Drawing identification and contour reconstruction-based paying-off visualization method, device and equipment

Abstract

The embodiment of the invention discloses a drawing identification and contour reconstruction-based paying-off visualization method, device and equipment. A specific embodiment of the method comprises the steps of performing element feature extraction processing on an acquired drawing image to obtain an element feature vector set; generating digital drawing data; generating a theoretical contour model; correcting the spatial inclination deviation of the pay-off surface relative to the coordinate system of the equipment to obtain a calibrated coordinate system; generating actually measured contour data in the same coordinate system with the theoretical contour model; determining a distance difference value of each sampling point to obtain a distance difference value set; performing dynamic correction processing on the digital drawing data to obtain a dynamic correction drawing; and performing projection processing on each line corresponding to the line type to obtain a visual paying-off result. According to the implementation mode, the data read-write frequency and memory occupation can be reduced, the utilization rate of system resources is improved, and the time consumed by final paying off and consumed computing resources can be reduced.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to a method, apparatus, and device for drawing recognition and contour-based layout visualization. Background Technology

[0002] In the construction and decoration process, setting out lines is a core procedure that determines construction accuracy and subsequent project quality. It requires the precise layout of water and electricity points, various control lines, base layer positioning lines, and finished decoration surface lines. Currently, the common method for setting out lines in construction and decoration projects is to use equipment such as laser line markers or total stations to sequentially set out single lines. For example, when setting out wall control lines, construction workers first use a laser line marker to project horizontal or vertical lines, mark them, and then switch equipment or adjust the mode to sequentially set out the electromechanical point lines, base layer control lines, and finished decoration surface lines.

[0003] However, when using the above method to lay out lines for architectural decoration projects, the following technical problems often arise: Each layout task requires repeated operations to project different types of lines one by one. This results in the need to repeatedly load and switch drawing data for different lines during construction, increasing the number of data read / write operations and memory usage, thereby reducing the utilization rate of system resources. Setting up a single laser line marker is only suitable for projecting simple lines at a fixed distance. It cannot adaptively adjust the contour recognition accuracy and projection parameters according to the actual distance changes on the layout surface. As a result, contour deviations caused by inconsistent layout accuracy at different distances need to be recalculated, which increases the final layout time and computational resources consumed.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide methods, apparatus, electronic devices, and computer-readable media for drawing recognition and contour-based layout visualization to address one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a drawing recognition and contour-based layout visualization method. The method includes: extracting element features from an acquired drawing image to obtain a set of element feature vectors; generating digitized drawing data based on the set of element feature vectors; generating a theoretical contour model based on the digitized drawing data and a preset sampling density set; correcting the spatial tilt deviation of the layout surface relative to the equipment coordinate system based on a set of reference points marked by the user to obtain a calibrated coordinate system; generating measured contour data in the same coordinate system as the theoretical contour model based on the calibrated coordinate system; determining the distance difference between each sampling point based on the measured contour data and the theoretical contour model to obtain a set of distance differences; dynamically correcting the digitized drawing data based on the set of distance differences to obtain a dynamically corrected drawing; and, in response to detecting a line type selected by the user for projection, projecting each line corresponding to the selected line type based on the dynamically corrected drawing, real-time distance data, and a preset projection order to obtain a visualized layout result.

[0008] Secondly, some embodiments of this disclosure provide a drawing recognition and contour-based layout visualization device, the device comprising: a feature extraction unit configured to perform element feature extraction processing on the acquired drawing image to obtain an element feature vector set; a first generation unit configured to generate digital drawing data based on the aforementioned element feature vector set; a second generation unit configured to generate a theoretical contour model based on the aforementioned digital drawing data and a preset sampling density set; a correction unit configured to correct the spatial tilt deviation of the layout surface relative to the device coordinate system based on a set of reference points marked by the user to obtain a calibrated coordinate system; and a third generation unit. The unit is configured to generate measured contour data in the same coordinate system as the theoretical contour model based on the calibrated coordinate system. The determination unit is configured to determine the distance difference between each sampling point based on the measured contour data and the theoretical contour model to obtain a set of distance differences. The dynamic correction unit is configured to perform dynamic correction processing on the digitized drawing data based on the set of distance differences to obtain a dynamically corrected drawing. The projection unit is configured to respond to the detection of the line type selected by the user for projection, and perform projection processing on each line corresponding to the line type based on the dynamically corrected drawing, real-time distance data and preset projection order to obtain a visualized layout result.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: The drawing recognition and contour-based reconstruction visualization method of some embodiments of this disclosure can reduce the number of data read / write operations and memory usage, improve system resource utilization, and reduce the time and computational resources consumed in the final layout. Specifically, the increased number of data read / write operations and memory usage, leading to reduced system resource utilization, and the increased time and computational resources consumed in the final layout, are due to the following: Each layout task requires repeated operations to release different types of lines one by one, resulting in repeated loading and switching of drawing data for different lines during construction, increasing the number of data read / write operations and memory usage, thus reducing system resource utilization; Setting up a single laser line marker is only suitable for simple line projection at a fixed distance, and cannot adaptively adjust the contour recognition accuracy and projection parameters according to the actual distance changes of the layout surface, thus requiring recalculation of contour deviations caused by inconsistent layout accuracy at near and far distances, increasing the time and computational resources consumed in the final layout. Based on this, some embodiments of the drawing recognition and contour-based layout method disclosed herein firstly extract element features from the acquired drawing image to obtain a set of element feature vectors. This yields a set of element feature vectors for each element. Next, digital drawing data is generated based on the aforementioned set of element feature vectors. This yields digital drawing data including the set of element feature vectors. Then, a theoretical contour model is generated based on the aforementioned digital drawing data and a preset sampling density set. This yields a theoretical contour model of the layout surface. Next, based on a set of user-marked reference points, the spatial tilt deviation of the layout surface relative to the equipment coordinate system is corrected to obtain a calibrated coordinate system. This yields a calibrated coordinate system. Then, based on the calibrated coordinate system, measured contour data in the same coordinate system as the theoretical contour model is generated. This yields measured contour data of the layout surface on site. Finally, based on the measured contour data and the theoretical contour model, the distance difference between each sampling point is determined to obtain a set of distance differences. This yields a set of distance differences between each sampling point. Secondly, based on the aforementioned set of distance differences, the digitized drawing data is dynamically corrected to obtain a dynamically corrected drawing. Thus, the corrected dynamically corrected drawing is obtained. Finally, in response to detecting the line type selected by the user, based on the dynamically corrected drawing, real-time distance data, and a preset projection order, each line corresponding to the aforementioned line type is projected to obtain a visual layout result. Thus, the visualized layout result is obtained.Because it doesn't project different types of lines one by one, but instead generates structured digital drawing data by identifying and classifying elements in the drawing image, and then dynamically corrects the drawing to project multiple types of lines simultaneously, all line layout operations can be completed with a single load. This reduces data read / write operations and memory usage, improving system resource utilization. Furthermore, instead of using a single laser line marker with fixed parameters, it collects actual distance data at a preset sampling density using an infrared range sensor. Based on this data, it dynamically adjusts the laser power and line width, achieving adaptive projection at varying distances. This reduces contour deviations and redundant calculations caused by distance changes, thus shortening layout time and reducing computational resource consumption. Therefore, it reduces data read / write operations and memory usage, improves system resource utilization, and reduces the time and computational resources required for final layout. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the drawing recognition and contour-based layout visualization method according to the present disclosure; Figure 2 These are schematic diagrams of some embodiments of the drawing recognition and contour-based layout visualization device according to this disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1 A flow 100 of some embodiments of the drawing recognition and contour-based layout visualization method according to this disclosure is shown. The drawing recognition and contour-based layout visualization method includes the following steps: Step 101: Extract element features from the acquired drawing image to obtain a set of element feature vectors.

