Adaptive light compensation method and system for bridge bottom three-dimensional greening

Abstract

The application discloses a kind of self-adapting illumination compensation method and system of bridge bottom three-dimensional greening, utilize first camera device to collect green canopy growth state diagram, pass through extracting growth state feature to generate growth health index, intuitively reflect green plant growth condition;With the aid of second camera device, obtain bridge three-dimensional space information and green plant position distribution information, generate green plant sheltering situation diagram, and adopt ray projection algorithm to simulate dynamic shadow, and then calculate canopy effective light radiation receiving rate, accurately master bridge bottom illumination environment dynamic change.Then growth health index is combined with canopy effective light radiation receiving rate to generate illumination compensation strategy, controls light compensation device to carry out illumination compensation.The application can be according to the actual growth state of bridge bottom green plant and dynamic illumination environment, and accurately illuminate compensation is carried out to bridge bottom green plant adaptively.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an adaptive illumination compensation method and system for vertical greening under bridges. Background Technology

[0002] With the continuous development of urban bridge construction, the space under bridges has gradually become an important area for urban greening. Currently, the common lighting management method for vertical greening under bridges involves pre-installing a certain number and power of supplemental lighting fixtures at fixed locations based on the approximate lighting environment under the bridge. Light sensors monitor the real-time light intensity in the area under the bridge, and when the light intensity falls below a preset threshold, the supplemental lighting devices are activated for artificial illumination. In addition, image recognition technology is now used to assess the lack of light for plants and then control the supplemental lighting fixtures accordingly. However, these methods rely on rough estimates of the lack of light under the bridge, lacking precise judgment of the actual growth status and light requirements of plants in different areas under the bridge, and failing to consider the dynamic changes in light obstruction caused by the bridge structure. Therefore, existing supplemental lighting solutions for green plants under bridges cannot provide precise lighting, resulting in poor light compensation effects and affecting the growth quality of the plants. Summary of the Invention

[0003] This invention provides an adaptive light compensation method and system for vertical greening under bridges. It can adaptively generate and implement a precise light compensation strategy based on the actual growth status and dynamic light environment of the green plants under the bridge, effectively improving the light compensation effect and enhancing the growth quality of the green plants under the bridge.

[0004] An embodiment of the present invention provides an adaptive light compensation method for vertical greening under bridges, comprising:

[0005] The first camera device was used to capture images of the canopy growth status of the green plants in each area under the bridge.

[0006] The second camera device acquires the three-dimensional spatial information of the bridge surface and the location distribution information of the green plants in each of the bridge bottom areas, and generates a map of the green plant occlusion situation in each of the bridge bottom areas based on the three-dimensional spatial information of the bridge surface and the location distribution information.

[0007] Based on the canopy growth status map, the growth status characteristics of the green plants in each of the bridge under areas are extracted, and the growth health index of the green plants in each of the bridge under areas is generated by quantification based on the growth status characteristics.

[0008] Based on the green vegetation shading diagram, a light projection algorithm is used to simulate the dynamic shadows in each of the bridge under areas, and the effective light radiation reception rate of the canopy of the green vegetation in each bridge under area is calculated based on the dynamic shadow simulation results.

[0009] Based on the growth health index and the effective light radiation absorption rate of the canopy of the green plants in each of the bridge under areas, a light compensation strategy for the green plants in each of the bridge under areas is generated.

[0010] According to the light compensation strategy, the supplementary lighting devices in each of the bridge under areas are controlled to provide light compensation for the greenery in the corresponding bridge under areas.

[0011] As an improvement to the above solution, the step of acquiring the three-dimensional spatial information of the bridge surface and the location distribution information of the vegetation in each of the bridge under areas through the second camera device, and generating a map showing the occlusion status of the vegetation in each of the bridge under areas using the three-dimensional spatial information of the bridge surface and the location distribution information, includes the following sub-steps:

[0012] Based on the three-dimensional spatial information of the bridge deck, a bridge occlusion model for each area under the bridge is constructed.

[0013] The location distribution information of the green plants in each of the bridge bottom areas is mapped into the bridge shading model to determine the shading influence parameters of each green plant unit;

[0014] Based on the sun's trajectory and the shading effect parameters, calculate the time-varying shading coefficient of the vegetation in each of the bridge under areas;

[0015] Based on each of the time-varying shading coefficients, a vegetation shading map of each of the bridge under areas is generated, wherein the vegetation shading map includes the shading intensity distribution in the time-space dimension.

[0016] As an improvement to the above scheme, the step of extracting the growth status characteristics of the green plants in each of the bridge underside areas based on the canopy growth status map, and quantifying and generating the growth health index of the green plants in each of the bridge underside areas based on the growth status characteristics, includes the following sub-steps:

[0017] The canopy growth status of the green plants in each of the bridge under areas was analyzed to extract chlorophyll distribution features and canopy morphology features.

[0018] The chlorophyll distribution characteristics and canopy morphology characteristics are fused together to generate comprehensive physiological indicators for each green plant unit.

[0019] The comprehensive physiological indicators are quantified and converted according to the preset health assessment rules to generate the growth health index of the green plants in each of the bridge bottom areas.

[0020] As an improvement to the above solution, the step of simulating the dynamic shadows of each of the bridge under areas using a light projection algorithm based on the green vegetation shading map, and calculating the effective light radiation absorption rate of the canopy of the green vegetation in each bridge under area based on the dynamic shadow simulation results, includes the following sub-steps:

[0021] Based on the time-varying occlusion coefficient of the green vegetation occlusion map, the dynamic light source parameters of the light projection algorithm are set.

[0022] A light projection algorithm was used to simulate the distribution of the canopy of vegetation in the bridge underside area at multiple time points.

[0023] Accumulate the data on the distribution of light-receiving areas at various time points, and calculate the average daily light radiation received by each green plant unit;

[0024] By comparing the average daily light radiation received with the standard light radiation requirement, the effective light radiation reception rate of the canopy of the green plants in each of the bridge under areas is generated.

[0025] As an improvement to the above scheme, the step of generating a light compensation strategy for the greenery in each of the bridge underside areas based on the growth health index and the effective light radiation absorption rate of the canopy includes the following sub-steps:

[0026] Establish a correlation matrix between the growth health index of green plants in each of the bridge under areas and the effective light radiation absorption rate of the canopy;

[0027] The correlation matrix is ​​divided into multiple compensation priority regions according to the preset compensation rules;

[0028] For each green plant unit's position coordinates in the correlation matrix, determine its corresponding compensation priority region;

[0029] Based on the time-varying shading coefficient of the aforementioned green vegetation shading map, the real-time supplemental lighting intensity required for each green plant unit is calculated.

