A garden to be painted road surface painting area calculation method, system and storage medium

Abstract

The application discloses a kind of park to be painted road surface painting area calculation method, this method first obtains target area time series change aerial image and three-dimensional point cloud data;Based on point cloud, construct ground elevation model, and utilize time series image to identify light interference area and static ground object, reconstruct pixel in interference area to restore real ground texture;Fusion analysis is carried out to the texture data after reconstruction and elevation model, and according to texture consistency and elevation constraint, distinguish to be painted and non-painting area;Finally, accurately calculate painting engineering quantity in digital modeling environment.The application is verified by the dual verification mechanism of texture restoration and elevation filtering, effectively eliminates the interference of shadow, reflection and non-painting ground object, solves the area calculation distortion problem caused by light blocking in traditional measurement, significantly improves the calculation accuracy and efficiency, improves the accuracy of engineering budget.

Description

Technical Field

[0001] This application relates to the field of engineering cost technology, specifically to a method, system, and storage medium for calculating the area of ​​road surface to be painted in a park. Background Technology

[0002] In the maintenance of facilities in industrial parks, logistics bases, and large factories, road marking, anti-corrosion coatings, and floor paint application are common operation and maintenance projects. Accurately calculating the area of ​​the road surface to be painted is a key prerequisite for preparing project budgets, procuring materials, and calculating construction costs. Traditional methods for calculating the painting area mainly rely on manual on-site measurement or two-dimensional image analysis based on a single drone aerial photograph.

[0003] However, existing technologies have significant technical bottlenecks in practical applications: (1) Light and shadow interference leads to recognition distortion; the factory environment is complex. The shadows cast by buildings, tall equipment and trees on the road surface move with the change of the sun's altitude angle, and water surface, glass curtain wall and smooth road surface are prone to strong specular reflection (reflection). In a single aerial image, shadowed areas are often misjudged as dark road surface or cannot be identified, while bright reflective areas are easily misjudged as white markings or noise, which causes the texture features of the area to be painted to be covered or distorted, seriously affecting the accuracy of area calculation.

[0004] (2) A single data source makes it difficult to distinguish the attributes of land features; relying solely on the texture features of two-dimensional images makes it difficult to effectively distinguish areas with different elevations but similar textures (such as flat roofs and roads, flower bed tops and roads), and easily leads to the incorrect inclusion of non-painted areas (such as roofs and flower beds) in the engineering quantity; while relying solely on three-dimensional point cloud data can obtain elevation information, it lacks the details of the surface material texture and cannot accurately define the applicable scope of the painting material.

[0005] (3) Difficulty in handling interference from dynamic objects; frequent vehicle traffic in the park, and parked vehicles may temporarily block the road. Traditional methods are difficult to distinguish between permanent non-painted objects and temporary obstructions, and often directly remove the obstructed area, resulting in the omission of the painted area. Summary of the Invention

[0006] This application provides a method, system, and storage medium for calculating the area of ​​road surface to be painted in a park. It can solve the technical problems existing in the prior art, such as the complex environment of the factory area, the movement of the shadows cast by buildings, tall equipment and trees on the road surface with the change of the sun's altitude angle, and the strong specular reflection caused by water surface, glass curtain wall and smooth road surface, which leads to recognition distortion.

[0007] In a first aspect, embodiments of this application provide a method for calculating the area to be painted on a road surface in a park, comprising: Acquire aerial data of the target area; the aerial data includes image data with time-series variations and 3D point cloud data; A surface elevation model is constructed based on the three-dimensional point cloud data; light and shadow interference areas and static features are identified based on the pixel features that change over time in the image data, and then the light and shadow interference areas are reconstructed. The reconstructed light and shadow interference area and the static land features are merged to obtain pure surface texture data. Then, a fusion analysis is performed based on the pure surface texture data and the surface elevation model to distinguish between the areas to be painted and the unpainted areas. The areas to be painted and the unpainted areas are mapped to the digital modeling environment to calculate the amount of painting work required for the areas to be painted.

[0008] Preferably, acquiring aerial data includes the following steps: The system controls a drone equipped with a positioning module and an airborne lidar scanning module to perform flight missions on the same target area at least at two different solar altitude angles to obtain time-series image data and simultaneously acquire high-density three-dimensional point cloud data.

