Buried pipe location estimation system

Abstract

To save labor and improve efficiency in estimation of a position where a buried pipe is buried.SOLUTION: A burying position estimation unit 42 estimates the position and depth of an underground buried structure based on a position measured by a survey position measuring device and an intensity pattern of a radio wave received by a radar survey device. A buried pipe determination unit 44 determines whether the underground buried structure continues linearly based on the position and depth of the underground buried structure estimated by the burying position estimation unit 42, and determines the underground buried structure determined to continue linearly as a buried pipe.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a buried pipe position estimation system for estimating the buried position of buried pipes such as water pipes, gas pipes, and electric wire pipes buried underground.

Background Art

[0002] Patent Document 1 describes a pipeline exploration method for exploring buried pipes using the reflection of radar waves.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The exploration method described in Patent Document 1 requires two measurements, one when a conductive liquid is injected into the pipeline and the other when it is not, which is time-consuming. Also, it cannot be applied when a liquid cannot be injected into the pipeline. In addition, since a skilled technician needs to visually analyze the obtained waveform image, the analysis work requires time and labor. An object of this invention is to solve such problems, for example.

Means for Solving the Problems

[0005] The buried pipe location estimation system comprises a radar exploration device that moves on the ground, irradiates radio waves into the ground, and receives radio waves reflected from underground structures; an exploration position measurement device that measures the position of the radar exploration device; and a buried pipe location estimation device that estimates the buried location of the buried pipe. The buried pipe location estimation device comprises a buried location estimation unit that estimates the position and depth of the underground structure based on the position measured by the exploration position measurement device and the intensity pattern of the radio waves received by the radar exploration device; and a buried pipe determination unit that determines whether the underground structure is linearly continuous based on the position and depth of the underground structure calculated by the buried location estimation unit, and determines that the underground structure determined to be linearly continuous is a buried pipe. Furthermore, the buried pipe location estimation device includes a three-dimensional model generation unit that generates a three-dimensional model based on the location and depth of the underground buried object estimated by the buried location estimation unit, for the underground buried object that the buried pipe determination unit has determined to be a buried pipe. , The three-dimensional model generation unit calculates a range in which the probability of the underground buried object being present exceeds a predetermined threshold, based on the location and depth of the underground buried object estimated by the buried object location estimation unit. It detects the contour of the calculated range, and for each line segment connecting two points on the detected contour, it calculates the rectangle with the maximum overlap with the range among the rectangles with the line segment as its diagonal. From the calculated rectangles, it removes any rectangles whose overlap with the other rectangles exceeds a predetermined threshold and whose overlap with the range is less than that of the other rectangles. Using the remaining rectangles, it generates a three-dimensional model of the underground buried object. The buried pipe location estimation device may further include a buried object discrimination unit that determines the type of buried object based on the intensity pattern of radio waves received by the radar exploration device. The buried location estimation unit may use artificial intelligence to estimate the location and depth of the buried object. Furthermore, the buried pipe location estimation system comprises a radar exploration device that moves on the ground, irradiates radio waves into the ground, and receives radio waves reflected from underground structures; an exploration position measuring device that measures the position of the radar exploration device; and a buried pipe location estimation device that estimates the buried location of the buried pipe. The buried pipe location estimation device includes a buried location estimation unit that estimates the position and depth of the underground structure based on the position measured by the exploration position measuring device and the intensity pattern of the radio waves received by the radar exploration device; a unit that determines whether the underground structure is linearly continuous based on the position and depth of the underground structure calculated by the buried location estimation unit; and for linearly continuous sections, it determines whether there is a buried pipe in the section based on the length of the section and the average value of the probability that the underground structure exists in the section calculated based on the position and depth of the underground structure estimated by the buried location estimation unit. The buried pipe location estimation device includes a buried pipe determination unit that calculates the probability of existence, and further comprises a three-dimensional model generation unit that generates a three-dimensional model based on the location and depth of the buried pipe for which the buried pipe determination unit has calculated the probability of existence, the three-dimensional model generation unit calculates a range in which the probability of existence of the buried object exceeds a predetermined threshold based on the location and depth of the buried object estimated by the buried location estimation unit, detects the contour of the calculated range, calculates the rectangle with the maximum overlap with the range among the rectangles with the line segment as the diagonal for each line segment connecting two points on the detected contour, removes the rectangles from the calculated rectangles whose overlap with the other rectangles exceeds a predetermined threshold and whose overlap with the range is less than that of the other rectangles, and generates a three-dimensional model of the buried object using the rectangles that were not removed. The probability of existence calculated by the buried pipe determination unit increases as the length of the section increases, and also increases as the average value increases, and the influence of the section length may be greater than the influence of the average value. The buried pipe determination unit may further calculate the probability of a buried object being present in a linearly continuous section, based on the length of the section and the average value of the probability that the buried object is present in the section, calculated based on the location and depth of the buried object estimated by the buried object location estimation unit. The probability of the presence of a buried object calculated by the buried pipe determination unit increases with increasing length of the section, and also increases with increasing average value, and the influence of the average value may be greater than the influence of the section length. [Effects of the Invention]