[0030] Based on the real-time supplementary lighting demand intensity and compensation priority area, a lighting compensation strategy is generated for the green plants in each of the bridge under areas. The lighting compensation strategy includes light intensity adjustment parameters and illumination time parameters.

[0031] Another embodiment of the present invention provides an adaptive light compensation system for vertical greening under bridges, comprising:

[0032] The data acquisition module is used to acquire images of the canopy growth status of the green plants in each area under the bridge using the first camera device.

[0033] The acquisition module is used to acquire the three-dimensional spatial information of the bridge surface and the location distribution information of the green plants in each of the bridge bottom areas through the second camera device, and generate a map of the occlusion of the green plants in each of the bridge bottom areas through the three-dimensional spatial information of the bridge surface and the location distribution information.

[0034] The analysis module is used to extract the growth status characteristics of the green plants in each of the bridge under areas based on the canopy growth status map, and to quantify and generate the growth health index of the green plants in each of the bridge under areas based on the growth status characteristics.

[0035] The simulation module is used to simulate the dynamic shadows of each of the bridge under areas using a light projection algorithm based on the green vegetation shading map, and to calculate the effective light radiation absorption rate of the canopy of the green vegetation in each bridge under area based on the dynamic shadow simulation results.

[0036] The strategy generation module is used to generate a light compensation strategy for the green plants in each of the bridge under areas based on the growth health index and the effective light radiation absorption rate of the canopy.

[0037] The control module is used to control the supplementary lighting devices in each of the bridge under areas to provide light compensation for the green plants in the corresponding bridge under areas, according to the light compensation strategy.

[0038] As an improvement to the above solution, the acquisition module is specifically used for:

[0039] Based on the three-dimensional spatial information of the bridge deck, a bridge occlusion model for each area under the bridge is constructed.

[0040] The location distribution information of the green plants in each of the bridge bottom areas is mapped into the bridge shading model to determine the shading influence parameters of each green plant unit;

[0041] Based on the sun's trajectory and the shading effect parameters, calculate the time-varying shading coefficient of the vegetation in each of the bridge under areas;

[0042] Based on each of the time-varying shading coefficients, a vegetation shading map of each of the bridge under areas is generated, wherein the vegetation shading map includes the shading intensity distribution in the time-space dimension.

[0043] As an improvement to the above solution, the analysis module is specifically used for:

[0044] The canopy growth status of the green plants in each of the bridge under areas was analyzed to extract chlorophyll distribution features and canopy morphology features.

[0045] The chlorophyll distribution characteristics and canopy morphology characteristics are fused together to generate comprehensive physiological indicators for each green plant unit.

[0046] The comprehensive physiological indicators are quantified and converted according to the preset health assessment rules to generate the growth health index of the green plants in each of the bridge bottom areas.

[0047] As an improvement to the above solution, the simulation module is specifically used for:

[0048] Based on the time-varying occlusion coefficient of the green vegetation occlusion map, the dynamic light source parameters of the light projection algorithm are set.

[0049] A light projection algorithm was used to simulate the distribution of the canopy of vegetation in the bridge underside area at multiple time points.

[0050] Accumulate the data on the distribution of light-receiving areas at various time points, and calculate the average daily light radiation received by each green plant unit;

[0051] By comparing the average daily light radiation received with the standard light radiation requirement, the effective light radiation reception rate of the canopy of the green plants in each of the bridge under areas is generated.

[0052] As an improvement to the above solution, the strategy generation module is specifically used for:

[0053] Establish a correlation matrix between the growth health index of green plants in each of the bridge under areas and the effective light radiation absorption rate of the canopy;

[0054] The correlation matrix is ​​divided into multiple compensation priority regions according to the preset compensation rules;

[0055] For each green plant unit's position coordinates in the correlation matrix, determine its corresponding compensation priority region;

[0056] Based on the time-varying shading coefficient of the aforementioned green vegetation shading map, the real-time supplemental lighting intensity required for each green plant unit is calculated.

[0057] Based on the real-time supplementary lighting demand intensity and compensation priority area, a lighting compensation strategy is generated for the green plants in each of the bridge under areas. The lighting compensation strategy includes light intensity adjustment parameters and illumination time parameters.

[0058] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0059] A first camera device captures images of the canopy growth status of the vegetation, while a second camera device simultaneously acquires three-dimensional spatial information of the bridge surface and the distribution of vegetation locations, generating an image showing vegetation shading. This provides a comprehensive understanding of the vegetation's growth status and the light shading environment under the bridge. Growth characteristics are extracted from the canopy growth image and quantified to obtain a growth health index, accurately reflecting the physiological state of the vegetation. A light projection algorithm is used to dynamically simulate shadows on the vegetation shading image, calculating the effective light radiation absorption rate of the canopy to quantify the actual light received level. Combining the growth health index and the effective light radiation absorption rate of the canopy, a targeted light compensation strategy is generated. Finally, adaptive light compensation for the vegetation under the bridge is achieved by controlling a supplementary lighting device. In summary, this invention can adaptively generate and implement precise light compensation strategies based on the actual growth status and dynamic light environment of the vegetation under the bridge, improving the light compensation effect and thus enhancing the growth quality of the vegetation. Attached Figure Description

[0060] Figure 1 This is a flowchart illustrating an adaptive light compensation method for vertical greening under bridges, provided in an embodiment of the present invention.

[0061] Figure 2 This is a schematic diagram of the structure of an adaptive light compensation system for vertical greening under bridges, provided in an embodiment of the present invention. Detailed Implementation

[0062] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] See Figure 1 This is a flowchart illustrating an adaptive light compensation method for vertical greening under bridges, provided in an embodiment of the present invention. The adaptive light compensation method for vertical greening under bridges includes the following sub-steps:

[0064] S10, The first camera device is used to collect images of the canopy growth status of the green plants in each area under the bridge;

[0065] S11, the second camera device acquires the three-dimensional spatial information of the bridge surface in each of the bridge bottom areas and the location distribution information of the green plants in each of the bridge bottom areas, and generates a map of the green plant occlusion in each of the bridge bottom areas based on the three-dimensional spatial information of the bridge surface and the location distribution information.

[0066] S12, Based on the canopy growth status map, extract the growth status characteristics of the green plants in each of the bridge bottom areas, and quantify and generate the growth health index of the green plants in each of the bridge bottom areas based on the growth status characteristics.

[0067] S13, Based on the green vegetation shading diagram, a light projection algorithm is used to simulate the dynamic shadows of each of the bridge under areas, and the effective light radiation reception rate of the canopy of the green vegetation in each bridge under area is calculated based on the dynamic shadow simulation results.

