Sensor network based LED scene adaptive power control method and system
By dynamically adjusting the LED light power through sensor networks and deep learning models, the problems of energy waste and insufficient safety in existing road lighting systems are solved. On-demand lighting and accurate pedestrian fall risk assessment are achieved, thereby improving energy efficiency and pedestrian safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIANGMEN LVJING SOLAR ELECTRICITY CO LTD
- Filing Date
- 2025-08-25
- Publication Date
- 2026-06-09
Smart Images
Figure CN121099494B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of sensor network technology, and in particular to an adaptive power control method and system for LED scenes based on sensor networks. Background Technology
[0002] In modern urban life, road lighting and pedestrian safety are two crucial aspects of urban infrastructure construction and management. Good road lighting not only provides pedestrians with clear visibility at night, ensuring their smooth passage, but also reduces the probability of various safety accidents to a certain extent. However, there are still many problems to be solved in the field of road lighting and pedestrian safety. In terms of pedestrian safety assessment, the current assessment methods are relatively simple, usually only considering pedestrian flow while ignoring complex factors such as pedestrian walking speed and walking trajectory. Different walking speeds and trajectories reflect different states and potential dangers of pedestrians on the road. For example, walking too fast may increase the risk of falling, while irregular walking trajectories may mean that pedestrians are disturbed by road conditions or other factors. The existing pedestrian safety assessment system cannot comprehensively analyze these complex situations, resulting in inaccurate prediction of dangerous situations such as pedestrian falls and difficulty in taking effective preventive measures in advance. In terms of road lighting control, traditional road lighting systems use fixed power lighting, and the lights always illuminate at a constant power regardless of the number of pedestrians on the road or the road environment. This approach not only results in significant energy waste and increases urban energy consumption and operating costs, but also fails to flexibly adjust to actual road hazards and pedestrian needs. In areas with fewer pedestrians and good road conditions, high-intensity lighting is redundant; while in areas with complex road conditions and more pedestrians, fixed-power lighting may not provide sufficient brightness to meet pedestrian safety requirements. Therefore, this application proposes an LED scene adaptive power control method and system based on sensor networks. Summary of the Invention
[0003] To overcome the defects and shortcomings mentioned in the background art, this application provides an LED scene adaptive power control method and system based on sensor networks.
[0004] To achieve the above objectives, this application adopts the following technical solution:
[0005] In a first aspect, this application provides an adaptive power control method for LED scenes based on sensor networks, comprising the following steps:
[0006] Step S1: Obtain feature data of the road surface and pedestrian traffic on the corresponding road surface through a sensor network, and simultaneously obtain weather information;
[0007] Step S2: Conduct road hazard analysis based on the smoothness characteristics of the road surface and the corresponding weather conditions;
[0008] Step S3: Analyze the degree of pedestrian hazard based on the pedestrian walking situation on the corresponding road surface and the road hazard analysis results;
[0009] Step S4: Based on the analysis results of the degree of walking hazard and the corresponding road surface hazard characteristics, conduct a risk assessment of pedestrian fall.
[0010] Step S5: Adjust the light power based on the risk assessment of personnel falling.
[0011] In one implementation of this application, the specific content of the sensor network acquiring the corresponding data is as follows: various types of sensors are reasonably deployed at key locations on the road to collect the required data comprehensively and accurately. The sensor network continuously collects characteristic data of the road surface, pedestrian traffic on the corresponding road surface, and weather conditions. The collected data is stored in digital form and transmitted to the data processing center in real time through wireless communication technology.
[0012] In one implementation of this application, step S2, which involves road hazard analysis based on the smoothness characteristics of the road surface and corresponding weather conditions, includes the following specific steps:
[0013] S21. Obtain the road surface conditions and weather conditions for the corresponding road location. Estimate the road surface humidity based on the road surface slope, water absorption, and porosity, as well as future weather conditions for the corresponding road location. Future weather conditions are obtained from weather forecasts. The road humidity estimation is performed by obtaining historical road surface slope, water absorption, and porosity, weather conditions, and road humidity data. Based on this historical data, a deep learning neural network model is constructed, taking the road surface slope, water absorption, and porosity, and weather conditions as inputs, and outputting the road humidity data. The historical data is divided into a 9:1 training set and a test set; 90% of the weights and biases are... The training set is used to train the deep learning neural network model to obtain the initial deep learning neural network model. The initial deep learning neural network model is tested using a test set with 10% weights and a bias. The output of the initial deep learning neural network model that satisfies the maximum accuracy of road humidity judgment is used as the deep learning neural network model. The corresponding time of future road humidity is estimated by estimating the distance of people from the corresponding road surface and the walking speed of people. The advantage is that it comprehensively considers the road's own characteristics and future weather conditions to predict road surface humidity. The deep learning neural network model is constructed using historical data, and the accuracy and generalization ability of the model are ensured by reasonably dividing the training set and the test set.