[0009] Preferably, based on the time-varying pixel features in the image data, areas of light and shadow interference and static features are identified, specifically including: First, radiometric consistency correction is performed on the image data; Pixel regions in the corrected image data whose position, shape, and brightness remain unchanged during the time series changes are identified as static ground features. Pixel regions in the corrected image data whose position, shape, and brightness change abruptly over time are identified as light and shadow interference regions. These light and shadow interference regions include shadow regions created by the movement of the sun's angle, as well as water surface or glass curtain wall reflection regions that shift with changes in illumination.

[0010] Preferably, the area of ​​light and shadow interference is reconstructed, specifically including: Identify shadow mask areas and specular reflection interference areas within areas of light and shadow interference; Reconstruct the shadow mask area according to strategy one; The specular reflection interference area is reconstructed according to strategy two; The reconstructed shadow mask area and specular reflection interference area are subjected to radiation equalization to obtain the reconstructed light and shadow interference area.

[0011] Preferably, identifying the shadow mask area and specular reflection interference area within the light and shadow interference area specifically includes: Obtain the geographic coordinates and timestamp of a ground feature at a certain moment, as well as the solar altitude angle and solar azimuth angle at the current moment; The elevation information of the features in the surface elevation model is extracted, and then the theoretical projection shape and area of ​​the features under the current solar altitude angle are calculated using trigonometric geometric relationships. The projection direction is determined by combining the solar azimuth angle. The calculated theoretical projection shape and area are mapped onto the light and shadow interference area in a determined projection direction to generate a shadow mask area; Spectral analysis was performed on the light and shadow interference area to extract the features of each pixel; the pixel features include brightness value, gradient value and polarization degree features. A preset object reflection threshold library is invoked, which stores standard reflection feature value ranges for different material types under different lighting conditions; the extracted pixel features are compared with the standard reflection feature values ​​in the object reflection threshold library; If a pixel feature falls within any standard reflection feature value range and exceeds a preset inverse threshold, the region is determined to be a specular reflection interference region.

[0012] Preferably, strategy one includes: Identify the shadow mask area and the specular reflection interference area within the light and shadow interference area; Based on the shadow mask area, locate the pixel area covered by the shadow; In image data containing time-series variations, image data of the same geographical location at other solar altitude angles are retrieved, and the moments when the area is not covered by the shadow mask area are selected as effective complementary frames. The pixel values ​​at the corresponding positions in the effective complementary frames are directly extracted and used to replace the pixel values ​​in the current shadow area; if there are no effective complementary frames, interpolation repair and reconstruction are performed based on the texture features of the adjacent non-shadow areas. The second strategy includes: For areas with specular reflection interference, an inverse threshold backtracking search is performed in image data containing time-series changes to find target images at the same location where the reflection feature value is lower than the inverse threshold; the target images are used as the real surface data source to replace the pixel values ​​of the current high-reflectivity areas. The multi-temporal data, after replacement, repair and reconstruction, are subjected to radiometric equalization to eliminate color patchwork traces caused by differences in illumination at different times, and finally synthesize a pure surface orthophoto image without shadows and reflection interference.

[0013] Preferably, a fusion analysis is performed based on the pure surface texture data and the surface elevation model to distinguish between the areas to be painted and the areas not to be painted, specifically including the following steps: Obtain the preset surface texture database; The surface texture database is used to identify the pure surface texture data to obtain the type of each texture in the pure surface texture data; then the elevation value of each texture is obtained according to the surface elevation model. If the texture type is identified as building type throughout the entire time series change, and the corresponding elevation value is greater than the first elevation value, then the true state of the area corresponding to the texture is building type; the first elevation value is greater than the road reference surface. If the texture type is identified as flower bed type throughout the entire time series change, and the corresponding elevation value is greater than the road reference surface but less than the first elevation value, then the true state of the area corresponding to the texture is flower bed type. If the texture type is identified as a ditch type throughout the entire time series change, and the corresponding elevation value is less than the road surface reference surface, then the true state of the area corresponding to the texture is a ditch type. If the texture type is identified as the road surface to be painted throughout the entire time series change, and the corresponding elevation value is located within the flat range of the road reference surface, then the true state of the area corresponding to the texture is the road surface to be painted. Areas that are actually classified as buildings, flower beds, or ditches are designated as non-painting areas, while the areas corresponding to the road surface to be painted are designated as painting areas.