[0068] S14, Based on the growth health index and the effective light radiation absorption rate of the canopy of the green plants in each of the bridge under areas, generate a light compensation strategy for the green plants in each of the bridge under areas;

[0069] S15, according to the light compensation strategy, control the supplementary lighting devices in each of the bridge bottom areas to provide light compensation for the green plants in the corresponding bridge bottom areas.

[0070] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0071] A first camera device captures images of the canopy growth status of the vegetation, while a second camera device simultaneously acquires three-dimensional spatial information of the bridge surface and the distribution of vegetation locations, generating an image showing vegetation shading. This provides a comprehensive understanding of the vegetation's growth status and the light shading environment under the bridge. Growth characteristics are extracted from the canopy growth image and quantified to obtain a growth health index, accurately reflecting the physiological state of the vegetation. A light projection algorithm is used to dynamically simulate shadows on the vegetation shading image, calculating the effective light radiation absorption rate of the canopy to quantify the actual light received level. Combining the growth health index and the effective light radiation absorption rate of the canopy, a targeted light compensation strategy is generated. Finally, adaptive light compensation for the vegetation under the bridge is achieved by controlling a supplementary lighting device. In summary, this invention can adaptively generate and implement precise light compensation strategies based on the actual growth status and dynamic light environment of the vegetation under the bridge, improving the light compensation effect and thus enhancing the growth quality of the vegetation.

[0072] As an improvement to the above embodiment, the step of acquiring the three-dimensional spatial information of the bridge surface and the location distribution information of the vegetation in each of the bridge under areas through the second camera device, and generating a map showing the occlusion status of the vegetation in each of the bridge under areas using the three-dimensional spatial information of the bridge surface and the location distribution information, includes the following sub-steps:

[0073] Based on the three-dimensional spatial information of the bridge deck, a bridge occlusion model for each area under the bridge is constructed.

[0074] The location distribution information of the green plants in each of the bridge bottom areas is mapped into the bridge shading model to determine the shading influence parameters of each green plant unit;

[0075] Based on the sun's trajectory and the shading effect parameters, calculate the time-varying shading coefficient of the vegetation in each of the bridge under areas;

[0076] Based on each of the time-varying shading coefficients, a vegetation shading map of each of the bridge under areas is generated, wherein the vegetation shading map includes the shading intensity distribution in the time-space dimension.

[0077] In this embodiment, a bridge shading model is first constructed based on the three-dimensional spatial information of the bridge deck. This model provides a basic framework for subsequent analysis of the shading situation. Then, the distribution information of the vegetation locations is mapped onto the bridge shading model to determine the shading impact parameters of the vegetation units, thereby quantifying the spatial relationship between the vegetation and the bridge. Next, combining the sun's trajectory and the shading impact parameters, a time-varying shading coefficient is calculated, fully considering the influence of time on light shading. Finally, based on the time-varying shading coefficient, a shading map of the vegetation, including the distribution of shading intensity in both time and space dimensions, is generated. This process, from static model construction to dynamic coefficient calculation and then to the generation of a dynamic shading map, achieves a comprehensive, dynamic, and accurate description of the light shading situation of the vegetation under the bridge. This embodiment provides more accurate and realistic shading information for adaptive lighting compensation of vertical greening under bridges by constructing a bridge shading model, mapping the location of green plants, calculating time-varying shading coefficients, and generating dynamic shading maps. This enables subsequent lighting compensation strategies generated based on this information to better adapt to the dynamic lighting environment under the bridge, further improving the accuracy and effectiveness of lighting compensation, thereby better meeting the lighting needs of the green plants under the bridge and promoting their growth.

[0078] Specifically, the working process of this embodiment is as follows:

[0079] To accurately assess the impact of the bridge structure on the lighting conditions of the vegetation beneath it, the system first utilizes a second camera device (such as a LiDAR or RGB-D camera) installed on the bridge structure to perform a high-precision scan of the bridge deck and its surrounding environment, acquiring 3D point cloud data of each component of the bridge. After data acquisition, the system employs existing point cloud filtering and segmentation algorithms (such as the RANSAC plane fitting algorithm) to identify the boundary information of key structural elements such as piers, arches, and bridge deck components. Furthermore, it uses triangulation to geometrically reconstruct the bridge structure, forming a 3D digital model with topological relationships—the "bridge occlusion model." This model, based on a global coordinate system, records the surface morphology of the bridge, the relative positions between components, and the bridge's contour features, serving as the fundamental geometric support for subsequent lighting simulation and occlusion calculations. Each bridge component is assigned a unique identifier and its coordinates in 3D space are stored. ,high Orientation angle Parameters such as these are used for occlusion effect analysis.

[0080] After constructing the bridge shading model, the system continues to collect spatial distribution information of plants within the green area under the bridge using a second camera device. This information includes attributes such as the planting location, canopy diameter, height, density, and plant type of each plant. After analysis using image recognition and target detection algorithms (such as YOLOv5 combined with an instance segmentation model), a spatial distribution matrix of plants is formed. Subsequently, the system maps each plant unit (defined as a single plant or a group of closely arranged plants) in the aforementioned plant distribution matrix to the constructed bridge shading model, establishing a spatial correspondence between the two. Specifically, based on the center coordinates of the plant unit, the system searches the bridge shading model for the presence of bridge structures (such as piers, beams, etc.) around it and determines whether the plant is within a potential shading area. Based on this, an shading influence parameter calculation model is used to quantify the impact of the bridge structure on the plant's lighting conditions. This model comprehensively considers factors such as bridge height, distance, solar incidence direction, and bridge projected area. Its calculation formula is as follows: ,in: Represents green plant unit Bridge body The degree of impact from occlusion; and This is an empirical adjustment coefficient that can be adjusted according to the light intensity in different regions. Indicates bridge body Height; Indicates green plants With the bridge body The horizontal distance between them; Indicates the direction of the sun's incidence and the bridge structure The included angle in the vertical direction; Indicates bridge body The projected area on the ground; Indicates green plants The canopy surface area. Using this formula, the system can calculate the area of ​​each green plant unit. With all surrounding bridge structures occlusion effect parameters The overall shading impact value of the green plant unit is obtained by summing these values: Compared to traditional occlusion assessment methods that rely solely on distance or angle, this embodiment introduces an exponential function and a projected area factor, which can more accurately reflect the actual impact of the bridge structure on the lighting of greenery.

