A geotechnical construction survey management platform and method based on drone aerial photography

Abstract

The present invention relates to the field of geotechnical construction technology, and specifically to a geotechnical construction investigation and management platform and method based on drone aerial photography, comprising: an acquisition layer, an identification layer, and an evaluation layer; boundary information of a geotechnical construction area is uploaded through the acquisition layer, and the acquisition layer constructs a geotechnical construction area model based on the uploaded boundary information, and synchronously sets a model division logic, and divides the geotechnical construction area model based on the division logic to obtain a plurality of groups of sub-geotechnical construction area models. The present invention globally acquires surface images of the geotechnical construction area, and based on image analysis, captures locations where cracks may exist on the surface of the geotechnical construction area, and further jointly analyzes the captured surface locations of the geotechnical construction area where cracks may exist, and evaluates and determines the construction safety risk of the geotechnical construction area. When the evaluation result is unsafe, the present invention can also locate and provide feedback on areas with higher surface risks in the geotechnical construction area.

Description

Technical Field

[0001] The present invention relates to the field of geotechnical construction technology, and in particular to a geotechnical construction survey and management platform and method based on unmanned aerial vehicle (UAV) aerial photography. Background Art

[0002] Geotechnical construction is a crucial engineering activity. It involves the treatment and transformation of rock and soil to meet the construction needs of various buildings and infrastructure. This includes ground preparation, foundation pit support, and slope reinforcement. Ensuring the stability and safety of the project through drilling, grouting, anchoring, and other technical means is crucial to the smooth operation of construction projects.

[0003] The invention patent with application number 202010726628.5 discloses a geotechnical engineering survey system, including an information collection terminal, an information processing terminal, an information management terminal and a wireless terminal, wherein the information collection terminal is communicatively connected to the information processing terminal through a wireless terminal, and the information processing terminal is communicatively connected to the information management terminal through a wireless terminal.

[0004] The application aims to solve the problem that "at present, the geotechnical engineering investigation work in my country, except for railways, highways, bridges, etc., is mainly carried out in various urban areas and newly developed blocks. According to relevant national standards and regulations, each building must be investigated in accordance with the current standards. Moreover, the investigation methods recognized by national standards are limited to drilling, static exploration, dynamic exploration, and water sampling and testing. It is bound to cause the same geotechnical engineering investigation to be repeated in the same geological unit, the same stratigraphic structure, and the same block, thus wasting a lot of manpower, material resources and financial resources."

[0005] However, during the geotechnical construction process, due to the large size of the geotechnical construction surface, the construction risks caused by construction cracks on the geotechnical construction surface cannot be comprehensively surveyed and managed. The cracks on the geotechnical construction surface accumulate and deteriorate over a long period of time, triggering a chain reaction, causing safety problems such as collapse and subsidence of the geotechnical construction surface to varying degrees, resulting in the inability to guarantee the safety of on-site workers during the geotechnical construction process.

[0006] To this end, we proposed a geotechnical construction investigation and management platform and method based on UAV aerial photography. Summary of the Invention

[0007] In response to the above-mentioned shortcomings of the existing technology, the present invention provides a geotechnical construction survey management platform and method based on drone aerial photography, which solves the technical problems raised in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] First, a geotechnical construction survey and management platform based on drone aerial photography includes: a collection layer, an identification layer, and an evaluation layer;

[0010] The boundary information of the geotechnical construction area is uploaded through the acquisition layer. The acquisition layer constructs a geotechnical construction area model based on the uploaded boundary information, and simultaneously sets the model division logic. The geotechnical construction area model is divided based on the division logic to obtain several groups of sub-geotechnical construction area models. Each sub-geotechnical construction area model is used as an image acquisition target, and the surface image of the geotechnical construction area is collected. The surface image of the geotechnical construction area is synchronously sent to the recognition layer. The recognition layer receives the surface image of the geotechnical construction area and synchronously identifies the dynamic risk of the geotechnical construction area based on the surface image of each geotechnical construction area. The assessment layer receives the dynamic risk of the geotechnical construction area identified by the recognition layer in real time, assesses the safety of the geotechnical construction based on the dynamic risk of the geotechnical construction area, and simultaneously locates the unsafe area in the geotechnical construction area when the assessment result is that the geotechnical construction is unsafe.

[0011] The recognition layer includes a receiving module, a processing module and a recognition module. The receiving module is used to receive the surface image of the geotechnical construction area and store the surface image of the geotechnical construction area. The processing module is used to obtain the surface image of the geotechnical construction area stored in the receiving module and perform feature highlighting processing on the surface image of the geotechnical construction area. The recognition module is used to traverse the surface image of the geotechnical construction area after feature highlighting processing and identify the dynamic risk of the geotechnical construction area based on the image.

[0012] The dynamic risk identification logic of the geotechnical construction area is expressed as:

[0013]

[0014] Where: K is the dynamic risk performance value of the geotechnical construction area; u is the set of sub-geotechnical construction area models; k v is the dynamic risk performance value of the geotechnical construction area reflected by the sub-geotechnical construction area model of group v; d(b q ,b v+1 ) is the distance between the sub-image with the largest feature judgment value in the set of all sub-images that have an intersection with the adjacent sub-geotechnical construction area models in the grayscale image corresponding to the vth group of sub-geotechnical construction area models, which is divided into 3×3 groups of sub-images, and the sub-image with the largest feature judgment value in the set of all sub-images that have an intersection with the adjacent sub-geotechnical construction area models in the grayscale image corresponding to the v+1th group of sub-geotechnical construction area models; d(a q ,p0) is the distance between the center of the grayscale image corresponding to the v-th group of sub-geotechnical construction area model and the sub-image with the maximum feature judgment value in the set of all sub-images that do not have an intersection area with the adjacent sub-geotechnical construction area model in the grayscale image corresponding to the v-th group of sub-geotechnical construction area model;

[0015] Among them, the larger the dynamic risk performance value K of the geotechnical construction area is, the lower the risk of the geotechnical construction area is; conversely, the higher the risk of the geotechnical construction area is.