[0014] Preferably, if the texture type is identified as a vehicle type at one point in the entire time series change, and the type is identified as the road surface to be painted at the other points, then the actual state of the area corresponding to the texture is the road surface to be painted.

[0015] Secondly, a system for calculating the area of ​​roads to be painted in a park is provided, which includes: The first module is used to acquire aerial data of the target area; the aerial data includes image data with time-series variations and 3D point cloud data; The second module is used to construct a surface elevation model based on the three-dimensional point cloud data; identify light and shadow interference areas and static features based on the pixel features that change over time in the image data, and then reconstruct the light and shadow interference areas; The third module is used to merge the reconstructed light and shadow interference area and the static land features to obtain pure surface texture data. Then, based on the pure surface texture data and the surface elevation model, a fusion analysis is performed to distinguish between the area to be painted and the unpainted area. The area to be painted and the unpainted area are mapped to the digital modeling environment to calculate the amount of painting work required for the area to be painted.

[0016] Thirdly, a computer-readable storage medium stores a program for calculating the area of ​​a road surface to be painted in a park, wherein when the program is executed by a processor, it implements the steps of a method for calculating the area of ​​a road surface to be painted in a park.

[0017] The beneficial effects of the technical solutions provided in this application include: First, by using time-series imagery to identify and reconstruct areas affected by light and shadow interference, the obscuring of surface texture by shadows and reflections can be eliminated from the data source, restoring true, clean surface texture data and ensuring the accuracy of subsequent texture classification. Second, by combining a surface elevation model constructed from 3D point clouds, a transition from planar vision to 3D space is achieved, effectively eliminating unpaintable areas such as buildings, flower beds, and ditches based on elevation differences. This dual verification mechanism of texture restoration and elevation filtering significantly improves the robustness of identifying areas to be painted, avoiding errors such as misjudging shadows as dark road surfaces or reflections as white markings. The resulting engineering quantity data output in the digital modeling environment has extremely high accuracy and reliability, solving the problem of area calculation distortion caused by light and shadow occlusion and specular reflection in traditional single 2D image measurement, as well as the difficulty of accurately identifying surface material properties by relying solely on elevation data. This significantly reduces the cost of manual verification and provides a scientific budget basis for the park's painting project. Attached Figure Description

[0018] Figure 1 A schematic diagram of the image data of the park at a certain moment provided in this application; Figure 2 This is a schematic diagram of the identified area to be painted provided in this application; Figure 3 This is a simplified flowchart illustrating the calculation method for the area of ​​the road surface to be painted in the park under this application. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] Firstly, reference Figure 3 As shown in the embodiment of this application, a method for calculating the area to be painted on a road surface in a park is provided, which includes: Step 100: Acquire aerial data of the target area; the aerial data includes image data with time-series variations and 3D point cloud data; image data reference. Figure 1 As shown; Step 200: Construct a surface elevation model based on 3D point cloud data; identify light and shadow interference areas and static features based on the pixel features that change over time in the image data, and then reconstruct the light and shadow interference areas; Step 300: Merge the reconstructed light and shadow interference area and static features to obtain clean surface texture data. Then, perform a fusion analysis based on the clean surface texture data and the surface elevation model to distinguish between the areas to be painted and the unpainted areas. Map the areas to be painted and the unpainted areas to the digital modeling environment to calculate the amount of painting work required for the areas to be painted. (Reference) Figure 2 The black area in the diagram represents the area to be painted; the steps for calculating the amount of paint to be applied to the area are standard procedures and will not be explained in detail again.

[0022] This method solves the problems of area calculation distortion caused by light and shadow occlusion and specular reflection in traditional single two-dimensional image measurement, as well as the difficulty of accurately identifying surface material properties by relying solely on elevation data. First, by using time-series imagery to identify and reconstruct areas affected by light and shadow interference, the method eliminates the obscuring of surface texture by shadows and reflections at the data source, restoring true, clean surface texture data and ensuring the accuracy of subsequent texture classification. Second, by combining a surface elevation model constructed from 3D point clouds, it achieves a transition from planar vision to 3D space, effectively eliminating unpaintable areas such as buildings, flower beds, and ditches based on elevation differences. This dual verification mechanism of texture restoration and elevation filtering significantly improves the robustness of identifying areas to be painted, avoiding errors such as misidentifying shadows as dark road surfaces or reflections as white markings. The resulting engineering quantity data output in the digital modeling environment has extremely high accuracy and reliability, significantly reducing the cost of manual verification and providing a scientific budget basis for park painting projects.

