Tracking Method and Device for Obtaining Soil Flow Direction Based on Image Recognition

Abstract

The present invention relates to the technical field of engineering surveying, and particularly to a tracking method and device for obtaining soil flow direction based on image recognition. The construction site is surveyed by means of drone oblique photography; according to the images of the construction site and the inspection point data obtained from the survey, the earthwork area in the earthwork operation area is determined; based on the images of the earthwork area, the soil types involved in the earthwork operation area are determined; based on the color values corresponding to the soil types, the potential earthwork areas within the construction site range are determined; based on the increment of the digital elevation model and the soil types, the excavation amounts of the various soil types contained in the earthwork and the flow directions within the operation area are determined; the earthwork area includes an earthwork excavation area and an earthwork accumulation area; the area of the potential earthwork area is greater than the earthwork threshold. In this way, the problems of large workload, low efficiency, large calculation error, high cost, etc. in the monitoring of soil flow direction during the earthwork excavation process are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering surveying, and particularly to a tracking method and device for obtaining soil flow direction based on image recognition. Background Art

[0002] Earthwork excavation is an essential part of engineering construction projects. In the current earthwork excavation process, the monitoring means of earthwork flow direction mainly rely on manual work, resulting in inaccurate earthwork flow direction results, large errors, low work efficiency, and heavy workload. In addition, the process of earthwork flow direction cannot be monitored, and there are also significant gaps in tracing the results of earthwork flow direction.

[0003] In view of the above problems, the present invention proposes a tracking method and device for obtaining soil mass flow direction based on image recognition, which can be used for automatic tracking and tracing of soil flow direction, and solves the problems of low tracking efficiency, large result errors, and heavy workload in the prior art for tracking soil flow direction. Summary of the Invention

[0004] At least some aspects and advantages of the present invention will be set forth in part in the description that follows, or may be obvious from the description, or may be obtained by practicing the subject matter of the present disclosure.

[0005] According to a first aspect of the present invention, a tracking method for obtaining soil flow direction based on image recognition includes:

[0006] Measuring a construction site by means of drone oblique photography;

[0007] Determining an earthwork area in the earthwork operation area according to the images of the construction site and the inspection point data obtained by the measurement;

[0008] Based on the images of the earthwork area, determining the soil types involved in the earthwork operation area;

[0009] Based on the color values corresponding to the soil types, determining potential earthwork areas within the scope of the construction site;

[0010] Based on the increment of the digital elevation model and the soil types, determining the excavation volume of each soil type included in the earthwork and the flow direction within the operation area;

[0011] The earthwork area includes an earthwork excavation area and an earthwork stacking area;

[0012] The area of the potential earthwork area is greater than the earthwork threshold.

[0013] According to an embodiment of the present invention, the determining of the earthwork area in the earthwork operation area of the construction site includes the following steps:

[0014] Align the images of the construction site based on the checkpoint data, and determine several regions where the color value change of the pixels is greater than the first preset value and the area of the region is greater than the second preset value based on pixel comparison as the first operation region;

[0015] Match the images within the first operation region based on the images of the preset soil types to obtain the earthwork regions in the earthwork operation region;

[0016] The earthwork region matches the images of at least one preset soil type.

[0017] According to an embodiment of the present invention, the steps for determining the soil types involved in the earthwork operation region include the following:

[0018] Based on the meteorological data during the measurement of the construction site, sort the historical meteorological data from high to low according to the approximation degree. The meteorological data includes 24-hour precipitation, temperature, and wind speed;

[0019] Obtain the image data of the soil samples tested under the meteorological data conditions with the highest approximation degree as the source soil image data;

[0020] Determine the soil types included in the earthwork region according to the characteristic pixel values of the source soil image data and the image of the earthwork region;

[0021] The characteristic pixel value of the source soil data is the average value of the pixel values of all pixel points in the source soil image;

[0022] The steps for determining the soil types included in the earthwork region include:

[0023] Calculate the difference between the pixel point values included in the image of the earthwork region and the characteristic pixel values point by point, and obtain the average value of the differences between the image of the earthwork region and the characteristic pixel values as the pixel difference value;

[0024] When the pixel difference value is lower than the third preset value, the soil in the earthwork region is the source soil type;

[0025] The difference between the pixel point value and the characteristic pixel value is the Euclidean distance between the pixel color value and the color value of the characteristic pixel value when the pixel color value is represented by the rgb three primary colors.