[0021] In some embodiments, the execution entity (e.g., a computer device) of the drawing recognition and contour-based layout method can perform element feature extraction processing on the acquired drawing image to obtain a set of element feature vectors. The drawing image can represent a CAD or PDF drawing acquired via a USB or wireless transmission interface. The element feature vectors in the set of element feature vectors can represent the feature vectors of elements extracted from the corresponding black-and-white binary image of the drawing image. These element feature vectors can be features of water and electricity points, control lines, electromechanical point positioning lines, base control lines, or finished surface lines. The water and electricity point features can represent the position coordinates and graphic symbols of terminal electrical appliances such as sockets, switches, and lamps identified in the drawing image. The control line features can represent lines used to establish spatial references, such as building axes, road centerlines, and elevation baselines. The electromechanical point positioning line features can represent the planar position of electromechanical equipment, switches, sockets, and lamps, and their corresponding pipeline center coordinates and extension direction lines. The pipeline center coordinates can represent the position of the pipeline in space. The aforementioned extension direction lines can characterize the approximate path and direction of pipelines extending in space. The aforementioned base layer control line features can characterize the baseline extracted based on the thickness of the decorative construction layer and architectural detail drawings. The aforementioned decorative construction layer thickness can characterize the sum of the thicknesses of all material layers in the decorative construction. Among all the aforementioned material layers, the material layer can be the base layer, leveling layer, or finishing layer. For example, the baseline can be the boundary of the base leveling layer or the keel installation control line. The aforementioned finished surface line features can characterize the elevation line, shape outline, and material junction line of the final finished surface of the finishing layer. The aforementioned shape outline line can characterize the lines that constitute the edge of an object or graphic. The aforementioned material junction line can characterize the junction line between different materials.

[0022] In some optional implementations of certain embodiments, the aforementioned execution entity may perform element feature extraction processing on the acquired drawing image through the following steps to obtain a set of element feature vectors: The first step is to perform noise removal processing on the aforementioned drawing image to obtain a denoised image. This denoised image represents the image obtained after noise removal processing of the aforementioned drawing image. In practice, the executing entity can use a Gaussian filter with a kernel size of 5×5 to remove noise from the drawing image, thus obtaining the denoised image.

[0023] The second step involves performing edge enhancement processing on the denoised image to obtain a black-and-white binary image. This black-and-white binary image represents the image obtained after edge enhancement processing of the denoised image. In practice, the executing entity can use the Sobel operator to perform edge enhancement processing on the denoised drawing image, converting the color drawing image into a black-and-white binary image to highlight lines and text annotations.

[0024] The third step is to perform feature extraction processing on the above black and white binary image to obtain a set of element feature vectors.

[0025] In addressing the aforementioned technical challenges in the application of this technology, particularly in scenario two—digital analysis of ancient building restoration drawings—the following technical issues arise: Traditional image recognition methods often confuse components of different forms when processing highly similar traditional architectural symbols such as brackets, corbels, and roof tiles. Furthermore, they struggle to simultaneously capture the multi-scale features of both macroscopic architectural outlines and microscopic component details, leading to incomplete extraction of restoration data and inaccurate positioning. Moreover, traditional single-scale recognition can only extract information in a single dimension, while extracting both macroscopic architectural outlines and microscopic component details from ancient building drawings increases computational overhead from repetitive image processing, resulting in lengthy and resource-intensive generation of element feature vector sets. Considering the following requirements for this application scenario—adaptability to complex drawings, high element similarity, and high accuracy—we have decided to adopt the following solution: Optionally, the aforementioned execution entity can perform feature extraction processing on the aforementioned black and white binary image through the following steps to obtain a set of element feature vectors: The first step involves performing a preliminary convolution process on the aforementioned black-and-white binary image to obtain an initial feature map. This initial feature map characterizes the feature map obtained after convolution processing the black-and-white binary image. In practice, the executing entity can input the aforementioned black-and-white binary image into a convolutional layer containing multiple 3×3 learnable convolutional kernels to obtain the initial feature map.

[0026] The second step involves spatial reconstruction of the initial feature map to obtain spatially refined features. These spatially refined features characterize the features obtained after feature separation and cross-reconstruction of the initial feature map. In practice, firstly, the execution entity can extract features from the initial feature map using a CBS convolutional block to obtain intermediate features. Then, these intermediate features are divided into two sub-features along the channel dimension, resulting in a first sub-feature and a second sub-feature. Finally, the first sub-feature is input into the spatial reconstruction unit of the channel reconstruction convolutional module for spatial redundancy removal, yielding the spatially refined features.

[0027] The third step involves performing channel reconstruction processing on the aforementioned spatial refinement features to obtain channel refinement features. These channel refinement features characterize the features obtained after performing feature separation, group convolution, and pointwise convolution on the channel dimension of the aforementioned spatial refinement features. In practice, the executing entity can input the aforementioned second sub-feature into the channel reconstruction unit of the channel reconstruction convolution module for redundancy removal between channels to obtain the spatial refinement features.

[0028] The fourth step involves performing a residual connection between the refined channel features and the initial feature map to obtain the joint optimized features. In practice, the executing entity can add the joint optimized features element-wise to the initial feature map to obtain the joint optimized features.

[0029] The fifth step involves generating a channel attention map based on the aforementioned joint optimization features. This channel attention map represents a weight vector, learned by an MLP after merging the spatial dimensions of the joint optimization features, used to dynamically weight each channel to highlight key features and suppress redundancy. In practice, firstly, the executing entity can merge the spatial dimensions of the joint optimization features to obtain a rearranged two-dimensional matrix. Then, a two-layer multilayer perceptron (MLP) is applied to this rearranged two-dimensional matrix to obtain the output features. Finally, the output features are replaced with the same dimensions as the joint optimization features to obtain the channel attention map.

[0030] The sixth step is to multiply the channel attention map and the joint optimized features element-wise to obtain the channel attention-enhanced features.