[0081] To more accurately assess the dynamic shading effect of the bridge structure on the vegetation beneath it, the system incorporates a solar trajectory model to calculate the solar altitude angle in real time based on geographical location (latitude and longitude) and date and time. With azimuth Set a time step. (For example, 10 minutes), within the daily time frame from sunrise to sunset, every [time period]. Update the sun's position once, and adjust the shading impact value based on the previous step. Further calculation of green plant units At that moment instantaneous occlusion ratio The calculation formula is as follows: ,in: Indicates time The altitude angle of the sun at that time; Reflects the angle at which sunlight hits the ground; Represents green plant unit The overall shading effect. This allows calculation of the impact of changes in solar altitude angle on the shading effect: the shading effect is more pronounced when the solar altitude angle is low (e.g., in the early morning or late afternoon); while the shading effect weakens as the sun rises higher. This is achieved through hourly calculations. The system can generate green plant units. Occlusion curves at various times of day are obtained, and then the time-varying occlusion coefficient is derived. This coefficient reflects the change in the degree of shading of green plants per unit time.

[0082] Finally, the system calculates the time-varying shading coefficients of all green plant units. By integrating these elements into a unified spatial-temporal dimension, a "Greenery Shading Map" is constructed. This map, with time as the horizontal axis and spatial location as the vertical axis, uses a heatmap format to visually display the changing trends in the intensity of shading of vegetation in different areas under the bridge over different time periods. Specifically, the system divides the area under the bridge into several grid units, each corresponding to a certain number of vegetation units. At each point in time The system calculates the average shading ratio of all green plant units within the grid. The system maps this value to color depth (darker colors indicate more severe shading). Ultimately, the system generates one or more dynamic heatmaps that change over time, forming a complete map of vegetation shading. Furthermore, the system can export a shading intensity distribution map for a specific time period (e.g., 9:00 AM to 11:00 AM) to guide the development of supplemental lighting activation strategies, based on user needs.

[0083] As an improvement to the above embodiment, the step of extracting the growth status characteristics of the green plants in each of the bridge underside areas based on the canopy growth status map, and quantifying and generating the growth health index of the green plants in each of the bridge underside areas based on the growth status characteristics, includes the following sub-steps:

[0084] The canopy growth status of the green plants in each of the bridge under areas was analyzed to extract chlorophyll distribution features and canopy morphology features.

[0085] The chlorophyll distribution characteristics and canopy morphology characteristics are fused together to generate comprehensive physiological indicators for each green plant unit.

[0086] The comprehensive physiological indicators are quantified and converted according to the preset health assessment rules to generate the growth health index of the green plants in each of the bridge bottom areas.

[0087] In this embodiment, key information about plant growth is extracted by starting with the canopy growth status map. First, the canopy growth status map is analyzed to extract chlorophyll distribution characteristics and canopy morphology characteristics. These two features reflect the plant's growth status from physiological and morphological perspectives, respectively. Then, these two types of features are fused to generate a comprehensive physiological index, integrating multi-dimensional information and more comprehensively reflecting the plant's growth status. Finally, based on preset health assessment rules, the comprehensive physiological index is quantified to obtain a growth health index, allowing the plant's growth status to be presented intuitively in numerical form. Therefore, this embodiment, by extracting and fusing chlorophyll distribution and canopy morphology characteristics and then quantifying them to generate a growth health index, can comprehensively and accurately assess the growth health of plants under bridges. This provides a reliable basis for generating a light compensation strategy based on the effective light radiation absorption rate of the canopy, enabling the light compensation strategy to be precisely adjusted for plants in different health states, thereby effectively improving plant growth conditions and enhancing the growth quality and the targeted effectiveness of light compensation in bridge-under vertical greening.

[0088] The working process of this embodiment is exemplarily shown below:

[0089] To obtain quantitative information on the growth status of the vegetation, the system first acquires images of the canopy growth status of vegetation in various areas under the bridge using a primary imaging device (such as a multispectral camera or an RGB-NIR fusion imaging device). These images contain information in the visible and near-infrared bands, reflecting changes in leaf color, structural integrity, and potential photosynthetic activity. Subsequently, the system performs feature analysis on these images, employing existing image segmentation and color space conversion algorithms (such as HSV color model analysis) to identify the boundary contours and color distribution of the vegetation canopy. Furthermore, it applies vegetation index calculation methods (such as NDVI normalized difference vegetation index) to extract distribution features related to chlorophyll content. In addition, the system combines edge detection algorithms (such as the Canny operator) to extract the geometric morphological features of the canopy, including canopy area, perimeter, and fractal dimension. These features collectively form the data foundation for the subsequent construction of comprehensive physiological indicators.

[0090] After extracting chlorophyll distribution characteristics and canopy morphology characteristics, the system further fuses these two types of features to form a comprehensive physiological index that fully reflects the growth status of green plants. To this end, this embodiment employs a feature fusion algorithm based on weighted fuzzy clustering. This algorithm introduces a fuzzy membership function and a dynamic weight allocation mechanism, allowing different types of features to have adjustable importance ratios during the fusion process. Specifically, let... This represents the set of chlorophyll-related features extracted from canopy images. To represent the set of canopy morphological features, the system defines a fuzzy membership function. This is used to measure the contribution of each feature to the health status of green plants, and a set of dynamic weighting coefficients is set. and These correspond to chlorophyll characteristics and morphological characteristics, respectively. Ultimately, the green plant unit... Comprehensive physiological indicators It can be represented as: ,in: Indicates the first Chlorophyll distribution characteristics; Indicates the first Morphological characteristics of the canopy layer; and These represent the fuzzy membership degrees of the corresponding features, with values ​​ranging from [0, 1]. and These are the corresponding feature weight coefficients. This embodiment improves the robustness and adaptability of feature fusion by introducing a fuzzy membership function, making the comprehensive physiological indicators closer to the changing trends of real plant physiological states.

[0091] After obtaining the comprehensive physiological indicators of each plant unit, the system quantifies and converts them according to preset health assessment rules, ultimately generating a growth health index that can be used to formulate light compensation strategies. Specifically, the system establishes a health level mapping table, which maps the comprehensive physiological indicators... Mapped to preset health level range For example, [0.0, 1.0] or [1, 5] represent different health levels from the worst to the best, respectively. The mapping function adopts a non-linear sigmoid function form to enhance the resolution of the low-value range and improve the ability to identify plants in a weakly healthy state. Its conversion formula is as follows: , Represents green plant unit Growth and health index; This indicates the comprehensive physiological indicators of the green plant unit; A gain factor used to control the steepness of the curve; This represents the health threshold offset, used to adjust the baseline for classifying health levels. The sigmoid function better simulates the nonlinear response characteristics of plant health status as physiological indicators change, thereby improving the accuracy and practicality of health assessment.