[0014] S22. A deep learning neural network model is used to obtain future road humidity and the height of various points on the road surface. Based on this height, road smoothness anomalies are assessed. The analysis method for road smoothness anomalies is as follows: the absolute values of the relative heights of each road point with respect to the road reference surface are summed, divided by the road surface safety fluctuation height, and then averaged to obtain the road smoothness anomaly result. Humidity anomalies are obtained by the ratio of future road humidity to safe humidity. Road anomalies are obtained by weighted summation of humidity anomalies and road smoothness anomalies. The methods for obtaining safe humidity and road surface safety fluctuation height align with actual road design and usage requirements. Road surface humidity affects road safety, slippage rate is related to humidity, and the height fluctuation of various points on the road surface reflects road smoothness; both factors jointly affect the overall road condition.
[0015] S23. Obtain the weather forecast of the future weather conditions, obtain the outlier value of the corresponding weather conditions by the standard deviation between the corresponding future weather conditions and the corresponding safe range, and obtain the future weather anomaly by weighted summation of the outlier values of all the weather conditions that affect the weather. The advantage is that the degree of anomaly of the future weather conditions can be quantified according to the weather forecast, and the comprehensive future weather anomaly can be obtained by weighted summation of the outlier values of each weather condition that affects the weather.
[0016] S24. The road hazard analysis result is obtained by weighted summation of future weather anomalies and corresponding road anomalies. The road hazard analysis result is obtained by weighted summation of future weather anomalies and road anomalies, which comprehensively considers the impact of weather and road factors on the degree of road hazard.
[0017] In one implementation of this application, the walking hazard analysis in step S3 includes the following specific steps:
[0018] S31. Obtain the walking speed and image changes of the corresponding personnel. Analyze the walking complexity based on the image changes of the corresponding personnel. The walking complexity analysis includes the following: obtaining the stability coefficient of the walking of the corresponding adjacent frame by dividing the area of the overlapping region of the walking images of adjacent frames by the area of the merged region; subtracting the stability coefficient of the walking of the corresponding adjacent frame from 1 to obtain the walking complexity of the corresponding adjacent frame; and obtaining the walking complexity analysis result by averaging the walking complexity of all adjacent frames in the corresponding time period. The advantage is that by obtaining the walking speed and image changes of the personnel, the walking complexity can be quantitatively analyzed in a scientific way.
[0019] S32. By weighted summing the results of the walking complexity analysis and the corresponding road hazard analysis, the walking hazard level of the corresponding person on the corresponding road can be obtained. By weighted summing the results of the walking complexity analysis and the road hazard analysis, the walking hazard level of the corresponding person on the corresponding road can be assessed more comprehensively and accurately, taking into account both the person's own walking condition and the objective hazard conditions of the road.
[0020] In one implementation of this application, the personnel fall risk assessment in step S4 includes the following specific contents:
[0021] S41. Obtain the road surface smoothness anomaly analysis results and road surface elasticity conditions of the corresponding road surface. Based on the road surface smoothness anomaly analysis results and road surface elasticity conditions of the corresponding road surface, conduct road fall injury analysis. The road fall injury analysis process is as follows: obtain the road surface elasticity anomaly by the ratio of the road surface elasticity condition to the average elasticity of human skin. Obtain the corresponding fall injury analysis result by weighted summing the road surface elasticity anomaly and the corresponding road surface smoothness anomaly analysis results. When a person falls and collides with the road surface, it causes injury to the person. Because road surface smoothness anomalies reflect the amount of road surface protrusions, they have a more serious impact on the person. When a person falls and collides with the road surface, the elasticity and surface smoothness of the road surface directly affect the impact force and energy transfer during the collision process. When the road surface has good elasticity, it can buffer the impact force generated by the collision to a certain extent and reduce the injury to the human body. When there are uneven conditions such as protrusions on the road surface, the collision will be more concentrated in a local area, increasing the possibility and severity of injury. When assessing road fall injury, two key factors, road surface smoothness anomalies and road surface elasticity conditions, are considered simultaneously.