[0026] According to an embodiment of the present invention, the steps for obtaining the potential earthwork region include:

[0027] Obtain the source soil data corresponding to the soil type according to the soil type;

[0028] Identify the potential earthwork region within the construction site scope according to the source soil data to obtain the potential earthwork region;

[0029] The potential earthwork area does not include the earthwork operation area, and the pixel difference from at least one source soil data is less than the fourth preset value;

[0030] The calculation process of the pixel difference includes:

[0031] Calculate the difference between the pixel values included in the image of the earthwork area and the characteristic pixel values of the source soil data point by point, and obtain the average value of the difference between the image of the earthwork area and the characteristic pixel values as the pixel difference;

[0032] Sort the source soil data from high to low according to the pixel difference, and obtain the source soil type with the smallest pixel difference and lower than the fourth preset value as the soil type of the potential earthwork area;

[0033] The difference between the pixel value and the characteristic pixel value is the Euclidean distance between the color value of the pixel and the characteristic pixel value.

[0034] According to an embodiment of the present invention, the determination of the excavation volume of each soil type included in the earthwork and the flow direction in the operation area includes:

[0035] Obtain the first elevation model according to the UAV oblique photography method;

[0036] Obtain the second elevation model obtained by the UAV oblique photography method from the database for the most recent time;

[0037] Obtain the difference model according to the first elevation model and the second elevation model;

[0038] Determine the earthwork excavation area according to the elevation reduction area and the relative elevation in the difference model, and determine the earthwork stacking area according to the elevation increase area and the relative elevation in the difference model;

[0039] Determine the initial position of the soil flow direction and the destination of the soil flow direction according to the earthwork type;

[0040] The relative elevation is calculated based on the elevation difference between the earthwork area and the adjacent area.

[0041] According to an embodiment of the present invention, according to the reduction value of the earthwork volume in the earthwork excavation area and the earthwork increase amount in the associated earthwork stacking area, determine the allocation amount of the excavated earthwork volume in the earthwork excavation area to the earthwork stacking area, and the associated earthwork stacking area and the earthwork excavation area have the same soil type.

[0042] According to an embodiment of the present invention, the determination of the destination of the soil flow direction and the destination of the soil flow direction according to the earthwork type includes:

[0043] Obtain the earthwork stacking area with the same earthwork type as the earthwork excavation area;

[0044] When the number of earthwork stacking areas is 1, the earthwork stacking area is the destination of the earthwork excavation area;

[0045] When the number of earthwork stacking areas is greater than 1, the distribution amount of the earthwork excavation area to the earthwork stacking area is determined according to the distance between the earthwork stacking area and the earthwork excavation area.

[0046] According to an embodiment of the present invention, the determination process of the distribution amount of the earthwork excavation area to the earthwork stacking area includes:

[0047] Determine the initial distribution amount according to the transportation distance of the earthwork stacking area, and the initial distribution amount is negatively correlated with the earthwork stacking area;

[0048] Adjust the earthwork for each earthwork stacking area in ascending order of the transportation distance of the earthwork stacking area;

[0049] The transportation distance is the distance from the earthwork excavation area to the earthwork stacking area.

[0050] According to an embodiment of the present invention, the earthwork adjustment includes the following steps:

[0051] Obtain the distribution amount of the current earthwork stacking area and the earthwork increment determined based on the difference model;

[0052] When the distribution amount of the earthwork stacking area is greater than the earthwork increment, obtain the difference value of the earthwork quantity;

[0053] When the difference value of the earthwork quantity is greater than the fifth threshold value, use the difference between the difference value of the earthwork quantity and the fifth threshold value as the earthwork to be distributed, and distribute the earthwork to be distributed within the earthwork stacking area sequence;

[0054] The earthwork stacking area sequence includes earthwork stacking areas with a transportation distance greater than that of the current earthwork stacking area.

[0055] According to a second aspect of the present invention, an electronic device includes a processor and a memory; the memory is used to store a program; the processor executes the program to implement the tracking method for obtaining the soil flow direction based on image recognition as described in the first aspect. Brief Description of the Drawings

[0056] Figure 1 Shows a schematic flow chart of the tracking method for obtaining the soil flow direction based on image recognition. Detailed Embodiments

[0057] Now, the content of the present disclosure will be described with reference to several exemplary embodiments. It should be understood that these embodiments are described only to enable those of ordinary skill in the art to better understand and thus implement the content of the present disclosure, rather than implying any limitation to the scope of the present disclosure.

[0058] As used herein, the term "comprising" and its variants are to be construed as open-ended terms meaning "including but not limited to". The term "based on" is to be construed as "at least partially based on". The terms "one embodiment" and "an embodiment" are to be construed as "at least one embodiment". The term "another embodiment" is to be construed as "at least one other embodiment". The orientation or positional relationships indicated by the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "vertical", "horizontal", "lateral", "longitudinal", etc. are based on the orientation or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit that the indicated devices, elements or components must have a specific orientation, or be constructed and operated in a specific orientation. And, in addition to being used to represent orientation or positional relationships, some of the above terms may also be used to represent other meanings. For example, the term "upper" may also be used to represent a certain attachment relationship or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in the present application can be understood according to specific circumstances. In addition, the terms "installed", "set", "provided with", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral structure; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, or there may be internal communication between two devices, elements or components. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances. In addition, the terms "first", "second", etc. are mainly used to distinguish different devices, elements or components (the specific types and structures may be the same or different), and are not used to indicate or imply the relative importance and quantity of the indicated devices, elements or components. Unless otherwise specified, the meaning of "a plurality" is two or more.

