A follow-up lighting system for night greenery garbage disposal

Abstract

The application relates to the lighting technical field and discloses a following type lighting system for night greenery garbage treatment. The system analyzes road surface information data, environmental information data and image information data before work of each corresponding cleaning unit through an analysis module, obtains comprehensive cleaning complexity of each cleaning unit, and obtains lighting parameters of each cleaning unit according to the comprehensive cleaning complexity. The lighting parameters of the corresponding lighting module are controlled by a control module according to the cleaning unit where a target object is currently located and the lighting parameters corresponding to the cleaning unit. The lighting brightness of the lighting module of the cleaning unit is adjusted according to the comprehensive cleaning complexity of the cleaning unit. The lighting brightness is increased in the cleaning unit with high comprehensive cleaning complexity, which is favorable for reducing a visual blind area caused by insufficient lighting, improving the identification ability of workers to road surface garbage and potential obstacles, and improving work safety.

Description

Technical Field

[0001] This invention relates to the field of lighting technology, and more specifically to a following lighting system for nighttime green waste disposal. Background Technology

[0002] Green waste refers to various plant remains, mainly including branches, leaves, grass clippings, flowers, etc. With the continuous development of urban greening, the number of gardens is gradually increasing, and the amount of green waste generated is also increasing year by year. In order to avoid green waste affecting tourists' visitor experience, staff usually handle green waste at night when there are fewer people. However, when handling green waste, staff need to carefully distinguish fallen leaves, dead branches and weeds on the ground, so good lighting is required when handling green waste.

[0003] In the prior art, a smart lighting system and method that follows the human body is disclosed in the publication number "CN107979904A". It includes a lighting network composed of multiple lighting devices. The human body sensing device feeds back the sensing information to the lighting device where the human body is located, and the lighting device where the human body is located starts to illuminate, so as to realize the following lighting based on the human body's position.

[0004] However, the aforementioned technology still has certain limitations. It primarily determines the central lighting device based on the position of the human body and adjusts the brightness of different lighting devices according to the positional relationship between the lighting device and the human body, as well as the ambient brightness. It does not determine corresponding lighting parameters for the road surface conditions and waste conditions of different cleaning units during nighttime green waste disposal operations. The road surface materials and post-rain dryness of different cleaning units affect the difficulty of the workers' work. Simultaneously, the spatial distribution of other waste and the quantity and size of large green waste also affect the difficulty of waste sorting, handling, and processing. Therefore, it is necessary to determine corresponding lighting parameters based on the actual cleaning complexity of different cleaning units. Summary of the Invention

[0005] The purpose of this invention is to provide a following lighting system for nighttime green waste disposal, thereby solving the above-mentioned technical problems: The objective of this invention can be achieved through the following technical solutions: A following lighting system for nighttime green waste disposal, the lighting system comprising: The partitioning module is used to divide the target area into several cleaning units and number each cleaning unit, wherein the number is denoted as . n ; The road surface information module is used to store road surface information data for each cleaning unit; Multiple image acquisition modules, one for each cleaning unit, are used to collect image information data of the corresponding cleaning unit before the operation. Multiple lighting modules, one for each cleaning unit, are used for illumination; The environmental information module is used to acquire environmental information data for the target area. The analysis module is used to analyze the road surface information data, environmental information data and pre-operation image information data of each corresponding cleaning unit to obtain the comprehensive cleaning complexity of each cleaning unit, and to obtain the lighting parameters of each cleaning unit based on the comprehensive cleaning complexity. The control module is used to control the corresponding lighting module to start working lighting according to the lighting parameters of the corresponding cleaning unit after detecting that the target object performing the green waste disposal operation has entered the corresponding cleaning unit, and to predict the movement trend of the target object in adjacent cleaning units and adjust the lighting modules of the adjacent cleaning units to the pre-set lighting parameters in advance. The control module is also used to reduce the lighting brightness of the current cleaning unit to the standby lighting brightness when it is detected that the target object leaves the current cleaning unit and enters the adjacent cleaning unit.