[0022] S42. The corresponding person's fall risk assessment result is obtained by multiplying the obtained road walking hazard level with the obtained road fall injury analysis result. This comprehensively considers both the road walking hazard level and the road fall injury, realizing a multi-dimensional assessment, avoiding the one-sidedness of single-factor assessment, making the results more accurate and comprehensive, and providing a more scientific and reliable basis for decision-making.
[0023] In one implementation of this application, the adjustment of the light power in step S5 includes the following specific aspects:
[0024] The system acquires the brightness of external natural light and the corresponding fall hazard assessment result. If the brightness of external natural light is less than the set brightness threshold and the fall hazard assessment result is less than the corresponding fall hazard assessment threshold, the light power remains at the rated power. If the brightness of external natural light is less than the set brightness threshold and the fall hazard assessment result is greater than or equal to the corresponding fall hazard assessment threshold, the light power is adjusted to 110% to 120% of the rated power. If the brightness of external natural light is greater than or equal to the set brightness threshold and the fall hazard assessment result is greater than or equal to the corresponding fall hazard assessment threshold, the light power remains at the rated power. If the brightness of external natural light is greater than or equal to the set brightness threshold and the fall hazard assessment result is less than the corresponding fall hazard assessment threshold, the light power is adjusted to 70% to 80% of the rated power. This allows for on-demand lighting, improves energy efficiency, and avoids unnecessary energy waste.
[0025] Secondly, this application also provides an LED scene adaptive power control system based on sensor networks, including:
[0026] The data acquisition module acquires feature data of the road surface and pedestrian traffic on the corresponding road surface through a sensor network, while also acquiring weather information;
[0027] The road hazard analysis module performs road hazard analysis based on the smoothness characteristics of the road surface and the corresponding weather conditions.
[0028] The pedestrian hazard analysis module analyzes the degree of pedestrian hazard based on pedestrian traffic conditions on the corresponding road surface and the results of road hazard analysis.
[0029] The fall risk assessment module assesses the risk of falls for individuals based on the analysis results of walking risk level and the corresponding road surface risk characteristics.
[0030] The power adjustment module adjusts the light power based on a risk assessment of falls.
[0031] Thirdly, this application provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an LED scene adaptive power control method based on a sensor network by calling the computer program stored in the memory.
[0032] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an LED scene adaptive power control method based on a sensor network.
[0033] Compared with the prior art, this application has the following advantages and beneficial effects:
[0034] By strategically deploying a sensor network to comprehensively and accurately collect road surface feature data, pedestrian traffic patterns, and weather conditions, road hazard analysis is first conducted based on road surface smoothness and weather conditions. Then, pedestrian traffic hazard analysis is performed, followed by a comprehensive assessment of fall risk based on road hazard characteristics. Finally, lighting power is adjusted according to the assessment results and natural light intensity. The advantages are threefold: First, it accurately acquires road and pedestrian-related data, using historical data to build models that ensure accurate humidity prediction and scientifically assess road anomalies, weather anomalies, and the complexity of pedestrian traffic. Second, it comprehensively considers road, pedestrian, and weather factors from multiple dimensions to comprehensively and accurately assess road hazards, pedestrian hazards, and fall risks, avoiding the bias of assessments based on a single factor. Third, it enables on-demand lighting, improving energy efficiency and avoiding energy waste. Simultaneously, it allows for flexible lighting adjustments based on different scenarios, ensuring pedestrian safety while adhering to the principle of prioritizing both energy conservation and safety, thus meeting the lighting and safety requirements of the real-world environment. Attached Figure Description
[0035] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:
[0036] Figure 1 This is a schematic diagram of the overall process of Embodiment 1 of the method of this application;
[0037] Figure 2 This is a schematic diagram of step S2 of embodiment 1 of the method of this application;
[0038] Figure 3 This is a schematic diagram of the structure of embodiment 2 of the system in this application. Detailed Implementation
[0039] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the specific embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0040] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.
[0041] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of this application. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.
