Lane light planning method, device and equipment and storage medium

Abstract

The application relates to the technical field of architectural design, and discloses a lane lamp planning method, device, equipment and storage medium.The method comprises the following steps: extracting a fire compartment image of a fire compartment design drawing from an obtained building model; identifying the fire compartment image to determine lane information in the image; correcting the lane information to obtain target lane information, and calculating the area of a corresponding lane region according to the target lane information; calculating the illumination of the lane region based on a preset illumination calculation formula to determine the arrangement quantity of lane lamps in the lane region; and planning the lane lamps based on the arrangement quantity, the installation height, the installation mode and the arrangement form of the lamps to obtain a corresponding lane lamp arrangement scheme.The scheme improves the accuracy of lane lamp arrangement by processing the lane information in the fire compartment image, meets the requirements of different arrangement forms, and improves the arrangement efficiency.

Description

Technical Field

[0001] This invention relates to the field of architectural design technology, and in particular to a method, apparatus, device and storage medium for lane lighting planning. Background Technology

[0002] Accelerating the integrated application of Building Information Modeling (BIM) technology throughout the entire lifecycle of engineering projects, improving data exchange and security standards, strengthening digital collaboration across design, production, and construction stages, and promoting the delivery and application of digital results throughout the entire engineering construction process are new requirements proposed in the "Construction Industry Development Plan." Since the data sources for BIM are primarily concentrated in the design phase, digital production faces significant challenges.

[0003] Lane lighting layout is an essential part of the design process. Currently, with both 2D and 3D forward design methods existing, efficiency-enhancing plugins are primarily used for auxiliary design. The design results are then manually reviewed and adjusted to meet the requirements of construction drawings and relevant standards. Existing layout methods fall into two categories: the first is based on 2D drafting software (CAD) and uses efficiency-enhancing plugins for two-point, linear, and rectangular layouts; the second is based on 3D modeling software (BIM), which identifies lane lines and arranges lights at fixed intervals along those lines. Therefore, how to reduce manual intervention time, achieve more accurate layout results, and simultaneously meet the requirements of different layout forms to significantly improve layout efficiency has become a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The main objective of this invention is to improve the accuracy of lane light layout by processing lane information in fire compartment images, thereby meeting the requirements of different layout forms and improving layout efficiency.

[0005] The first aspect of this invention provides a lane light planning method, comprising: acquiring a building model and extracting a fire compartment image of a fire compartment design drawing from the building model; identifying the fire compartment image to determine lane information in the fire compartment image; correcting the lane information to obtain target lane information, and calculating the area of ​​the corresponding target lane region based on the target lane information; calculating the illuminance of the target lane region based on a preset illuminance calculation formula to determine the number of lane lights to be arranged in the target lane region; and planning the lane lights based on the number of lane lights, as well as the installation height, installation method, and arrangement form of the lane lights, to obtain a lane light arrangement scheme corresponding to the fire compartment image.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the step of identifying the fire compartment image and determining the lane information in the fire compartment image includes: identifying the fire compartment image, obtaining lane line images in the fire compartment image, and identifying the lane line images using a preset lane line recognition model to obtain lane line recognition results; sampling the lane lines based on the lane line recognition results to obtain multiple sampling points corresponding to the lane lines; and determining the lane information in the fire compartment image based on the multiple sampling points corresponding to the lane lines and preset historical lane line recognition results, wherein the lane information includes the lane line color and lane line type of the lane lines.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of sampling the lane line based on the lane line recognition result to obtain multiple sampling points corresponding to the lane line includes: determining the lane line fitting equation corresponding to the lane line based on the lane line recognition result; and sampling the lane line based on the lane line fitting equation and the start and end point data corresponding to the lane line to obtain multiple sampling points corresponding to the lane line.

[0008] Optionally, in a third implementation of the first aspect of the present invention, determining the lane information in the fire compartment image based on multiple sampling points corresponding to the lane lines and preset historical lane line recognition results includes: establishing a multi-dimensional feature vector based on saturation and hue information in a preset HSV color space; constructing a lane line pixel set based on the multiple sampling points, and converting the RGB colors of all lane line pixels in the lane line pixel set to the HSV color space; classifying all lane line pixels in the lane line pixel set according to the multi-dimensional feature vector, and normalizing the classified multi-dimensional feature vector to obtain a normalized result; and classifying the normalized result using an SVM support vector machine classifier to determine the lane lines in the fire compartment image, wherein the lane lines include the lane line type and the lane line color.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the step of correcting the lane information to obtain target lane information includes: identifying the centerline of the lane information based on a preset machine learning model to obtain the lane line to be corrected, which includes multiple reference points; determining a correction point within a preset area corresponding to each reference point, correcting the reference point to the correction point, and fitting the correction point using a preset sliding window method to obtain a fitted line; and correcting the lane line to be corrected according to the fitted line to obtain the target lane information.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the step of calculating the area of ​​the corresponding target lane region based on the target lane information includes: determining the target lane region corresponding to the target lane line based on the target lane information; mapping each pixel in the target lane region to the three-dimensional coordinate system of the fire compartment to obtain the coordinates of each pixel in the three-dimensional coordinate system of the fire compartment; and calculating the area of ​​the target lane region corresponding to the target lane line based on the coordinates.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, before identifying the fire compartment image and determining the lane information in the fire compartment image, the method further includes: detecting the fire compartment image and determining whether the fire compartment data and lane information contained in the fire compartment image are complete.