[0006] According to the aforementioned buried pipe location estimation system, analysis by skilled technicians becomes unnecessary, leading to labor savings and increased efficiency. Furthermore, it prevents oversights, improving on-site safety. [Brief explanation of the drawing]

[0007] [Figure 1] A schematic diagram showing an example of a buried pipe location estimation system. [Figure 2] A block diagram showing an example of a buried pipe location estimation device. [Figure 3] A graph showing an example of the intensity pattern of reflected waves. [Figure 4] A graph showing an example of the intensity pattern of reflected waves. [Figure 5] A graph showing an example of the intensity pattern of reflected waves. [Figure 6] This diagram shows an example of an overhead view of buried pipes generated based on a three-dimensional model. [Figure 7] A block diagram showing an example of a three-dimensional model generation unit. [Figure 8] A diagram showing an example of the range calculated by the range calculation unit. [Figure 9] A diagram showing an example of a region calculated by the region calculation unit. [Figure 10] A diagram showing an example of a contour detected by the contour detection unit. [Figure 11] A diagram showing an example of a line segment calculated by the rectangle calculation unit. [Figure 12] A diagram showing an example of a circle calculated by the rectangle calculation unit. [Figure 13] A diagram showing an example of a rectangle calculated by the rectangle calculation unit. [Figure 14] A diagram showing an example of a rectangle calculated by the rectangle calculation unit. [Figure 15] A diagram showing an example of a rectangle extracted by the rectangular extraction unit. [Figure 16] A block diagram showing an example of a buried pipe detection unit. [Figure 17] A diagram showing an example of the probability of existence calculated by the buried pipe detection unit. [Figure 18] A diagram showing an example of the probability of existence calculated by the buried pipe detection unit.

Best Mode for Carrying Out the Invention

[0008] As shown in FIG. 1, the buried pipe position estimation system 10 has, for example, a carriage 11, a radar exploration device 21, a exploration position measurement device 31, and a buried pipe position estimation device 41. The carriage 11 has, for example, wheels 12 and can move on the ground 80. The carriage 11 may be moved manually, may be towed and moved by an automobile or the like, or may move by itself.

[0009] The radar exploration device 21 is mounted on the carriage 11 and moves together with the carriage 11. The radar exploration device 21 may further move relative to the carriage 11. The radar exploration device 21 has, for example, an antenna 22, radiates pulsed radio waves into the ground, and receives the radio waves reflected by hitting buried objects in the ground such as buried objects 81 and buried pipes 82 buried in the ground. The distance to the buried object in the ground can be known from the time taken from radiating the radio waves to receiving them. The antenna 22 may be divided into a transmitting antenna and a receiving antenna.

[0010] The exploration position measurement device 31 is mounted on the carriage 11 and moves together with the carriage 11. The exploration position measurement device 31 measures the position of the radar exploration device 21 that moves by the movement of the carriage 11. The exploration position measurement device 31 may calculate, for example, the moving distance of the carriage 11 from the number of rotations of the wheels 12, or may calculate the moving direction and speed of the carriage 11 based on the acceleration measured by, for example, an acceleration sensor or the like. Alternatively, the position of the carriage 11 may be measured using a positioning device such as a global positioning system (GPS) receiver. When the radar exploration device 21 moves relative to the carriage 11, the exploration position measurement device 31 may calculate the absolute position of the radar exploration device 21 from the absolute position of the carriage 11 and the relative position of the radar exploration device 21 with respect to the carriage 11.

[0011] The buried pipe location estimation device 41 estimates the location of the buried pipe 82 based on the intensity pattern of the radio waves received by the radar detection device 21 and the position of the radar detection device 21 measured by the detection position measurement device 31. The buried pipe location estimation device 41 is, for example, a computer, and the processing unit executes a program stored in the memory device to realize the functional blocks described below.