[0042] Example 1
[0043] like Figures 1 to 2 As shown, this embodiment provides an adaptive power control method for LED scenes based on sensor networks, specifically including the following steps:
[0044] Step S1: Obtain feature data of the road surface and pedestrian traffic on the corresponding road surface through a sensor network, and simultaneously obtain weather information;
[0045] In this embodiment, the specific content of the sensor network acquiring the corresponding data is as follows: Multiple types of sensors are rationally deployed at key locations on the road to comprehensively and accurately collect the required data. These key locations include, but are not limited to, densely populated pedestrian areas (such as shopping malls and school entrances), road bends, and uphill and downhill sections. The specifically deployed sensors include: Road surface feature sensors: using laser rangefinders, etc. Laser rangefinders can accurately measure changes in road surface height to detect unevenness such as potholes and bumps. Simultaneously, road construction data is used to obtain information on road elasticity, slope, water absorption, and porosity for analyzing road surface moisture under different environments; Pedestrian walking monitoring sensors: using high-definition cameras and infrared sensors... The camera features high resolution and a wide field of view, clearly capturing pedestrians' walking posture, speed, direction, and other information. Infrared sensors can accurately detect the location and movement of people at night or in low-light environments. Weather sensors are installed at weather stations, including temperature sensors, humidity sensors, rainfall sensors, and wind speed sensors. The temperature sensor measures ambient temperature, the humidity sensor acquires air humidity, the rainfall sensor monitors rainfall in real time, and the wind speed sensor measures wind speed and direction. Through the sensor network, characteristic data of the road surface, pedestrian traffic on the corresponding road surface, and weather conditions are continuously collected. The collected data is stored in digital form and transmitted to the data processing center in real time via wireless communication technology.
[0046] Step S2: Conduct road hazard analysis based on the smoothness characteristics of the road surface and the corresponding weather conditions;
[0047] In this embodiment, step S2 involves road hazard analysis based on the smoothness characteristics of the road surface and the corresponding weather conditions, including the following specific steps:
[0048] S21. Obtain the road surface conditions and weather conditions for the corresponding road location. Estimate the road surface humidity based on the road surface slope, water absorption, and porosity, as well as future weather conditions for the corresponding road surface location. Future weather conditions are obtained from weather forecasts. The road humidity estimation is performed as follows: Obtain historical road surface slope, water absorption, and porosity, weather conditions, and road humidity data for the corresponding road surface. Based on this historical data, construct a deep learning neural network model that takes the road surface slope, water absorption, and porosity, and weather conditions as input, and outputs the road humidity data. Divide the historical data into a 9:1 training set and a test set. Input 90% of the weights and the bias training set into the deep learning neural network model for training to obtain the initial deep learning neural network model. Utilize... The initial deep learning neural network model was tested with a 10% weight and bias test set. The output of the initial deep learning neural network model that satisfies the maximum accuracy of road humidity judgment was used as the deep learning neural network model. The corresponding time of future road humidity was estimated by the distance of people to the road surface and the walking speed of people. The advantage is that it comprehensively considers the road's own characteristics and future weather conditions to predict road surface humidity. The deep learning neural network model was built using historical data. The accuracy and generalization ability of the model were ensured by reasonably dividing the training set and the test set. It can also predict the corresponding time of humidity based on the distance of people and walking speed. There is an intrinsic correlation between road surface slope, water absorption, porosity and weather conditions and road surface humidity. Historical data can reflect this correlation and be used for model learning.
[0049] S22. The future humidity of the road is obtained through a deep learning neural network model, along with the height of various points on the road surface. Based on the height of these points, the road smoothness anomaly is assessed. The method for analyzing road smoothness anomalies is as follows: the absolute values of the relative heights of each road point with respect to the road reference surface are summed and divided by the road surface safety fluctuation height. The average of these values is then used to obtain the road smoothness anomaly result. The ratio of the future road humidity to the safe humidity level is used to obtain the humidity anomaly. The road anomaly is obtained by weighted summation of the humidity anomaly and the road smoothness anomaly. The methods for obtaining the road's safe humidity and the road surface safety fluctuation height are: during the road design phase... The system determines the road surface smoothness requirements based on factors such as road grade and usage function. It obtains the safe humidity of the road surface based on the slipperiness of the road surface. If the humidity is higher than a certain level and the slipperiness rate exceeds a threshold, the corresponding humidity is set as the safe humidity. The advantage is that it can accurately obtain the future humidity of the road and assess road smoothness anomalies by combining the height of various points on the road surface. The road anomalies are obtained by weighted summation of humidity anomalies and smoothness anomalies. The method of obtaining safe humidity and safe road surface fluctuation height is in line with the actual road design and usage needs. Road surface humidity affects road safety, slipperiness rate is related to humidity, and height fluctuation of various points on the road surface reflects road smoothness. Both of them jointly affect the overall condition of the road.