[0059] In a first aspect, according to an embodiment of the present invention, a method for tracking the direction of soil flow based on image recognition includes:

[0060] Measuring a construction site by means of an unmanned aerial vehicle (UAV) oblique photography method;

[0061] Determining an earthwork area in the earthwork operation area according to the image of the construction site and the inspection point data obtained by the measurement;

[0062] Determining the soil type involved in the earthwork operation area based on the image of the earthwork area;

[0063] Determining potential earthwork areas within the construction site based on the color values corresponding to the soil type;

[0064] Based on the increment of the digital elevation model and the soil type, determine the excavation volume of each soil type contained in the earthwork and its flow direction within the operation area;

[0065] The earthwork area includes an earthwork excavation area and an earthwork stacking area;

[0066] The area of the potential earthwork area is greater than the earthwork threshold.

[0067] In this embodiment, a tracking method for obtaining the soil flow direction based on image recognition is proposed. First, use an unmanned aerial vehicle (UAV) to measure the construction site by the oblique photography method, and determine the earthwork area in the earthwork operation area through the images of the construction site obtained by photography and the checkpoint data; then, according to the image of the earthwork area, determine its soil type, and determine the potential earthwork area on the construction site according to the color value corresponding to the soil type; finally, obtain the earthwork increment and soil type of the excavation area and the stacking area by building a digital elevation model, and confirm the excavation volume of the soil types contained in the earthwork and the flow direction of each type of soil on the construction site.

[0068] Specifically, the UAV oblique photography method is a technology that uses a UAV equipped with an oblique photography device to collect images of the ground from an oblique perspective, and then realizes the reconstruction of a three-dimensional model through image processing technology. It changes the limitation that aerial survey remote sensing images can only be taken from the vertical direction in the past. The oblique photogrammetry technology collects data from different angles through multiple sensors, quickly and efficiently obtains rich data information, and truly reflects the objective situation of the ground.

[0069] Specifically, the checkpoint data is the checkpoint and its related information set at specific positions when the UAV executes a flight mission to verify the accuracy of information such as the flight path, altitude, speed, and coordinates. By reasonably setting the checkpoints, it can ensure that the UAV can fully cover the flight area and verify the accuracy of the flight path during photography to ensure the quality of the data captured by the UAV.

[0070] Specifically, the Digital Elevation Model (DEM) is a technology that digitally simulates the ground terrain through limited terrain elevation data, which can provide important geographical information support for construction site planning and construction, help engineers and planners better understand and cope with the environment and conditions of the construction site, and thus improve engineering efficiency and safety. In this application, a first digital elevation model of the construction site is established through the images of the construction site and the POS data collected by the UAV.

[0071] Specifically, based on the measured images of the construction site and the inspection point data, the earthwork areas in the earthwork operation area can be determined. For example, from the images, it can be clearly seen which positions have relatively regular soil pits and which positions around them have a large amount of earthwork piled up. Moreover, by setting inspection points in the areas around the earthwork, the earthwork areas in the earthwork operation area can be confirmed.

[0072] Specifically, through the images of the earthwork areas in the images, the soil types of the corresponding areas can be confirmed. There are many types of soils, and the visual characteristics presented by different types of soils are different, such as differences in color, texture, and shape, etc. Among them, most soil types can be distinguished through color differences. For example, black soil, loess, red soil, cinnamon soil, albic soil, etc. can be directly distinguished by color, while some soils that are visually similar in color, such as cinnamon soil and grey cinnamon soil, loess and yellow brown soil, etc., can be distinguished by the color values of the soils.

[0073] Specifically, through the different color values of the soils, the potential earthwork areas on the construction site can be determined. Normally, the earthwork stacking areas on the construction site are preset in advance. However, in actual scenarios, there will still be some abnormal weather and human errors that cause the earthwork to be piled up in non-preset areas, that is, there are potential earthwork areas. Generally speaking, the soil types of the earthwork transported from each earthwork excavation area are certain. Therefore, through the differences in the color values corresponding to each soil type, the earthwork transported from the earthwork excavation area in the non-preset area can be found, that is, the potential earthwork areas can be found.

[0074] Specifically, generally speaking, the stacking of earthwork will occupy a relatively large floor area in the stacking area. Therefore, the potential earthwork area is greater than a threshold value, which can be 10m 2 , or it can be 60m 2 , or it can be 200m 2 It needs to be determined according to the actual size of the construction site.