[0012] A second aspect of the present invention provides a lane light planning device, comprising: an extraction module for acquiring a building model and extracting a fire compartment image of a fire compartment design drawing from the building model; an identification module for identifying the fire compartment image and determining lane information in the fire compartment image; a calculation module for correcting the lane information to obtain target lane information and calculating the area of ​​the corresponding target lane region based on the target lane information; a determination module for performing illuminance calculation on the target lane region based on a preset illuminance calculation formula and determining the number of lane lights corresponding to the target lane region; and a planning module for planning the lane lights based on the number of lane lights, as well as the installation height, installation method, and arrangement form of the lane lights, to obtain a lane light arrangement scheme corresponding to the fire compartment image.

[0013] Optionally, in a first implementation of the second aspect of the present invention, the identification module includes: an identification unit, configured to identify the fire compartment image, obtain lane line images in the fire compartment image, and identify the lane line images using a preset lane line identification model to obtain lane line identification results; a sampling unit, configured to sample the lane lines based on the lane line identification results to obtain multiple sampling points corresponding to the lane lines; and a determination unit, configured to determine lane information in the fire compartment image based on the multiple sampling points corresponding to the lane lines and preset historical lane line identification results, wherein the lane information includes the lane line color and lane line type of the lane lines.

[0014] Optionally, in a second implementation of the second aspect of the present invention, the sampling unit is specifically used to: determine the lane line fitting equation corresponding to the lane line based on the lane line recognition result; and sample the lane line based on the lane line fitting equation and the start and end point data corresponding to the lane line to obtain multiple sampling points corresponding to the lane line.

[0015] Optionally, in a third implementation of the second aspect of the present invention, the determining unit is specifically used for: establishing a multi-dimensional feature vector based on saturation and hue information in a preset HSV color space; constructing a lane line pixel set based on the multiple sampling points, and converting the RGB colors of all lane line pixels in the lane line pixel set to the HSV color space; classifying all lane line pixels in the lane line pixel set according to the multi-dimensional feature vector, and normalizing the classified multi-dimensional feature vector to obtain a normalized result; classifying the normalized result using an SVM support vector machine classifier to determine the lane lines in the fire compartment image, wherein the lane lines include the lane line type and the lane line color.

[0016] Optionally, in a fourth implementation of the second aspect of the present invention, the calculation module is specifically used to: identify the center line of the lane information based on a preset machine learning model to obtain the lane line to be corrected containing multiple reference points; determine a correction point within a preset area corresponding to each reference point, correct the reference point to the correction point, and fit the correction point through a preset sliding window method to obtain a fitted line; and correct the lane line to be corrected according to the fitted line to obtain the target lane information.

[0017] Optionally, in a fifth implementation of the second aspect of the present invention, the calculation module is further configured to: determine the target lane area corresponding to the target lane line based on the target lane information; map each pixel in the target lane area to the three-dimensional coordinate system of the fire compartment to obtain the coordinates of each pixel in the three-dimensional coordinate system of the fire compartment; and calculate the area of ​​the target lane area corresponding to the target lane line based on the coordinates.

[0018] Optionally, in a sixth implementation of the second aspect of the present invention, the lane light planning device further includes: a judgment module, used to detect the fire compartment image and determine whether the fire compartment data and lane information contained in the fire compartment image are complete.

[0019] A third aspect of the present invention provides a lane light planning device, comprising: a memory and at least one processor, wherein the memory stores instructions, and the memory and the at least one processor are interconnected via a circuit;

[0020] The at least one processor invokes the instructions in the memory to cause the lane light planning device to perform the various steps of the lane light planning method described above.

[0021] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the steps of the lane light planning method described above.

[0022] The technical solution provided by this invention involves extracting fire compartment images from the fire compartment design drawings of an acquired building model; identifying the fire compartment images to determine lane information; correcting the lane information to obtain target lane information; calculating the area of ​​the corresponding lane region based on the target lane information; calculating the illuminance of the lane region based on a preset illuminance calculation formula to determine the number of lane lights to be arranged in the lane region; and planning the lane lights based on the number of lights, as well as the installation height, installation method, and arrangement form to obtain the corresponding lane light arrangement scheme. This solution improves the accuracy of lane light arrangement by processing the lane information in the fire compartment images, meets the requirements of different arrangement forms, and improves the arrangement efficiency. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the first embodiment of the lane light planning method provided by the present invention;

[0024] Figure 2 A schematic diagram of a second embodiment of the lane light planning method provided by the present invention;

[0025] Figure 3 A schematic diagram of the third embodiment of the lane light planning method provided by the present invention;

[0026] Figure 4 A schematic diagram of the first embodiment of the lane light planning device provided by the present invention;

[0027] Figure 5 A schematic diagram of a second embodiment of the lane light planning device provided by the present invention;

[0028] Figure 6 This is a schematic diagram of an embodiment of the lane light planning device provided by the present invention. Detailed Implementation

[0029] This invention provides a lane light planning method, apparatus, device, and storage medium. The technical solution first extracts fire compartment images from an acquired building model; identifies the lane information within the fire compartment images; corrects the lane information to obtain target lane information; and calculates the area of ​​the corresponding lane region based on the target lane information. Illuminance is calculated for the lane region using a preset illuminance calculation formula to determine the number of lane lights to be arranged in the lane region. Based on the number of lights, as well as their installation height, installation method, and arrangement, lane light planning is performed to obtain a corresponding lane light arrangement scheme. This solution improves the accuracy of lane light arrangement by processing the lane information in the fire compartment images, meets the requirements of different arrangement forms, and enhances arrangement efficiency.

[0030] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The first embodiment of the lane light planning method in this invention includes:

[0032] 101. Obtain the building model and extract the fire compartment images from the fire compartment design drawings from the building model;

[0033] In this embodiment, a building model is acquired, and fire compartment images from the fire compartment design drawing are extracted from the building model. Specifically, a .RVT format BIM model built by the architectural and structural professionals using 3D modeling software (Revit) is read, and the completeness of information such as fire compartments, driveway lines, and driveway widths is checked.