[0092] As an improvement to the above embodiment, the step of simulating the dynamic shadows of each of the bridge under areas using a light projection algorithm based on the green vegetation shading map, and calculating the effective light radiation absorption rate of the canopy of the green vegetation in each bridge under area based on the dynamic shadow simulation results, includes the following sub-steps:

[0093] Based on the time-varying occlusion coefficient of the green vegetation occlusion map, the dynamic light source parameters of the light projection algorithm are set.

[0094] A light projection algorithm was used to simulate the distribution of the canopy of vegetation in the bridge underside area at multiple time points.

[0095] Accumulate the data on the distribution of light-receiving areas at various time points, and calculate the average daily light radiation received by each green plant unit;

[0096] By comparing the average daily light radiation received with the standard light radiation requirement, the effective light radiation reception rate of the canopy of the green plants in each of the bridge under areas is generated.

[0097] In this embodiment, based on the time-varying shading coefficient of the vegetation shading map, the dynamic light source parameters of the light projection algorithm are precisely set to provide realistic initial conditions for the simulation. Then, the light projection algorithm is used to simulate the distribution of light-receiving areas of the vegetation canopy in each bridge under area at multiple time points, capturing the dynamic changes in light intensity over time. By accumulating the distribution data of light-receiving areas at each time point, the average daily light radiation received by the vegetation unit is calculated, quantifying the actual light received by the vegetation. Finally, the average daily light radiation received is compared with the standard light radiation requirement value to obtain the effective light radiation reception rate of the canopy, intuitively reflecting the degree to which the light requirements of the vegetation canopy are met. This process, by combining dynamic shading conditions with the light projection algorithm, achieves dynamic and accurate calculation of the light radiation reception of the vegetation canopy under the bridge. This embodiment sets light source parameters based on time-varying shading coefficients, simulates the distribution of light-receiving areas, calculates the average daily light radiation received and compares it with standard values. This allows for the accurate calculation of the effective light radiation received rate of the green canopy under the bridge, which facilitates the generation of precise light compensation strategies. This ensures that the light compensation closely matches the actual light needs of the green plants under the bridge, avoiding problems of insufficient or excessive supplemental lighting.

[0098] For ease of understanding, the working process of this embodiment is described below:

[0099] To accurately simulate the light exposure of vegetation under the bridge at different times, the system first obtains the time-varying shading coefficient for each area under the bridge based on the vegetation shading map generated in the above embodiment. This coefficient reflects the green plant unit per unit time. The trend of shading intensity change. Subsequently, the system outputs the solar altitude angle from the solar trajectory model. and azimuth Using the light source direction as input, and combining the spatial location information of the bridge structure and the morphological data of the green canopy, a dynamic set of light source parameters is constructed. This set includes the light source direction vector. Light intensity attenuation function and atmospheric scattering correction factor This is used to drive subsequent ray casting algorithms. The above parameters are based on timestamps. It is updated in real time to ensure that the shadow simulation can reflect changes in real lighting conditions.

[0100] After setting the light source parameters, the system uses an improved ray projection algorithm to simulate the lighting conditions of the canopy of vegetation under the bridge. This algorithm, based on a geometric model in three-dimensional space and the principle of ray tracing, simulates the process of sunlight reaching the vegetation canopy frame-by-frame from sunrise to sunset. Specifically, the system treats the sun as a point light source, emitting several rays from its position towards the surface of the vegetation canopy, and determines whether each ray is blocked by the bridge structure or other vegetation. For unblocked rays, the system records their incident angle and contact area, and uses this information to plot the lighting at each time point. A distribution map of the light-receiving area of ​​the lower green canopy. Based on this, this embodiment improves the calculation accuracy of the light-receiving area under complex shading environments by using a light penetration correction model based on shading probability weights. This model defines green plant units. In time Effective light-receiving area at time as follows: , Represents green plant unit canopy surface area; This indicates the time period of the green plant unit. The time-varying occlusion coefficient; This represents the angle between the incident direction of the light ray and the canopy normal vector; This reflects the impact of the incident angle of light on the light reception efficiency. This model introduces an occlusion coefficient and an incident angle correction term, improving the accuracy of the simulation of the light-receiving area distribution.

[0101] After acquiring the distribution of the light-receiving area at each time point, the system further performs cumulative processing on the data from all time points to calculate the green plant unit. The total amount of light radiation received in a day. Specifically, the system simulates the light-receiving area for each frame. Corresponding light intensity Multiply the values ​​to obtain the received light radiation per unit time, and then integrate the data over the entire day. Let the simulation time step be... Then the green plant unit Daily average solar radiation received It can be represented as: , This represents the total number of time points simulated throughout the day; Indicates time The intensity of sunlight at that time is determined by both the atmospheric transmittance model and the solar altitude angle. This represents the time interval between adjacent time points, such as 10 minutes. This embodiment achieves an accurate estimation of the total amount of sunlight received throughout the day by accumulating the time.

[0102] Finally, the system will calculate the average daily solar radiation received. Compared with the preset standard light radiation requirement value A comparison is made to assess whether the actual light received by the plants meets their growth requirements. To this end, the system defines a dimensionless canopy effective light radiation absorption rate index. The calculation formula is as follows: , Represents green plant unit The average daily solar radiation received; This represents the standard light radiation requirement for a specific plant species, which is usually determined based on the plant's biological characteristics. This is the canopy reflectance correction factor, used to account for the impact of leaf reflection on actual absorbed light energy. This index reflects the proportion of effective light energy that the plant canopy can obtain under current light conditions; the closer the value is to 1, the more ideal the light conditions. If the light intensity is too high, it indicates that the plant is not getting enough light and a supplemental lighting device needs to be activated; otherwise, the intensity of the supplemental lighting can be reduced to save energy.

[0103] As an improvement to the above embodiment, the step of generating a light compensation strategy for the greenery in each of the bridge underside areas based on the growth health index and the effective light radiation absorption rate of the canopy includes the following sub-steps:

[0104] Establish a correlation matrix between the growth health index of green plants in each of the bridge under areas and the effective light radiation absorption rate of the canopy;

[0105] The correlation matrix is ​​divided into multiple compensation priority regions according to the preset compensation rules;

[0106] For each green plant unit's position coordinates in the correlation matrix, determine its corresponding compensation priority region;

[0107] Based on the time-varying shading coefficient of the aforementioned green vegetation shading map, the real-time supplemental lighting intensity required for each green plant unit is calculated.

[0108] Based on the real-time supplementary lighting demand intensity and compensation priority area, a lighting compensation strategy is generated for the green plants in each of the bridge under areas. The lighting compensation strategy includes light intensity adjustment parameters and illumination time parameters.