[0006] As a further aspect of the present invention: the process of obtaining the overall cleanup complexity is as follows: S1: The analysis module analyzes the environmental information data and the road surface information data of each cleaning unit to obtain the actual road surface complexity of each cleaning unit; S2: Collect image information data of each cleaning unit before operation through the image acquisition module of each cleaning unit at the preset acquisition time every day; S3: The analysis module analyzes the pre-operation image information data of each cleaning unit to obtain the garbage cleaning complexity of each cleaning unit; S4: The analysis module analyzes the actual road surface complexity and garbage cleaning complexity of each cleaning unit to obtain the comprehensive cleaning complexity of each cleaning unit.

[0007] As a further aspect of the present invention: through the formula: ; The calculation number is The actual road surface complexity of the cleaning unit ; in, For the judgment function, when hour, ;when hour, ; This is the pavement complexity adjustment coefficient for the pavement material corresponding to this cleaning unit; Based on the complexity of the road surface; This represents the duration from the last time rainfall stopped to the current time. Preset drying time; The duration of a unit of time; The rainfall impact coefficient is the road surface material corresponding to this cleaning unit; This is the first preset constant.

[0008] 5. As a further aspect of the present invention: through the formula: ; Calculate the preset drying time ; in, The current time; To ensure effective statistical duration, its value is determined by the following rule: when... hour, ;when hour, ,in, The preset minimum positive duration, and ; The preset duration was previously known; The function represents the change in real-time rainfall intensity over time in the target area. This is the preset cumulative rainfall; The function represents the real-time humidity variation of the target area over time. Preset humidity; The real-time temperature change function of the target area over time; Preset temperature; This is the first weighting coefficient; This is the second weighting coefficient; This is the third weighting coefficient; This is the second preset constant; This is the third preset constant; This is the fourth preset constant; The baseline drying time is used to characterize the baseline time required for a road surface to go from a wet state to a dry state under preset baseline environmental conditions.

[0009] As a further aspect of the present invention: numbered The method for obtaining the garbage collection complexity of the cleaning unit includes the following steps: S10: The analysis module will process the code numbered... The waste in the pre-operation image information data of the cleaning unit is divided into two categories: other waste and green waste; S20: Identify other debris in the pre-operation image information data of the cleaning unit; when other debris exists, determine the location of each piece of debris, and obtain the minimum coverage circle that covers all other debris locations based on the location of each piece of debris; when no other debris exists, set the pixel area of ​​the minimum coverage circle that covers all other debris locations to 0. S30: The analysis module identifies all green waste from the pre-operation image information data of the cleaning unit and obtains the pixel area of ​​each piece of green waste; when the pixel area of ​​green waste is greater than or equal to the preset pixel area threshold, it is identified as large green waste, and when the pixel area of ​​green waste is less than the preset pixel area threshold, it is identified as small green waste. S40: The garbage cleaning complexity of this cleaning unit is obtained by analyzing the minimum coverage circle that covers all other garbage locations, as well as the number and pixel area of ​​large green garbage.

[0010] As a further aspect of the present invention: through the formula: ; The calculation number is The complexity of garbage collection in the cleaning unit ; in, The complexity of basic waste cleanup; The pixel area of ​​the smallest coverage circle that the cleaning unit can cover all other garbage locations; The total pixel area of ​​the image information data before the operation; Let h be the total number of large green waste items in this cleaning unit, and h be the serial number of the large green waste items, where h = 1, 2, ..., H; For this cleaning unit The pixel area of ​​a large piece of green waste; To remove the unit coefficient; This is the first major complexity weighting coefficient; This is the second largest complexity weighting coefficient; This is the first garbage collection complexity weighting coefficient; This is the second garbage collection complexity weighting coefficient; This is the first preset constant; This is the second preset constant.

[0011] As a further aspect of the present invention: through the formula: ; The calculation number is The overall cleaning complexity of the cleaning unit .

[0012] As a further aspect of the present invention: through the formula: ; The calculation number is The lighting brightness of the cleaning unit's lighting module ; in, The complexity is in units; Based on the brightness of the lighting.

