixel point in the dotted line part and the pixel value of the second current pixel point is greater than 0, and the solid line part is the selected area corresponding to the dotted line part.

[0144] In this embodiment, by traversing the pixel points in the ground model and calculating the difference between the pixel value of the pixel point corresponding to the traversed second current pixel point in the projected raster image and the pixel value of the second current pixel point, the pixel points of the selected area are determined according to the comparison result of the difference and the preset fault tolerance threshold, thereby filtering out the interfering pixel points. Since the selected area must belong to the stacking area, the stacking area is divided and determined according to the selected area, so that the division result is accurate.

[0145] Figure 5 1 is a flow chart of a method for determining a stacking area provided in an embodiment of the present application. After the candidate areas are determined, the stacking area in the ground model is determined according to each candidate area in the above step S105.

[0146] S501, dilate and invert the selected area to obtain a background area.

[0147] Specifically, the region to be selected is first dilated, and then the region after dilation is inverted to obtain the background region. The dilation process may be as follows: a pixel block is pre-set, the pixel block has a core pixel, the core pixel of the pixel block is sequentially placed on each pixel point in the region to be selected, and all pixel points covered by the pixel block are used as pixel points included in the region after dilation of the region to be selected.

[0148] Optionally, since the dilation and inversion is performed on the selected area, the background area is the ground area.

[0149] S502: Determine a plurality of first water filling points according to the distances between edge pixels in the background area and pixels in each of the candidate areas, and use the background area as a second water filling point.

[0150] The edge pixel points in the background area are the pixel points located at the edge of the background area. There are two situations for the pixel points: one is that the pixel points are located at the edge of the target area, and the other is that the pixel points are adjacent to the pixel points in the selected area.

[0151] Specifically, each candidate area is traversed, and for the current candidate area traversed, the shortest distance between each pixel point in the current candidate area and the edge pixel point in the background area is calculated, and the pixel point in the current candidate area corresponding to the maximum value of the shortest distance is used as a first water injection point.

[0152] Optionally, all pixel points in the background area are used as second water filling points.

[0153] S503: Based on the multiple first water injection points and the second water injection points, determine the stacking area in the ground model according to the watershed algorithm.

[0154] The watershed algorithm is used to find the peaks and valleys of the pixel values ​​of each pixel point in the ground model, so as to segment and determine the stacking area of ​​the ground model. Specifically, water is injected into multiple first water injection points and second water injection points at the same time, and the intersection of the water injected by each water injection point is used as the segmentation boundary, and then the segmentation boundary and the boundary line of the selected area are combined as the dividing line of the stacking area. The dividing line can be the corresponding dividing line between the first water injection point and the second water injection point, or the corresponding dividing line between multiple first water injection points, or the dividing line between multiple first water injection points and second water injection points.

[0155] As an optional implementation, the pixel points in the selected area can be used as a mask in combination with a watershed algorithm to determine the stacking area in the ground model, so as to reduce the amount of calculation and improve the calculation efficiency.

[0156] In this embodiment, the background area is obtained by dilating and inverting the selected area, and the first water injection point is determined according to the distance between the pixel points in the background area and the selected area. The background area is used as the second water injection point to reduce the amount of calculation and avoid the appearance of a large number of interfering boundary lines. Finally, based on multiple first water injection points and second water injection points, the stacking area in the ground model is determined according to the watershed algorithm, thereby avoiding the problem of inaccurate division of the stacking area caused by multiple stacks connected to form a tight stack.

[0157] Next, before determining the stacking area in the target area according to the stacking area in the ground model in the above step S105, the following steps may be performed. Figure 6 It is a flowchart of a method for filtering out interference areas provided in an embodiment of the present application.

[0158] S601, traverse each stacking area, and for the current stacking area traversed, input the pixel value of each pixel point in the current stacking area and the pixel value of the corresponding pixel point in the projected raster image into a pre-trained instance partitioning model, and output the repose angle parameters, area parameters and minimum bounding rectangle parameters of each stacking area.

[0159] Among them, the instance partitioning model can determine the repose angle parameters, area parameters and minimum bounding rectangle parameters of each stacking area according to the pixel values ​​of the current stacking area and the pixel points in the projected raster image.