[0034] By reading fire compartments from the building model and obtaining their outlines, these fire compartments are presented as detailed project items in the current viewport for preview. Users can select fire compartments for driveway lighting based on their needs, either individually or in multiple selections. The driveway lighting arrangement within each fire compartment is relatively independent. Simultaneously, lane lines are read by name to obtain lane width information, which will be used in subsequent steps.

[0035] 102. Identify the fire compartment images and determine the lane information within them;

[0036] In this embodiment, the fire compartment image is identified to determine the lane information within the fire compartment image. Specifically, centerline identification is performed on the lane information based on a preset machine learning model to obtain a lane line to be corrected, which includes multiple reference points. Specifically, an image including the lane line is acquired, and the lane line to be corrected is identified from it. The lane line can be sampled according to a preset sampling interval to obtain multiple reference points on the lane line.

[0037] In another approach, the lane line can be processed based on its alignment to determine multiple inflection points as reference points. These inflection points can be, for example, points where the lane line's alignment changes. Other methods can also be used to process the lane line and obtain these reference points. For instance, the lane line can be sampled at preset sampling intervals to obtain some reference points, and further processed based on its alignment to determine other inflection points as reference points, thus obtaining multiple reference points for the lane line.

[0038] 103. Correct the lane information to obtain the target lane information, and calculate the area of ​​the corresponding target lane region based on the target lane information;

[0039] In this embodiment, the lane information is corrected to obtain target lane information, and the area of ​​the corresponding target lane region is calculated based on the target lane information. Specifically, in the implementation, the center points of the sliding window during the sliding process can be connected according to a preset sliding window movement sequence to obtain the corrected lane line, thus realizing the correction of the lane line.

[0040] The lane line correction locations include free endpoints, turns, T-junctions, cross intersections, and intersections with fire compartment outlines. At fire compartment outline intersections, all lane lines are cut off by the fire compartment outline, meaning the lane lines are grouped according to fire compartments, and the lane lines of each fire compartment are relatively independent. At free endpoints, the endpoints are extended along the direction of lane line travel to the fire compartment outline or the walls and columns of the civil engineering data model, based on the shortest distance, and the extension terminates upon encountering a wall (column / fire compartment outline). At turns, when the bending angle is [85, 120], the longer lane line is extended by 1 / 2 lane width; the shorter lane line is cut off by 1 / 2 lane width. At T-junctions, the vertical lane line corresponding to the T is cut off by 1 / 2 lane width. At cross intersections, when intersecting with the main lane line, the non-main lane line is cut off by 1 / 2 lane width. When two non-main lane lines intersect, the lane with fewer intersection points is cut off, with the cut-off length being 1 / 2 lane line length.

[0041] 104. Calculate the illuminance of the target lane area based on the preset illuminance calculation formula, and determine the number of lane lights to be arranged in the target lane area;

[0042] In this embodiment, illuminance is calculated for the target lane area based on a preset illuminance calculation formula to determine the number of lane lights to be installed in the target lane area. Specifically, based on the area of ​​the target lane area generated in step 103, illuminance is calculated independently for each target lane area. First, the selection parameters of the luminaires are determined, including power, luminous flux, number of light sources, color rendering index, color temperature, etc.; further, the design parameters within the lane area are automatically obtained, including illuminance requirement value, utilization coefficient, maintenance coefficient, and current power density value; these parameters are then substituted into the preset illuminance calculation formula:

[0043] E = (Φ × N) × (U) × (K) / (A)

[0044] Wherein: Φ refers to the luminous flux of a single lamp, which is generally selected according to the lamp sample (luminous flux of a single lamp = number of light sources in the lamp × luminous flux of the light source), N refers to the number of lamps, U refers to the lamp utilization factor, K refers to the lamp maintenance factor, and A refers to the area.

[0045] The number N of lane lights in the target lane area is determined according to the calculation formula. The calculated number N is rounded up; for example, if N = 1.1, then N is rounded to 2; if N = 0.8, then N is rounded to 1.

[0046] 105. Based on the number of lane lights, as well as their installation height, installation method, and layout, lane light planning is carried out to obtain the lane light layout scheme corresponding to the fire compartment image.

[0047] In this embodiment, the lane lights are planned based on the number of lights, their installation height, installation method, and layout, resulting in a lane light layout scheme corresponding to the fire compartment image. In specific application scenarios, the lane lights are mainly installed using slinging, which can be divided into chain hoisting and cable tray hoisting. The installation height refers to the distance between the lane light and the ground (reference elevation is the building elevation); the rotation angle refers to the angle between the center line of the light fixture and the lane line; the layout can be divided into single-row and double-row layouts: in a single-row layout, the number of rows is 1 and the number of columns is N. In a single-row layout, the lights are evenly distributed on the lane line; in a double-row layout, the number of rows is 2 and the number of columns is N; in a double-row layout, the lights are evenly distributed on both sides of the lane line. In this case, the number of lane lights N calculated in step 104 needs to be corrected. When N is odd, it needs to be rounded up to an even number. For example, when N = 7, the number of lane lights N is 8.

[0048] Based on steps 104 and 105, calculate the coordinates of each lamp. The lamps are arranged uniformly, illustrated by a double-row arrangement: calculate the lamp spacing, d = 2L / N; calculate the distance between the lamp and the lane line, w = W / 4; read the lamp installation height h; calculate the relative coordinates of each lamp, taking the leftmost and bottommost points of the lane area as the coordinate points, then the coordinates of the lamps can be represented as ((n-0.5)d, 0.25W, h), ((n-0.5)d, 0.75W, h); where 1≤n≤N / 2.