[0109] In this embodiment, a correlation matrix is ​​established between the plant growth health index and the effective light radiation reception rate of the canopy, systematically linking key data reflecting plant growth status and lighting conditions. Compensation priority areas are divided according to preset compensation rules, determining the compensation priority order for plants in different situations. Based on the position coordinates of each plant unit in the correlation matrix, its corresponding compensation priority area is identified, achieving precise positioning of individual plant units. Then, combined with the time-varying shading coefficient of the plant shading map, the real-time supplementary lighting demand intensity for each plant unit is calculated, comprehensively considering dynamic lighting environment factors. Finally, based on the real-time supplementary lighting demand intensity and the compensation priority areas, a lighting compensation strategy including light intensity adjustment parameters and illumination time parameters is generated, achieving refined control of supplementary lighting. This embodiment, by establishing a correlation matrix, dividing compensation priority areas, determining the location of plant units, calculating the real-time supplementary lighting demand intensity, and generating a lighting compensation strategy, can fully combine the growth status of the plants under the bridge and the dynamic lighting environment to accurately formulate a lighting compensation scheme that meets the actual needs of each plant unit. This effectively avoids the problem of insufficient or excessive lighting for some green plants under the unified supplemental lighting mode, improves the accuracy and efficiency of light compensation, and thus provides more suitable lighting conditions for the green plants under the bridge, thereby improving the growth quality of the green plants and the effect of vertical greening under the bridge.

[0110] As an example, the working process of this embodiment is as follows:

[0111] To achieve quantitative analysis of light compensation needs, the system first analyzes the growth health index of vegetation in each area under the bridge. With the effective light radiation receiving rate of the canopy Organize in a structured manner and construct a two-dimensional association matrix. This is used to characterize the coupling relationship between the health status of green plants and light conditions. Assume the system has a total of... If there are 100 green plant units, the correlation matrix can be represented as: , Indicates the first The growth health index of each green plant unit; This represents the effective light radiation reception rate of the canopy for this plant unit. This matrix not only records the current physiological state and light reception capacity of each plant unit, but also provides a data basis for subsequent compensation priority allocation.

[0112] After constructing the correlation matrix, the system classifies the green plant units in the matrix according to preset compensation rules, forming multiple regions with different supplemental lighting priorities. For this purpose, the system sets two thresholds: a health status threshold and a... and light reception threshold Based on this, the green plant units are divided into four compensation priority zones: high priority (poor health and insufficient light), medium priority (average health or slightly low light), low priority (good health and sufficient light), and no compensation zone (excellent health and sufficient light). The specific division rules are as follows: If and If it is, then it is classified into the high-priority area; if and ,or and If it is, then it is classified into the medium priority area; if and If it is, then it is classified into the low priority area; if and If the light intensity is low, it will be classified as an area that does not require compensation. The above rules can be flexibly adjusted according to the actual application scenario to ensure that the light compensation strategy can meet the needs of plant growth while avoiding resource waste.

[0113] After defining the compensation rules, the system analyzes each green plant unit in the association matrix. Each item is evaluated individually and mapped to its corresponding compensation priority region. Specifically, the system iterates through each row of data in the matrix. This is then compared with a preset priority determination boundary to ultimately determine the priority category to which the green plant unit belongs. For example, if a certain green plant unit... , The set health threshold Light reception threshold Then because and The vegetation is classified as a high-priority supplemental lighting target.

[0114] After prioritizing the data, the system further incorporates the time-varying shading coefficients from the vegetation shading map. The required supplemental lighting intensity for each green plant unit at different time points is dynamically calculated. To this end, this implementation adopts a supplemental lighting demand intensity calculation model based on shading compensation factors and priority weights. Under the premise of insufficient light, green plants with higher priority and more severe shading should receive stronger supplemental lighting support. This model defines green plant units... In time The intensity of supplemental lighting requirements as follows: , Represents green plant unit The priority weight function has a value range of [0.5, 1.5], and the higher the priority, the greater the weight. This indicates the effective light radiation receiving rate of the green plant unit; This indicates the time period of the green plant unit. The time-varying occlusion coefficient; This is an occlusion sensitivity adjustment factor used to control the amplification of the effect of occlusion on the supplementary light intensity. The model introduces priority weights and an occlusion correction term, enabling the supplementary light intensity to dynamically adjust with temporal and spatial changes, thereby improving the intelligence level of the illumination compensation system.

[0115] Finally, the system comprehensively considers the real-time supplemental lighting demand intensity. Based on the compensation priority region to which the green plant unit belongs, a light compensation strategy is generated to control the operation of the supplemental lighting device. This strategy consists of two core parameters: light intensity adjustment parameters. and irradiation time parameters Specifically, the system adjusts the intensity of the supplemental lighting based on the required lighting level. The output light intensity of the supplemental light is set, and the daily illumination duration is determined in conjunction with the plant's diurnal rhythm and energy consumption optimization principles. The calculation formula is as follows: , ,in, This indicates the maximum output light intensity of the fill light; This indicates the highest required supplemental lighting intensity among all green plant units; Indicates the baseline exposure duration; This is the irradiation time spread factor, typically ranging from 0.1 to 0.3. and These represent the minimum and maximum values ​​of the priority weight function, respectively.

[0116] In summary, this embodiment generates a light compensation strategy for controlling the light compensation device by modeling the correlation between the health index of green plants and their light reception capacity, combined with priority division and shading correction mechanisms.

[0117] As an example, the system uses the light intensity modulation parameters included in the illumination compensation strategy. and irradiation time parameters The system intelligently controls the supplemental lighting devices in various areas under the bridge to dynamically adjust the lighting environment for the greenery. Specifically, the control system adjusts the light intensity parameters in the lighting compensation strategy. and irradiation time parameters The data is transmitted to the corresponding supplemental lighting device controller, which then drives the device to output supplemental lighting at a specified intensity during the set time period. For example, during the period of lowest daily light intensity (such as from 10:00 AM to 2:00 PM), if a certain green plant unit under a bridge... If the area has a high demand for supplemental lighting, the supplemental lights in that area will activate high-brightness mode and extend the illumination time; conversely, if the plants in that area are healthy and there is sufficient light, only low-intensity maintenance supplemental lighting will be activated or it will not be activated at all. In addition, the system also incorporates time-varying shading coefficients. Adjust the direction and coverage of the light source in real time to ensure that the supplemental light energy is concentrated on the target green canopy and avoid ineffective radiation waste.

[0118] See Figure 2 This is a schematic diagram of an adaptive light compensation system for vertical greening under bridges, provided in an embodiment of the present invention. The adaptive light compensation system for vertical greening under bridges includes:

[0119] The acquisition module 10 is used to acquire images of the canopy growth status of the green plants in each area under the bridge through the first camera device;

[0120] The acquisition module 11 is used to acquire the three-dimensional spatial information of the bridge surface and the location distribution information of the green plants in each of the bridge bottom areas through the second camera device, and generate a map of the occlusion of the green plants in each of the bridge bottom areas through the three-dimensional spatial information of the bridge surface and the location distribution information.