[0031] Step 7: Generate a spatial attention map based on the enhanced channel attention features described above. This spatial attention map represents the feature map obtained after convolution and activation processing of the enhanced channel attention features. In practice, the executing entity can use the sigmoid function to map the output values ​​of the enhanced channel attention features after applying the double convolutional layer to 0-1 to obtain the spatial attention map. The double convolutional layer can consist of two convolutional layers. The size of these two convolutional layers can be 7×7.

[0032] Step 8: Multiply the spatial attention map and the channel attention-enhanced features element-wise to obtain the attention-enhanced features. These attention-enhanced features characterize the features resulting from spatial feature enhancement of the channel attention-enhanced features.

[0033] Step nine involves performing multi-scale feature fusion processing on the aforementioned attention-enhancing features to obtain a multi-scale feature map. This multi-scale feature map represents the feature map obtained after multi-scale feature fusion processing of the attention-enhancing features. In practice, firstly, the execution entity can use a SimConv convolutional layer to reduce the number of channels in the attention-enhancing features by half, obtaining compressed features. Then, multiple max-pooling operations and feature concatenation are performed on the compressed features to obtain the target enhanced features. The number of max-pooling operations is not limited; for example, it can be 3. Finally, the SimConv convolutional layer restores the number of channels in the target enhanced features to the same number as the attention-enhancing features.

[0034] Step 10: Input the aforementioned multi-scale feature maps into the neck network and head network of the target neural network model to obtain the set of element feature vectors corresponding to the aforementioned drawing image. The aforementioned target neural network model can represent a deep learning model that takes the aforementioned black-and-white binary image as input and outputs the set of element feature vectors. The aforementioned target neural network model can represent a model based on the YOLOv8 network architecture. The aforementioned target neural network model can be trained in batches. The aforementioned neck network can adopt a Path Aggregation Network-Feature Pyramid Network (PAN-FPN) structure. The aforementioned head network can adopt a decoupled head structure. The aforementioned decoupled head structure can include several convolutional layers, classification branches, and regression branches.

[0035] The above-described technical solution, as an inventive point of this disclosure, solves technical problem two: "Incomplete extraction and inaccurate positioning of repair evidence lead to increased computational consumption of repeated image processing, resulting in longer time and higher resource consumption for generating element feature vector sets." The reasons for this are as follows: Traditional image recognition methods, when processing highly similar traditional architectural symbols such as brackets, corbels, and tilework, often confuse components of different forms. Furthermore, they struggle to simultaneously consider the multi-scale features of both macroscopic architectural outlines and microscopic component details, leading to incomplete extraction and inaccurate positioning of repair evidence. Moreover, traditional single-scale recognition can only capture single-dimensional information; extracting both macroscopic architectural outlines and microscopic component details from ancient architectural drawings increases computational consumption of repeated image processing, resulting in longer time and higher resource consumption for generating element feature vector sets. To achieve this effect, the disclosed drawing recognition and contour reconstruction-based layout method first performs spatial reconstruction, channel reconstruction, and residual connection processing on the initial feature map corresponding to the black-and-white binary image to obtain jointly optimized features. This effectively eliminates redundant features between components of different shapes and accurately distinguishes similar symbols such as brackets and corbels. Then, channel attention enhancement and spatial attention enhancement are applied to the aforementioned jointly optimized features to obtain attention-enhanced features, thereby increasing the focus on key repair annotation areas such as beam frame decay and column cracks. Finally, multi-scale max pooling operations are used to fuse local and global features, taking into account multi-scale features of both macroscopic building contours and microscopic component details. This ensures complete extraction and accurate positioning of repair data, thereby reducing the number of rework attempts and verification costs in digital modeling of ancient buildings, shortening the time spent on preliminary repair work, and reducing resource investment. Thus, the extraction of repair data is more complete and the positioning more accurate, reducing the computational consumption of repeated image processing, and consequently reducing the time and resources spent generating element feature vector sets.

[0036] Step 102: Generate digital drawing data based on the set of element feature vectors.

[0037] In some embodiments, the executing entity can generate digital drawing data based on the aforementioned set of element feature vectors. This digital drawing data can represent a drawing labeled with fields such as coordinates, type labels, priority, and line width. The type labels can represent the category corresponding to the element feature vectors in the aforementioned set. These type labels can be features of water and electricity points, control lines, electromechanical point positioning lines, base control lines, or finished surface lines. In practice, firstly, the executing entity can input the aforementioned set of element feature vectors into a Support Vector Machine (SVM) classifier for classification to obtain the type labels corresponding to each element feature vector in the set. Then, for each element feature vector in the aforementioned set, the vector coordinate data corresponding to the element feature vector stored in the drawing image is directly read. For example, the vector coordinate data can be the starting and ending coordinates of a line segment, or the center coordinates of a circle. Next, the priority corresponding to the element feature vector is determined by querying a preset priority mapping table. This priority mapping table can represent a table storing the correspondence between the aforementioned element feature vectors and their priorities. Secondly, the line width corresponding to the feature vector of the aforementioned element is read from the line width attribute of the drawing image. Finally, a structured data encapsulation method is used to generate a digital drawing image containing type labels, coordinates, priority, and line width.

[0038] Step 103: Generate a theoretical contour model based on the digital drawing data and the preset sampling density set.

[0039] In some embodiments, the executing entity can generate a theoretical contour model based on the aforementioned digital drawing data and a preset sampling density set. This theoretical contour model can represent a three-dimensional model reflecting the idealized shape of the layout surface. The theoretical contour model can include the theoretical coordinates and theoretical distance values ​​of the sampling points obtained based on the preset sampling density set. The theoretical distance values ​​can represent the theoretical distance from the sampling points to the equipment deployment center.

[0040] In some optional implementations of certain embodiments, the aforementioned execution entity can generate a theoretical contour model based on the aforementioned digital drawing data and a preset sampling density set through the following steps: The first step is to convert the aforementioned digital drawing data into a three-dimensional coordinate model with the equipment deployment center as the origin. This three-dimensional coordinate model can be labeled with distance parameters for each contour point relative to the equipment deployment center. The contour points can represent key geometric feature points in the drawing. These key geometric feature points can be points on the intersection of a wall and a floor, or points on a curved surface with the greatest curvature change. The equipment deployment center can represent the coordinates of the intersection of the rotation axes of the laser emitting modules after the laser line-laying device is set up on the construction site. The distance parameters represent the straight-line distance between each contour point and the equipment deployment center. In practice, firstly, the executing entity can use a coordinate transformation algorithm to convert the two-dimensional coordinates in the digital drawing data into three-dimensional coordinates with the equipment deployment center as the origin. Then, iterate through each contour point in the digital drawing data, determining the straight-line distance between each contour point and the equipment deployment center as a distance parameter, obtaining a set of distance parameters. Next, each distance parameter in the set of distance parameters is labeled as an attribute value on the corresponding contour point in the three-dimensional coordinate model, resulting in the three-dimensional coordinate model. Here, the specific type of the laser line-emitting device is not limited, as long as it can generate and output horizontal or vertical laser lines of different colors such as red, green, and blue. For example, the laser line-emitting device can be a multi-color laser level. The laser emitting module described above can be characterized as a component integrating a laser diode, collimating lens, driving circuit, heat dissipation structure, and positioning structure for laser emission.