[0075] Specifically, knowing the soil types of the earthwork areas and the potential earthwork areas, the flow direction of the earthwork excavated from the earthwork areas can be traced according to the soil types, and the specific volume of the earthwork can also be calculated through the digital elevation model.

[0076] According to an embodiment of the present invention, the determination of the earthwork area in the earthwork operation area of the construction site includes the following steps:

[0077] Align the images of the construction site based on the inspection point data, and determine several areas where the color value change of the pixels is greater than the first preset value and the area is greater than the second preset value based on pixel comparison as the first operation area;

[0078] Match the images in the first working area based on the images of preset soil types to obtain the earthwork area in the earthwork operation area;

[0079] The earthwork area matches at least the images of one preset soil type.

[0080] In this embodiment, a specific method for determining the earthwork area in the earthwork operation area of a construction site is proposed. First, align the images of the construction site based on the checkpoint data, compare the color value changes of the pixels in the same area in different images, and divide the area where the change value of the compared pixels is greater than the first preset value and the area is greater than the second preset value into the first working area. The area in the first working area where the soil type is the same as that in the earthwork area is the earthwork area.

[0081] Specifically, in the earthwork area at the construction site, in the image before earthwork excavation, since the soil surface is covered, the color of the soil in the photo may be relatively single, and it is not easy to see the layers and color changes of the soil itself; in the image after excavation for a period of time, since the soil is directly exposed, the true color of the soil will be clearly shown in the image. In some special cases, such as encountering special soils like five-color soil, the photo after excavation will show more abundant colors, so there will be color value changes. In addition, the light and weather conditions during shooting will also affect the color of the photo. For example, on a sunny day, the color of the soil under direct sunlight may be more vivid; while on a cloudy or rainy day, the color of the soil may appear darker. Therefore, when there is an obvious change in the color value of the soil, that is, when the color value change of the soil is greater than the first preset value, it can be determined that this area is the earthwork area. For example, before excavation, the average rgb value of the soil color is 227, 177, 45, and after excavation, due to the soil being water-containing, the corresponding color may become 128, 64, 64; in this way, the rgb and the difference in change can be used to calculate whether it is the working area. Specifically, calculate dr^2 + dg^2 + db^2 = (227 - 128)^2 + (177 - 64)^2 + (45 - 64)^2. If this value is greater than the preset value, it means that work has occurred. If there is no change or the change is small, the possibility of work is small; if it is raining, then changing the reference soil color change value to the color of ordinary soil after rain can effectively overcome this defect.

[0082] Specifically, the first preset value needs to be determined according to the actual soil conditions of the construction site. In some earthwork areas where the soil color is relatively vivid, such as loess and black soil, a relatively large first preset value can be taken. In some earthwork areas where the soil color is relatively dull, the color value change shown in the picture is relatively small, and a relatively small first preset value can be taken.

[0083] Specifically, the reason why the area of the region needs to be greater than the second preset value is that the earthwork area is generally relatively large. Therefore, by setting a threshold for the area of the region, the interference caused by color value changes brought about by other smaller objects can be excluded.

[0084] According to an embodiment of the present invention, the steps for determining the soil type involved in the earthwork operation area are as follows:

[0085] Based on the meteorological data during the measurement of the construction site, sort the historical meteorological data from high to low according to the degree of approximation. The meteorological data includes 24-hour precipitation, temperature, and wind speed;

[0086] Obtain the image data of the soil sample tested under the meteorological data with the highest degree of approximation as the source soil image data;

[0087] Determine the soil type contained in the earthwork area according to the characteristic pixel value of the source soil image data and the image of the earthwork area;

[0088] The characteristic pixel value of the source soil data is the average value of the pixel values of all pixel points in the source soil image;

[0089] The steps for determining the soil type contained in the earthwork area include:

[0090] Calculate the difference between the pixel point value contained in the image of the earthwork area and the characteristic pixel value point by point, and obtain the average value of the difference between the image of the earthwork area and the characteristic pixel value as the pixel difference value;

[0091] When the pixel difference value is lower than the third preset value, the soil in the soil area is the source soil type;

[0092] The difference between the pixel point value and the characteristic pixel value is the Euclidean distance between the pixel color value and the characteristic pixel value when the pixel color value is represented by the rgb three primary colors.

[0093] In this embodiment, the steps for determining the soil type involved in the earthwork operation area are proposed. First, considering weather factors, based on the meteorological data during measurement, including data such as 24-hour precipitation, temperature, and wind speed, obtain the measured soil sample data under the meteorological data with the highest degree of approximation in the historical meteorological data as the source soil image data, and then determine the soil type contained in the earthwork area according to the characteristic pixel value of the image in the source soil image data and the image of the earthwork area.