[0023] In some preferred embodiments, acquiring aerial data includes the following steps: The system controls a drone equipped with a positioning module and an airborne lidar scanning module to perform flight missions on the same target area at least at two different solar altitude angles to obtain time-series image data and simultaneously acquire high-density three-dimensional point cloud data.

[0024] First, the multi-time-period flight strategy utilizes the shadow movement patterns caused by changes in the sun's position to ensure that the same road surface area has different lighting conditions at different times. This provides "complementary frame" data for subsequent algorithms—that is, an area covered by shadow at one time may be under direct sunlight at another time, providing a physical basis for eliminating shadow interference. Second, the simultaneous acquisition of high-density 3D point cloud data not only ensures the accuracy of the surface elevation model but also accurately captures subtle changes in elevation (such as curbs and shallow ditches), which is impossible with pure image matching. The active laser emission characteristic of lidar makes it unaffected by lighting conditions, allowing it to work stably at night or in strong light, complementing the passive image data. This data acquisition mode fundamentally guarantees the integrity and diversity of the input data, so that subsequent area calculations are no longer limited by the weather or lighting randomness of a single flight, greatly improving the system's environmental adaptability and the stability of the measurement results. In some preferred embodiments, areas of light and shadow interference and static features are identified based on time-varying pixel features in the image data, specifically including: First, perform radiometric consistency correction on the image data; Pixel regions in the corrected image data whose position, shape, and brightness remain unchanged during the time series changes are identified as static ground features. Pixel regions in the corrected image data whose position, shape, and brightness change abruptly over time are identified as light and shadow interference regions. These include shadow regions created by the movement of the sun's angle, as well as water surface or glass curtain wall reflections that shift with changes in illumination.

[0025] This method eliminates radiation errors caused by changes in UAV flight attitude, atmospheric scattering, and sensor gain fluctuations, ensuring the comparability of pixel values ​​across multiple temporal images. Building upon this, it utilizes the invariance of position, shape, and brightness over time to identify static ground features, and leverages abrupt changes to identify light and shadow interference. This is a logical judgment based on physical laws, rather than simple threshold segmentation. This method effectively distinguishes between shadows that move with the sun's angle (gradual brightness changes, edge movement) and water / glass reflections that change with the viewing angle (abrupt brightness changes, positional jumps), avoiding the pitfalls of traditional single-image processing that easily misidentify dark roads as shadows or bright reflections as white lines. Through this temporal difference mechanism, the system can automatically strip away interference factors that are not inherent to the ground features themselves, simplifying complex scenes into a clean static background and a dynamic interference layer. This provides precise mask guidance for subsequent targeted reconstruction processing, significantly improving the accuracy and automation of ground feature recognition under complex lighting conditions.

[0026] In some preferred embodiments, the reconstruction of the light and shadow interference area specifically includes: Identify shadow mask areas and specular reflection interference areas within areas of light and shadow interference; Reconstruct the shadow mask area according to strategy one; The specular reflection interference area is reconstructed according to strategy two; The reconstructed shadow mask area and specular reflection interference area are subjected to radiation equalization to obtain the reconstructed light and shadow interference area.

[0027] The above method subdivides the light and shadow interference area into shadow mask areas and specular reflection interference areas, and processes them using strategies one and two respectively, before finally performing radiometric equalization. This layered processing mechanism avoids the limitations of a single restoration algorithm when dealing with different types of interference. Shadow areas typically exhibit color distortion under low illumination, while specular reflection areas exhibit highlight clipping and texture loss; the recovery difficulty and required information sources differ between the two. Through classification processing, the system can prioritize finding complementary data from high-illumination times for shadow areas and prioritize finding real data from non-reflective times for reflection areas, maximizing the use of effective information from multi-temporal data. Furthermore, the final radiometric equalization step is crucial, eliminating stitching marks (such as color difference blocks) caused by differences in light color temperature and intensity collected at different times, ensuring the visual and content consistency of the reconstructed image. The final generated "reconstructed light and shadow interference area" is not only geometrically accurate but also seamlessly integrated with the surrounding static features in terms of radiometric characteristics, laying a solid foundation for generating high-quality, clean surface orthophotos and directly improving the reliability of subsequent texture classification.