[0121] Analysis module 12 is used to extract the growth status characteristics of the green plants in each of the bridge bottom areas based on the canopy growth status map, and to quantify and generate the growth health index of the green plants in each of the bridge bottom areas based on the growth status characteristics.

[0122] The simulation module 13 is used to simulate the dynamic shadow of each of the bridge bottom areas using a light projection algorithm based on the green vegetation shading map, and to calculate the effective light radiation receiving rate of the canopy of the green vegetation in each bridge bottom area based on the dynamic shadow simulation results.

[0123] Strategy generation module 14 is used to generate a light compensation strategy for the green plants in each of the bridge under areas based on the growth health index and the effective light radiation absorption rate of the canopy.

[0124] Control module 15 is used to control the supplementary lighting devices in each of the bridge under areas to provide light compensation for the green plants in the corresponding bridge under areas according to the light compensation strategy.

[0125] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0126] A first camera device captures images of the canopy growth status of the green plants, while a second camera device simultaneously acquires three-dimensional spatial information of the bridge surface and the distribution of the green plants, generating an image showing the shading of the green plants. This provides a comprehensive understanding of the plant growth status and the light shading environment under the bridge. Growth characteristics are extracted from the canopy growth image and quantified to obtain a growth health index, accurately reflecting the physiological state of the plants. A light projection algorithm is used to dynamically simulate shadows on the shading image, calculating the effective light radiation reception rate of the canopy to quantify the actual light received level. A targeted light compensation strategy is then generated by combining the growth health index and the effective light radiation reception rate of the canopy. Finally, adaptive light compensation for the green plants under the bridge is achieved by controlling a supplementary lighting device. In summary, this invention can adaptively generate and implement precise light compensation strategies based on the actual growth status and dynamic light environment of the green plants under the bridge, effectively improving the light compensation effect, enhancing the growth quality of the green plants, and improving the three-dimensional greening effect under the bridge.

[0127] As an improvement to the above embodiments, the acquisition module is specifically used for:

[0128] Based on the three-dimensional spatial information of the bridge deck, a bridge occlusion model for each area under the bridge is constructed.

[0129] The location distribution information of the green plants in each of the bridge bottom areas is mapped into the bridge shading model to determine the shading influence parameters of each green plant unit;

[0130] Based on the sun's trajectory and the shading effect parameters, calculate the time-varying shading coefficient of the vegetation in each of the bridge under areas;

[0131] Based on each of the time-varying shading coefficients, a vegetation shading map of each of the bridge under areas is generated, wherein the vegetation shading map includes the shading intensity distribution in the time-space dimension.

[0132] As an improvement to the above solution, the analysis module is specifically used for:

[0133] The canopy growth status of the green plants in each of the bridge under areas was analyzed to extract chlorophyll distribution features and canopy morphology features.

[0134] The chlorophyll distribution characteristics and canopy morphology characteristics are fused together to generate comprehensive physiological indicators for each green plant unit.

[0135] The comprehensive physiological indicators are quantified and converted according to the preset health assessment rules to generate the growth health index of the green plants in each of the bridge bottom areas.

[0136] As an improvement to the above embodiments, the simulation module is specifically used for:

[0137] Based on the time-varying occlusion coefficient of the green vegetation occlusion map, the dynamic light source parameters of the light projection algorithm are set.

[0138] A light projection algorithm was used to simulate the distribution of the canopy of vegetation in the bridge underside area at multiple time points.

[0139] Accumulate the data on the distribution of light-receiving areas at various time points, and calculate the average daily light radiation received by each green plant unit;

[0140] By comparing the average daily light radiation received with the standard light radiation requirement, the effective light radiation reception rate of the canopy of the green plants in each of the bridge under areas is generated.

[0141] As an improvement to the above embodiments, the strategy generation module is specifically used for:

[0142] Establish a correlation matrix between the growth health index of green plants in each of the bridge under areas and the effective light radiation absorption rate of the canopy;

[0143] The correlation matrix is ​​divided into multiple compensation priority regions according to the preset compensation rules;

[0144] For each green plant unit's position coordinates in the correlation matrix, determine its corresponding compensation priority region;

[0145] Based on the time-varying shading coefficient of the aforementioned green vegetation shading map, the real-time supplemental lighting intensity required for each green plant unit is calculated.

[0146] Based on the real-time supplementary lighting demand intensity and compensation priority area, a lighting compensation strategy is generated for the green plants in each of the bridge under areas. The lighting compensation strategy includes light intensity adjustment parameters and illumination time parameters.

[0147] It should be noted that the above-described embodiment of the adaptive light compensation system for vertical greening under bridges can be referenced to the relevant content of the above-described embodiment of the adaptive light compensation method for vertical greening under bridges, and will not be repeated here.

[0148] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0149] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An adaptive light compensation method for vertical greening under bridges, characterized in that, Includes the following steps: The first camera device was used to capture images of the canopy growth status of the green plants in each area under the bridge. The second camera device acquires the three-dimensional spatial information of the bridge surface and the location distribution information of the green plants in each of the bridge bottom areas, and generates a map of the green plant occlusion situation in each of the bridge bottom areas based on the three-dimensional spatial information of the bridge surface and the location distribution information. Based on the canopy growth status map, the growth status characteristics of the green plants in each of the bridge under areas are extracted, and the growth health index of the green plants in each of the bridge under areas is generated by quantification based on the growth status characteristics. Based on the green vegetation shading diagram, a light projection algorithm is used to simulate the dynamic shadows in each of the bridge under areas, and the effective light radiation reception rate of the canopy of the green vegetation in each bridge under area is calculated based on the dynamic shadow simulation results. Based on the growth health index and the effective light radiation absorption rate of the canopy of the green plants in each of the bridge under areas, a light compensation strategy for the green plants in each of the bridge under areas is generated. According to the light compensation strategy, the supplementary lighting devices in each of the bridge under areas are controlled to provide light compensation for the greenery in the corresponding bridge under areas. The step of acquiring three-dimensional spatial information of the bridge surface and the location distribution information of the vegetation in each of the bridge under areas using the second camera device, and generating a map showing the occlusion status of the vegetation in each of the bridge under areas using the three-dimensional spatial information of the bridge surface and the location distribution information, includes the following sub-steps: Based on the three-dimensional spatial information of the bridge deck, a bridge occlusion model for each area under the bridge is constructed. The location distribution information of the green plants in each of the bridge bottom areas is mapped into the bridge shading model to determine the shading influence parameters of each green plant unit; Based on the sun's trajectory and the shading effect parameters, calculate the time-varying shading coefficient of the vegetation in each of the bridge under areas; Based on each of the time-varying shading coefficients, a vegetation shading map of each of the bridge under areas is generated, wherein the vegetation shading map includes the shading intensity distribution in the time-space dimension.