[0016] The receiving module is interactively connected to the processing module and the identification module through a wireless network, the identification module is interactively connected to the camera module through a wireless network, the camera module is interactively connected to the division module and the construction module through a wireless network, the receiving module is interactively connected to the evaluation module through a wireless network, and the evaluation module is interactively connected to the positioning module and the output module through a wireless network.

[0017] Furthermore, the acquisition layer includes a construction module, a division module, and a camera module. The construction module is used to upload geotechnical construction area boundary information and use the geotechnical construction area boundary information to construct a geotechnical construction area model. The division module is used to receive the geotechnical construction area model constructed in the construction module and divide the geotechnical construction area model to decompose the geotechnical construction area model into a plurality of sub-geotechnical construction area models. The camera module is used to pick up the model boundary coordinates of each sub-geotechnical construction area model, determine the acquisition area of the geotechnical construction area surface image based on the model boundary coordinates, and execute the acquisition of the geotechnical construction area surface image.

[0018] Among them, the boundary information of the geotechnical construction area uploaded during the operation phase of the construction module, that is, no less than three groups of boundary coordinates of the geotechnical construction area, are connected to each other based on the boundary coordinates of the geotechnical construction area to form a closed area. The closed area is the geotechnical construction area model. The geotechnical construction area model is a two-dimensional model. The camera module is integrated by a panoramic camera. The camera module determines the boundary coordinates of the sub-geotechnical construction area model based on the boundary coordinates of the geotechnical construction area model and the division results of the sub-geotechnical construction area model. When the camera module collects the surface image of the geotechnical construction area, the image collection range is determined based on the boundary coordinates of the sub-geotechnical construction area model, and a panoramic image of the sub-geotechnical construction area model is collected, that is, the surface image of the geotechnical construction area.

[0019] Furthermore, the division module is provided with a model division logic, and the division module divides the geotechnical construction area model based on the model division logic;

[0020] The partitioning logic set in the partitioning module is expressed as:

[0021] Calculating the size of the geotechnical construction area model based on the geotechnical construction area boundary information, setting the number and size of the sub-geotechnical construction area model divisions, and dividing the geotechnical construction area model according to the set number and size of the sub-geotechnical construction area model divisions, so that the geotechnical construction area model is divided into sub-geotechnical construction area models equal to the set number of divisions, and the sizes of the respective geotechnical construction area models are equal to each other;

[0022] Among them, adjacent sub-geotechnical construction area models overlap with each other, and the model area of the overlapping sub-geotechnical construction area models is always smaller than half of the corresponding area of any group of models in the overlapping sub-geotechnical construction area models.

[0023] Furthermore, each sub-geotechnical construction area model obtained by dividing the geotechnical construction area model in the division module also obeys:

[0024]

[0025] Where: n is the set of sub-geotechnical construction area models; s(p i ∩p i+1 ) is the size of the intersection of the adjacent i-th group of sub-geotechnical construction area models and the i+1-th group of sub-geotechnical construction area models; s p0 is the size of the sub-geotechnical construction area model division set in the division logic; q is the number of sub-geotechnical construction area model divisions set in the division logic; S0 is the size of the geotechnical construction area model determined based on the geotechnical construction area boundary information.

[0026] Furthermore, each time the platform runs, it only collects a surface image of the geotechnical construction area for each sub-geotechnical construction area model once, and all collected surface images of the geotechnical construction area cover the entire geotechnical construction area;

[0027] When receiving the surface image of the geotechnical construction area, the receiving module preferentially receives the surface image of the geotechnical construction area having a large intersection area with the surface image of the adjacent geotechnical construction area;

[0028] The processing module runs continuously in the recognition layer, and each time it runs in the receiving module, it obtains a set of surface images of the geotechnical construction area based on the time sequence. After the processing module obtains the surface images of the geotechnical construction area and processes the surface images of the geotechnical construction area, the recognition module runs synchronously with the processing module.

[0029] Furthermore, in the processing module, the feature highlighting processing operation for the surface image of the geotechnical construction area is:

[0030]

[0031] Where Gray(i,j) is the output gray value of pixel (i,j); R(i,j), G(i,j), B(i,j) are the color components of pixel (i,j) based on R, G, B channels; ω1, ω2, ω3 are weights; χ is a constant offset; C is the feature judgment value; N, M are the rows and columns of the gray image; G x,y is the grayscale value of the pixel at the xth row and yth column; F x,y is the weighting coefficient of the pixel corresponding to the xth row and yth column;

[0032] Among them, the weights ω1, ω2, and ω3 are set by the system end user, and the sum of the weights ω1, ω2, and ω3 is 1. The constant offset χ ≥ 0. Based on formula (1), each pixel in the surface image of the geotechnical construction area is processed to output the grayscale image of the surface image of the geotechnical construction area. x,y The value is subject to, F x,y ∈(0,1], the closer the pixel point at row x and column y is to the center of the image F x,y The larger the value, the smaller the F x,y The smaller the value;

[0033] The grayscale image output by formula (1) is further divided into 3×3 groups of sub-images. Each group of sub-images is used as the calculation target of formula (2). After the feature judgment value C is obtained for each sub-image, each group of sub-images is divided into two groups of sub-image sets. One group of sub-image sets is the set of all sub-images that do not have an intersection area with the adjacent sub-geotechnical construction area model, and the other group of sub-image sets is the set of all sub-images that have an intersection area with the adjacent sub-geotechnical construction area model. A group of sub-images with the largest feature judgment value C is picked up from each of the two groups. Based on the picked sub-images, the corresponding regional image is determined in the surface image of the geotechnical construction area. The regional image determined in the surface image of the geotechnical construction area is the feature highlighting processing result of the surface image of the geotechnical construction area in the processing module.