[0160] S602: Determine whether the current stacking area is an interference area according to the angle of repose threshold, the area threshold, the minimum bounding rectangle threshold, the angle of repose parameter, the area parameter and the minimum bounding rectangle parameter.

[0161] Specifically, determine whether the angle of repose parameter exceeds the angle of repose threshold, if so, the current stacking area is an interference area, and / or determine whether the area parameter exceeds the area threshold, if so, the current stacking area is an interference area, and / or determine whether the minimum enclosing rectangle parameter exceeds the minimum enclosing rectangle threshold, if so, the current stacking area is an interference area.

[0162] Exemplarily, the angle of repose threshold may be 85, the area threshold may be 100, and the minimum bounding rectangle threshold may indicate that the aspect ratio is greater than 10. The interference area may be an area where the angle of repose parameter is greater than 85, or the area parameter is less than 100, and the minimum bounding rectangle parameter indicates that the aspect ratio is greater than 10.

[0163] S603: If yes, filter out the interference area.

[0164] Specifically, the pixels in the interference area are removed from the pixels in the stacking area.

[0165] Among them, the interference areas may be areas such as cranes and houses.

[0166] In this embodiment, the repose angle parameter, area parameter and minimum bounding rectangle parameter of each stacking area are output through a pre-trained instance partitioning model, and interference areas are filtered out according to the above parameters and corresponding thresholds, thereby improving the accuracy of the stacking area.

[0167] As an optional implementation, the pixel values ​​of the pixels in the ground model can also be partially changed. This method can be applied before updating the ground model based on the projected raster image. Figure 7 Introduce the above methods:

[0168] S701. Obtain local change parameters input by a user, where the local change parameters include a range of changed pixels and a changed pixel value of the changed pixels.

[0169] The changed pixels are the pixels in the ground model.

[0170] S702: Determine the pixels to be changed in the ground model according to the range of the changed pixels.

[0171] S703: Replace the pixel value of the pixel to be changed with the changed pixel value.

[0172] As an optional implementation, a first mask can be constructed based on the range of pixels to be changed, the first mask of the pixels to be changed is set to 0, the first mask of other pixels is set to 1, the mask of each pixel is multiplied by the pixel value to obtain the first pixel value of each pixel, and the pixels with non-0 pixel values ​​are retained as the first pixel cluster. A second mask is constructed based on the range of pixels to be changed, the second mask of the pixels to be changed is set to the changed pixel value, and the second mask of other pixels is 0. The pixels with non-0 pixel values ​​are retained as the second pixel cluster, and the first pixel cluster is combined with the second pixel cluster to form an updated ground model.

[0173] It is worth noting that after obtaining the local change parameters input by the user and changing the pixel values ​​of the pixels in the ground model according to the local change parameters, the ground model is no longer updated according to the pixel values ​​of the pixels in the corresponding area in the projected raster image.

[0174] In this embodiment, by obtaining the local change parameters input by the user, the pixels to be changed in the ground model are determined according to the range of the changed pixels, and the pixel values ​​of the pixels to be changed are replaced with the changed pixel values. This is suitable for situations where a ground model for special circumstances needs to be constructed, so that the ground model fits the actual ground height and the stacking area is more accurate.

[0175] Based on the same inventive concept, an embodiment of the present application also provides a ground stack determination device corresponding to the ground stack determination method. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned ground stack determination method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0176] Reference Figure 8As shown, it is a structural schematic diagram of a ground stacking determination device provided in an embodiment of the present application, the device includes: an acquisition module 801, a judgment module 802, a generation and update module 803, a first determination module 804 and a second determination module 805; wherein:

[0177] The acquisition module 801 is used to acquire a projected grid image in the target area. The projected grid image is obtained by projecting the point cloud in the target area. The pixel value of each pixel point in the projected grid image is the height value of the point cloud corresponding to the pixel point.