[0050] S23. Obtain the forecast of future weather conditions, obtain the outlier values of the corresponding weather conditions by the standard deviation between the corresponding future weather conditions and the corresponding safe range, and obtain the future weather anomaly by weighted summation of the outlier values of all the weather conditions that affect the road. The advantage is that the degree of anomaly of the future weather conditions can be quantified according to the weather forecast. By weighted summation of the outlier values of each weather condition that affects the road, the degree of deviation of different weather conditions from their safe range can reflect the potential impact of the weather on the road. Quantification facilitates subsequent analysis.
[0051] S24. The road hazard analysis results are obtained by weighted summation of future weather anomalies and corresponding road anomalies. The road hazard analysis results are obtained by weighted summation of future weather anomalies and road anomalies, which comprehensively considers the influence of weather and road factors on the degree of road hazard. Weather conditions and road conditions jointly determine the degree of road hazard. The combined analysis of the two can more comprehensively and accurately assess road safety.
[0052] Step S3: Analyze the degree of pedestrian hazard based on the pedestrian walking situation on the corresponding road surface and the road hazard analysis results;
[0053] In this embodiment, the walking hazard analysis in step S3 includes the following specific steps:
[0054] S31. Obtain the walking speed and changes in the walking images of the corresponding personnel. Analyze the complexity of walking based on these changes. The complexity analysis includes the following: obtaining the stability coefficient of walking in adjacent frames by dividing the area of the intersecting region after the overlapping of walking images of adjacent frames by the area of the merging region; subtracting the stability coefficient from 1 to obtain the complexity of walking in adjacent frames; and finally, taking the average of the complexity of walking in all adjacent frames within the corresponding time period to obtain the analysis result. The advantage is that by obtaining the walking speed and changes in the images, the complexity of walking can be quantitatively analyzed in a scientific way. The stability coefficient is calculated using the area of the intersecting and merging regions after the overlapping of walking images of adjacent frames, thus obtaining the complexity of walking in adjacent frames. The final analysis result is obtained by taking the average value within the time period, which accurately reflects the complexity of walking and shows that changes in the walking images can reflect the stability of walking.
[0055] S32. By weighted summing the results of the walking complexity analysis and the corresponding road hazard analysis, the walking hazard level of the corresponding person on the corresponding road can be obtained. By weighted summing the results of the walking complexity analysis and the road hazard analysis, the individual's walking condition and the objective road hazard conditions are comprehensively considered. This allows for a more comprehensive and accurate assessment of the walking hazard level of the corresponding person on the corresponding road. The complexity of the person's walking and the hazard conditions of the road jointly affect the safety of the person walking on the road. Combining the two in the analysis is consistent with the actual situation.
[0056] Step S4: Based on the analysis results of the degree of walking hazard and the corresponding road surface hazard characteristics, conduct a risk assessment of pedestrian fall.