[0034] Furthermore, the assessment layer includes an assessment module, a positioning module, and an output module. The assessment module is used to continuously receive the dynamic risks of the geotechnical construction area identified in the identification layer, and evaluate whether the geotechnical construction is safe based on the continuously received dynamic risks of the geotechnical construction area. The positioning module is used to obtain the assessment result of whether the geotechnical construction is safe in the assessment module, and when the assessment result is negative, locate the unsafe area in the geotechnical construction area. The output module is used to receive the unsafe area in the geotechnical construction area located in the positioning module, obtain the coordinates of the unsafe area, and output them.

[0035] The evaluation logic of whether geotechnical construction is safe in the evaluation module is expressed as follows:

[0036]

[0037] Where: K1, K2, K3, ... are the dynamic risk performance values of the geotechnical construction area continuously received by the assessment module; K O is the dynamic risk determination value of the geotechnical construction area;

[0038] Among them, K1, K2, K3, ... are sorted based on the identification time sequence, and K1, K2, K3, ... are not less than three groups. K1 is the dynamic risk performance value of the geotechnical construction area identified the earliest, and the dynamic risk judgment value of the geotechnical construction area K O Based on the user customization on the system side, if any of the above formulas is true, it means that the current geotechnical construction status is unsafe; otherwise, it means that the current geotechnical construction status is safe.

[0039] Furthermore, the positioning logic of the unsafe area in the geotechnical construction area in the positioning module is expressed as follows:

[0040] K v1 >K v2 >K v3 >......;

[0041] Where: K v1 , K v2 , K v3 , ...is the dynamic risk performance value of the geotechnical construction area reflected by the sub-geotechnical construction area model of group v based on K1, K2, K3, ...;

[0042] Among them, K v1 , K v2 , K v3 , ... sorting based on recognition time sequence, K v1 The dynamic risk performance value of the geotechnical construction area identified earliest is based on the above formula. Each sub-geotechnical construction area model is used as the judgment target, and the area corresponding to the sub-geotechnical construction area model that meets the above formula is judged as an unsafe area in the geotechnical construction area.

[0043] Secondly, a geotechnical construction survey management method based on drone aerial photography includes:

[0044] S1: Upload the boundary information of the geotechnical construction area, build a geotechnical construction area model, divide the geotechnical construction area model, and obtain several groups of sub-geotechnical construction area models;

[0045] S2: Based on the corresponding area of the sub-geotechnical construction area model, collect surface images of the geotechnical construction area and perform feature highlighting processing on the collected surface images of the geotechnical construction area;

[0046] S3: Obtain the feature highlighting processing results of the surface image of the geotechnical construction area, and use the feature highlighting processing results to identify the dynamic risks of the geotechnical construction area;

[0047] S4: Continuously record the dynamic risk identification results of the geotechnical construction area and evaluate whether the current geotechnical construction is safe based on the continuously recorded identification results;

[0048] S5: When the assessment result shows that the current geotechnical construction is unsafe, the unsafe area in the geotechnical construction area is located and output.

[0049] Compared with the known public technology, the technical solution provided by the present invention has the following advantages:

[0050] Beneficial effects:

[0051] The present invention provides a geotechnical construction survey and management platform based on drone aerial photography. During operation, the platform uses a set geotechnical construction area surface image acquisition logic to perform global acquisition of the geotechnical construction area surface image, and then based on image analysis, captures the locations where cracks may exist on the surface of the geotechnical construction area. Further, based on the captured surface locations of the geotechnical construction area where cracks may exist, a joint analysis is performed to assess and determine the construction safety risks of the geotechnical construction area. When the assessment result is unsafe, the platform can also locate and provide feedback on areas with higher surface risks in the geotechnical construction area, thereby providing maximum and comprehensive construction safety survey and management for geotechnical construction. In addition, during the implementation phase of the solution, the solution requires less manual operation and is energy-saving, efficient, and intelligent overall.

[0052] In addition, based on the further configuration of a geotechnical construction survey management method based on drone aerial photography, auxiliary logic support is provided for the operation of the above-mentioned platform, ensuring that the technical solution composed of the above-mentioned platform and method is more stable and reliable during the specific implementation and application stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0054] Figure 1 This is a structural diagram of a geotechnical construction survey and management platform based on drone aerial photography;

[0055] Figure 2 This is a flowchart of a geotechnical construction investigation and management method based on drone aerial photography;

[0056] Figure 3 This is a schematic diagram showing the logic of the geotechnical construction area model division in the present invention;

[0057] Figure 4 This is a schematic diagram of the source of application parameters in the dynamic risk identification logic of geotechnical construction areas in the present invention;

[0058] The numbers in the figure represent: 1. Example 1 of sub-geotechnical construction area model; 2. Example 2 of sub-geotechnical construction area model. DETAILED DESCRIPTION

[0059] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0060] The present invention will be further described below with reference to the embodiments.