[0178] A determination module 802 is used to determine whether there is a ground model;

[0179] Generate an update module 803, for updating the ground model according to the projected raster image if yes, otherwise, generate a ground model according to the projected raster image, wherein the pixel value of the pixel point corresponding to the non-ground pixel point in the projected raster image in the ground model is the pixel value corresponding to the ground pixel point;

[0180] A first determination module 804 is used to determine at least one area to be selected in the ground model according to the projected grid image, the ground model and a preset fault tolerance threshold, where the area to be selected is a partial stacking area;

[0181] The second determination module 804 is used to determine the stacking area in the ground model according to each candidate area based on the watershed algorithm, and determine the stacking area in the target area according to the stacking area in the ground model.

[0182] Optionally, the generation update module 803 is specifically used for:

[0183] Determine the majority of heights in a projected raster image;

[0184] Generate a water level estimate based on the height mode and a preset mode threshold;

[0185] Generate a ground model based on the pixel value of each pixel in the projected raster image and the estimated value of the horizontal plane.

[0186] Optionally, the generation update module 803 is specifically used for:

[0187] Traverse each pixel point in the projected raster image, and for the first current pixel point traversed, determine whether the pixel value of the first current pixel point is greater than the horizontal plane estimation value. If so, replace the pixel value of the first current pixel point with the horizontal plane estimation value to obtain the pixel value of the pixel point corresponding to the first current pixel point in the ground model.

[0188] Optionally, the generation update module 803 is specifically used for:

[0189] Determine whether there are pixels with no data in the projected raster image;

[0190] If yes, then replace the pixel value of the pixel point without data in the projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, obtain the updated projected raster image, and compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and take the lower pixel value as the pixel value of the corresponding pixel point in the ground model;

[0191] If not, then compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and use the lower pixel value as the pixel value of the corresponding pixel point in the ground model.

[0192] Optionally, the first determining module 804 is specifically configured to:

[0193] Traversing the pixel points in the ground model, for the traversed second current pixel point, calculating the difference between the pixel value of the pixel point corresponding to the second current pixel point in the projected raster image and the pixel value of the second current pixel point;

[0194] If the difference is greater than the preset error tolerance threshold, the second current pixel point is taken as a pixel point in a candidate area.

[0195] Optionally, the second determining module 805 is specifically configured to:

[0196] Dilate and invert the selected area to obtain the background area;

[0197] Determine a plurality of first water filling points according to the distance between the edge pixel points in the background area and each pixel in each candidate area, and use the background area as the second water filling point;

[0198] Based on the plurality of first water injection points and the second water injection points, a stacking area in the ground model is determined according to a watershed algorithm.

[0199] Optionally, the second determining module 805 is further configured to:

[0200] Traverse each stacking area, and for the current stacking area traversed, input the pixel value of each pixel point in the current stacking area and the pixel value of the corresponding pixel point in the projected raster image into the pre-trained instance partitioning model, and output the repose angle parameter, area parameter and minimum bounding rectangle parameter of each stacking area;

[0201] Determine whether the current stacking area is an interference area according to the angle of repose threshold, area threshold, minimum bounding rectangle threshold, angle of repose parameter, area parameter and minimum bounding rectangle parameter;

[0202] If so, filter out the interfering area.

[0203] Optionally, the generation update module 803 is specifically used for:

[0204] Obtaining local change parameters input by the user, the local change parameters including the range of changed pixels and the changed pixel values ​​of the changed pixels;

[0205] Determine the pixel points to be changed in the ground model according to the range of the changed pixel points;

[0206] Replace the pixel value of the pixel to be changed with the changed pixel value.

[0207] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0208] The present application also provides an electronic device, such as Fig. 9 , which is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, includes: a processor 901, a memory 902 and a bus. The memory 902 stores machine-readable instructions executable by the processor 901 (for example, Figure 8 In the device, the execution instructions corresponding to the acquisition module 801, the judgment module 802, the generation and update module 803, the first determination module 804 and the second determination module 805 are generated, etc.), when the computer device is running, the processor 901 communicates with the memory 902 through a bus, and when the machine-readable instructions are executed by the processor 901, the above-mentioned ground stacking determination method is executed.

[0209] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned ground stack determination method are executed.

[0210] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0211] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program code.