[0049] In this embodiment of the invention, fire compartment images from fire compartment design drawings are extracted from an acquired building model; the fire compartment images are identified to determine lane information; the lane information is corrected to obtain target lane information, and the area of ​​the corresponding lane region is calculated based on the target lane information; illuminance is calculated for the lane region based on a preset illuminance calculation formula to determine the number of lane lights to be arranged in the lane region; based on the number of lights, as well as the installation height, installation method, and arrangement form of the lights, the lane lights are planned to obtain the corresponding lane light arrangement scheme. This scheme improves the accuracy of lane light arrangement by processing the lane information in the fire compartment images, meets the requirements of different arrangement forms, and improves the arrangement efficiency.

[0050] Please see Figure 2 The second embodiment of the lane light planning method in this invention includes:

[0051] 201. Obtain the building model and extract the fire compartment images from the fire compartment design drawings from the building model;

[0052] 202. Recognize the fire compartment image, obtain the lane line image in the fire compartment image, and recognize the lane line image through the preset lane line recognition model to obtain the lane line recognition result;

[0053] In this embodiment, the fire compartment image is identified to obtain the lane line image in the fire compartment image, and the lane line image is identified by a preset lane line recognition model to obtain the lane line recognition result. Specifically, in this embodiment, when identifying lane lines, it is necessary to first obtain the lane line image collected at the current time, and then use a pre-trained lane line recognition model to identify the lane line image, thereby obtaining the lane line recognition result at the current time, such as a lane line binary image, which may contain one or more lane lines.

[0054] The lane line recognition model can be trained based on existing deep learning models, including but not limited to various deep neural networks (DNN), convolutional neural networks (CNN), support vector machines (SVM), decision trees, random forest models, etc. How to train the lane line recognition model can be flexibly set by those skilled in the art according to actual needs, and no specific limitation is made here.

[0055] 203. Based on the lane line recognition results, determine the lane line fitting equation corresponding to the lane line;

[0056] In this embodiment, based on the lane line recognition results, the lane line fitting equation corresponding to each lane line is determined. Specifically, the lane line recognition results may also include the lane line fitting equation corresponding to each lane line, as well as the lane line start and end point information. The lane line fitting equation is to fit a line based on the information of all lane line points corresponding to the same lane line, so that these lane line points are located as close as possible to this line. For example, it can be expressed in the following cubic equation form:

[0057] y = ax³ + bx² + cx + d

[0058] Where x represents the column coordinate of the image, y represents the row coordinate of the image, and a, b, c, and d are the coefficients of the equation.

[0059] However, since trained lane recognition algorithms inevitably contain some recognition error, not all actually identified lane points can perfectly match the lane line fitting equation for each lane line. Furthermore, the intervals between the identified lane point intervals are uncertain, making them difficult to directly use for subsequent lane line color and type recognition. Therefore, assuming the accuracy of the lane line fitting equation is acceptable, this embodiment uses the lane line start and end points as constraints and employs the lane line fitting equation to determine multiple sampling points using a uniformly spaced sampling method. While some of these sampling points may not be the lane line points actually identified by the algorithm, they may be closer to the actual lane lines. Therefore, the resulting error in subsequent lane line color and type recognition is acceptable.

[0060] 204. Based on the lane line fitting equation and the corresponding start and end point data of the lane line, sample the lane line to obtain multiple sampling points corresponding to the lane line;

[0061] In this embodiment, based on the lane line fitting equation and the corresponding start and end point data of the lane line, the lane line is sampled to obtain multiple sampling points corresponding to the lane line. Specifically, the uniform sampling method can use the image column coordinate x as the independent variable of the equation and sample at intervals of 2 or more pixels. The reason for sampling at equal intervals rather than continuous sampling is mainly to improve the efficiency of lane line recognition, which also meets the real-time requirements of lane line recognition in autonomous driving scenarios.

[0062] 205. Establish a multi-dimensional feature vector based on saturation and hue information in the preset HSV color space;

[0063] In this embodiment, a multi-dimensional feature vector is established based on saturation and hue information in a preset HSV color space. HSV (Hue, Saturation, Value) is a color space created by A.R. Smith in 1978 based on the intuitive characteristics of color; it is also known as the Hexcone Model. In this model, the parameters of color are hue (H), saturation (S), and value (V). Hue H...

[0064] Measured in degrees, the range is 0° to 360°, calculated counterclockwise starting from red. Red is 0°, green is 120°, and blue is 240°. Their complementary colors are: yellow is 60°, cyan is 180°, and violet is 300°.

[0065] Saturation (S) indicates how closely a color approximates a spectral color. A color can be considered the result of mixing a spectral color with white. The greater the proportion of the spectral color, the closer the color is to the spectral color, and the higher the saturation. High saturation results in a deep and vibrant color. Spectral colors have zero white light component, reaching their highest saturation. The typical value ranges from 0% to 100%; the higher the value, the more saturated the color.

[0066] Lightness (V): Lightness represents the brightness of a color. For light source colors, the lightness value is related to the luminance of the light source; for object colors, this value is related to the transmittance or reflectance of the object. It typically ranges from 0% (black) to 100% (white). RGB and CMY color models are hardware-oriented, while the HSV (Hue Saturation Value) color model is user-oriented.

[0067] The 3D representation of the HSV model evolved from an RGB cube. Imagine observing from the white vertices along the diagonal of the cube towards the black vertices; you will then see the hexagonal shape of the cube. The hexagonal boundaries represent colors, the horizontal axis represents saturation, and brightness is measured along the vertical axis.