[0013] The beneficial effects of this invention are: This invention divides the target area into several cleaning units using a partitioning module, stores road surface information data for each cleaning unit using a road surface information module, acquires pre-operation image information data for each cleaning unit using an image acquisition module, illuminates each cleaning unit using a lighting module, obtains environmental information data for the target area using an environmental information module, and analyzes the road surface information data, environmental information data, and pre-operation image information data for each cleaning unit using an analysis module to obtain the overall cleaning complexity of each cleaning unit. Based on the overall cleaning complexity, it obtains the lighting parameters for each cleaning unit. A control module controls the corresponding lighting module according to the lighting parameters of each cleaning unit after the target object enters the lighting area of ​​that cleaning unit. This allows for adjusting the lighting brightness of the cleaning unit's lighting module based on the overall cleaning complexity of the cleaning unit. Increasing the lighting brightness in cleaning units with higher overall cleaning complexity helps reduce blind spots caused by insufficient lighting, improves workers' ability to identify road debris and potential obstacles, and enhances operational safety. Attached Figure Description

[0014] The invention will now be further described with reference to the accompanying drawings.

[0015] Figure 1 This is a system module framework diagram of one embodiment of the present invention. Detailed Implementation

[0016] 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.

[0017] Please see Figure 1 As shown, in one embodiment, a following lighting system for nighttime green waste disposal is provided, the lighting system comprising: The partitioning module is used to divide the target area into several cleaning units and number each cleaning unit, wherein the number is denoted as . n ; The road surface information module is used to store road surface information data for each cleaning unit; Multiple image acquisition modules, one for each cleaning unit, are used to collect image information data of the corresponding cleaning unit before the operation. Multiple lighting modules, one for each cleaning unit, are used for illumination; The environmental information module is used to acquire environmental information data for the target area. The analysis module is used to analyze the road surface information data, environmental information data, and pre-operation image information data of each corresponding cleaning unit to obtain the comprehensive cleaning complexity of each cleaning unit, and to obtain the lighting parameters of each cleaning unit based on the comprehensive cleaning complexity; the lighting parameters include lighting brightness. The control module is used to control the corresponding lighting module to start working lighting according to the lighting parameters of the corresponding cleaning unit after detecting that the target object performing the green waste disposal operation has entered the corresponding cleaning unit, and to predict the movement trend of the target object in adjacent cleaning units and adjust the lighting modules of adjacent cleaning units to the pre-set lighting parameters in advance. The control module is also used to reduce the lighting brightness of the current cleaning unit to the standby lighting brightness when the target object leaves the current cleaning unit and enters an adjacent cleaning unit. The standby lighting brightness is a preset fixed low illuminance value, which is lower than the working lighting brightness of any cleaning unit, and is used to maintain basic safe lighting and reduce energy consumption after the target object leaves.

[0018] It should be noted that the "following" lighting described in this invention refers to the lighting system dynamically adjusting the lighting parameters of the cleaning unit and its adjacent cleaning units based on the current location of the target object, rather than a single lighting device mechanically following the movement of a human body. The target object refers to the worker performing the green waste disposal operation or automated equipment. In a preferred embodiment, the target object is a worker wearing an identifiable tag or detectable by a human body sensor; in another embodiment, the target object is an automated cleaning robot equipped with a positioning module.

[0019] Through the above technical solution, this embodiment divides the target area into several cleaning units using a partitioning module, stores road surface information data for each cleaning unit using a road surface information module, collects pre-operation image information data for each cleaning unit using multiple image acquisition modules, illuminates each cleaning unit using multiple lighting modules, acquires environmental information data for the target area using an environmental information module, analyzes the road surface information data, environmental information data, and pre-operation image information data for each cleaning unit using an analysis module to obtain the overall cleaning complexity of each cleaning unit, and obtains the lighting parameters for each cleaning unit based on the overall cleaning complexity analysis, and controls the corresponding lighting modules according to the lighting parameters of each cleaning unit after the target object enters the lighting area of ​​the corresponding cleaning unit using a control module, thereby adjusting the lighting brightness of the lighting modules of the cleaning unit according to the overall cleaning complexity of the cleaning unit. Increasing the lighting brightness in cleaning units with higher overall cleaning complexity helps reduce blind spots caused by insufficient lighting, improves the ability of workers to identify road debris and potential obstacles, and improves operational safety.