[0028] In some preferred embodiments, identifying shadow mask areas and specular reflection interference areas within the light and shadow interference area specifically includes: Obtain the geographic coordinates and timestamp of a ground feature at a certain moment, as well as the solar altitude angle and solar azimuth angle at the current moment; The elevation information of ground features in the surface elevation model is extracted, and then the theoretical projection shape and area of ​​the ground features under the current solar altitude angle are calculated using trigonometric geometric relationships. The projection direction is determined by combining the solar azimuth angle. The calculated theoretical projection shape and area are mapped onto the light and shadow interference area in a determined projection direction to generate a shadow mask area; Spectral analysis was performed on the light and shadow interference area to extract the features of each pixel; the pixel features include brightness value, gradient value and polarization degree features. The system calls a pre-set object reflection threshold library, which stores standard reflection feature value ranges for different material types under different lighting conditions; the extracted pixel features are then compared with the standard reflection feature values ​​in the object reflection threshold library. If a pixel feature falls within any standard reflection feature value range and exceeds a preset inverse threshold, the region is determined to be a specular reflection interference region.

[0029] The identification principles for shadow and reflection areas employ two distinct techniques: geometric deduction and threshold database matching. This significantly improves the physical interpretability and accuracy of the identification. For shadow areas, the theoretical projection is calculated using trigonometric relationships (Pythagorean theorem) based on the solar altitude angle, azimuth angle, and elevation of ground features. This method does not rely on the statistical characteristics of image pixels but is based on deterministic calculations from astronomy and geometry. Therefore, it is unaffected by the depth of ground color and can accurately delineate shadow boundaries, avoiding the error of misidentifying dark asphalt pavement as shadow. For reflection areas, a pre-set "object reflection threshold database" is introduced. By comparing the matching degree of multi-dimensional features such as brightness, gradient, and polarization degree with standard reflection values, it can intelligently distinguish highly reflective glass / water surfaces from ordinary bright objects (such as white car roofs). This identification method based on the spectral characteristics of materials effectively overcomes the false alarm rate of relying solely on brightness thresholds. The combination of these two methods ensures both the geometric accuracy of shadow boundaries and the spectral accuracy of reflection areas, resulting in a mask with extremely high confidence.

[0030] In some preferred embodiments, strategy one includes: Identify the shadow mask area and the specular reflection interference area within the light and shadow interference area; Based on the shadow mask area, locate the pixel area covered by the shadow; In image data containing time-series variations, image data of the same geographical location at other solar altitude angles are retrieved, and the moments when the area is not covered by the shadow mask area are selected as effective complementary frames. The pixel values ​​at the corresponding positions in the effective complementary frames are directly extracted and used to replace the pixel values ​​in the current shadow area; if there are no effective complementary frames, interpolation repair and reconstruction are performed based on the texture features of the adjacent non-shadow areas. Strategy Two includes: For areas with specular reflection interference, an inverse threshold backtracking search is performed in image data containing time-series changes to find target images at the same location where the reflection feature value is lower than the inverse threshold; the target images are used as the real surface data source to replace the pixel values ​​of the current high-reflectivity areas. The multi-temporal data, after replacement, repair and reconstruction, are subjected to radiometric equalization to eliminate color patchwork traces caused by differences in illumination at different times, and finally synthesize a pure surface orthophoto image without shadows and reflection interference.

[0031] The principle of prioritizing real data replacement over algorithmic restoration was established to preserve the true texture information of the ground surface to the greatest extent. Strategy 1 directly replaces the current shadowed pixels with real pixels from other times when there are no shadows by searching for effective complementary frames. This "spatiotemporal complementarity" mechanism essentially fills in the information gaps with real observation data, rather than relying on algorithmic guessing. Therefore, the reconstructed area has rich texture details and realistic colors, completely avoiding the blurring, texture duplication, or artifacts that may occur in traditional image restoration techniques. Strategy 2 works similarly, using inverse threshold backtracking to find real ground surface data from times without reflection and replacing it, completely eliminating the texture distortion caused by specular reflection. Interpolation restoration is only used in the extreme case where there are no effective complementary frames, ensuring the robustness of the system. Finally, radiometric equalization further eliminates the color block effect during multi-source data fusion. This reconstruction scheme, with real data replacement as its core, ensures that the final clean ground image highly restores the real state of the factory area's road surface in both microscopic texture and macroscopic color.