[0068] 206. Construct a set of lane line pixels based on multiple sampling points, and convert the RGB colors of all lane line pixels in the set to the HSV color space;

[0069] In this embodiment, a set of lane line pixels is constructed based on multiple sampling points, and the RGB colors of all lane line pixels in the set are converted to the HSV color space. Specifically, when performing lane line color recognition, this embodiment can first use the saturation and hue information defined in the HSV (Hue-Saturation-Value) color space to establish a multi-dimensional feature vector Vtemplate. For example, a 360-dimensional feature vector can be established, with saturation normalized into 36 groups and hue normalized into 10 groups.

[0070] Then, obtain all sampling points to establish a set S of lane line pixels. Convert the RGB colors of all pixels in this set S to the HSV color space. Then, based on the previously obtained feature vector Vtemplate, classify all sampling points in set S and normalize the classified feature vectors to obtain Vlane. Finally, use the SVM (Support Vector Machine) classifier to classify Vlane, thereby obtaining the color classification of the lane lines.

[0071] 207. Based on the multidimensional feature vector, classify all lane line pixels in the set of lane line pixels, and normalize the classified multidimensional feature vector to obtain the normalized result.

[0072] In this embodiment, all lane line pixels in the lane line pixel set are classified according to the multidimensional feature vector, and the classified multidimensional feature vector is normalized to obtain the normalized result.

[0073] The normalization method has two forms: one transforms the number into a decimal between (0, 1), and the other transforms a dimensional expression into a dimensionless expression. This method is primarily proposed for ease of data processing, mapping data to the 0-1 range for faster and more convenient processing, and should be categorized under digital signal processing. Specifically, normalization is a method of simplifying calculations, transforming a dimensional expression into a dimensionless expression, becoming a pure scalar. For example, complex impedance can be normalized to: Z = R + jωL = R(1 + jωL / R), where the complex part becomes a pure scalar without dimensions.

[0074] 208. Use an SVM (Support Vector Machine) classifier to classify the normalized results and determine the lane lines in the fire compartment image. The lane lines include lane line type and lane line color.

[0075] In this embodiment, an SVM (Support Vector Machine) classifier is used to classify the normalized results and determine the lane lines in the fire compartment image. The lane lines include lane line type and lane line color. Specifically, the lane line identification results from historical moments are used as prior information. Based on the information from multiple sampling points corresponding to each lane line at the current moment, the lane line color (e.g., white or yellow) and lane line type (e.g., solid or dashed) at the current moment are determined, thus providing reliable data support for the fusion positioning module and other components.

[0076] 209. Correct the lane information to obtain the target lane information, and calculate the area of ​​the corresponding target lane region based on the target lane information;

[0077] 210. Calculate the illuminance of the target lane area based on the preset illuminance calculation formula, and determine the number of lane lights to be arranged in the target lane area;

[0078] 211. Based on the number of lane lights, as well as their installation height, installation method, and layout, lane light planning is carried out to obtain the lane light layout scheme corresponding to the fire compartment image.

[0079] Steps 201 and 209-211 in this embodiment are similar to steps 101 and 103-105 in the first embodiment, and will not be repeated here.

[0080] In this embodiment of the invention, fire compartment images from fire compartment design drawings are extracted from an acquired building model; the fire compartment images are identified to determine lane information; the lane information is corrected to obtain target lane information, and the area of ​​the corresponding lane region is calculated based on the target lane information; illuminance is calculated for the lane region based on a preset illuminance calculation formula to determine the number of lane lights to be arranged in the lane region; based on the number of lights, as well as the installation height, installation method, and arrangement form of the lights, the lane lights are planned to obtain the corresponding lane light arrangement scheme. This scheme improves the accuracy of lane light arrangement by processing the lane information in the fire compartment images, meets the requirements of different arrangement forms, and improves the arrangement efficiency.

[0081] Please see Figure 3 The third embodiment of the lane light planning method in this invention includes:

[0082] 301. Obtain the building model and extract the fire compartment images from the fire compartment design drawings from the building model;

[0083] 302. Detect the fire compartment images and determine whether the fire compartment data and lane information contained in the fire compartment images are complete;

[0084] In this embodiment, the fire compartment image is inspected to determine whether the fire compartment data and lane information contained in the fire compartment image are complete. Specifically, the civil engineering module inspects the fire compartment image to determine whether the fire compartment data and lane information contained in the fire compartment image are complete. The purpose of this inspection is to check the completeness of the information; therefore, this step cannot directly extract information without checking its completeness. This is because the extracted information represents the input conditions for the function's operation, and incomplete information will lead to program errors. It cannot be guaranteed that the civil engineering module necessarily possesses this information.

[0085] Specifically, the system reads the .RVT format BIM model built using Revit 3D modeling software by architects and structural engineers, and checks the completeness of information such as fire compartments, driveway lines, and driveway widths. Fire compartments are retrieved by name to obtain their outlines, and then presented as detailed projects in the current viewport for preview. Users can select fire compartments for driveway lighting based on their needs, either individually or in multiple selections. The driveway lighting arrangement within each fire compartment is relatively independent. Simultaneously, driveway lines are retrieved by name to obtain driveway width information, which will be used in subsequent steps.

[0086] 303. Identify the fire compartment images and determine the lane information within them;

[0087] 304. Based on a preset machine learning model, centerline identification is performed on lane information to obtain lane lines to be corrected, which contain multiple reference points;

[0088] In this embodiment, centerline identification is performed on lane information based on a preset machine learning model to obtain a lane line to be corrected containing multiple reference points. Specifically, an image including the lane line is acquired, and the lane line to be corrected is identified from it. The lane line can be sampled according to a preset sampling interval to obtain multiple reference points on the lane line.