[0061] Example 1:

[0062] This embodiment is a geotechnical construction survey management platform based on drone aerial photography, such as Figure 1 As shown, it includes: acquisition layer, recognition layer and evaluation layer;

[0063] The boundary information of the geotechnical construction area is uploaded through the acquisition layer. The acquisition layer constructs a geotechnical construction area model based on the uploaded boundary information, and simultaneously sets the model division logic. The geotechnical construction area model is divided based on the division logic to obtain several groups of sub-geotechnical construction area models. Each sub-geotechnical construction area model is used as an image acquisition target, and the surface image of the geotechnical construction area is collected. The surface image of the geotechnical construction area is synchronously sent to the recognition layer. The recognition layer receives the surface image of the geotechnical construction area and synchronously identifies the dynamic risk of the geotechnical construction area based on the surface image of each geotechnical construction area. The assessment layer receives the dynamic risk of the geotechnical construction area identified by the recognition layer in real time, assesses the safety of the geotechnical construction based on the dynamic risk of the geotechnical construction area, and simultaneously locates the unsafe area in the geotechnical construction area when the assessment result is that the geotechnical construction is unsafe.

[0064] The acquisition layer includes a construction module, a division module, and a camera module. The construction module is used to upload the boundary information of the geotechnical construction area and use the boundary information of the geotechnical construction area to construct a geotechnical construction area model. The division module is used to receive the geotechnical construction area model constructed in the construction module and divide the geotechnical construction area model to decompose the geotechnical construction area model into several groups of sub-geotechnical construction area models. The camera module is used to pick up the model boundary coordinates of each sub-geotechnical construction area model, determine the acquisition area of the geotechnical construction area surface image based on the model boundary coordinates, and execute the acquisition of the geotechnical construction area surface image;

[0065] Among them, the geotechnical construction area boundary information uploaded during the operation phase of the construction module, that is, no less than three groups of geotechnical construction area boundary coordinates, the construction module is connected to each other based on the geotechnical construction area boundary coordinates to form a closed area, the closed area is the geotechnical construction area model, the geotechnical construction area model is a two-dimensional model, the camera module is integrated by a panoramic camera, the camera module determines the boundary coordinates of the sub-geotechnical construction area model based on the boundary coordinates of the geotechnical construction area model and the division result of the sub-geotechnical construction area model, when the camera module collects the surface image of the geotechnical construction area, the image collection range is determined based on the boundary coordinates of the sub-geotechnical construction area model, and a panoramic image of the sub-geotechnical construction area model is collected, that is, the surface image of the geotechnical construction area;

[0066] The recognition layer includes a receiving module, a processing module, and a recognition module. The receiving module is used to receive and store surface images of the geotechnical construction area. The processing module is used to obtain the surface images of the geotechnical construction area stored in the receiving module and perform feature highlighting on the surface images of the geotechnical construction area. The recognition module is used to traverse the surface images of the geotechnical construction area after feature highlighting and identify dynamic risks of the geotechnical construction area based on the images.

[0067] The dynamic risk identification logic of geotechnical construction area is expressed as:

[0068]

[0069] Where: K is the dynamic risk performance value of the geotechnical construction area; u is the set of sub-geotechnical construction area models; k v is the dynamic risk performance value of the geotechnical construction area reflected by the sub-geotechnical construction area model of group v; d(b q ,b v+1 ) is the distance between the sub-image with the largest feature judgment value in the set of all sub-images that have an intersection with the adjacent sub-geotechnical construction area models in the grayscale image corresponding to the vth group of sub-geotechnical construction area models, which is divided into 3×3 groups of sub-images, and the sub-image with the largest feature judgment value in the set of all sub-images that have an intersection with the adjacent sub-geotechnical construction area models in the grayscale image corresponding to the v+1th group of sub-geotechnical construction area models; d(a q ,p0) is the distance between the center of the grayscale image corresponding to the v-th group of sub-geotechnical construction area model and the sub-image with the maximum feature judgment value in the set of all sub-images that do not have an intersection area with the adjacent sub-geotechnical construction area model in the grayscale image corresponding to the v-th group of sub-geotechnical construction area model;

[0070] Among them, the larger the dynamic risk performance value K of the geotechnical construction area is, the lower the risk of the geotechnical construction area is; conversely, the higher the risk of the geotechnical construction area is.

[0071] The assessment layer includes an assessment module, a positioning module, and an output module. The assessment module is used to continuously receive the dynamic risks of the geotechnical construction area identified in the identification layer, and evaluate whether the geotechnical construction is safe based on the continuously received dynamic risks of the geotechnical construction area. The positioning module is used to obtain the assessment result of whether the geotechnical construction is safe in the assessment module. When the assessment result is negative, the unsafe area in the geotechnical construction area is located. The output module is used to receive the unsafe area in the geotechnical construction area located by the positioning module, obtain the coordinates of the unsafe area, and output it.

[0072] The evaluation logic of whether geotechnical construction is safe in the evaluation module is expressed as follows:

[0073]

[0074] Where: K1, K2, K3, ... are the dynamic risk performance values of the geotechnical construction area continuously received by the assessment module; K O is the dynamic risk determination value of the geotechnical construction area;

[0075] Among them, K1, K2, K3, ... are sorted based on the identification time sequence, and K1, K2, K3, ... are not less than three groups. K1 is the dynamic risk performance value of the geotechnical construction area identified the earliest, and the dynamic risk judgment value of the geotechnical construction area K O Based on the user customization of the system end, in the above formula, if any one of the formulas is true, it means that the current geotechnical construction status is unsafe, otherwise, it means that the current geotechnical construction status is safe;

[0076] The positioning logic of the unsafe area in the geotechnical construction area in the positioning module is expressed as follows:

[0077] K v1 >K v2 >K v3 >......;

[0078] Where: K v1 , K v2 , K v3 , ...is the dynamic risk performance value of the geotechnical construction area reflected by the sub-geotechnical construction area model of group v based on K1, K2, K3, ...;

[0079] Among them, K v1 , K v2 , K v3 , ... sorting based on recognition time sequence, K v1 is the dynamic risk performance value of the earliest identified geotechnical construction area. Based on the above formula, each sub-geotechnical construction area model is used as the judgment target, and the area corresponding to the sub-geotechnical construction area model that meets the above formula is judged as an unsafe area in the geotechnical construction area.