[0094] Specifically, the characteristic pixel value is the mean value of the pixel values of all pixel points in the source soil image. Specifically, the method for determining the soil type included in the earthwork area is as follows: calculate the difference between the value of each pixel point in the earthwork area and the characteristic pixel value point by point, and take the mean value as the pixel difference value. When the pixel difference value is lower than the third threshold value, the soil type in this earthwork area is the soil type of the corresponding area in the source soil image.

[0095] Specifically, during photography, there will be obvious differences in the image data obtained under different meteorological conditions. Therefore, it is necessary to select the image of the soil sample data under the meteorological conditions closest to those in the database as the source soil image data. For example: if the meteorological conditions during this measurement are sunny, 33 degrees Celsius, and a southeast wind of level 7.5, then search for the image data with the most similar meteorological conditions in the historical measurement data as the source soil data.

[0096] Specifically, the smaller the pixel difference value, the closer the image of the earthwork area measured this time is to the source soil image data. When the pixel difference value is greater than the third threshold value, it is considered that the image of the earthwork area measured this time is not comparable to the source soil image data, and the soil type of the corresponding area in the source soil image data cannot be used as the soil type of the earthwork area. Therefore, the third threshold value is a sufficiently small value. The smaller the third threshold value, the more accurate the final result. However, considering the different soil types in different regions, the third threshold value needs to be determined according to different actual situations.

[0097] Specifically, when the difference between the pixel point value and the characteristic pixel value is that when the pixel color value is represented by the rgb three primary colors, the Euclidean distance between the pixel color value and the color value of the characteristic pixel value. That is, when calculating the difference between the pixel point value and the characteristic pixel value, it is necessary to calculate according to the Euclidean distance of the three color channels of r, g, and b respectively.

[0098] According to an embodiment of the present invention, the steps for obtaining the potential earthwork area include:

[0099] Obtain the source soil data corresponding to this soil type according to the soil type;

[0100] Identify the potential earthwork area for the construction site range according to the source soil data to obtain the potential earthwork area;

[0101] The potential earthwork area does not include the earthwork operation area, and the pixel difference value from at least one source soil data is less than the fourth preset value;

[0102] The calculation process of the pixel difference value includes:

[0103] Calculate the difference between the pixel point value included in the image of the earthwork area and the characteristic pixel value of the source soil data point by point, and obtain the mean value of the difference between the image of the earthwork area and the characteristic pixel value as the pixel difference value;

[0104] Sort the source soil data from high to low according to the pixel difference, and obtain the source soil type with the smallest pixel difference and lower than the fourth preset value as the soil type of the potential earthwork area;

[0105] The difference between the pixel point value and the characteristic pixel value is the Euclidean distance between the color value of the pixel and the characteristic pixel value.

[0106] In this embodiment, a specific method for obtaining the potential earthwork area is proposed: obtain the corresponding source soil data of the soil according to the soil type, then in the non-earthwork operation area, the area where the pixel difference from the source soil data is less than the fourth preset value is the potential earthwork area.

[0107] Specifically, when calculating the pixel difference, calculate the difference between the values of all pixel points included in the image of the earthwork area and the characteristic pixel value of the source soil data point by point, and obtain the average value of the difference between the image of the earthwork area and the characteristic pixel value of the source soil data as the pixel difference. Subsequently, sort the source soil data from high to low according to the pixel difference, and take the source soil type with the smallest pixel difference and lower than the fourth threshold as the soil type of the potential earthwork area.

[0108] Specifically, since it is necessary to judge the potential earthwork area, and the soil in the potential earthwork area is transported from the earthwork area, the corresponding source soil data of these soil types are obtained according to all soil types involved in the earthwork area, and the areas identified within the construction site that are similar in characteristics to the source soil data may be potential earthwork areas.

[0109] Specifically, since the soil in the potential earthwork area is of the same soil type as the soil in the earthwork excavation area, the pixel difference from the characteristic pixel value of any one of all the source soil data is similar, that is, the pixel difference needs to be less than the fourth preset value, and those greater than the fourth preset value are considered not to be potential earthwork areas.

[0110] Specifically, the difference between the pixel point value and the characteristic pixel value is the Euclidean distance between the color value of the pixel and the characteristic pixel value.

[0111] Specifically, for example: there are six areas a, b, c, d, e, f in the construction site, where a, b, c are earthwork excavation areas, d, e are preset earthwork stacking areas, and all soil types in areas a, b, c are m, n, j, k. Obtain the corresponding source soil data of the four soil types m, n, j, k, and then identify the earthwork within the construction site. If the average value of the pixel points in area f is less than the fourth preset value from the characteristic pixel value of any one of the four source soil data, then area f is considered a potential earthwork area. According to an embodiment of the present invention, the determination of the excavation volume of each soil type included in the earthwork and the flow direction within the operation area includes:

[0112] Obtain the first elevation model according to the UAV oblique photography method;

[0113] Obtain the second elevation model obtained by the UAV oblique photography method most recently from the database;

[0114] Obtain the difference model according to the first elevation model and the second elevation model;

[0115] Determine the earthwork excavation area according to the elevation reduction area and relative elevation in the difference model, and determine the earthwork stacking area according to the elevation increase area and relative elevation in the difference model;

[0116] Determine the initial position of the soil flow direction and the destination of the soil flow direction according to the soil type;

[0117] The relative elevation is calculated based on the elevation difference between the earthwork area and the adjacent area.