[0089] In another approach, the lane line can be processed based on its alignment to determine multiple inflection points as reference points. These inflection points can be, for example, points where the lane line's alignment changes. Other methods can also be used to process the lane line and obtain these reference points. For instance, the lane line can be sampled at preset sampling intervals to obtain some reference points, and further processed based on its alignment to determine other inflection points as reference points, thus obtaining multiple reference points for the lane line.

[0090] In this embodiment, regardless of the method used to obtain the lane line to be corrected, the lane line to be corrected can be a lane line obtained based on the lane line reflection value base map. Of course, other methods can also be used to obtain the initial lane line. The lane line to be corrected can also be referred to as the initial lane line.

[0091] 305. Determine correction points within the preset area corresponding to each reference point, correct the reference points to the correction points, and fit the correction points using a preset sliding window method to obtain the fitted line;

[0092] In this embodiment, a correction point is determined within a preset area corresponding to each reference point. The reference point is corrected to the correction point, and the correction point is fitted using a preset sliding window method to obtain a fitted line. Specifically, the reference point can be moved from its original position to the position of the marker point with the highest confidence. Each of the multiple reference points is moved to the position of the marker point with the highest confidence, resulting in a moved reference point. The position of each reference point is moved to the position of the marker point with the highest confidence corresponding to that reference point, thus resulting in multiple moved reference points. According to a preset sliding window size, the sliding window is slid along the lane line, and the moved reference points inside the sliding window during the sliding process are fitted to obtain a fitted line. The fitted line may include multiple moved reference points.

[0093] 306. Correct the lane line to be corrected based on the fitted line to obtain the target lane information;

[0094] In this embodiment, the lane line to be corrected is modified based on the fitted line to obtain the target lane information. Specifically, the center point of the sliding window is determined based on the fitted line; the lane line is then modified based on the center point of the sliding window. The center point of the sliding window can be the projection point of a sampling point onto the fitted line, i.e., a moved sampling point. This moved sampling point can also be referred to as the projection point of the sampling point.

[0095] In practice, the center points of the sliding window can be connected according to the preset sliding window movement sequence to obtain the corrected lane line, thus realizing the correction of the lane line. The lane line correction locations include free endpoints, turns, T-junctions, cross intersections, and intersections with fire compartment outlines. At fire compartment outline intersections, all lane lines are cut off by the fire compartment outline, meaning the lane lines are grouped according to fire compartments, and the lane lines of each fire compartment are relatively independent. At free endpoints, the endpoints are extended along the direction of lane line travel to the fire compartment outline or the walls and columns of the civil engineering data model, based on the shortest distance, and the extension terminates upon encountering a wall (column / fire compartment outline). At turns, when the bending angle is [85, 120], the longer lane line is extended by 1 / 2 lane width; the shorter lane line is cut off by 1 / 2 lane width. At T-junctions, the vertical lane line corresponding to the T is cut off by 1 / 2 lane width. At cross intersections, when intersecting with the main lane line, the non-main lane line is cut off by 1 / 2 lane width. When two non-main lane lines intersect, the lane with fewer intersection points is cut off, with the cut-off length being 1 / 2 lane line length.

[0096] 307. Based on the target lane information, determine the target lane area corresponding to the target lane line;

[0097] In this embodiment, the target lane area corresponding to the target lane line is determined based on the target lane information. The target lane area is drawn based on the corrected lane line and lane width, and the target lane area is mostly rectangular.

[0098] 308. Map each pixel in the target lane area to the three-dimensional coordinate system of the fire compartment to obtain the coordinates of each pixel in the three-dimensional coordinate system of the fire compartment.

[0099] In this embodiment, each pixel in the target lane area is mapped to the three-dimensional coordinate system of the fire compartment to obtain the coordinates of each pixel in the three-dimensional coordinate system of the fire compartment. Specifically, each pixel in the area to be identified can be mapped to the image physical coordinate system, where the image physical coordinate system indicates the actual physical location of the area to be identified. It is established on the image with the origin O1 at the focal point of the camera's light source and the image plane (called the principal point of the image), and the imaging coordinate system xy is established on the image in physical units. The unit of the coordinate system is millimeters, and (x, y) represents the coordinates of each pixel in the area to be identified in the image physical coordinate system.

[0100] 309. Based on the coordinates, calculate the area of ​​the region corresponding to the target lane line;

[0101] In this embodiment, the area of ​​the target lane region corresponding to the target lane line is calculated based on the coordinates. Specifically, after calculating the coordinates of each pixel in the three-dimensional coordinate system of the fire compartment, the actual area of ​​the region to be identified can be calculated using existing or future area calculation formulas.

[0102] 310. Calculate the illuminance of the target lane area based on the preset illuminance calculation formula, and determine the number of lane lights to be arranged in the target lane area;

[0103] 311. Based on the number of lane lights, as well as their installation height, installation method, and layout, lane light planning is carried out to obtain the lane light layout scheme corresponding to the fire compartment image.

[0104] Steps 301, 303, and 310-311 in this embodiment are similar to steps 101-102 and 105 in the first embodiment, and will not be repeated here.

[0105] In this embodiment of the invention, fire compartment images from fire compartment design drawings are extracted from an acquired building model; the fire compartment images are identified to determine lane information; the lane information is corrected to obtain target lane information, and the area of ​​the corresponding lane region is calculated based on the target lane information; illuminance is calculated for the lane region based on a preset illuminance calculation formula to determine the number of lane lights to be arranged in the lane region; based on the number of lights, as well as the installation height, installation method, and arrangement form of the lights, the lane lights are planned to obtain the corresponding lane light arrangement scheme. This scheme improves the accuracy of lane light arrangement by processing the lane information in the fire compartment images, meets the requirements of different arrangement forms, and improves the arrangement efficiency.