[0080] The receiving module is interactively connected to the processing module and the recognition module through a wireless network, the recognition module is interactively connected to the camera module through a wireless network, the camera module is interactively connected to the division module and the construction module through a wireless network, the receiving module is interactively connected to the evaluation module through a wireless network, and the evaluation module is interactively connected to the positioning module and the output module through a wireless network.

[0081] In this embodiment, the construction module runs to upload the boundary information of the geotechnical construction area, and uses the boundary information of the geotechnical construction area to construct a geotechnical construction area model. The division module synchronously receives the geotechnical construction area model constructed in the construction module, divides the geotechnical construction area model, and decomposes the geotechnical construction area model into several groups of sub-geotechnical construction area models. The camera module further picks up the model boundary coordinates of each sub-geotechnical construction area model, determines the acquisition area of the surface image of the geotechnical construction area based on the model boundary coordinates, and executes the acquisition of the surface image of the geotechnical construction area. The receiving module runs to receive the surface image of the geotechnical construction area, stores the surface image of the geotechnical construction area, and then the processing module obtains the image in the receiving module. The stored surface image of the geotechnical construction area is subjected to feature highlighting processing on the surface image of the geotechnical construction area. The recognition module further traverses the surface image of the geotechnical construction area after feature highlighting processing, and identifies the dynamic risk of the geotechnical construction area based on the image. Finally, the dynamic risk of the geotechnical construction area identified in the recognition layer is continuously received by the evaluation module. Whether the geotechnical construction is safe is evaluated based on the continuously received dynamic risk of the geotechnical construction area. The positioning module obtains the evaluation result of whether the geotechnical construction is safe in the evaluation module in real time. When the evaluation result is no, the unsafe area in the geotechnical construction area is located, and the output module receives the unsafe area in the geotechnical construction area located in the positioning module, obtains the coordinates of the unsafe area and outputs it.

[0082] Through the above-mentioned embodiments, the system brings about the implementation of survey and management of geotechnical crack risk hazards in geotechnical construction, brings more effective safety maintenance for geotechnical construction, and provides protection for the safety of on-site workers during geotechnical construction.

[0083] See also Figure 3 As shown, based on the sub-geotechnical construction area model example 1, sub-geotechnical construction area model example 2 and arrow indications in the figure, the dotted line in the sub-geotechnical construction area model example 1 represents the area, that is, the intersection area of the sub-geotechnical construction area model example 1 and the sub-geotechnical construction area model example 2, which is used as an example for the following embodiments s(p i ∩p i+1 ) to demonstrate examples.

[0084] See also Figure 4As shown in the figure, the segmentation operation of the grayscale image corresponding to the sub-geotechnical construction area model is further demonstrated. The a marked in the figure represents the a applied in the dynamic risk identification logic of the geotechnical construction area in the following embodiment. q , b represents p0 applied in the dynamic risk identification logic of geotechnical construction area in the following embodiment, and c represents b applied in the dynamic risk identification logic of geotechnical construction area in the following embodiment. q , d represents the b used in the dynamic risk identification logic of geotechnical construction area in the following embodiment v+1 ;

[0085] ab represents the line between markers a and b, and cd represents the line between markers c and d, which is the feature highlighting result obtained when the system is running (ab is d (a q ,p0),cd is d(b q ,b v+1 )), in other words, the rock and soil cracks and fissures in the sub-rock and soil construction area model predicted by the system operation;

[0086] It should be noted that the camera module is a panoramic camera integrated into the surface of the drone, and the drone is carried and flown to realize the collection of surface images of the geotechnical construction area.

[0087] Example 2:

[0088] In terms of specific implementation, based on the first embodiment, this embodiment refers to Figure 1 The geotechnical construction survey management platform based on drone aerial photography in Example 1 is further described in detail:

[0089] The partitioning module is provided with a model partitioning logic, and the partitioning module partitions the geotechnical construction area model based on the model partitioning logic;

[0090] The partitioning logic set in the partitioning module is expressed as:

[0091] Calculating the size of the geotechnical construction area model based on the geotechnical construction area boundary information, setting the number and size of the sub-geotechnical construction area model divisions, and dividing the geotechnical construction area model according to the set number and size of the sub-geotechnical construction area model divisions, so that the geotechnical construction area model is divided into sub-geotechnical construction area models equal to the set number of divisions, and the sizes of the respective geotechnical construction area models are equal to each other;

[0092] Among them, adjacent sub-geotechnical construction area models overlap with each other, and the model area of the overlapping sub-geotechnical construction area models is always smaller than half of the corresponding area of any group of models in the overlapping sub-geotechnical construction area models;

[0093] In the division module, each sub-geotechnical construction area model obtained by dividing the geotechnical construction area model also obeys:

[0094]

[0095] Where: n is the set of sub-geotechnical construction area models; s(p i ∩p i+1 ) is the size of the intersection of the adjacent i-th group of sub-geotechnical construction area models and the i+1-th group of sub-geotechnical construction area models; is the size of the sub-geotechnical construction area model division set in the division logic; q is the number of sub-geotechnical construction area model divisions set in the division logic; S0 is the size of the geotechnical construction area model determined based on the geotechnical construction area boundary information.

[0096] In this embodiment, through the above settings, further operation data support is provided for the operation of the system in Example 1, and the division logic of the division module when dividing the geotechnical construction area model is limited to ensure that the geotechnical construction area model is stably divided to obtain several groups of sub-geotechnical construction area models for further operation of the system in Example 1.