[0012] As shown in Figure 2, the buried pipe location estimation device 41 includes, for example, an image generation unit 48, a buried location estimation unit 42, a buried object discrimination unit 43, a buried pipe determination unit 44, and a three-dimensional model generation unit 45.

[0013] The image generation unit 48 generates an image representing the intensity pattern of radio waves received by the radar detection device 21, based on the intensity pattern of radio waves received by the radar detection device 21 and the position of the radar detection device 21 measured by the detection position measurement device 31. For example, if the radar detection device 21 moves in a straight line, the intensity pattern of the reflected wave from a single reflection point will be such that the amplitude of the reflected wave will be larger and the intensity will be stronger and clearer as the reflectivity of the underground structure increases. If we plot the distance traveled by the radar detection device 21 on the horizontal axis and the delay time from transmission to reception of radio waves on the vertical axis, as shown in Figure 3, connecting the points where the amplitude of the reflected wave is large forms a hyperbola.

[0014] The speed at which radio waves propagate through the ground is determined by the relative permittivity of the ground. Therefore, if the relative permittivity of the ground is known, the depth of the underground reflector can be determined from the delay time between the transmission and reception of radio waves. The image generation unit 48 calculates the depth of the underground reflector from the delay time between transmitting and receiving radio waves, using, for example, a predetermined value set as the relative permittivity of the ground. Then, it takes the distance traveled by the radar detection device 21 in the horizontal direction and the depth of the reflector calculated from the delay time in the vertical direction, and generates an image in which the intensity of the radio waves received by the radar detection device 21 is used as the attribute of the pixels. For example, it generates a grayscale image in which the intensity of the received radio waves is represented by the brightness of the pixels, with lower brightness (i.e., darker) for weaker intensity and higher brightness (i.e., brighter) for stronger intensity. Alternatively, it may generate a grayscale image in which lower brightness is higher for weaker intensity and lower brightness for stronger intensity, or it may generate a color image in which the intensity of the radio waves is represented by hue instead of brightness.

[0015] The image generated in this way shows a hyperbolic pattern similar to that in Figure 3. However, since there are many underground structures, the radar detection device 21 receives reflected waves from many reflection points. As a result, the image generated by the image generation unit 48 shows a complex pattern, for example, as shown in Figure 4.

[0016] The buried location estimation unit 42 estimates the location of the buried object based on the image generated by the image generation unit 48. For example, it uses artificial intelligence (AI) to analyze complex patterns like the one shown in Figure 4 and estimate the location of the buried object (reflector). For example, the buried location estimation unit 42 inputs the image generated by the image generation unit 48 into the AI. The AI ​​is pre-trained with a large number of such images, and the AI ​​uses the learned model to analyze the input image and estimate the location of the buried object. For example, the buried location estimation unit 42 calculates the probability that the buried object is present at that location.

[0017] The buried object discrimination unit 43 determines the type of buried object based on the image generated by the image generation unit 48. For example, if the underground structure is a metal pipe, the intensity of the radio waves received by the radar detection device 21 will decrease in intensity, then increase, and then decrease again, starting from the shortest delay time (i.e., closer to the radar detection device 21). Therefore, the image generated by the image generation unit 48 will show a striped pattern of black (representing low intensity), white (representing high intensity), and black, such as pattern 91. In contrast, if the underground structure is a non-metallic pipe, the intensity of the radio waves received by the radar detection device 21 increases first, then decreases, and then increases again, starting with the shortest delay time. Therefore, the image generated by the image generation unit 48 will have a white, black, white striped pattern, such as pattern 92, which is the opposite of pattern 91. Furthermore, if water is present inside the pipe, a multiple reflection wave phenomenon like pattern 93 can be observed in the image generated by the image generation unit 48, as shown in Figure 5.

[0018] Therefore, the buried object discrimination unit 43 discriminates the type of buried object based on these differences in patterns. For example, the artificial intelligence can be pre-trained with a large number of such patterns, and the AI ​​uses the learned model to analyze the patterns and estimate the type of buried object. For example, the buried object discrimination unit 43 calculates the probability that the buried object is of that type. Note that the artificial intelligence of the buried object discrimination unit 43 may be the same as that of the buried location estimation unit 42. In other words, a single artificial intelligence may estimate the location and type of the buried object simultaneously.