[0106] The lane light planning method in the embodiments of the present invention has been described above. The lane light planning device in the embodiments of the present invention will be described below. Please refer to [link / reference]. Figure 4The first embodiment of the lane light planning device in this invention includes:

[0107] Extraction module 401 is used to acquire a building model and extract the fire compartment image of the fire compartment design drawing from the building model;

[0108] The identification module 402 is used to identify the fire compartment image and determine the lane information in the fire compartment image;

[0109] The calculation module 403 is used to correct the lane information to obtain target lane information, and calculate the area of ​​the corresponding target lane region based on the target lane information.

[0110] The determination module 404 is used to perform illuminance calculation on the target lane area based on a preset illuminance calculation formula, and determine the number of lane lights to be arranged in the target lane area.

[0111] The planning module 405 is used to plan the lane lights based on the number of lane lights, as well as the installation height, installation method and layout of the lane lights, to obtain the lane light layout scheme corresponding to the fire compartment image.

[0112] In this embodiment of the invention, fire compartment images from fire compartment design drawings are extracted from an acquired building model; the fire compartment images are identified to determine lane information; the lane information is corrected to obtain target lane information, and the area of ​​the corresponding lane region is calculated based on the target lane information; illuminance is calculated for the lane region based on a preset illuminance calculation formula to determine the number of lane lights to be arranged in the lane region; based on the number of lights, as well as the installation height, installation method, and arrangement form of the lights, the lane lights are planned to obtain the corresponding lane light arrangement scheme. This scheme improves the accuracy of lane light arrangement by processing the lane information in the fire compartment images, meets the requirements of different arrangement forms, and improves the arrangement efficiency.

[0113] Please see Figure 5 A second embodiment of the lane light planning device in this invention specifically includes:

[0114] Extraction module 401 is used to acquire a building model and extract the fire compartment image of the fire compartment design drawing from the building model;

[0115] The identification module 402 is used to identify the fire compartment image and determine the lane information in the fire compartment image;

[0116] The calculation module 403 is used to correct the lane information to obtain target lane information, and calculate the area of ​​the corresponding target lane region based on the target lane information.

[0117] The determination module 404 is used to perform illuminance calculation on the target lane area based on a preset illuminance calculation formula, and determine the number of lane lights to be arranged in the target lane area.

[0118] The planning module 405 is used to plan the lane lights based on the number of lane lights, as well as the installation height, installation method and layout of the lane lights, to obtain the lane light layout scheme corresponding to the fire compartment image.

[0119] In this embodiment, the identification module 402 includes:

[0120] The recognition unit 4021 is used to recognize the fire compartment image, obtain the lane line image in the fire compartment image, and recognize the lane line image through a preset lane line recognition model to obtain the lane line recognition result.

[0121] The sampling unit 4022 is used to sample the lane line based on the lane line recognition result to obtain multiple sampling points corresponding to the lane line;

[0122] The determining unit 4023 is used to determine the lane information in the fire compartment image based on multiple sampling points corresponding to the lane lines and preset historical lane line recognition results, wherein the lane information includes the lane line color and lane line type of the lane lines.

[0123] In this embodiment, the sampling unit 4022 is specifically used for:

[0124] Based on the lane line recognition results, determine the lane line fitting equation corresponding to the lane line;

[0125] Based on the lane line fitting equation and the corresponding start and end point data of the lane line, the lane line is sampled to obtain multiple sampling points corresponding to the lane line.

[0126] In this embodiment, the determining unit 4023 is specifically used for:

[0127] A multi-dimensional feature vector is established based on saturation and hue information in the preset HSV color space;

[0128] A set of lane line pixels is constructed based on the multiple sampling points, and the RGB colors of all lane line pixels in the set are converted to the HSV color space.

[0129] Based on the multidimensional feature vector, all lane line pixels in the lane line pixel set are classified, and the classified multidimensional feature vector is normalized to obtain the normalization result.

[0130] The normalized results are classified using an SVM (Support Vector Machine) classifier to determine the lane lines in the fire compartment image, wherein the lane lines include the lane line type and the lane line color.

[0131] In this embodiment, the calculation module 403 is specifically used for:

[0132] Based on a preset machine learning model, the centerline of the lane information is identified to obtain the lane line to be corrected, which contains multiple reference points.

[0133] A correction point is determined within a preset area corresponding to each reference point. The reference point is corrected to the correction point, and the correction point is fitted using a preset sliding window method to obtain a fitted line.

[0134] The lane line to be corrected is corrected based on the fitted line to obtain the target lane information.

[0135] In this embodiment, the calculation module 403 is further configured to:

[0136] Based on the target lane information, determine the target lane area corresponding to the target lane line;

[0137] Map each pixel in the target lane area to the three-dimensional coordinate system of the fire compartment to obtain the coordinates of each pixel in the three-dimensional coordinate system of the fire compartment;

[0138] Based on the coordinates, calculate the area of ​​the target lane region corresponding to the target lane line.

[0139] In this embodiment, the lane light planning device further includes:

[0140] The judgment module 406 is used to detect the fire compartment image and determine whether the fire compartment data and lane information contained in the fire compartment image are complete.

[0141] In this embodiment of the invention, fire compartment images from fire compartment design drawings are extracted from an acquired building model; the fire compartment images are identified to determine lane information; the lane information is corrected to obtain target lane information, and the area of ​​the corresponding lane region is calculated based on the target lane information; illuminance is calculated for the lane region based on a preset illuminance calculation formula to determine the number of lane lights to be arranged in the lane region; based on the number of lights, as well as the installation height, installation method, and arrangement form of the lights, the lane lights are planned to obtain the corresponding lane light arrangement scheme. This scheme improves the accuracy of lane light arrangement by processing the lane information in the fire compartment images, meets the requirements of different arrangement forms, and improves the arrangement efficiency.