[0118] In this embodiment, a method for determining the excavation volume of each soil type included in the fixed earthwork and the flow direction within the operation area is proposed. First, obtain the first elevation model according to the measurement data, then obtain the second elevation model obtained by the most recent measurement from the database, obtain the difference model according to the two models, determine the earthwork excavation area according to the elevation reduction area and relative elevation in the difference model, and determine the earthwork stacking area according to the elevation increase area and relative elevation in the difference model. Finally, determine the initial position of the soil flow direction according to the soil type in the earthwork excavation area, and determine the destination of the soil flow direction according to the soil types in the earthwork excavation area and the earthwork stacking area.

[0119] Specifically, determining the earthwork excavation area according to the elevation reduction area and relative elevation in the difference model means that the altitude decreases and it is relatively higher than the surrounding altitude, belonging to the excavation area; if it is relatively higher than the surrounding altitude, even if the altitude decreases, it does not belong to the excavation area.

[0120] Specifically, for example, if the soil type in the earthwork excavation area obtained through the difference model is a, the soil type in the preset earthwork stacking area should also be a. The initial position of the soil flow direction is the earthwork excavation area, and the destination of the soil flow direction is the earthwork stacking area.

[0121] According to an embodiment of the present invention, determine the allocation amount of the excavated soil volume in the earthwork excavation area to the earthwork stacking area according to the reduction value of the earthwork volume in the earthwork excavation area and the earthwork increase amount in the associated earthwork stacking area, and the associated earthwork stacking area and the earthwork excavation area have the same soil type.

[0122] In this embodiment, determine the allocation amount from the earthwork excavation area to the earthwork stacking area according to the reduction amount of the earthwork in the earthwork excavation area and the increase amount of the earthwork in the corresponding earthwork stacking area.

[0123] Specifically, the associated earthwork stacking area refers to an earthwork stacking area with the same soil type as the earthwork excavation area.

[0124] According to an embodiment of the present invention, the determination of the initial position of the soil flow direction and the destination of the soil flow direction based on the soil type includes:

[0125] Obtain an earthwork stacking area with the same earthwork type as the earthwork excavation area;

[0126] When the number of earthwork stacking areas is 1, the earthwork stacking area is the destination of the earthwork excavation area;

[0127] When the number of earthwork stacking areas is greater than 1, determine the distribution amount of the earthwork excavation area to the earthwork stacking area according to the distance between the earthwork stacking area and the earthwork excavation area.

[0128] According to an embodiment of the present invention, the determination process of the distribution amount of the earthwork excavation area to the earthwork stacking area includes:

[0129] Determine the initial distribution amount according to the transportation distance of the earthwork stacking area, and the initial distribution amount is negatively correlated with the distance of the earthwork stacking area;

[0130] Adjust the earthwork for each earthwork stacking area in ascending order of the transportation distance of the earthwork stacking area;

[0131] The transportation distance is the distance from the earthwork excavation area to the earthwork stacking area.

[0132] According to an embodiment of the present invention, the earthwork adjustment includes the following steps:

[0133] Obtain the distribution amount of the current earthwork stacking area and the earthwork increment determined based on the difference model;

[0134] When the distribution amount of the earthwork stacking area is greater than the earthwork increment, obtain the difference value of the earthwork quantity;

[0135] When the difference value of the earthwork quantity is greater than the fifth threshold value, use the difference between the difference value of the earthwork quantity and the fifth threshold value as the earthwork to be distributed, and distribute the earthwork to be distributed within the earthwork stacking area sequence;

[0136] The earthwork stacking area sequence includes earthwork stacking areas with a transportation distance greater than that of the current earthwork stacking area.

[0137] In this embodiment, steps are proposed to determine the initial position of the soil flow direction and the destination of the soil flow direction based on the soil type. First, obtain the soil stacking area that is the same as the soil type in the soil excavation area. If the number of soil stacking areas is 1, then this soil stacking area is the destination of the soil excavation area. If the number of soil stacking areas is greater than 1, then determine the allocation amount according to the distance between each soil stacking area and the soil excavation area.

[0138] Specifically, the process of determining the allocation amount from the soil excavation area to the soil stacking area is as follows: Determine the initial allocation amount according to the transportation distance of the soil stacking area, that is, the distance between the soil stacking area and the soil excavation area. The farther the distance, the lower the allocation amount. Adjust the soil for each soil stacking area according to the transportation distance of the soil stacking area.