[0057] In this embodiment, the fall risk assessment in step S4 includes the following specific contents:
[0058] S41. Obtain the road surface smoothness anomaly analysis results and road surface elasticity conditions for the corresponding road surface. Based on the road surface smoothness anomaly analysis results and road surface elasticity conditions, conduct road fall injury analysis. The road fall injury analysis process is as follows: Obtain the road surface elasticity anomaly by the ratio of the road surface elasticity condition to the average elasticity of human skin. Obtain the corresponding fall injury analysis result by weighted summing the road surface elasticity anomaly and the corresponding road surface smoothness anomaly analysis results. When a person falls and collides with the road surface, it causes injury to the person. Because road surface smoothness anomalies reflect the amount of road surface protrusions, they have a more serious impact on the person. When a person falls and collides with the road surface, the road surface elasticity and surface smoothness directly affect the impact force and energy transfer during the collision process. When the road surface has good elasticity, it can buffer the impact force generated by the collision to a certain extent and reduce the injury to the person. When there are uneven conditions such as protrusions on the road surface, the collision will be more concentrated in a local area, increasing the possibility and severity of injury. When assessing road fall injury, two key factors, road surface smoothness anomalies and road surface elasticity conditions, are considered simultaneously. Road surface irregularities reflect the unevenness of the road surface, while road surface elasticity reflects the cushioning performance of the road. Combining these two factors in the analysis provides a more comprehensive reflection of the actual road surface conditions and their impact on fall injuries, avoiding the limitations of single-factor assessments. This results in more accurate and reliable fall injury analysis. For example, in some older residential areas, roads may have uneven surfaces, but the road material also has a certain degree of elasticity. Considering only road surface irregularities might overestimate the severity of fall injuries; while considering only road surface elasticity might underestimate the potential danger caused by road surface bumps. Taking both factors into account yields a more realistic injury assessment result. It should be noted that the weighting parameters in this application are obtained by acquiring historical road surface feature data and corresponding pedestrian traffic patterns, along with weather conditions. This historical data is then imported into various steps of this embodiment for analysis of the corresponding fall risk assessment results. Simultaneously, actual fall injury results in the environment are acquired, and the obtained analysis results and actual fall injury results in the environment are imported into MATLAB fitting software for data fitting to obtain values that meet the highest fall safety accuracy.
[0059] S42. The corresponding personnel fall risk assessment result is obtained by multiplying the obtained road walking hazard level with the obtained road fall injury analysis result. The assessment comprehensively considers both the road walking hazard level and the road fall injury, realizing multi-dimensional assessment, avoiding the one-sidedness of single-factor assessment, making the result more accurate and comprehensive, providing a more scientific and reliable basis for decision-making, and helping relevant departments or individuals to formulate targeted preventive measures to effectively reduce the risk of personnel falling. From the perspective of physical principles, both road walking hazard and road surface conditions will affect the impact force and energy transfer during a fall.
[0060] Step S5: Adjust the light power based on the risk assessment of personnel falling;
[0061] In this embodiment, the adjustment of the light power in step S5 includes the following specific aspects:
[0062] The system acquires the brightness of external natural light and the corresponding fall hazard assessment result. If the brightness of the external natural light is less than the set brightness threshold, and the corresponding fall hazard assessment result is less than the corresponding fall hazard assessment threshold, the light power is maintained at the rated power. If the brightness of the external natural light is less than the set brightness threshold, and the corresponding fall hazard assessment result is greater than or equal to the corresponding fall hazard assessment threshold, the light power is adjusted to 110% to 120% of the rated power. If the brightness of the external natural light is greater than or equal to the set brightness threshold, and the corresponding fall hazard assessment result is greater than or equal to the corresponding fall hazard assessment threshold, the light power is maintained at the rated power. If the fall risk assessment result is less than the corresponding fall risk assessment threshold, the light power will be adjusted to 70% to 80% of the rated power. This enables on-demand lighting, improves energy efficiency, and avoids unnecessary energy waste. Simultaneously, the lighting can be flexibly adjusted according to different scenarios. When the fall risk assessment result is high, the lighting can be appropriately increased to ensure personnel safety. When the risk assessment result is low and natural light is sufficient, the lighting power can be reduced. This takes into account the impact of natural light on indoor lighting needs. When natural light is insufficient, the decision to increase lighting can be made based on the degree of fall risk. Conversely, when natural light is sufficient, the power can be reasonably reduced based on the fall risk situation. This approach meets actual lighting needs while adhering to the principle of balancing energy conservation and safety, aligning with the lighting and safety requirements of the real-world environment.
[0063] In this embodiment, it is important to note that it offers the following advantages: By strategically deploying a sensor network, it comprehensively and accurately collects road surface feature data, pedestrian activity, and weather conditions. First, it performs road hazard analysis based on road surface smoothness and weather conditions. Then, it analyzes the degree of pedestrian hazard based on pedestrian activity. Next, it assesses the risk of falls by comprehensively considering road hazard characteristics. Finally, it adjusts the lighting power based on the assessment results and natural light intensity. The benefits are threefold: First, it accurately acquires road and pedestrian-related data, utilizes historical data to build models to ensure accurate humidity prediction, and scientifically assesses road anomalies, weather anomalies, and the complexity of pedestrian activity. Second, it comprehensively considers road, pedestrian, and weather factors from multiple dimensions to comprehensively and accurately assess road hazards, pedestrian hazards, and the risk of falls, avoiding the bias of single-factor assessments. Third, it achieves on-demand lighting, improves energy efficiency, avoids energy waste, and flexibly adjusts lighting according to different scenarios, ensuring pedestrian safety while adhering to the principle of prioritizing both energy conservation and safety, thus meeting the lighting and safety requirements of the real-world environment.