[0019] The buried pipe determination unit 44 determines whether or not an underground buried object is a buried pipe based on the location of the buried object estimated by the buried location estimation unit 42. Various things are buried underground, but buried pipes 82 such as water pipes, gas pipes, and electrical conduits extend in a linear fashion. In contrast, buried objects 81 such as stones exist in isolation. Therefore, the buried pipe determination unit 44 determines that an underground object extending in a linear fashion is a buried pipe 82.

[0020] Furthermore, the buried pipe determination unit 44 may determine whether a linearly extending underground buried object is a buried pipe 82 based on the type of underground buried object determined by the buried object determination unit 43. For example, if the buried object determination unit 43 determines that the linearly extending underground buried object is a metal pipe or a non-metal pipe, it may determine that it is a buried pipe 82. If the buried object determination unit 43 determines that it is something else, it may determine that it is not a buried pipe 82.

[0021] The three-dimensional model generation unit 45 generates a three-dimensional model of the underground buried object that the buried pipe determination unit 44 has determined to be a buried pipe 82, based on the location estimated by the buried location estimation unit 42 and the type determined by the buried object discrimination unit 43. The three-dimensional model is data in a format that can be linked with BIM (Building Information Modeling / Management) or CIM (Construction Information Modeling / Management), or data for three-dimensional CAD (Computer-Aided Design), and includes information representing the location and type of the buried pipe 82. The three-dimensional model generation unit 45 may create an overhead view, such as the one shown in Figure 6, based on the generated three-dimensional model. In the overhead view, the buried pipes 82 may be color-coded according to their type. The three-dimensional model generation unit 45 may also create data for two-dimensional CAD, such as a plan view, based on the generated three-dimensional model.

[0022] In this way, based on the location and depth of the buried objects estimated by the buried object location estimation unit 42, it is determined whether or not the buried objects are continuous in a linear fashion, and if the buried objects are determined to be continuous in a linear fashion, they are identified as buried pipes 82, thus enabling accurate estimation of the location of the buried pipes 82. By identifying the type of underground structure, it is easy to determine whether the buried pipe 82 is a metal pipe or a non-metal pipe, and whether or not there is water inside the buried pipe 82. By using artificial intelligence, the accuracy of estimations can be improved. By generating a three-dimensional model, the estimated results can be easily used in other systems such as BIM / CIM.

[0023] In construction work, accidents have occurred where underground excavation has damaged buried pipes such as water pipes, gas pipes, and electrical conduits. One method for locating buried objects is to use ground-penetrating radar, which involves irradiating the ground with radar and estimating the location of buried objects based on the characteristics of the reflected waves. However, conventionally, skilled technicians visually identified buried objects from waveform images obtained by ground-penetrating radar, and then created reports illustrating the locations of these buried objects. This process required considerable effort and time for analysis. By using AI to identify buried objects and systematizing the analysis process, it is possible to reduce labor and improve efficiency. This method reduces the time and effort required from analysis to visualization, leading to labor savings and increased efficiency. By using radar waveforms to locate buried pipes, the need for skilled technicians is eliminated, thus addressing the shortage of personnel. This eliminates the possibility of overlooking buried object detection from waveform images, improving analysis accuracy and contributing to enhanced safety. This system utilizes AI to analyze waveform images from ground-penetrating radar to automatically detect buried objects. An algorithm is developed to estimate the location of buried pipes based on the continuity of these buried object detections. Finally, the buried pipe locations are automatically converted into 2D / 3D CAD models. By systematizing this entire process, the analysis work can be streamlined and made more efficient. This system uses AI to automatically detect buried objects in ground-penetrating radar waveform images. For example, it recognizes feature points in a bell-shaped waveform image (a cross-section of the ground) through AI image analysis and marks them as evidence of buried objects. The three-dimensional position of buried pipes is estimated from the continuity of buried object reactions. For example, buried object reactions are extracted from a vast amount of waveform images (cross-sectional views) acquired by a ground-penetrating radar, and the position of the buried pipes is estimated from their continuity. Automatically creates 2D / 3D models of buried pipe locations. For example, the 3D model is output with different colors for each type of buried pipe (metallic / non-metallic, presence or absence of water inside the pipe). The shape of the waveform image (specific feature points) can be used to classify whether the material is metallic or non-metallic, and whether or not there is water inside the pipe. This can reduce the workload of analysis tasks by half. For example, if the exploration range is 500m 2 In this case, the number of man-days required can be reduced from four to two. Furthermore, it can prevent overlooking buried object detection through visual inspection and improve analysis accuracy, thereby contributing to improved safety on site.