[0041] The second step involves sampling the aforementioned layout surface according to the pre-defined sampling density set, obtaining a set of sampling point coordinates. The pre-defined sampling density in this set represents the sampling point density corresponding to different types of regions on the layout surface. For example, for planar regions, the sampling point density is one sampling point every 0.5 meters; for curved surfaces, it's one sampling point every 0.3 meters; and for irregularly shaped surfaces, it's one sampling point every 0.2 meters. The sampling point coordinates in this set represent the three-dimensional coordinates of discrete points laid out on the layout surface according to the pre-defined sampling density set. In practice, firstly, the executing entity can determine the region type of the layout surface by reading CAD layer attributes. Then, using the pre-defined sampling density corresponding to the determined region type from the pre-defined sampling density set, the layout surface is sampled to obtain the set of sampling point coordinates.

[0042] The third step involves generating a theoretical contour model based on the aforementioned 3D coordinate model and the set of sample point coordinates. In practice, firstly, the executing entity can project each contour point in the 3D coordinate model onto a 2D plane and connect them according to the projection geometry of the aforementioned drawing image to obtain the contour line. The projection geometry can be orthogonal projection. Then, for each sample point coordinate in the aforementioned set of sample point coordinates, in response to determining that the sample point corresponding to the aforementioned sample point coordinate is located on the aforementioned contour line, the distance from the aforementioned sample point to the aforementioned equipment deployment center is determined as the theoretical distance value of the aforementioned sample point. In response to determining that the aforementioned sample point is not located on the aforementioned contour line, a cubic spline interpolation algorithm (spline order 3) is used to determine the theoretical distance value of the aforementioned sample point coordinate based on the distance parameters of the two contour points on the aforementioned contour line that are closest to the aforementioned sample point. Next, a key-value pair data structure is used to integrate each sample point coordinate in the aforementioned set of sample point coordinates and its corresponding theoretical distance value to obtain a theoretical distance mapping table. Finally, a theoretical contour model is generated based on the aforementioned theoretical distance mapping table using the NURBS surface reconstruction algorithm.

[0043] Step 104: Based on the set of reference points marked by the user, the spatial tilt deviation of the laying surface relative to the equipment coordinate system is corrected to obtain the calibrated coordinate system.

[0044] In some embodiments, the execution entity can correct the spatial tilt deviation of the layout surface relative to the equipment coordinate system based on a set of reference points marked by the user, thereby obtaining a calibrated coordinate system. The set of reference points includes at least three reference points. The spatial tilt deviation characterizes the tilt deviation of the layout surface relative to the equipment coordinate system in three-dimensional space. The calibrated coordinate system characterizes the coordinate system obtained after calibrating the spatial tilt deviation of the layout surface at the construction site relative to the equipment coordinate system. The equipment coordinate system characterizes the actual coordinate system established with the laser layout device as the origin. In practice, firstly, the execution entity can collect the three-dimensional coordinates of each reference point in the set of reference points marked by the user and obtain the theoretical coordinates of each reference point from the digital drawing data. Then, using a coordinate transformation algorithm, the actual tilt angle of the wall, ground, or ceiling is determined based on the three-dimensional coordinates and corresponding theoretical coordinates of each reference point. Finally, using the Euler angle method, a rotation matrix and translation vector are generated based on the actual tilt angle to correct the spatial tilt deviation, resulting in a calibrated coordinate system.

[0045] Step 105: Generate measured contour data in the same coordinate system as the theoretical contour model, based on the calibrated coordinate system.

[0046] In some embodiments, the executing entity can generate measured contour data in the same coordinate system as the theoretical contour model, based on the calibrated coordinate system. The measured contour data can characterize the actual geometric shape of the layout surface at the construction site. The measured contour data can include spatial location and surface morphology. The spatial location can characterize the actual orientation and distance of the layout surface relative to the laser layout device. The surface morphology can characterize flatness, curvature, and the actual angle and position of facade transitions.

[0047] In some optional implementations of certain embodiments, the execution entity can generate measured contour data in the same coordinate system as the theoretical contour model by following these steps: The first step involves controlling the infrared ranging sensor to collect the actual distance data of each sampling point according to the calibrated coordinate system, thus obtaining an actual distance data set. The actual distance data in this set represents the measured and corrected distance between the sampling points (obtained after sampling at the preset sampling density set) and the equipment deployment center point. In practice, the executing entity first controls the infrared ranging sensor to measure each sampling point obtained according to the preset sampling density set, obtaining the original distance of each sampling point on the laying surface. Then, using the rotation matrix and translation vector, the obtained original distances are transformed from the equipment coordinate system to the calibrated coordinate system, resulting in the actual distance data set in the calibrated coordinate system.

[0048] The second step involves generating measured contour data in the same coordinate system as the theoretical contour model, based on the aforementioned actual distance data set. In practice, the executing entity can use a line fitting algorithm to generate measured contour data in the same coordinate system as the theoretical contour model, based on the aforementioned actual distance data set. This line fitting algorithm can be a spline interpolation algorithm.

[0049] Step 106: Based on the measured contour data and the theoretical contour model, determine the distance difference between each sampling point to obtain a set of distance differences.

[0050] In some embodiments, the execution entity can determine the distance difference between each sampling point based on the measured contour data and the theoretical contour model, thus obtaining a set of distance differences. The distance differences in this set can characterize the difference between the actual distance data and the theoretical distance value for each sampling point. In practice, firstly, for each sampling point included in the above-mentioned sampling points, the execution entity can determine the difference between the actual distance data and the theoretical distance value of the sampling point as a distance difference. Then, the obtained distance differences are defined as a set of distance differences.

[0051] Step 107: Based on the distance difference set, perform dynamic correction processing on the digitized drawing data to obtain dynamically corrected drawings.

[0052] In some embodiments, the execution entity can dynamically correct the digitized drawing data based on the aforementioned distance difference set to obtain a dynamically corrected drawing. The dynamically corrected drawing can represent the drawing obtained after correcting the digitized drawing data.