[0032] In some preferred embodiments, a fusion analysis is performed based on clean surface texture data and a surface elevation model to distinguish between areas to be painted and areas not to be painted. This specifically includes the following steps: Obtain the preset surface texture database; The clean surface texture data is identified using a surface texture database to obtain the type of each texture in the clean surface texture data; then the elevation value of each texture is obtained according to the surface elevation model. If the texture type is identified as building type throughout the entire time series change, and the corresponding elevation value is greater than the first elevation value, the actual state of the area is building type; the first elevation value is greater than the road reference surface; If the texture type is identified as flower bed type throughout the entire time series change, and the corresponding elevation value is greater than the road reference surface but less than the first elevation value, then the true state of the area corresponding to the texture is flower bed type. If the texture type is identified as a ditch type throughout the entire time series change, and the corresponding elevation value is less than the road surface reference surface, then the true state of the area corresponding to the texture is a ditch type. If the texture type is identified as the road surface to be painted throughout the entire time series change, and the corresponding elevation value is located within the flat range of the road reference surface, then the true state of the area corresponding to the texture is the road surface to be painted. Areas that are actually classified as buildings, flower beds, or ditches are designated as non-painting areas, while the areas corresponding to the road surface to be painted are designated as painting areas.

[0033] It solves the misjudgment problem that is easy to occur in single-dimensional classification: relying solely on texture can easily misclassify roofs as roads, and relying solely on elevation can easily misclassify flat roofs as roads.

[0034] This solution requires that texture types (such as houses, flower beds, ditches, and roads) remain consistent throughout the entire time series and must meet specific elevation constraints (such as houses being above the first elevation value, ditches being below the reference surface, and roads being located in flat areas). This joint judgment mechanism of spatiotemporal consistency and three-dimensional spatial constraints greatly improves the accuracy of classification. For example, it can effectively exclude non-painting objects such as the roofs of high-rise buildings (which have road textures but are too high in elevation), flower beds (which are on the road but are slightly higher in elevation and have specific textures), and drainage ditches (which are too low in elevation). By mapping the recognition results to the digital modeling environment, the system can not only calculate the area but also intuitively display the spatial distribution of various land features, achieving a leap from pixel-level classification to object-level understanding. This ensures that the final calculated painting workload only includes the road areas that actually need to be painted, eliminating false reporting and underreporting.

[0035] In some preferred embodiments, if the texture type is identified as a vehicle type at one point in the entire time series change, and the type is identified as road surface to be painted at the other points, then the actual state of the area corresponding to the texture is the road surface to be painted.

[0036] In park settings, vehicles frequently park on surfaces awaiting painting. Relying solely on single images for identification can lead to misclassification of vehicle-covered areas as vehicles and their exclusion, resulting in an underestimation of the painting area. Alternatively, shadows left by departing vehicles may be misidentified. This solution examines the entire time series to identify a region as a vehicle only at a specific moment, while at other times it remains as surface to be painted. This logically infers that the region's essential attribute is indeed surface to be painted. It cleverly utilizes the temporary nature of vehicle movement to automatically recover the true attributes of temporarily obscured surfaces. This eliminates the need for manual vehicle location marking and complex vehicle detection and removal algorithms; it achieves immunity to dynamic occlusions solely through logical reasoning, ensuring the integrity of the painting area calculation, especially in park environments with high vehicle traffic.

[0037] Secondly, a system for calculating the area of ​​roads to be painted in a park is provided, which includes: The first module is used to acquire aerial data of the target area; the aerial data includes image data with time-series variations and 3D point cloud data; The second module is used to construct a surface elevation model based on 3D point cloud data; identify light and shadow interference areas and static features based on the pixel features that change over time in the image data, and then reconstruct the light and shadow interference areas; The third module is used to merge the reconstructed light and shadow interference area and static features to obtain pure surface texture data. Then, based on the pure surface texture data and the surface elevation model, a fusion analysis is performed to distinguish between the areas to be painted and the unpainted areas. The areas to be painted and the unpainted areas are mapped to the digital modeling environment to calculate the amount of painting work required for the areas to be painted.