[0024] Next, we will describe the details of the three-dimensional model generation unit 45. As shown in Figure 7, the three-dimensional model generation unit 45 includes, for example, a range calculation unit 52, a region calculation unit 53, a contour detection unit 54, a rectangle calculation unit 55, a rectangle extraction unit 56, and a model calculation unit 57.

[0025] The range calculation unit 52 calculates a range in which the probability of an underground buried object being present exceeds a predetermined threshold, as shown in Figure 8, based on the location and depth of the underground buried object estimated by the buried location estimation unit 42, for example, for the underground buried object that the buried pipe determination unit 44 has determined to be a buried pipe 82. For example, the range calculation unit 52 divides the search area into squares of a predetermined size and calculates the probability that a buried pipe 82 exists beneath each of the divided squares (the buried pipe probability distribution, probability map, in the top view). The range calculation unit 52 compares the calculated probability with a threshold and extracts only the squares where the probability of the buried pipe 82 existing exceeds the threshold. In Figure 8, the squares extracted by the range calculation unit 52 are represented by white pixels, and the squares that were not extracted are represented by black pixels. The threshold used by the range calculation unit 52 may be a predetermined fixed value, or it may be a value calculated based on the distribution of the probability of existence of the buried pipes 82 or the extracted squares. For example, the threshold may be calculated based on the average value of the probability of existence of the buried pipes 82, or the threshold may be adjusted so that the proportion of extracted squares is a predetermined value.

[0026] The area calculation unit 53 calculates the area where the buried pipe 82 exists, for example, as shown in Figure 9, based on the range calculated by the range calculation unit 52. For example, the area calculation unit 53 extracts only the squares extracted by the range calculation unit 52 that form an area of ​​a predetermined size or larger when adjacent to each other, and removes isolated extracted squares that form an area smaller than the predetermined size from the extracted range. Similarly, it adds isolated unextracted squares that were not extracted by the range calculation unit 52 but form an area smaller than the predetermined volume when adjacent to each other to the extracted range. The area calculation unit 53 uses the extracted range adjusted in this way as the area where the buried pipe 82 exists.

[0027] The contour detection unit 54 detects the contour 95 of each region based on the region calculated by the region calculation unit 53, for example, as shown in Figure 10. For example, the contour detection unit 54 extracts a single continuous region from the extraction range calculated by the region calculation unit 53, which is formed by adjacent squares included in the extraction range. The contour detection unit 54 detects the boundary between the squares included in that region and the squares not included in that region, and calculates a polygon that approximates that boundary to form the contour 95. This process is repeated for all regions.

[0028] The rectangle calculation unit 55 calculates a line segment 96 connecting two points on the contour 95, as shown in Figure 11, based on the contour 95 detected by the contour detection unit 54. For example, the rectangle calculation unit 55 calculates the diagonals connecting the vertices of the polygon calculated by the contour detection unit 54, and extracts only those diagonals that satisfy predetermined conditions from among the calculated diagonals to form line segments 96.

[0029] The rectangle calculation unit 55 further calculates a rectangle for each of the calculated line segments 96, using that line segment as its diagonal, and then calculates the rectangle that has the greatest overlap with the aforementioned region from among the calculated rectangles. For example, the rectangle calculation unit 55 selects one line segment 96 from the calculated line segments 96. The rectangle calculation unit 55 calculates a circle 97 with that line segment 96 as its diameter, for example as shown in Figure 12. Next, for example as shown in Figure 13, it places a vertex 98 on the calculated circle 97 and calculates a rectangle 99 with line segment 96 as its diagonal. As the rectangle 99 changes by moving the vertex 98, the rectangle 99 that has the greatest overlap with the target area is calculated from among the rectangles 99 with line segment 96 as its diagonal, and this rectangle 99 is set as the rectangle corresponding to that line segment 96. The overlap between rectangle 99 and the target area can be calculated, for example, as follows: The area of ​​the portion included in both rectangle 99 and the target area is calculated as the overlapping area, and the area of ​​the portion included in rectangle 99 but not in the target area is calculated as the non-overlapping area. Then, the difference between the overlapping area and the non-overlapping area is calculated to determine the overlap between rectangle 99 and the target area. The rectangle calculation unit 55 calculates multiple rectangles 99 by repeating this process for multiple line segments 96, as shown in Figure 15, for example.