[0053] In addressing the technical challenges of the aforementioned background technologies, and specifically for scenario three: laying out the finishing lines for the walls of high-end hotel rooms, which requires simultaneously completing the precise placement of wall leveling control lines, bedside socket switch locations, wood veneer finish lines, concealed light trough outlines, and decorative border lines, the following technical issues often arise: the on-site walls exhibit various deviations, including overall tilt, localized protrusions, and depressions, with varying magnitudes and characteristics at different locations. Traditional line-by-line laying methods cannot compensate for all deviations simultaneously in a single operation, leading to the discovery of mismatches between the lines and the actual base layer after laying, necessitating repeated rework and adjustments. This significantly increases the difficulty and computational resource consumption for subsequent corrections to the digital drawings. Considering the following requirements for this application scenario: adaptability to multiple deviation types, accuracy in outline recognition at different distances, and simultaneous laying of multiple types of lines, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the aforementioned execution entity may perform dynamic correction processing on the aforementioned digitized drawing data based on the aforementioned distance difference set through the following steps to obtain dynamically corrected drawings: The first step involves determining that the distance differences in the aforementioned set of distance differences satisfy a preset deviation condition, and then identifying the sampling points corresponding to these distance differences as deviation sampling points, thus obtaining a set of deviation sampling points. The preset deviation condition can be that the distance differences in the aforementioned set of distance differences are greater than or equal to a first preset value. Here, the specific value of the first preset value is not limited. For example, the first preset value can be 1 mm.

[0054] The second step involves determining that, in response to the existence of consecutive deviation sampling points in the aforementioned set of deviation sampling points that satisfy a first preset correction condition, defining the region corresponding to these consecutive deviation sampling points as a linear deviation region. The first preset correction condition can be that the difference between the distances between any two consecutive deviation sampling points in the aforementioned set of deviation sampling points is less than or equal to a target threshold. The specific value of the target threshold is not limited here. For example, the target threshold could be 2 mm. The aforementioned linear deviation region can characterize the region of linear deviation (overall offset).

[0055] Thirdly, in response to determining that there are deviation sampling points in the aforementioned set of deviation sampling points that satisfy the second preset correction condition, the regions corresponding to each of the aforementioned deviation sampling points are defined as local deviation regions. The aforementioned second preset correction condition can be that there is a sudden change in the distance difference corresponding to one or a small number of sampling points in the aforementioned set of deviation sampling points. The aforementioned local deviation region can characterize a region of local deviation (protrusion or depression). Here, the specific number of sampling points included in the aforementioned small number of sampling points is not limited. The specific number of sampling points included in the aforementioned small number of sampling points can be 3.

[0056] Fourthly, in response to the determination that the curvature between the theoretical contour curve corresponding to the theoretical contour model and the actual contour curve corresponding to the measured contour data satisfies the third preset correction condition, the region corresponding to the measured contour data is defined as the contour deviation region. The theoretical contour curve can represent a continuous geometric line extracted from the digitized drawing data, reflecting the theoretical design shape of the layout surface. The actual contour curve can represent a continuous curve reconstructed from measured distance data collected on-site by an infrared ranging sensor, reflecting the actual geometric shape of the layout surface. The third preset correction condition can be that the mean curvature deviation between the theoretical contour curve and the actual contour curve at each sampling point is greater than or equal to 0.05.

[0057] The fifth step involves visually annotating the aforementioned linear deviation areas, local deviation areas, and contour deviation areas according to a preset color correspondence set, resulting in a visualized drawing. The preset color correspondence set represents the colors corresponding to different types of deviation areas in the digitized drawing data. For example, the color corresponding to a linear deviation area could be yellow, a local deviation area could be orange, and a contour deviation area could be red. The visualized drawing represents the drawing obtained after visually annotating the digitized drawing data. In practice, the executing entity can annotate linear deviation areas with yellow, local deviation areas with orange, and contour deviation areas with red.

[0058] Step 6: Based on the target algorithm set, the linear deviation areas, local deviation areas, and contour deviation areas included in the above-mentioned visualization result drawing are corrected to obtain a dynamically corrected drawing. The target algorithms in the target algorithm set represent algorithms for correcting different types of deviation areas. The dynamically corrected drawing represents the drawing obtained after correcting the above-mentioned visualization result drawing. In practice, the execution entity can use a coordinate translation algorithm to adjust the linear deviation areas in the above-mentioned visualization result drawing, use a local interpolation algorithm to adjust the local deviation areas in the above-mentioned visualization result drawing, and for the contour deviation areas, use spline interpolation to refit the contour curve and update the drawing model to obtain the dynamically corrected drawing.

[0059] The above-described technical solution, as an inventive point of this disclosure, solves technical problem three: "The subsequent correction of digital drawing data is difficult and consumes a lot of computational resources." The reasons for this difficulty and high computational resource consumption in subsequent correction of digital drawing data are as follows: The on-site wall surface exhibits various types of deviations, such as overall tilt, local protrusions, and depressions, and the magnitude and nature of these deviations vary at different locations. Traditional line-by-line laying-out methods cannot compensate for all deviations simultaneously in a single operation. This results in the discovery, after laying out the lines, that they do not match the actual base layer, requiring repeated rework and adjustments, thus making subsequent correction of digital drawing data difficult and consuming a lot of computational resources. To achieve this effect, the disclosed drawing recognition and contour reconstruction-based layout method automatically identifies linear deviations, local deviations, and contour deviations by comparing measured contour data with theoretical contour models point by point. Based on the type of deviation, it dynamically corrects the drawing data using coordinate translation, local interpolation, or contour refitting algorithms, generating a dynamically corrected drawing that integrates all on-site deviation information. This ensures that all lines accurately match the actual shape of the wall during the initial layout, eliminating the need for subsequent rework and repeated corrections, thereby reducing the difficulty and computational resource consumption of correcting digital drawing data. This reduces the difficulty and computational resource consumption of subsequent corrections to digital drawing data.

[0060] Step 108: In response to detecting the line type selected by the user for projection, the lines corresponding to the line type are projected based on the dynamically corrected drawing, real-time distance data and preset projection order to obtain a visual layout result.

[0061] In some embodiments, in response to detecting that the user has selected a line type for projection, the execution entity can perform projection processing on each line corresponding to the line type based on the dynamically corrected drawing, real-time distance data, and a preset projection order to obtain a visualized layout result. The visualized layout result characterizes the effect produced after the layout surface is laid out. The line type characterizes the type of line being projected. The line type can be a control line, outline line, electromechanical point positioning line, base control line, or finished surface line. The real-time distance data characterizes the distance from the projection point on each line corresponding to the line type to the equipment deployment center. The preset projection order characterizes the pre-set order in which the line types are projected. The preset projection order can be base control line, electromechanical point positioning line, control line, finished surface line, or outline line. The control line can be projected using a red laser, the outline line using a blue laser, the electromechanical point positioning line using a green laser, the base control line using a yellow laser, and the finished surface line using a purple laser.

[0062] In some optional implementations of certain embodiments, the aforementioned execution entity may, in response to detecting the user's selection of the line type to be projected, perform projection processing on each line corresponding to the aforementioned line type based on the aforementioned dynamically corrected drawing, real-time distance data, and preset projection order, thereby obtaining a visualized line layout result: The first step involves extracting and processing each line corresponding to the user-selected line type in the aforementioned dynamically corrected drawing to obtain a set of basic line data. This set of basic line data represents the starting and ending coordinates, line type (straight or curved), projected color, and line width of the corresponding line. In practice, firstly, for each line corresponding to the user-selected line type, the executing entity can directly read the starting and ending coordinates, line type, projected color, and line width of the line from the aforementioned dynamically corrected drawing as the basic line data. Then, the obtained basic line data is used to define the set of basic line data.