[0139] Specifically, the soil adjustment includes the following steps: Obtain the allocation amount of the current soil stacking area and the soil increment determined based on the difference model. When the allocation amount is greater than the soil increment, obtain the difference value between the allocation amount and the soil increment. When the difference value is greater than the fifth threshold, use the difference between the difference value of the soil amount and the fifth threshold as the soil to be allocated, and allocate the soil to be allocated to other preset soil stacking areas where the transportation distance is greater than the transportation distance of the current soil.

[0140] Specifically, the allocation amount is a reference value of the soil amount determined by the distance, indicating the approximate soil amount of a soil stacking area. Correspondingly, the farther away from the soil excavation area, the lower the allocation amount. For example: the soil amount in the soil excavation area is 1000 m 3 , and it is necessary to stack the excavated soil into three soil stacking areas A, B, and C. The distances from the soil excavation area to A, B, and C are 3:1:1. Then the allocation amount of soil stacking area A should be 600 m 3 , and the allocation amounts of soil stacking areas B and C should be 200 m 3 .

[0141] Specifically, in the increment of the soil stacking area obtained from the difference model, due to external factors such as thermal expansion and contraction, wind, and rain, there is a certain difference between the increment and the allocation amount.

[0142] Specifically, the difference value is the ratio of the soil increment to the allocation amount. When the difference value is greater than the increment and the ratio of the difference value to the increment is less than the fifth threshold, it is possible that the soil in the soil excavation area has been transported to other areas, and on-site investigation is required to prevent affecting the construction progress.

[0143] Specifically, when the difference value is greater than the fifth threshold, use the difference between the difference value and the fifth threshold as the soil to be allocated, and transport the soil to be allocated to the soil stacking area where the transportation distance is greater than the transportation distance of the current soil stacking area.

[0144] Specifically, the fifth threshold is determined according to the actual situation of the construction site and is preferably 1 / 2.

[0145] In a second aspect, the present invention provides an electronic device, including a processor and a memory; the memory is used to store a program; the processor executes the program to implement the method for tracking soil flow direction based on image recognition described in the first aspect.

[0146] The beneficial effects of the present invention are as follows: Through the soil flow direction tracking method of the present invention, the soil flow direction during the earthwork excavation process can be effectively and automatically monitored, greatly reducing the workload of manual monitoring, and improving the accuracy and efficiency of the monitoring results.

[0147] Those of ordinary skill in the art can realize that the modules and algorithm steps described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0148] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0149] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or modules can be in an electrical, mechanical or other forms.

[0150] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present invention.

[0151] In addition, in the embodiments of the present invention, the various functional modules can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0152] If the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method for sending / receiving energy-saving signals in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0153] The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, and should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the inventive concept. For example, the technical solution formed by mutually replacing the above-mentioned features with the (but not limited to) technical features with similar functions disclosed in the present application.

[0154] It should be understood that the magnitudes of the sequence numbers of the steps in the content of the present invention and the embodiments do not absolutely mean the sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention. For the purposes of illustration and description, the foregoing description of the implementation of the present disclosure has been given. The foregoing description is not exhaustive and is not intended to limit the present disclosure to the exact form disclosed. According to the above teachings, various deformations and modifications may exist, or various deformations and modifications may be obtained from the practice of the present disclosure. These embodiments are selected and described to illustrate the principles of the present disclosure and its practical applications, so that those skilled in the art can utilize the present disclosure in various embodiments and various modifications suitable for the specific purposes conceived.

Claims

1. A method for tracking soil flow direction based on image recognition, characterized in that: include: Surveying the construction site through drone oblique photography; Determine the earthwork area in the earthwork operation area based on the image and checkpoint data of the construction site obtained by measurement; Determine the soil type involved in the earthwork area based on the image of the earthwork area; Determine potential earthwork areas within the construction site based on the color values ​​corresponding to the soil types; Based on the increments and soil types of the digital elevation model, determine the excavation volume of each soil type contained in the earthwork and its flow direction within the work area; The earthwork area includes an earthwork excavation area and an earthwork accumulation area; The area of ​​the potential earthwork area is greater than the earthwork threshold; Determining the earthwork area in the earthwork operation area comprises the following steps: Aligning the images of the construction site based on the checkpoint data, and determining, based on pixel comparison, several regions where the color value change of the pixels is greater than a first preset value and the area is greater than a second preset value as first working regions; Matching the image in the first operation area based on the image of the preset soil type to obtain the earthwork area in the earthwork operation area; The earthwork area is matched with an image of at least one preset soil type; The steps of obtaining the potential earthwork area include: According to the soil type, source soil data corresponding to the soil type is obtained; Identify potential earthwork areas within the construction site based on source soil data to obtain potential earthwork areas; The potential earthwork area does not include an earthwork operation area, and the pixel difference between the potential earthwork area and at least one source soil data is less than a fourth preset value; The pixel difference calculation process includes: The difference between the pixel point value contained in the image of the earthwork area and the characteristic pixel value of the source soil data is calculated point by point, and the average value of the difference between the image of the earthwork area and the characteristic pixel value is obtained as the pixel difference value; Sort the source soil data from high to low according to the pixel difference, and obtain the source soil type with the smallest pixel difference and lower than a fourth preset value as the soil type of the potential earthwork area; The difference between the pixel point value and the characteristic pixel value is the Euclidean distance between the color value of the pixel and the characteristic pixel value.