[0038] The functions of each module in the above-mentioned park road surface area calculation device correspond to the steps in the above-mentioned park road surface area calculation method embodiment, and their functions and implementation processes will not be described in detail here.

[0039] This application provides a device for calculating the area of ​​a road surface to be painted in a park. The device can be a personal computer (PC), a laptop, a server, or other device with data processing capabilities.

[0040] In this embodiment, the device for calculating the area of ​​the road surface to be painted in the park may include a processor, a memory, a communication interface, and a communication bus.

[0041] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0042] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces. These interfaces enable interconnection of internal components within the campus road surface area calculation device, as well as interfaces for interconnection between the device and other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0043] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0044] The processor can be a general-purpose processor, which can call the program for calculating the area of ​​the road surface to be painted in the park stored in the memory and execute the method for calculating the area of ​​the road surface to be painted in the park provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the program for calculating the area of ​​the road surface to be painted in the park is called can refer to the various embodiments of the method for calculating the area of ​​the road surface to be painted in the park provided in this application, and will not be repeated here.

[0045] This application also provides a computer-readable storage medium.

[0046] The computer-readable storage medium of this application stores a program for calculating the area of ​​the road surface to be painted in a park. When the program is executed by a processor, it implements the steps of the method for calculating the area of ​​the road surface to be painted in a park as described above.

[0047] The method implemented when the program for calculating the area of ​​the road surface to be painted in the park is executed can be referred to in various embodiments of the method for calculating the area of ​​the road surface to be painted in the park in this application, and will not be repeated here.

[0048] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0049] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0050] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0051] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0052] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0053] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0054] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for calculating the area of ​​a road surface to be painted in a park, characterized in that, It includes: Acquire aerial data of the target area; the aerial data includes image data with time-series variations and 3D point cloud data; A surface elevation model is constructed based on the three-dimensional point cloud data; light and shadow interference areas and static features are identified based on the pixel features that change over time in the image data, and then the light and shadow interference areas are reconstructed. The reconstructed light and shadow interference area and the static land features are merged to obtain pure surface texture data. Then, a fusion analysis is performed based on the pure surface texture data and the surface elevation model to distinguish between the areas to be painted and the unpainted areas. The areas to be painted and the unpainted areas are mapped to the digital modeling environment to calculate the amount of painting work required for the areas to be painted.

2. The method for calculating the area of ​​the road surface to be painted in the park as described in claim 1, characterized in that, Acquiring aerial data includes the following steps: The system controls a drone equipped with a positioning module and an airborne lidar scanning module to perform flight missions on the same target area at least at two different solar altitude angles to obtain time-series image data and simultaneously acquire high-density three-dimensional point cloud data.

3. The method for calculating the area of ​​road surface to be painted in the park as described in claim 2, characterized in that, Based on the time-varying pixel features in the image data, areas of light and shadow interference and static features are identified, specifically including: First, radiometric consistency correction is performed on the image data; Pixel regions in the corrected image data whose position, shape, and brightness remain unchanged during the time series changes are identified as static ground features. Pixel regions in the corrected image data whose position, shape, and brightness change abruptly over time are identified as light and shadow interference regions. These light and shadow interference regions include shadow regions created by the movement of the sun's angle, as well as water surface or glass curtain wall reflection regions that shift with changes in illumination.

4. The method for calculating the area of ​​the road surface to be painted in the park as described in claim 1, characterized in that, Reconstructing areas of light and shadow interference specifically includes: Identify shadow mask areas and specular reflection interference areas within areas of light and shadow interference; Reconstruct the shadow mask area according to strategy one; The specular reflection interference area is reconstructed according to strategy two; The reconstructed shadow mask area and specular reflection interference area are subjected to radiation equalization to obtain the reconstructed light and shadow interference area.