[0063] The second step is to perform the following steps for each line basic data in the above line basic data set: The first sub-step involves performing the following steps for each projection point of the line corresponding to the aforementioned basic line data: First, in response to determining that the real-time distance data between the projection point and the equipment deployment center meets a first preset threshold condition, the first laser projection information is determined as the laser projection information corresponding to the projection point. The first preset threshold condition can characterize that the actual distance data between the projection point and the equipment deployment center is greater than or equal to a second preset value. Here, the specific value of the second preset value is not limited. For example, the second preset value can be 10m. The first laser projection information can characterize the laser power and line width projected onto the projection point when the real-time distance data of the projection point meets the first preset threshold condition. The projection point can characterize a point where the line is projected at intervals of 0.1mm. In practice, the executing entity can increase the power of the projected laser to 90% of its rated power and control the line width to 1.2mm as the first laser projection information for the projection point.

[0064] Then, in response to determining that the real-time distance data between the projection point and the equipment deployment center meets the second preset threshold condition, the second laser projection information is determined as the laser projection information corresponding to the projection point. The second preset threshold condition can characterize that the actual distance data between the projection point and the equipment deployment center is less than or equal to a second preset value. Here, the specific value of the second preset value is not limited. For example, the second preset value can be 3m. The second laser projection information can characterize the laser power and line width projected onto the projection point when the real-time distance data of the projection point meets the second preset threshold condition. The projection point can characterize a point where the line is projected at intervals of 0.1mm. In practice, the executing entity can increase the power of the projected laser to 50% of the rated power and control the line width to 0.5mm as the laser projection information for the projection point. In response to the determination that the actual distance data between the projection point and the equipment deployment center does not meet the first preset threshold condition and does not meet the second preset threshold condition, the execution entity can increase the power of the projected laser to 70% of the rated power and control the line width to 0.8mm as the second laser projection information of the projection point.

[0065] The second sub-step involves determining the obtained laser projection information as a group of laser projection information for the aforementioned lines.

[0066] The third step is to determine the obtained laser projection information groups as a laser projection information set.

[0067] The fourth step involves projecting each line corresponding to the aforementioned basic line data set according to the preset projection order, the laser projection information set, and the basic line data set, to obtain a visualized line layout result. In practice, the executing entity can perform projection processing on each line according to the preset projection order, based on the starting coordinates, ending coordinates, line type (straight or curved), the color to be projected, and the line width, to obtain a visualized line layout result.

[0068] In addressing the technical challenges of the aforementioned background technologies, and specifically considering the fourth application scenario—the rock formations of grottoes like the Yungang Grottoes being constantly affected by weathering and earthquakes, resulting in minute cracks and deformations requiring long-term monitoring—traditional monitoring methods often present the following technical problems: they cannot dynamically correct the crack expansion process in real time, relying solely on periodic inspections to obtain phased data. Furthermore, each inspection necessitates a complete cloud scan and comparison of the entire site, repeatedly processing large amounts of data from unchanged areas, leading to a significant waste of computational resources. Considering the following requirements for this application scenario: adaptability to real-time dynamic monitoring and low computational resource consumption, we have decided to adopt the following solution: Optionally, after step 107, the aforementioned executing entity may also perform the following steps: The first step is to determine the target distance deviation set based on the actual distances to each projection point monitored in real time during the laying-out process. The target distance deviation in this set represents the absolute value of the difference between the actual distance to a projection point and its corresponding theoretical distance. In practice, firstly, the executing entity uses an infrared ranging sensor to continuously collect the actual distances from the equipment deployment center to each projection point on the laying-out surface at a sampling frequency of no less than 15Hz, obtaining the actual distance of each projection point. Then, the theoretical distance value of the corresponding projection point is read from the dynamically corrected drawing. Next, the absolute value of the difference between the theoretical distance value and the actual distance is determined as the target distance deviation. Finally, the obtained target distance deviations are defined as the target distance deviation set.

[0069] The second step involves, in response to determining that the target distance deviation in the aforementioned target distance deviation set meets a preset error threshold condition, controlling the laser line-laying device to emit a flashing laser at a preset frequency at the position corresponding to the target distance deviation for on-site early warning. The preset error threshold condition can be that the target distance deviation is greater than or equal to a fourth preset value. Here, the specific value of the fourth preset value is not limited. For example, the fourth preset value can be 2 mm. The preset frequency can be 3 Hz. In practice, the executing entity can control the laser line-laying device to emit a flashing laser at the preset frequency at the position corresponding to the target distance deviation for on-site early warning.

[0070] The third step involves generating an error distribution heatmap based on the aforementioned target distance deviation set. This heatmap uses different color gradients to represent the magnitude of deviation in each region. Red areas indicate larger deviations, while green areas indicate smaller deviations. In practice, the executing entity first divides the theoretical contour model into grid-like regions. These regions can be 100mm × 100mm in size. Then, the average target distance deviation of all sampling points within each region is determined as the region's deviation value. Next, a color mapping algorithm is used to linearly map the region's deviation value to a color band ranging from green to red. Finally, the colors obtained from mapping the region's deviation values ​​are displayed on the dynamically corrected drawing, resulting in the error distribution heatmap. This heatmap supports zooming and panning; users can click on any location on the map to view detailed deviation data for that point. This detailed deviation data can include the theoretical distance value, actual distance, target distance deviation, and measurement time.

[0071] Fourth, in response to the detection that the movement of the laser projection device or the deviation of the outline of the projection surface meets the preset triggering conditions, the following steps are executed: The first sub-step involves generating the boundary polygon coordinates corresponding to the continuous deviation region based on the target distance deviations of each sampling point. The continuous deviation region can represent a connected region where the target distance deviation of each sampling point is greater than or equal to the fourth preset value. The preset trigger condition can be that the target distance deviation of each sampling point is greater than or equal to the fourth preset value. The boundary polygon coordinates can represent the set of coordinates of the smallest convex or concave polygon enclosing the continuous deviation region in three-dimensional space. In practice, firstly, the executing entity can mark the sampling points corresponding to the target distance deviations greater than or equal to the fourth preset value in the target distance deviation set as candidate deviation points. Then, using a density-based spatial clustering algorithm, cluster analysis is performed on the marked candidate deviation points to group spatially adjacent candidate deviation points with the same deviation direction into continuous deviation regions. Next, a concave hull algorithm or a convex hull algorithm is applied to each clustered continuous deviation region to extract the boundary vertices of the smallest polygon enclosing the continuous deviation region. Finally, the vertices included in the boundary vertices are arranged in clockwise or counterclockwise order to obtain a sequence of polygon vertices in three-dimensional spatial coordinates as the boundary polygon coordinates.