[0212] The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A method for determining ground stacking, characterized in that: The method comprises: Acquire a projected grid image in the target area, wherein the projected grid image is obtained by projecting a point cloud in the target area, and the pixel value of each pixel point in the projected grid image is the height value of the point cloud corresponding to the pixel point; Determine whether there is a ground model; If yes, then update the ground model according to the projected raster image; otherwise, generate a ground model according to the projected raster image, wherein the pixel value of the pixel point corresponding to the non-ground pixel point in the projected raster image in the ground model is the pixel value corresponding to the ground pixel point; Determine at least one area to be selected in the ground model according to the projected grid image, the ground model and a preset fault tolerance threshold, wherein the area to be selected is a partial stacking area; According to each of the candidate areas, based on a watershed algorithm, a stacking area in the ground model is determined, and according to the stacking area in the ground model, a stacking area in the target area is determined.

2. The method for determining ground stacking according to claim 1, characterized in that: The generating of the ground model according to the projected raster image comprises: determining a height mode in the projected raster image; Generate a water level estimate based on the height mode and a preset mode threshold; The ground model is generated according to the pixel value of each pixel point in the projected raster image and the horizontal plane estimation value.

3. The method for determining ground stacking according to claim 2, characterized in that: The generating the ground model according to the pixel value of each pixel point in the projected raster image and the horizontal plane estimation value comprises: Traverse each pixel point in the projected raster image, and for the first current pixel point traversed, determine whether the pixel value of the first current pixel point is greater than the horizontal plane estimation value; if so, replace the pixel value of the first current pixel point with the horizontal plane estimation value to obtain the pixel value of the pixel point corresponding to the first current pixel point in the ground model.

4. The method for determining ground stacking according to claim 1, characterized in that: The updating of the ground model according to the projected raster image comprises: Determine whether there are pixels without data in the projected raster image; If yes, then replace the pixel value of the pixel point without data in the projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, to obtain the updated projected raster image, and compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and take the lower pixel value as the pixel value of the corresponding pixel point in the ground model; If not, then compare the pixel value of each pixel point in the updated projected raster image with the pixel value of the corresponding pixel point in the ground model before updating, and use the lower pixel value as the pixel value of the corresponding pixel point in the ground model.

5. The method for determining ground stacking according to claim 1, characterized in that: The step of determining the area to be selected according to the projected grid image, the ground model and a preset error tolerance threshold comprises: Traversing the pixel points in the ground model, and for the traversed second current pixel point, calculating the difference between the pixel value of the pixel point corresponding to the second current pixel point in the projected raster image and the pixel value of the second current pixel point; If the difference is greater than the preset error tolerance threshold, the second current pixel point is taken as a pixel point in a candidate area.

6. The method for determining ground stacking according to claim 1, characterized in that: The step of determining the stacking area in the ground model based on the watershed algorithm according to each of the selected areas includes: Dilate and invert the selected area to obtain a background area; Determine a plurality of first water filling points according to the distance between the edge pixel points in the background area and each pixel in each of the to-be-selected areas, and use the background area as the second water filling point; Based on the plurality of the first water injection points and the second water injection points, a stacking area in the ground model is determined according to the watershed algorithm.

7. The method for determining ground stacking according to claim 1, characterized in that: Before determining the stacking area in the target area according to the stacking area in the ground model, the method includes: Traversing each stacking area, for the current stacking area traversed, inputting the pixel value of each pixel point in the current stacking area and the pixel value of the corresponding pixel point in the projected raster image into a pre-trained instance partitioning model, and outputting the repose angle parameter, area parameter and minimum bounding rectangle parameter of each stacking area; Determine whether the current stacking area is an interference area according to the angle of repose threshold, the area threshold, the minimum bounding rectangle threshold, the angle of repose parameter, the area parameter and the minimum bounding rectangle parameter; If so, the interference area is filtered out.

8. The method for determining ground stacking according to claim 1, characterized in that: The method further comprises: Acquire local change parameters input by a user, wherein the local change parameters include a range of changed pixels and a changed pixel value of the changed pixels; Determining the pixel points to be changed in the ground model according to the range of the changed pixel points; The pixel value of the pixel to be changed is replaced by the changed pixel value.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor executes the machine-readable instructions to perform the steps of the ground stack determination method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the ground stack determination method as claimed in any one of claims 1 to 8.

Images