[0097] Example 3:

[0098] In terms of specific implementation, based on the first embodiment, this embodiment refers to Figure 1 The geotechnical construction survey management platform based on drone aerial photography in Example 1 is further described in detail:

[0099] Each time the platform runs, it only collects one surface image of the geotechnical construction area for each sub-geotechnical construction area model. All collected surface images of the geotechnical construction area cover the entire geotechnical construction area.

[0100] When receiving the surface image of the geotechnical construction area, the receiving module gives priority to receiving the surface image of the geotechnical construction area having a large intersection area with the surface image of the adjacent geotechnical construction area;

[0101] The processing module runs continuously in the recognition layer. Each time it runs in the receiving module, it obtains a set of surface images of the geotechnical construction area based on the time sequence. The recognition module processes the surface images of the geotechnical construction area obtained by the processing module and then runs synchronously with the processing module.

[0102] In the processing module, the feature highlighting processing operation for the surface image of the geotechnical construction area is as follows:

[0103]

[0104] Where Gray(i,j) is the output gray value of pixel (i,j); R(i,j), G(i,j), B(i,j) are the color components of pixel (i,j) based on R, G, B channels; ω1, ω2, ω3 are weights; χ is a constant offset; C is the feature judgment value; N, M are the rows and columns of the gray image; G x,y is the grayscale value of the pixel at the xth row and yth column; G x,y-1 is the grayscale value of the pixel at the xth row and y-1th column; G x-1,y is the grayscale value of the pixel at the x-1th row and yth column; F x,y is the weighting coefficient of the pixel corresponding to the xth row and yth column;

[0105] Among them, the weights ω1, ω2, and ω3 are set by the system end user, and the sum of the weights ω1, ω2, and ω3 is 1. The constant offset χ ≥ 0. Based on formula (1), each pixel in the surface image of the geotechnical construction area is processed to output the grayscale image of the surface image of the geotechnical construction area. x,y The value is subject to F x,y ∈(0,1], the closer the pixel point at row x and column y is to the center of the image F x,y The larger the value, the smaller the F x,y The smaller the value;

[0106] The grayscale image output by formula (1) is further divided into 3×3 groups of sub-images. Each group of sub-images is used as the calculation target of formula (2). After the feature judgment value C is obtained for each sub-image, each group of sub-images is divided into two groups of sub-image sets. One group of sub-image sets is the set of all sub-images that do not have an intersection area with the adjacent sub-geotechnical construction area model, and the other group of sub-image sets is the set of all sub-images that have an intersection area with the adjacent sub-geotechnical construction area model. A group of sub-images with the largest feature judgment value C is picked up from each of the two groups. Based on the picked sub-images, the corresponding regional image is determined in the surface image of the geotechnical construction area. The regional image determined in the surface image of the geotechnical construction area is the feature highlighting processing result of the surface image of the geotechnical construction area in the processing module.

[0107] In this embodiment, by setting the above-mentioned logical formula, the operational logic of the feature highlighting processing in the processing module is further limited, so that the recognition layer can stably operate and output images, providing an evaluation basis for the geotechnical construction safety evaluation in the evaluation layer.

[0108] Example 4:

[0109] In terms of specific implementation, based on the first embodiment, this embodiment refers to Figure 2 The geotechnical construction survey management platform based on drone aerial photography in Example 1 is further described in detail:

[0110] A geotechnical construction survey management method based on drone aerial photography, comprising:

[0111] S1: Upload the boundary information of the geotechnical construction area, build a geotechnical construction area model, divide the geotechnical construction area model, and obtain several groups of sub-geotechnical construction area models;

[0112] S2: Based on the corresponding area of the sub-geotechnical construction area model, collect surface images of the geotechnical construction area and perform feature highlighting processing on the collected surface images of the geotechnical construction area;

[0113] S3: Obtain the feature highlighting processing results of the surface image of the geotechnical construction area, and use the feature highlighting processing results to identify the dynamic risks of the geotechnical construction area;

[0114] S4: Continuously record the dynamic risk identification results of the geotechnical construction area and evaluate whether the current geotechnical construction is safe based on the continuously recorded identification results;

[0115] S5: When the assessment result shows that the current geotechnical construction is unsafe, the unsafe area in the geotechnical construction area is located and output.