[0072] The second sub-step involves adaptively re-sampling the point cloud in the continuous deviation region based on the coordinates of the boundary polygon, obtaining local point cloud data. This local point cloud data characterizes the point cloud data corresponding to the continuous deviation region. In practice, firstly, the executing entity can solve for the rigid body transformation matrix using the SVD decomposition method, based on the corresponding coordinates of at least three reference points in the coordinate system of the drawing and the local coordinate system of the laser line-laying device. Then, the rigid body transformation matrix is ​​applied to transform the coordinates of the boundary polygon to the local coordinate system of the laser line-laying device as the target area to be scanned. Secondly, the laser line-laying device is controlled to perform a helical scan of the target area. For areas within the target area where the distance deviation between targets is 2-3 mm, 3 points are sampled per square millimeter; for areas where the distance deviation between targets is 3-5 mm, 5 points are sampled per square millimeter; and for areas where the distance deviation between targets is greater than 5 mm, 8 points are sampled per square millimeter, thus obtaining local point cloud data.

[0073] The third sub-step involves registering and fusing the aforementioned local point cloud data with the global point cloud model of the aforementioned layout surface to obtain the reconstructed contour data. The global point cloud model represents the set of 3D point cloud data of the entity building corresponding to the layout surface obtained through laser scanning. The reconstructed contour data represents the updated measured contour data. In practice, firstly, the executing entity can use a coarse registration method to initially align the local point cloud data with the global point cloud model based on the pose of the laser layout device during scanning. Secondly, an iterative nearest-neighbor algorithm is used to iteratively search for nearest neighbor pairs, solve for the optimal rotation matrix and translation vector, and continuously reduce the registration error between the local point cloud data and the global point cloud model until it converges to a preset accuracy (e.g., 0.1 mm). Then, the registered local point cloud data replaces the original data in the corresponding region of the global point cloud model. Finally, a weighted average filter is used to smooth the replaced boundary region to obtain the reconstructed contour data.

[0074] Fifth, based on the reconstructed contour data, update the dynamically corrected drawing in real time. It should be noted that the method for updating the dynamically corrected drawing in real time based on the reconstructed contour data is the same as the method for correcting the digitized drawing data based on the measured contour data, and will not be repeated here.

[0075] The above-described technical solution, as an inventive point of this disclosure, addresses technical problem four: "The need to repeatedly process a large amount of data in unchanged areas leads to a serious waste of computing resources." The reasons for this repeated processing of data in unchanged areas and the resulting waste of computing resources are as follows: Traditional monitoring methods cannot dynamically correct the crack propagation process in real time; they can only obtain phased data through periodic inspections. Each inspection requires a complete global point cloud scan and comparison, repeatedly processing a large amount of data in unchanged areas, thus causing a serious waste of computing resources. If these factors are resolved, the repeated processing of data in large amounts of unchanged areas can be eliminated, reducing the serious waste of computing resources. To achieve this effect, the drawing recognition and contour reconstruction-based layout method of this disclosure automatically triggers local retesting and adaptive point cloud acquisition when equipment movement or excessive contour deviation is detected. The new data is registered and fused with the global point cloud model in real time to obtain the reconstructed contour. Based on the deviation between the reconstructed contour and the theoretical contour, the crack annotations in the drawing are dynamically updated, achieving real-time capture and correction of crack propagation. Therefore, the repeated processing of data in large amounts of unchanged areas can be eliminated, reducing the serious waste of computing resources.

[0076] The above-described embodiments of this disclosure have the following beneficial effects: The drawing recognition and contour-based layout method of some embodiments of this disclosure can reduce the number of data read / write operations and memory usage, improve system resource utilization, and reduce the time and computational resources consumed in the final layout. Specifically, the reason for increasing the number of data read / write operations and memory usage, thereby reducing system resource utilization, and increasing the time and computational resources consumed in the final layout is that: for each layout task, multiple repetitive operations are required to lay out different types of lines one by one, resulting in repeated loading and switching of drawing data for different lines during construction, increasing the number of data read / write operations and memory usage, thereby reducing system resource utilization; setting a single laser line marker is only suitable for simple line projection at a fixed distance, and cannot adaptively adjust the contour recognition accuracy and projection parameters according to the actual distance changes of the layout surface, thus requiring recalculation of contour deviations caused by inconsistent layout accuracy at near and far distances, increasing the time and computational resources consumed in the final layout. Based on this, some embodiments of the drawing recognition and contour-based layout method disclosed herein firstly extract element features from the acquired drawing image to obtain a set of element feature vectors. This yields a set of element feature vectors for each element. Next, digital drawing data is generated based on the aforementioned set of element feature vectors. This yields digital drawing data including the set of element feature vectors. Then, a theoretical contour model is generated based on the aforementioned digital drawing data and a preset sampling density set. This yields a theoretical contour model of the layout surface. Next, based on a set of user-marked reference points, the spatial tilt deviation of the layout surface relative to the equipment coordinate system is corrected to obtain a calibrated coordinate system. This yields a calibrated coordinate system. Then, based on the calibrated coordinate system, measured contour data in the same coordinate system as the theoretical contour model is generated. This yields measured contour data of the layout surface on site. Finally, based on the measured contour data and the theoretical contour model, the distance difference between each sampling point is determined to obtain a set of distance differences. This yields a set of distance differences between each sampling point. Secondly, based on the aforementioned set of distance differences, the digitized drawing data is dynamically corrected to obtain a dynamically corrected drawing. Thus, the corrected dynamically corrected drawing is obtained. Finally, in response to detecting the line type selected by the user, based on the dynamically corrected drawing, real-time distance data, and a preset projection order, each line corresponding to the aforementioned line type is projected to obtain a visual layout result. Thus, the visualized layout result is obtained.Because it doesn't project different types of lines one by one, but instead generates structured digital drawing data by identifying and classifying elements in the drawing image, and then dynamically corrects the drawing to project multiple types of lines simultaneously, all line layout operations can be completed with a single load. This reduces data read / write operations and memory usage, improving system resource utilization. Furthermore, instead of using a single laser line marker with fixed parameters, it collects actual distance data at a preset sampling density using an infrared range sensor. Based on this data, it dynamically adjusts the laser power and line width, achieving adaptive projection at varying distances. This reduces contour deviations and redundant calculations caused by distance changes, thus shortening layout time and reducing computational resource consumption. Therefore, it reduces data read / write operations and memory usage, improves system resource utilization, and reduces the time and computational resources required for final layout.