[0030] The rectangle extraction unit 56 extracts rectangles 99 based on the rectangle calculation unit 55, for example, as shown in Figure 15. For example, the rectangle extraction unit 56 selects a rectangle 99 from among the rectangles 99 calculated by the rectangle calculation unit 55 whose overlap with another second rectangle 99 exceeds a predetermined threshold. The rectangle extraction unit 56 compares the overlap between that rectangle 99 and the target area with the overlap between the second rectangle 99 and the target area. If the overlap between that rectangle 99 and the target area is less than the overlap between the second rectangle 99 and the target area, the rectangle extraction unit 56 removes that rectangle 99. In this way, rectangles 99 are filtered out, and only the last remaining rectangle 99 is extracted. The overlap between rectangles 99 may be calculated using the same method as when calculating the overlap between rectangle 99 and the target area, or it may be calculated using a different method than when calculating the overlap between rectangle 99 and the target area.

[0031] The model calculation unit 57 generates a three-dimensional model of the underground buried object based on the rectangle 99 extracted by the rectangle extraction unit 56. For example, the model calculation unit 57 uses the shorter side of the rectangle 99 extracted by the rectangle extraction unit 56 as the diameter, calculates a cylinder extending in the direction of the longer side of the rectangle 99, and obtains a three-dimensional model of the buried pipe 82. By generating a three-dimensional model based on the rectangles extracted in this way, the positional relationships of the buried pipes 82 can be accurately estimated even when the buried pipes 82 intersect or branch in a complex manner.

[0032] As described above, the probability distribution of buried pipes is output from the top view of the AI ​​model (estimation result), a threshold is adjusted to keep only regions with a certain area, one region is selected, its outline is detected and represented as a polygon, two points are selected from each vertex of the polygon, a straight line is drawn between these two points, those that satisfy the conditions are kept, one straight line is selected, a circle is drawn with that straight line as its diameter, rectangles are drawn based on the circle for each rotation angle, the rectangle with the largest overlap area with the pipe estimation region is selected, this process is repeated for each straight line, all rectangle candidates are collected, and only those with the largest ratio / area of ​​the pipe estimation region among the overlapping rectangle regions of a certain percentage or more are kept, thereby allowing the positional relationship of multiple pipes to be estimated on the probability map.

[0033] Instead of determining whether or not an underground object is an underground object, the buried pipe determination unit 44 may calculate the probability that the underground object is an underground object. For example, as shown in Figure 16, the buried pipe determination unit 44 includes a region extraction unit 441, a section extraction unit 442, a length calculation unit 443, an average strength calculation unit 444, and a probability of existence calculation unit 445.

[0034] The region extraction unit 441 extracts regions where the reaction intensity (probability) of underground buried objects exceeds a predetermined threshold (e.g., 5%), based on the location of the underground buried objects calculated by the buried object location estimation unit 42. For example, the underground area of ​​the search target is divided into rectangular prisms of a predetermined size (e.g., cubes with sides of 10 cm), and for each rectangular prism, it is determined whether or not the intensity of the underground buried objects exceeds the threshold, and all rectangular prisms where the intensity of the underground buried objects exceeds the threshold are extracted.

[0035] The interval extraction unit 442 extracts linearly continuous intervals within the region extracted by the region extraction unit 441. For example, it draws a straight line that intersects the region extracted by the region extraction unit 441, and extracts all the rectangular prisms that the straight line passes through from among the rectangular prisms included in the region extracted by the region extraction unit 441, forming a single linear interval. By repeating this process while changing the position and orientation of the straight line, multiple intervals are extracted. Furthermore, a limit may be placed on the length of the intervals. For example, if the length at which the region extracted by the region extraction unit 441 intersects with a straight line exceeds a predetermined threshold (e.g., 100 cm), the region is divided into multiple intervals for extraction. In this case, the multiple intervals to be extracted may overlap with each other. For example, if the intersecting length is 120 cm, three 100 cm intervals may be extracted, each shifted by 10 cm. Furthermore, the sections extracted by the section extraction unit 442 are not limited to linearly continuous sections, but may also be curved and continuous sections. In that case, restrictions may be placed on the curvature of the curve. For example, the curvature may be 1 / 100 cm. -1 You can also extract only the intervals less than the given value.

[0036] The length calculation unit 443 calculates the length of each section extracted by the section extraction unit 442. For example, it calculates the distance between the center point of a rectangular prism at one end of a straight section and the center point of a rectangular prism at the other end, and uses this as the length of the section.