[0116] In summary, during the operation of the platform in the above embodiment, the surface image of the geotechnical construction area is globally collected according to the set surface image collection logic of the geotechnical construction area, and then based on image analysis, the location of possible cracks on the surface of the geotechnical construction area is captured, and further joint analysis is performed based on the captured surface locations of the geotechnical construction area where cracks may exist, to evaluate and determine the construction safety risks of the geotechnical construction area, and when the assessment result is unsafe, it can also locate and provide feedback on the areas with higher surface risks in the geotechnical construction area, thereby providing construction safety survey and management for geotechnical construction to the greatest extent and in a comprehensive manner, and during the implementation stage of the solution, the demand for manual operation is low, and the overall solution is energy-saving, efficient, and intelligent; in addition, based on the further configuration of a geotechnical construction survey and management method based on drone aerial photography, auxiliary logic support is provided for the operation of the above platform, ensuring that the technical solution composed of the above platform and method is more stable and reliable in the specific implementation and application stage.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A geotechnical construction survey and management platform based on drone aerial photography, characterized by: include: Collection layer, identification layer and evaluation layer; The boundary information of the geotechnical construction area is uploaded through the acquisition layer. The acquisition layer constructs a geotechnical construction area model based on the uploaded boundary information, and simultaneously sets the model division logic. The geotechnical construction area model is divided based on the division logic to obtain several groups of sub-geotechnical construction area models. Each sub-geotechnical construction area model is used as an image acquisition target, and the surface image of the geotechnical construction area is collected. The surface image of the geotechnical construction area is synchronously sent to the recognition layer. The recognition layer receives the surface image of the geotechnical construction area and synchronously identifies the dynamic risk of the geotechnical construction area based on the surface image of each geotechnical construction area. The assessment layer receives the dynamic risk of the geotechnical construction area identified by the recognition layer in real time, assesses the safety of the geotechnical construction based on the dynamic risk of the geotechnical construction area, and simultaneously locates the unsafe area in the geotechnical construction area when the assessment result is that the geotechnical construction is unsafe. The recognition layer includes a receiving module, a processing module and a recognition module. The receiving module is used to receive the surface image of the geotechnical construction area and store the surface image of the geotechnical construction area. The processing module is used to obtain the surface image of the geotechnical construction area stored in the receiving module and perform feature highlighting processing on the surface image of the geotechnical construction area. The recognition module is used to traverse the surface image of the geotechnical construction area after feature highlighting processing and identify the dynamic risk of the geotechnical construction area based on the image. The dynamic risk identification logic of the geotechnical construction area is expressed as: Where: K is the dynamic risk performance value of the geotechnical construction area; u is the set of sub-geotechnical construction area models; k v is the dynamic risk performance value of the geotechnical construction area reflected by the sub-geotechnical construction area model of group v; d(b q ,b v+1 ) is the distance between the sub-image with the largest feature judgment value in the set of all sub-images that have an intersection with the adjacent sub-geotechnical construction area models in the grayscale image corresponding to the vth group of sub-geotechnical construction area models, which is divided into 3×3 groups of sub-images, and the sub-image with the largest feature judgment value in the set of all sub-images that have an intersection with the adjacent sub-geotechnical construction area models in the grayscale image corresponding to the v+1th group of sub-geotechnical construction area models; d(a q ,p0) is the distance between the center of the grayscale image corresponding to the v-th group of sub-geotechnical construction area model and the sub-image with the maximum feature judgment value in the set of all sub-images that do not have an intersection area with the adjacent sub-geotechnical construction area model in the grayscale image corresponding to the v-th group of sub-geotechnical construction area model; Among them, the larger the dynamic risk performance value K of the geotechnical construction area is, the lower the risk of the geotechnical construction area is; conversely, the higher the risk of the geotechnical construction area is. In the processing module, the feature highlighting processing operation for the surface image of the geotechnical construction area is as follows: Where Gray(i,j) is the output gray value of pixel (i,j); R(i,j), G(i,j), B(i,j) are the color components of pixel (i,j) based on R, G, B channels; ω1, ω2, ω3 are weights; χ is a constant offset; C is the feature judgment value; N, M are the rows and columns of the gray image; G x,y is the grayscale value of the pixel at the xth row and yth column; F x,y is the weighting coefficient of the pixel corresponding to the xth row and yth column; Among them, the weights ω1, ω2, and ω3 are set by the system end user, and the sum of the weights ω1, ω2, and ω3 is 1. The constant offset χ ≥ 0. Based on formula (1), each pixel in the surface image of the geotechnical construction area is processed to output the grayscale image of the surface image of the geotechnical construction area. x,y The value is subject to F x,y ∈(0,1], the closer the pixel point at row x and column y is to the center of the image F x,y The larger the value, the smaller the F x,y The smaller the value is; the grayscale image output by formula (1) is further divided into 3×3 groups of sub-images, and each group of sub-images is used as the calculation target of formula (2). After the feature judgment value C is obtained for each sub-image, each group of sub-images is divided into two groups of sub-image sets. One group of sub-image sets is the set of all sub-images that do not have an intersection area with the adjacent sub-geotechnical construction area model, and the other group of sub-image sets is the set of all sub-images that have an intersection area with the adjacent sub-geotechnical construction area model. A group of sub-images with the largest feature judgment value C is picked up from the two groups respectively, and the corresponding regional image is determined in the surface image of the geotechnical construction area based on the picked sub-image. The regional image determined in the surface image of the geotechnical construction area is the feature highlighting processing result of the surface image of the geotechnical construction area in the processing module.

2. The geotechnical construction survey and management platform based on drone aerial photography according to claim 1 is characterized in that: The acquisition layer includes a construction module, a division module, and a camera module. The construction module is used to upload geotechnical construction area boundary information and use the geotechnical construction area boundary information to construct a geotechnical construction area model. The division module is used to receive the geotechnical construction area model constructed in the construction module and divide the geotechnical construction area model to decompose the geotechnical construction area model into a plurality of sub-geotechnical construction area models. The camera module is used to pick up the model boundary coordinates of each sub-geotechnical construction area model, determine the acquisition area of the geotechnical construction area surface image based on the model boundary coordinates, and execute the acquisition of the geotechnical construction area surface image. Among them, the boundary information of the geotechnical construction area uploaded during the operation phase of the construction module, that is, no less than three groups of boundary coordinates of the geotechnical construction area, are connected to each other based on the boundary coordinates of the geotechnical construction area to form a closed area. The closed area is the geotechnical construction area model. The geotechnical construction area model is a two-dimensional model. The camera module is integrated by a panoramic camera. The camera module determines the boundary coordinates of the sub-geotechnical construction area model based on the boundary coordinates of the geotechnical construction area model and the division results of the sub-geotechnical construction area model. When the camera module collects the surface image of the geotechnical construction area, the image collection range is determined based on the boundary coordinates of the sub-geotechnical construction area model, and a panoramic image of the sub-geotechnical construction area model is collected, that is, the surface image of the geotechnical construction area.