[0077] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a drawing recognition and contour-based layout method, and these device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0078] like Figure 2As shown, a drawing recognition and contour-based layout device 200 according to some embodiments includes: a feature extraction unit 201, a first generation unit 202, a second generation unit 203, a correction unit 204, a third generation unit 205, a determination unit 206, a dynamic correction unit 207, and a projection unit 208. The feature extraction unit 201 is configured to perform element feature extraction processing on the acquired drawing image to obtain a set of element feature vectors; the first generation unit 202 is configured to generate digitized drawing data based on the aforementioned set of element feature vectors; the second generation unit 203 is configured to generate a theoretical contour model based on the aforementioned digitized drawing data and a preset sampling density set; the correction unit 204 is configured to correct the spatial tilt deviation of the layout surface relative to the equipment coordinate system based on a set of reference points marked by the user to obtain a calibrated coordinate system; the third generation unit 205 is configured to, based on the aforementioned calibrated coordinate system, ... The system generates measured contour data in the same coordinate system as the theoretical contour model. A determining unit 206 is configured to determine the distance difference between each sampling point based on the measured contour data and the theoretical contour model, thus obtaining a set of distance differences. A dynamic correction unit 207 is configured to dynamically correct the digitized drawing data based on the set of distance differences, thus obtaining a dynamically corrected drawing. A projection unit 208 is configured to, in response to detecting the line type selected by the user, perform projection processing on each line corresponding to the line type based on the dynamically corrected drawing, real-time distance data, and a preset projection order, thus obtaining a visualized layout result.

[0079] It is understandable that the units and references described in the drawing recognition and contour reconstruction-based layout device 200 are... Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the drawing recognition and contour-based layout device 200 and the units contained therein, and will not be repeated here.

[0080] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device (such as a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0081] like Figure 3As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0082] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0083] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0084] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0085] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0086] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently without being assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: perform element feature extraction processing on the acquired drawing image to obtain a set of element feature vectors; generate digitized drawing data based on the set of element feature vectors; generate a theoretical contour model based on the digitized drawing data and a preset sampling density set; correct the spatial tilt deviation of the layout surface relative to the device coordinate system based on a set of reference points marked by the user to obtain a calibrated coordinate system; generate measured contour data in the same coordinate system as the theoretical contour model based on the calibrated coordinate system; determine the distance difference between each sampling point based on the measured contour data and the theoretical contour model to obtain a set of distance differences; perform dynamic correction processing on the digitized drawing data based on the set of distance differences to obtain a dynamically corrected drawing; and, in response to detecting the line type selected by the user for projection, perform projection processing on each line corresponding to the line type based on the dynamically corrected drawing, real-time distance data, and a preset projection order to obtain a visualized layout result.

[0087] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0089] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a feature extraction unit, a first generation unit, a second generation unit, a correction unit, a third generation unit, a determination unit, a dynamic correction unit, and a projection unit. The names of these units do not necessarily limit the specific unit; for example, the feature extraction unit may also be described as "performing element feature extraction processing on the acquired drawing image to obtain a set of element feature vectors."

[0090] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0091] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A drawing recognition and contour-based layout visualization method, characterized in that, include: The acquired drawing images are processed to extract element features, resulting in a set of element feature vectors; Based on the set of element feature vectors, digital drawing data is generated; Based on the digital drawing data and the preset sampling density set, a theoretical contour model is generated; Based on the set of reference points marked by the user, the spatial tilt deviation of the laying surface relative to the equipment coordinate system is corrected to obtain the calibrated coordinate system. Based on the calibrated coordinate system, the measured contour data in the same coordinate system as the theoretical contour model are generated; Based on the measured contour data and the theoretical contour model, the distance difference between each sampling point is determined, and a set of distance differences is obtained. Based on the set of distance differences, the digitized drawing data is dynamically corrected to obtain a dynamically corrected drawing; In response to detecting the line type selected by the user, the system projects each line corresponding to the line type based on the dynamically corrected drawing, real-time distance data, and preset projection order to obtain a visual layout result.

2. The method according to claim 1, characterized in that, The process of extracting element features from the acquired drawing image to obtain a set of element feature vectors includes: The drawing image is subjected to noise removal processing to obtain a denoised image; The denoised image is then subjected to edge enhancement processing to obtain a black and white binary image; The black-and-white binary image is subjected to feature extraction processing to obtain a set of element feature vectors.

3. The method according to claim 1, characterized in that, The process of generating a theoretical contour model based on the digitized drawing data and a preset sampling density set includes: The digitized drawing data is converted into a three-dimensional coordinate model with the equipment deployment center as the origin. The three-dimensional coordinate model is labeled with the distance parameters of each contour point relative to the equipment deployment center. Based on the preset sampling density set, the laying surface is sampled to obtain a set of sampling point coordinates; A theoretical contour model is generated based on the three-dimensional coordinate model and the set of sampling point coordinates.

4. The method according to claim 1, characterized in that, The step of generating measured contour data in the same coordinate system as the theoretical contour model based on the calibrated coordinate system includes: Based on the calibrated coordinate system, the infrared ranging sensor is controlled to collect the actual distance data of each sampling point to obtain the actual distance data set. Based on the actual distance data set, measured contour data in the same coordinate system as the theoretical contour model are generated.

5. The method according to claim 1, characterized in that, In response to detecting the line type selected by the user, based on the dynamically corrected drawing, real-time distance data, and preset projection order, the system projects each line corresponding to the line type to obtain a visualized line layout result, including: Extract each line corresponding to the line type selected by the user in the dynamically corrected drawing to obtain a set of basic line data; For each line basic data in the aforementioned line basic data set, perform the following steps: For each projection point of the line corresponding to the basic line data, perform the following steps: In response to determining that the real-time distance data between the projection point and the equipment deployment center meets a first preset threshold condition, the first laser projection information is determined as the laser projection information corresponding to the projection point; In response to determining that the real-time distance data between the projection point and the equipment deployment center meets the second preset threshold condition, the second laser projection information is determined as the laser projection information corresponding to the projection point; The obtained laser projection information is determined as the laser projection information group of the line; Each group of laser projection information obtained is defined as a laser projection information set; Based on the preset projection order, the laser projection information set, and the line basic data set, each line corresponding to the line basic data set is projected to obtain a visualized line layout result.

6. A drawing recognition and contour-based layout visualization device, characterized in that, include: The feature extraction unit is configured to perform element feature extraction processing on the acquired drawing image to obtain a set of element feature vectors; The first generation unit is configured to generate digital drawing data based on the set of element feature vectors; The second generation unit is configured to generate a theoretical contour model based on the digital drawing data and a preset sampling density set. The correction unit is configured to correct the spatial tilt deviation of the laying surface relative to the equipment coordinate system based on the set of reference points marked by the user, so as to obtain the calibrated coordinate system. The third generation unit is configured to generate measured contour data in the same coordinate system as the theoretical contour model, based on the calibrated coordinate system. The determining unit is configured to determine the distance difference of each sampling point based on the measured contour data and the theoretical contour model, thereby obtaining a set of distance differences; The dynamic correction unit is configured to perform dynamic correction processing on the digitized drawing data according to the set of distance differences to obtain a dynamically corrected drawing; The projection unit is configured to, in response to detecting the line type selected by the user, project each line corresponding to the line type based on the dynamically corrected drawing, real-time distance data and preset projection order, to obtain a visualized line layout result.

7. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images