[0064] Example 2
[0065] like Figure 3 As shown, this embodiment provides an LED scene adaptive power control system based on a sensor network for implementing the LED scene adaptive power control method based on a sensor network in Embodiment 1. Specifically, it includes: a data acquisition module, which acquires feature data of the road surface and the pedestrian traffic on the corresponding road surface through a sensor network, and also acquires weather conditions.
[0066] The road hazard analysis module performs road hazard analysis based on the smoothness characteristics of the road surface and the corresponding weather conditions.
[0067] The pedestrian hazard analysis module analyzes the degree of pedestrian hazard based on pedestrian traffic conditions on the corresponding road surface and the results of road hazard analysis.
[0068] The fall risk assessment module assesses the risk of falls for individuals based on the analysis results of walking risk level and the corresponding road surface risk characteristics.
[0069] The power adjustment module adjusts the light power based on the risk assessment of personnel falling. The specific steps of each module in this embodiment are the same as those in the method embodiment of embodiment 1, and will not be repeated here.
[0070] Example 3
[0071] An electronic device according to an embodiment of this application includes a processor and a memory. The memory stores a computer program that can be called by the processor. The processor executes an LED scene adaptive power control method based on a sensor network by calling the computer program stored in the memory. It should be noted that all computer programs for the LED scene adaptive power control method based on a sensor network are implemented using the C language.
[0072] Example 4
[0073] This embodiment proposes a computer-readable storage medium on which an erasable and rewritable computer program is stored.
[0074] When the computer program runs on the computer device, it causes the computer device to execute the above-mentioned sensor network-based LED scene adaptive power control method.
[0075] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions according to the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives (SSDs).
[0076] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0077] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0078] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0079] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.
[0080] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0081] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0082] The foregoing has shown and described the basic principles, main features, and advantages of this application. Those skilled in the art should understand that this application is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this application. Various changes and modifications can be made to this application without departing from the spirit and scope thereof, and all such changes and modifications fall within the scope of this application as claimed. The scope of protection of this application is defined by the appended claims and their equivalents.
Claims
1. An adaptive power control method for LED scenes based on sensor networks, characterized in that, Includes the following steps: Step S1: Obtain feature data of the road surface and pedestrian traffic on the corresponding road surface through a sensor network, and simultaneously obtain weather information; Step S2: Conduct road hazard analysis based on the smoothness characteristics of the road surface and the corresponding weather conditions; The specific steps include the following: Obtain the road surface conditions and weather conditions of the corresponding road location, and predict the road surface humidity based on the road surface slope, water absorption and porosity, and the future weather conditions of the corresponding road surface location. The future humidity of the road is obtained by using a deep learning neural network model, and the height of each point on the road surface is also obtained. The road smoothness anomaly is evaluated based on the height of each point on the road surface. The humidity anomaly is obtained by the ratio of the future humidity of the road to the safe humidity. The road anomaly is obtained by weighted summation of the humidity anomaly and the road smoothness anomaly. Obtain the future weather conditions from the weather forecast, obtain the outliers of the corresponding weather conditions by the standard deviation between the corresponding future weather conditions and the corresponding safe range, and obtain the future weather anomalies by weighted summation of the outliers of all the affected weather conditions. The road hazard analysis results are obtained by weighted summation of future weather anomalies and corresponding road anomalies. Step S3: Analyze the degree of pedestrian hazard based on the pedestrian walking situation on the corresponding road surface and the road hazard analysis results; The specific steps include the following: The walking speed and changes in the walking images of the corresponding personnel are obtained. The walking complexity analysis is performed based on the changes in the walking images of the corresponding personnel. The walking complexity analysis includes the following: the area of the intersection region after the walking images of adjacent frames overlap is divided by the area of the merged region to obtain the stability coefficient of the walking of the corresponding adjacent frame; the walking complexity of the corresponding adjacent frame is obtained by subtracting the stability coefficient of the walking of the corresponding adjacent frame from 1; and the walking complexity analysis result is obtained by averaging the walking complexity of all adjacent frames in the corresponding time period. The degree of danger for a person walking on a corresponding road is obtained by weighted summing the results of the walking complexity analysis and the corresponding road hazard analysis. Step S4: Based on the analysis results of the degree of walking hazard and the corresponding road surface hazard characteristics, conduct a risk assessment of pedestrian fall. Includes the following specific content: Obtain the road surface smoothness anomaly analysis results and road surface elasticity conditions of the corresponding road surface. Based on the road surface smoothness anomaly analysis results and road surface elasticity conditions of the corresponding road surface, conduct road surface fall injury analysis. The road surface fall injury analysis process is as follows: obtain the road surface elasticity anomaly by the ratio of the road surface elasticity condition to the average elasticity of human skin. Obtain the corresponding fall injury analysis result by weighted summing the road surface elasticity anomaly and the corresponding road surface smoothness anomaly analysis results. The corresponding pedestrian risk assessment result is obtained by multiplying the obtained road walking hazard level with the obtained road surface fall injury analysis result; Step S5: Adjust the light power based on the risk assessment of personnel falling.