2. The adaptive light compensation method for bridge under-bridge vertical greening as described in claim 1, characterized in that, The step of extracting the growth status characteristics of the vegetation in each of the bridge underside areas based on the canopy growth status map, and quantifying and generating the growth health index of the vegetation in each of the bridge underside areas based on the growth status characteristics, includes the following sub-steps: The canopy growth status of the green plants in each of the bridge under areas was analyzed to extract chlorophyll distribution features and canopy morphology features. The chlorophyll distribution characteristics and canopy morphology characteristics are fused together to generate comprehensive physiological indicators for each green plant unit. The comprehensive physiological indicators are quantified and converted according to the preset health assessment rules to generate the growth health index of the green plants in each of the bridge bottom areas.

3. The adaptive light compensation method for vertical greening under bridges as described in claim 2, characterized in that, The step of simulating dynamic shadows in each of the bridge underside areas using a light projection algorithm based on the vegetation shading map, and calculating the effective light radiation absorption rate of the canopy of vegetation in each bridge underside area based on the dynamic shadow simulation results, includes the following sub-steps: Based on the time-varying occlusion coefficient of the green vegetation occlusion map, the dynamic light source parameters of the light projection algorithm are set. A light projection algorithm was used to simulate the distribution of the canopy of vegetation in the bridge underside area at multiple time points. Accumulate the data on the distribution of light-receiving areas at various time points, and calculate the average daily light radiation received by each green plant unit; By comparing the average daily light radiation received with the standard light radiation requirement, the effective light radiation reception rate of the canopy of the green plants in each of the bridge under areas is generated.

4. The adaptive light compensation method for vertical greening under bridges as described in claim 3, characterized in that, The process of generating a light compensation strategy for the greenery in each of the bridge-under areas based on the growth health index and the effective light radiation absorption rate of the canopy includes the following sub-steps: Establish a correlation matrix between the growth health index of green plants in each of the bridge under areas and the effective light radiation absorption rate of the canopy; The correlation matrix is ​​divided into multiple compensation priority regions according to the preset compensation rules; For each green plant unit's position coordinates in the correlation matrix, determine its corresponding compensation priority region; Based on the time-varying shading coefficient of the aforementioned green vegetation shading map, the real-time supplemental lighting intensity required for each green plant unit is calculated. Based on the real-time supplementary lighting demand intensity and compensation priority area, a lighting compensation strategy is generated for the green plants in each of the bridge under areas. The lighting compensation strategy includes light intensity adjustment parameters and illumination time parameters.

5. An adaptive light compensation system for vertical greening under bridges, characterized in that, include: The data acquisition module is used to acquire images of the canopy growth status of the green plants in each area under the bridge using the first camera device. The acquisition module is used to acquire the three-dimensional spatial information of the bridge surface and the location distribution information of the green plants in each of the bridge bottom areas through the second camera device, and generate a map of the occlusion of the green plants in each of the bridge bottom areas through the three-dimensional spatial information of the bridge surface and the location distribution information. The analysis module is used to extract the growth status characteristics of the green plants in each of the bridge under areas based on the canopy growth status map, and to quantify and generate the growth health index of the green plants in each of the bridge under areas based on the growth status characteristics. The simulation module is used to simulate the dynamic shadows of each of the bridge under areas using a light projection algorithm based on the green vegetation shading map, and to calculate the effective light radiation absorption rate of the canopy of the green vegetation in each bridge under area based on the dynamic shadow simulation results. The strategy generation module is used to generate a light compensation strategy for the green plants in each of the bridge under areas based on the growth health index and the effective light radiation absorption rate of the canopy. The control module is used to control the supplementary lighting devices in each of the bridge under areas to provide light compensation for the green plants in the corresponding bridge under areas according to the light compensation strategy. Specifically, the acquisition module is used for: Based on the three-dimensional spatial information of the bridge deck, a bridge occlusion model for each area under the bridge is constructed. The location distribution information of the green plants in each of the bridge bottom areas is mapped into the bridge shading model to determine the shading influence parameters of each green plant unit; Based on the sun's trajectory and the shading effect parameters, calculate the time-varying shading coefficient of the vegetation in each of the bridge under areas; Based on each of the time-varying shading coefficients, a vegetation shading map of each of the bridge under areas is generated, wherein the vegetation shading map includes the shading intensity distribution in the time-space dimension.

6. The adaptive light compensation system for vertical greening under bridges as described in claim 5, characterized in that, The analysis module is specifically used for: The canopy growth status of the green plants in each of the bridge under areas was analyzed to extract chlorophyll distribution features and canopy morphology features. The chlorophyll distribution characteristics and canopy morphology characteristics are fused together to generate comprehensive physiological indicators for each green plant unit. The comprehensive physiological indicators are quantified and converted according to the preset health assessment rules to generate the growth health index of the green plants in each of the bridge bottom areas.

7. The adaptive light compensation system for vertical greening under bridges as described in claim 5, characterized in that, The simulation module is specifically used for: Based on the time-varying occlusion coefficient of the green vegetation occlusion map, the dynamic light source parameters of the light projection algorithm are set. A light projection algorithm was used to simulate the distribution of the canopy of vegetation in the bridge underside area at multiple time points. Accumulate the data on the distribution of light-receiving areas at various time points, and calculate the average daily light radiation received by each green plant unit; By comparing the average daily light radiation received with the standard light radiation requirement, the effective light radiation reception rate of the canopy of the green plants in each of the bridge under areas is generated.

8. The adaptive light compensation system for vertical greening under bridges as described in claim 5, characterized in that, The strategy generation module is specifically used for: Establish a correlation matrix between the growth health index of green plants in each of the bridge under areas and the effective light radiation absorption rate of the canopy; The correlation matrix is ​​divided into multiple compensation priority regions according to the preset compensation rules; For each green plant unit's position coordinates in the correlation matrix, determine its corresponding compensation priority region; Based on the time-varying shading coefficient of the aforementioned green vegetation shading map, the real-time supplemental lighting intensity required for each green plant unit is calculated. Based on the real-time supplementary lighting demand intensity and compensation priority area, a lighting compensation strategy is generated for the green plants in each of the bridge under areas. The lighting compensation strategy includes light intensity adjustment parameters and illumination time parameters.

Images