5. The method for calculating the area of ​​the road surface to be painted in the park as described in claim 4, characterized in that, Identify shadow mask areas and specular reflection interference areas within the light and shadow interference area, specifically including: Obtain the geographic coordinates and timestamp of a ground feature at a certain moment, as well as the solar altitude angle and solar azimuth angle at the current moment; The elevation information of the features in the surface elevation model is extracted, and then the theoretical projection shape and area of ​​the features under the current solar altitude angle are calculated using trigonometric geometric relationships. The projection direction is determined by combining the solar azimuth angle. The calculated theoretical projection shape and area are mapped onto the light and shadow interference area in a determined projection direction to generate a shadow mask area; Spectral analysis was performed on the light and shadow interference area to extract the features of each pixel; the pixel features include brightness value, gradient value and polarization degree features. A preset object reflection threshold library is invoked, which stores standard reflection feature value ranges for different material types under different lighting conditions; the extracted pixel features are compared with the standard reflection feature values ​​in the object reflection threshold library; If a pixel feature falls within any standard reflection feature value range and exceeds a preset inverse threshold, the region is determined to be a specular reflection interference region.

6. The method for calculating the area of ​​road surface to be painted in the park as described in claim 4, characterized in that: Strategy one includes: Identify the shadow mask area and the specular reflection interference area within the light and shadow interference area; Based on the shadow mask area, locate the pixel area covered by the shadow; In image data containing time-series variations, image data of the same geographical location at other solar altitude angles are retrieved, and the moments when the area is not covered by the shadow mask area are selected as effective complementary frames. The pixel values ​​at the corresponding positions in the effective complementary frames are directly extracted and used to replace the pixel values ​​in the current shadow area; if there are no effective complementary frames, interpolation repair and reconstruction are performed based on the texture features of the adjacent non-shadow areas. The second strategy includes: For areas with specular reflection interference, an inverse threshold backtracking search is performed in image data containing time-series changes to find target images at the same location where the reflection feature value is lower than the inverse threshold; the target images are used as the real surface data source to replace the pixel values ​​of the current high-reflectivity areas. The multi-temporal data, after replacement, repair and reconstruction, are subjected to radiometric equalization to eliminate color patchwork traces caused by differences in illumination at different times, and finally synthesize a pure surface orthophoto image without shadows and reflection interference.

7. The method for calculating the area of ​​the road surface to be painted in the park as described in claim 1, characterized in that, A fusion analysis is performed based on the pure surface texture data and surface elevation model to distinguish between areas to be painted and areas not to be painted. This includes the following steps: Obtain the preset surface texture database; The surface texture database is used to identify the pure surface texture data to obtain the type of each texture in the pure surface texture data; then the elevation value of each texture is obtained according to the surface elevation model. If the texture type is identified as building type throughout the entire time series change, and the corresponding elevation value is greater than the first elevation value, then the true state of the area corresponding to the texture is building type; the first elevation value is greater than the road reference surface. If the texture type is identified as flower bed type throughout the entire time series change, and the corresponding elevation value is greater than the road reference surface but less than the first elevation value, then the true state of the area corresponding to the texture is flower bed type. If the texture type is identified as a ditch type throughout the entire time series change, and the corresponding elevation value is less than the road surface reference surface, then the true state of the area corresponding to the texture is a ditch type. If the texture type is identified as the road surface to be painted throughout the entire time series change, and the corresponding elevation value is located within the flat range of the road reference surface, then the true state of the area corresponding to the texture is the road surface to be painted. Areas that are actually classified as buildings, flower beds, or ditches are designated as non-painting areas, while the areas corresponding to the road surface to be painted are designated as painting areas.

8. The method for calculating the area of ​​road surface to be painted in the park as described in claim 7, characterized in that: If the texture type is identified as a vehicle at one point in the entire time series, and as a road surface to be painted at the other points, then the actual state of the area corresponding to the texture is the road surface to be painted.

9. A system for calculating the area of ​​a road surface to be painted in a park, characterized in that, It includes: The first module is used to acquire aerial data of the target area; the aerial data includes image data with time-series variations and 3D point cloud data; The second module is used to construct a surface elevation model based on the three-dimensional point cloud data; identify light and shadow interference areas and static features based on the pixel features that change over time in the image data, and then reconstruct the light and shadow interference areas; The third module is used to merge the reconstructed light and shadow interference area and the static land features to obtain pure surface texture data. Then, based on the pure surface texture data and the surface elevation model, a fusion analysis is performed to distinguish between the area to be painted and the unpainted area. The area to be painted and the unpainted area are mapped to the digital modeling environment to calculate the amount of painting work required for the area to be painted.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for calculating the area of ​​the road surface to be painted in the park. When the program is executed by a processor, it implements the steps of the method for calculating the area of ​​the road surface to be painted in the park as described in any one of claims 1 to 8.

Images