3. The geotechnical construction survey and management platform based on drone aerial photography according to claim 2 is characterized in that: The division module is provided with a model division logic, and the division module divides the geotechnical construction area model based on the model division logic; The partitioning logic set in the partitioning module is expressed as: Calculating the size of the geotechnical construction area model based on the geotechnical construction area boundary information, setting the number and size of the sub-geotechnical construction area model divisions, and dividing the geotechnical construction area model according to the set number and size of the sub-geotechnical construction area model divisions, so that the geotechnical construction area model is divided into sub-geotechnical construction area models equal to the set number of divisions, and the sizes of the respective geotechnical construction area models are equal to each other; Among them, adjacent sub-geotechnical construction area models overlap with each other, and the model area of the overlapping sub-geotechnical construction area models is always smaller than half of the corresponding area of any group of models in the overlapping sub-geotechnical construction area models.

4. The geotechnical construction survey and management platform based on drone aerial photography according to claim 3 is characterized in that: Each sub-geotechnical construction area model obtained by dividing the geotechnical construction area model in the division module also obeys: Where: n is the set of sub-geotechnical construction area models; s(p i ∩p i+1 ) is the size of the intersection of the adjacent i-th group of sub-geotechnical construction area models and the i+1-th group of sub-geotechnical construction area models; is the size of the sub-geotechnical construction area model division set in the division logic; q is the number of sub-geotechnical construction area model divisions set in the division logic; S0 is the size of the geotechnical construction area model determined based on the geotechnical construction area boundary information.

5. The geotechnical construction survey and management platform based on drone aerial photography according to claim 1 is characterized in that: Each time the platform runs, it only collects a surface image of the geotechnical construction area for each sub-geotechnical construction area model once, and all collected surface images of the geotechnical construction area cover the entire geotechnical construction area; When receiving the surface image of the geotechnical construction area, the receiving module preferentially receives the surface image of the geotechnical construction area having a large intersection area with the surface image of the adjacent geotechnical construction area; The processing module runs continuously in the recognition layer, and each time it runs in the receiving module, it obtains a set of surface images of the geotechnical construction area based on the time sequence. After the processing module obtains the surface images of the geotechnical construction area and processes the surface images of the geotechnical construction area, the recognition module runs synchronously with the processing module.

6. The geotechnical construction survey and management platform based on drone aerial photography according to claim 1 is characterized in that: The assessment layer includes an assessment module, a positioning module, and an output module. The assessment module is used to continuously receive the dynamic risks of the geotechnical construction area identified in the identification layer, and evaluate whether the geotechnical construction is safe based on the continuously received dynamic risks of the geotechnical construction area. The positioning module is used to obtain the assessment result of whether the geotechnical construction is safe in the assessment module, and when the assessment result is negative, locate the unsafe area in the geotechnical construction area. The output module is used to receive the unsafe area in the geotechnical construction area located by the positioning module, obtain the coordinates of the unsafe area, and output them. The evaluation logic of whether geotechnical construction is safe in the evaluation module is expressed as follows: Where, K1, K2, K3, ... are the dynamic risk performance values of the geotechnical construction area continuously received by the assessment module; K O is the dynamic risk determination value of the geotechnical construction area; Among them, K1, K2, K3, ... are sorted based on the identification time sequence, and K1, K2, K3, ... are not less than three groups. K1 is the dynamic risk performance value of the geotechnical construction area identified the earliest, and the dynamic risk judgment value of the geotechnical construction area K O Based on the user customization on the system side, if any of the above formulas is true, it means that the current geotechnical construction status is unsafe; otherwise, it means that the current geotechnical construction status is safe.

7. The geotechnical construction survey and management platform based on drone aerial photography according to claim 6 is characterized in that: The positioning logic of the unsafe area in the geotechnical construction area in the positioning module is expressed as follows: K v1 >K v2 >K v3 >......; Where: K v1 , K v2 , K v3 , ...is the dynamic risk performance value of the geotechnical construction area reflected by the sub-geotechnical construction area model of group v based on K1, K2, K3, ...; Among them, K v1 , K v2 , K v3 , ... sorting based on recognition time sequence, K v1 The dynamic risk performance value of the geotechnical construction area identified earliest is based on the above formula. Each sub-geotechnical construction area model is used as the judgment target, and the area corresponding to the sub-geotechnical construction area model that meets the above formula is judged as an unsafe area in the geotechnical construction area.

8. The geotechnical construction survey and management platform based on drone aerial photography according to claim 1 is characterized in that: The receiving module is interactively connected to the processing module and the camera module through a wireless network, the identification module is interactively connected to the processing module through a wireless network, the camera module is interactively connected to the division module and the construction module through a wireless network, the identification module is interactively connected to the evaluation module through a wireless network, and the evaluation module is interactively connected to the positioning module and the output module through a wireless network.

9. A geotechnical construction survey and management method based on drone aerial photography, the method being an implementation method of the geotechnical construction survey and management platform based on drone aerial photography as claimed in any one of claims 1 to 8, characterized in that: include: S1: Upload the boundary information of the geotechnical construction area, build a geotechnical construction area model, divide the geotechnical construction area model, and obtain several groups of sub-geotechnical construction area models; S2: Based on the corresponding area of the sub-geotechnical construction area model, collect surface images of the geotechnical construction area and perform feature highlighting processing on the collected surface images of the geotechnical construction area; S3: Obtain the feature highlighting processing results of the surface image of the geotechnical construction area, and use the feature highlighting processing results to identify the dynamic risks of the geotechnical construction area; S4: Continuously record the dynamic risk identification results of the geotechnical construction area and evaluate whether the current geotechnical construction is safe based on the continuously recorded identification results; S5: When the assessment result shows that the current geotechnical construction is unsafe, the unsafe area in the geotechnical construction area is located and output.

Images