2. The method for tracking soil flow direction based on image recognition according to claim 1, characterized in that: Determining the soil type involved in the earthwork area includes the following steps: Based on the meteorological data when measuring the construction site, the historical meteorological data are sorted from high to low according to the similarity, wherein the meteorological data includes 24-hour precipitation, temperature and wind speed; Acquire image data of soil samples tested and obtained under the meteorological data condition with the highest approximation as source soil image data; Determine the soil type contained in the earthwork area according to the characteristic pixel value of the source soil image data and the image of the earthwork area; The characteristic pixel value of the source soil data is the average of the pixel values ​​of all pixels in the source soil image; The soil types contained in the determined earthwork area include: The difference between the pixel point value and the characteristic pixel value contained in the image of the earthwork area is calculated point by point, and the average value of the difference between the image of the earthwork area and the characteristic pixel value is obtained as the pixel difference value; When the pixel difference is lower than a third preset value, the soil in the earthwork area is of the source soil type; The difference between the pixel point value and the characteristic pixel value is the Euclidean distance between the pixel color value and the color value of the characteristic pixel value when the color value of the pixel is represented by the three primary colors of RGB.

3. The method for tracking soil flow direction based on image recognition according to claim 1, characterized in that: The determination of the excavation volume of each soil type contained in the earthwork and the flow direction in the working area includes: The first elevation model is obtained according to the UAV oblique photography method; The second elevation model obtained by the most recent UAV oblique photography method is obtained from the database; obtaining a difference model according to the first elevation model and the second elevation model; The earthwork excavation area is determined according to the elevation reduction area and relative elevation in the difference model, and the earthwork accumulation area is determined according to the elevation increase area and relative elevation in the difference model; Determine the initial position and target location of soil flow according to the type of earthwork; The relative elevation is calculated based on the elevation difference between the earthwork area and the adjacent area.

4. The method for tracking soil flow direction based on image recognition as claimed in claim 3, characterized in that: The distribution amount of the excavated soil in the earthwork excavation area to the earthwork accumulation area is determined according to the reduction value of the earthwork amount in the earthwork excavation area and the increase of the earthwork in the associated earthwork accumulation area, wherein the associated earthwork accumulation area and the earthwork excavation area have the same soil type.

5. The method for tracking soil flow direction based on image recognition as claimed in claim 3, characterized in that: The initial position of the soil flow direction and the target location of the soil flow direction determined according to the earthwork type include: Acquire the earthwork accumulation area with the same earthwork type as the earthwork excavation area; When the number of earthwork accumulation areas is 1, the earthwork accumulation area is the destination of the earthwork excavation area; When the number of earth accumulation areas is greater than 1, the allocation amount of the earth excavation area to the earth accumulation area is determined according to the distance between the earth accumulation area and the earth excavation area.

6. The method for tracking soil flow direction based on image recognition as claimed in claim 5, characterized in that: The process of determining the distribution amount from the earthwork excavation area to the earthwork accumulation area includes: Determine the initial distribution amount according to the transportation distance of the earthwork accumulation area, wherein the initial distribution amount is negatively correlated with the earthwork accumulation area; Adjust the earthwork in each earthwork accumulation area in the order of transportation distance from the smallest to the largest; The transportation distance is the distance from the earth excavation area to the earth accumulation area.

7. The method for tracking soil flow direction based on image recognition as claimed in claim 6, characterized in that: The earthwork adjustment comprises the following steps: Obtain the current earthwork accumulation area allocation and earthwork increment determined based on the difference model; When the distribution amount in the earthwork accumulation area is greater than the earthwork increment, the difference value of the earthwork amount is obtained; When the difference value of the earthwork volume is greater than the fifth threshold, the difference between the difference value of the earthwork volume and the fifth threshold is used as the earthwork to be allocated, and the earthwork to be allocated is allocated within the earthwork accumulation area sequence; The transportation distance of the earthwork accumulation area included in the earthwork accumulation area sequence is greater than the transportation distance of the current earthwork accumulation area.

8. An electronic device, characterized in that: It includes a processor and a memory; the memory is used to store programs; the processor executes the program to implement the tracking method for obtaining soil flow direction based on image recognition as described in any one of claims 1-7.

Images