[0037] The average strength calculation unit 444 calculates the average strength of the underground buried objects for each section extracted by the section extraction unit 442. For example, the average strength is calculated by summing the reaction strengths of the underground buried objects for each rectangular prism included in the section and dividing by the number of rectangular prisms included in the section.

[0038] The existence probability calculation unit 445 calculates the probability that a buried pipe exists in each of the intervals extracted by the linear interval extraction unit 442, based on the length calculated by the length calculation unit 443 and the average strength calculated by the average strength calculation unit 444. For example, the existence probability can be calculated using a function that takes two variables as input. Alternatively, as shown in Figure 17, the existence probability may be calculated using a correspondence table that shows the correspondence between length, average strength, and existence probability. Here, the relationship between length, average intensity, and probability of existence is predetermined to satisfy the following three conditions: (1) The longer the length, the higher the probability of existence. (2) The higher the average intensity, the higher the probability of existence. (3) Length has a greater influence on the probability of existence than average intensity. In other words, even if the average intensity is low, if the length is long, the probability of a buried pipe being present is high. This is because if there is a continuous reaction in a linear fashion, even if the reaction is weak, there is a high probability that a buried pipe is present. Conversely, even if the average intensity is high, if the length is short, the probability of a buried pipe being present is low. This is because even if the reaction is strong, if it is not continuous in a linear fashion, there is a low probability that it is a buried pipe.

[0039] The buried pipe determination unit 44 may output the existence probability calculated by the existence probability calculation unit 445 for each of the sections extracted by the straight section extraction unit 442. In this case, the existence probability may be output for all sections extracted by the section extraction unit 442, or only the existence probability for sections that satisfy predetermined conditions may be output. For example, only those whose existence probability exceeds a predetermined threshold may be output, or only those with the highest existence probability among adjacent sections may be output. Alternatively, the buried pipe determination unit 44 may output the highest of the existence probabilities calculated by the existence probability calculation unit 445 for each rectangular parallelepiped into which the search target range has been divided, as the existence probability of the buried pipe for that rectangular parallelepiped.

[0040] Furthermore, the existence probability calculation unit 445 may calculate not only the probability of buried pipes existing, but also the probability of all buried objects, including objects other than buried pipes, existing in that section. In that case, for example, as shown in Figure 18, the relationship between length, average strength, and existence probability is predetermined to satisfy the following three conditions: (1) The longer the length, the greater the existence probability. (2) The higher the average strength, the greater the existence probability. (3) Average strength has a greater influence on existence probability than length. That is, even if the length is long, if the average strength is low, the probability of buried objects existing will be small, and even if the length is short, if the average strength is high, the probability of buried objects existing will be large. This is because buried objects include things that do not extend linearly, such as buried pipes, so if the reaction is strong, there is a high possibility that something is there even if it is not linearly continuous.

[0041] As described above, the probability of a buried pipe being present is determined based on the length and intensity of the reaction, resulting in higher detection accuracy for buried pipes. By prioritizing length over reaction intensity, it is possible to accurately detect buried pipes specifically, rather than general buried objects. Furthermore, since it can determine the probability of the presence of buried objects other than buried pipes, it can accurately detect general buried objects as well. Therefore, it is possible to perform appropriate probability calculations depending on the situation, preventing the oversight of buried pipes and other buried objects.

[0042] The embodiments described above are examples intended to facilitate understanding of the present invention. The present invention is not limited thereto and includes various modifications, changes, additions, or deletions without departing from the scope defined by the appended claims. This will be readily apparent to those skilled in the art from the above description. [Explanation of symbols]

[0043] 10 Buried pipe location estimation system, 11 Cart, 12 Wheels, 21 Radar detection device, 22 Antenna, 31 Detection position measurement device, 41 Buried pipe location estimation device, 48 Image generation unit, 42 Buried location estimation unit, 43 Buried object discrimination unit, 44 Buried pipe determination unit, 441 Region extraction unit, 442 Section extraction unit, 443 Length calculation unit, 444 Average intensity calculation unit, 445 Probability of existence calculation unit, 45 Three-dimensional model generation unit, 52 Range calculation unit, 53 Region calculation unit, 54 Contour detection unit, 55 Rectangle calculation unit, 56 Rectangle extraction unit, 57 Model calculation unit, 80 Ground, 81 Buried object, 82 Buried pipe, 91-93 Pattern, 95 Contour, 96 Line segment, 97 Circle, 98 Vertex, 99 Rectangle.