2. The LED scene adaptive power control method based on sensor networks according to claim 1, characterized in that, The adjustment of the light power includes the following specific aspects: The system acquires the brightness of external natural light and the corresponding fall risk assessment result. If the brightness of external natural light is less than the set brightness threshold and the fall risk assessment result is less than the corresponding fall risk assessment threshold, the light power is maintained at the rated power. If the brightness of external natural light is less than the set brightness threshold and the fall risk assessment result is greater than or equal to the corresponding fall risk assessment threshold, the light power is adjusted to 110% to 120% of the rated power. If the brightness of external natural light is greater than or equal to the set brightness threshold and the fall risk assessment result is greater than or equal to the corresponding fall risk assessment threshold, the light power is maintained at the rated power. If the brightness of external natural light is greater than or equal to the set brightness threshold and the fall risk assessment result is less than the corresponding fall risk assessment threshold, the light power is adjusted to 70% to 80% of the rated power.
3. The LED scene adaptive power control method based on sensor networks according to claim 1, characterized in that, The construction of the deep learning neural network model includes the following specific steps: obtaining the road surface slope, water absorption and porosity, weather conditions, and road humidity of the corresponding historical road surface; constructing a deep learning neural network model based on the historical data, with the road surface slope, water absorption and porosity, and weather conditions as inputs and the road humidity as output; dividing the historical data into a 9:1 training set and a test set; inputting 90% of the weights and biases of the training set into the deep learning neural network model for training to obtain the initial deep learning neural network model; testing the initial deep learning neural network model using 10% of the weights and biases of the test set, and outputting the initial deep learning neural network model that satisfies the maximum accuracy of road humidity judgment as the deep learning neural network model.
4. The LED scene adaptive power control method based on sensor network according to claim 1, characterized in that, The specific content of the sensor network acquiring the corresponding data is as follows: various types of sensors are reasonably deployed at key locations on the road; the specific deployed sensors include: road surface feature sensors, pedestrian walking monitoring sensors and weather sensors, which collect feature data of the road surface, pedestrian walking conditions on the corresponding road surface and weather conditions. The collected data is stored in digital form and transmitted to the data processing center in real time through wireless communication technology.
5. An LED scene adaptive power control system based on sensor networks, used to implement the LED scene adaptive power control method based on sensor networks as described in any one of claims 1-4, characterized in that, The system includes: The data acquisition module acquires feature data of the road surface and pedestrian traffic on the corresponding road surface through a sensor network, while also acquiring weather information; The road hazard analysis module performs road hazard analysis based on the smoothness characteristics of the road surface and the corresponding weather conditions. The pedestrian hazard analysis module analyzes the degree of pedestrian hazard based on pedestrian traffic conditions on the corresponding road surface and the results of road hazard analysis. The fall risk assessment module assesses the risk of falls for individuals based on the analysis results of walking risk level and the corresponding road surface risk characteristics. The power adjustment module adjusts the light power based on a risk assessment of falls.
6. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the LED scene adaptive power control method based on a sensor network as described in any one of claims 1-4 by calling the computer program stored in the memory.