[0142] above Figure 4 and Figure 5 The lane light planning device in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The lane light planning device in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0143] Figure 6 This is a schematic diagram of a lane light planning device 800 provided in an embodiment of the present invention. The lane light planning device 800 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 810 (e.g., one or more processors) and a memory 820, and one or more storage media 830 (e.g., one or more mass storage devices) storing application programs 833 or data 832. The memory 820 and storage media 830 can be temporary or persistent storage. The program stored in the storage media 830 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the lane light planning device 800. Furthermore, the processor 810 may be configured to communicate with the storage media 830 and execute the series of instruction operations in the storage media 830 on the lane light planning device 800 to implement the steps of the lane light planning method provided in the above-described method embodiments.

[0144] The lane light planning device 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input / output interfaces 860, and / or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 6 The lane light planning device structure shown does not constitute a limitation on the lane light planning device provided in this application. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0145] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the lane light planning method described above.

[0146] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0147] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0148] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A lane light planning method characterized by, The lane light planning method comprises: acquire a building model, and extract a fire compartment image of a fire compartment design drawing from the building model; identify the fire compartment image to determine lane information in the fire compartment image; correct the lane information to obtain target lane information, and calculate an area of a target lane region corresponding to the target lane information; calculate the illumination of the target lane region based on a preset illumination calculation formula to determine the arrangement number of the lane lights corresponding to the target lane region; plan the lane lights based on the arrangement number, the installation height, the installation method and the arrangement form of the lane lights to obtain a lane light arrangement scheme corresponding to the fire compartment image.

2. The lane light planning method of claim 1, wherein, The identification of the fire compartment image to determine the lane information in the fire compartment image comprises: identify the fire compartment image to obtain a lane line image in the fire compartment image, and identify the lane line image through a preset lane line identification model to obtain a lane line identification result; sample the lane line based on the lane line identification result to obtain a plurality of sampling points corresponding to the lane line; determine the lane information in the fire compartment image according to the plurality of sampling points corresponding to the lane line and a preset historical lane line identification result, wherein the lane information comprises a lane line color and a lane line type of the lane line.

3. The lane light planning method of claim 2, wherein, The sampling of the lane line based on the lane line identification result to obtain a plurality of sampling points corresponding to the lane line comprises: determine a lane line fitting equation corresponding to the lane line based on the lane line identification result; sample the lane line based on the lane line fitting equation and start and end point data corresponding to the lane line to obtain a plurality of sampling points corresponding to the lane line.

4. The lane light planning method of claim 2, wherein, The determination of the lane information in the fire compartment image according to the plurality of sampling points corresponding to the lane line and a preset historical lane line identification result comprises: establish a multi-dimensional feature vector based on saturation information and hue information in a preset HSV color space; construct a lane line pixel point set based on the plurality of sampling points, and convert RGB colors of all lane line pixel points in the lane line pixel point set to an HSV color space; classify all lane line pixel points in the lane line pixel point set according to the multi-dimensional feature vector, and normalize the classified multi-dimensional feature vector to obtain a normalization result; classify the normalization result by using an SVM support vector machine classifier to determine the lane line in the fire compartment image, wherein the lane line comprises the lane line type and the lane line color.

5. The lane light planning method of claim 1, wherein, The correction of the lane information to obtain target lane information comprises: identify a center line of the lane information based on a preset machine learning model to obtain a to-be-corrected lane line containing a plurality of reference points; determine a correction point in a preset region corresponding to each reference point, correct the reference point to the correction point, and fit the correction point by using a preset sliding window method to obtain a fitting line; According to the fitting line, the to-be-corrected lane line is corrected to obtain target lane information.

6. The lane light planning method of claim 1, wherein, The calculating the area of the target lane area corresponding to the target lane information comprises: According to the target lane information, a target lane area corresponding to the target lane line is determined. Each pixel point in the target lane area is mapped to a three-dimensional coordinate system of the fire compartment to obtain a coordinate of each pixel point in the three-dimensional coordinate system of the fire compartment. According to the coordinate, the area of the target lane area corresponding to the target lane line is calculated.

7. The lane light planning method of claim 1, wherein, Before the identifying the fire compartment image and determining the lane information in the fire compartment image, the method further comprises: Detecting the fire compartment image to determine whether the fire compartment data and the lane information contained in the fire compartment image are complete.

8. A lane light planning device characterized by comprising: The lane light planning device comprises: An extraction module configured to obtain a building model and extract a fire compartment image of a fire compartment design drawing from the building model; An identification module configured to identify the fire compartment image to determine lane information in the fire compartment image; A calculation module configured to correct the lane information to obtain target lane information, and calculate the area of a target lane area corresponding to the target lane information; A determination module configured to perform illumination calculation on the target lane area based on a preset illumination calculation formula to determine the arrangement number of lane lights corresponding to the target lane area; A planning module configured to plan lane lights based on the arrangement number, the installation height, the installation mode and the arrangement form of the lane lights to obtain a lane light arrangement scheme corresponding to the fire compartment image.

9. A lane light planning device characterized by comprising: The lane light planning device comprises a memory and at least one processor, the memory stores instructions, and the memory and the at least one processor are interconnected by a circuit; The at least one processor invokes the instructions in the memory to enable the lane light planning device to perform each step of the lane light planning method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program, when executed by a processor, implements each step of the lane light planning method of any one of claims 1-7.

Images