Claims

1. A radar exploration device that moves along the ground, emits radio waves into the ground, and receives the radio waves reflected after hitting underground objects, A search position measuring device for measuring the position of the radar search device, A buried pipe location estimation device that estimates the buried location of buried pipes, and Equipped with, The buried pipe location estimation device is, A buried location estimation unit estimates the location and depth of the buried object based on the position measured by the exploration position measuring device and the intensity pattern of radio waves received by the radar exploration device. Based on the location and depth of the underground buried object calculated by the buried object location estimation unit, the buried pipe determination unit determines whether the underground buried object is continuous in a linear fashion, and determines that the underground buried object determined to be continuous in a linear fashion is a buried pipe. It has, The buried pipe location estimation device is, The system further comprises a three-dimensional model generation unit that generates a three-dimensional model based on the location and depth of the underground buried object estimated by the buried location estimation unit, for the underground buried object that the buried pipe determination unit has determined to be a buried pipe. The three-dimensional model generation unit, Based on the location and depth of the underground object estimated by the burial location estimation unit, the range in which the probability of the underground object existing exceeds a predetermined threshold is calculated. The contour of the calculated range is detected, For each line segment connecting two points on the detected contour, calculate the rectangle that has the greatest overlap with the range among the rectangles whose diagonals are the line segments. From the calculated rectangles, remove any rectangles whose overlap with other rectangles exceeds a predetermined threshold and whose overlap with the range is less than that of the other rectangles. Using the remaining rectangle that was not removed, a three-dimensional model of the underground buried object is generated. A system for estimating the location of buried pipes.

2. The buried pipe location estimation device is, The radar detection device further includes a buried object identification unit that determines the type of buried object based on the intensity pattern of radio waves received by the radar detection device. A buried pipe location estimation system according to claim 1.

3. The buried location estimation unit uses artificial intelligence to estimate the location and depth of the buried object. A buried pipe location estimation system according to claim 1 or 2.

4. A radar exploration device that moves along the ground, emits radio waves into the ground, and receives radio waves that hit and are reflected by underground buried objects, A search position measuring device for measuring the position of the radar search device, A buried pipe location estimation device that estimates the buried location of buried pipes, and Equipped with, The buried pipe location estimation device is, A buried location estimation unit estimates the location and depth of the buried object based on the position measured by the exploration position measuring device and the intensity pattern of radio waves received by the radar exploration device. A buried pipe determination unit determines whether the buried objects are continuous in a linear fashion based on the location and depth of the buried objects calculated by the buried location estimation unit, and calculates the probability of a buried pipe existing in a section based on the length of the section and the average value of the probability that the buried objects exist in the section, calculated based on the location and depth of the buried objects estimated by the buried location estimation unit. It has, The buried pipe location estimation device is, The buried pipe determination unit further comprises a three-dimensional model generation unit that generates a three-dimensional model based on the location and depth of the buried pipe for which the probability of existence has been calculated. The three-dimensional model generation unit, Based on the location and depth of the underground object estimated by the burial location estimation unit, the range in which the probability of the underground object existing exceeds a predetermined threshold is calculated. The contour of the calculated range is detected, For each line segment connecting two points on the detected contour, calculate the rectangle that has the greatest overlap with the range among the rectangles whose diagonals are the line segments. From the calculated rectangles, remove any rectangles whose overlap with other rectangles exceeds a predetermined threshold and whose overlap with the range is less than that of the other rectangles. Using the remaining rectangle that was not removed, a three-dimensional model of the underground buried object is generated. A system for estimating the location of buried pipes.

5. The probability of existence calculated by the buried pipe determination unit increases as the length of the section increases, and also increases as the average value increases, and the influence of the section length is greater than the influence of the average value. The buried pipe location estimation system according to claim 4.

6. The buried pipe determination unit further calculates the probability of a buried object being present in a linearly continuous section, based on the length of the section and the average value of the probability that the buried object is present in the section, calculated based on the location and depth of the buried object estimated by the buried object location estimation unit. A buried pipe location estimation system according to claim 4 or 5.

7. The probability of the presence of a buried object calculated by the buried pipe determination unit increases with increasing length of the section, increases with increasing average value, and the influence of the average value is greater than the influence of the section length. The buried pipe location estimation system according to claim 6.

Images