[0020] The road surface complexity adjustment coefficient It should be noted that the lighting area of ​​each cleaning unit is a preset area, which will not be described in detail here; in this embodiment, the target object is the staff performing the green waste disposal operation. The human body sensing device can detect whether the target object has entered the lighting area of ​​the corresponding cleaning unit and send the detection result to the control module; the control module controls the lighting module of the corresponding cleaning unit to start the lighting according to the detection result.

[0021] It should be noted that the human body sensing device is a pyroelectric infrared sensor or millimeter-wave radar, which is installed on the lamp post of each lighting module. Each human body sensing device is communicatively connected to the control module. When any sensing device detects a target object, it is determined that the target object has entered the lighting area of ​​the cleaning unit corresponding to that sensing device.

[0022] Specifically, the control module predicts adjacent cleaning units based on the target object's movement trend as follows: The control module records the sequence of human body sensing device numbers continuously triggered by the target object, and establishes a movement trajectory vector based on the position coordinates of at least two consecutively triggered cleaning units; subsequently, the movement trajectory vector is extended along the current direction, and the first adjacent cleaning unit that intersects in the extended direction is determined as the predicted adjacent cleaning unit. If the target object triggers only a single cleaning unit (such as just entering the target area), then all cleaning units physically adjacent to that cleaning unit are considered as predicted adjacent cleaning units.

[0023] The pre-lighting parameter refers to the transitional lighting brightness between the standby lighting brightness and the working lighting brightness. In this embodiment, the control module sets the predicted pre-lighting brightness of adjacent cleaning units to 50% of the corresponding working lighting brightness of that unit. By adjusting the predicted adjacent units to the pre-lighting parameter in advance, the overall energy consumption of the system can be reduced while eliminating the brief visual dark area that the target object may face when crossing the boundary of the cleaning unit, thus achieving a smooth visual transition buffer.

[0024] As one embodiment of the present invention, the process of obtaining the overall cleanup complexity is as follows: S1: The analysis module analyzes the environmental information data and the road surface information data of each cleaning unit to obtain the actual road surface complexity of each cleaning unit; S2: Collect image information data of each cleaning unit before operation through the image acquisition module of each cleaning unit at the preset acquisition time every day; S3: The analysis module analyzes the pre-operation image information data of each cleaning unit to obtain the garbage cleaning complexity of each cleaning unit; S4: The analysis module analyzes the actual road surface complexity and garbage cleaning complexity of each cleaning unit to obtain the comprehensive cleaning complexity of each cleaning unit; Through the above technical solution, this embodiment analyzes environmental information data and road surface information data of each cleaning unit through an analysis module to obtain the actual road surface complexity of each cleaning unit; it collects pre-operation image information data of each cleaning unit through an image acquisition module at a preset acquisition time every day; it analyzes the pre-operation image information data of each cleaning unit through an analysis module to obtain the garbage cleaning complexity of each cleaning unit; it analyzes the actual road surface complexity and garbage cleaning complexity of each cleaning unit through an analysis module to obtain the comprehensive cleaning complexity of each cleaning unit; and it sets the preset acquisition time every day to a preset time point before the start of nighttime green waste treatment operations, so that the acquisition time of pre-operation image information data is close to the nighttime green waste treatment time, and the pre-operation image information data is acquired under the condition of meeting the image acquisition lighting requirements, thereby improving the accuracy of garbage cleaning complexity calculation; The road surface information data includes road surface materials, and the environmental information data includes real-time rainfall intensity, real-time humidity, and real-time temperature of the target area. It should be noted that the road surface materials include gravel roads, dirt roads, sand and gravel roads, and asphalt roads. Different road surface materials have different road surface complexities, therefore, each road surface material corresponds to a corresponding road surface complexity adjustment coefficient; different road surface materials are affected by rainfall to different degrees, therefore, each road surface material corresponds to a corresponding rainfall impact coefficient; the methods for obtaining real-time rainfall intensity, real-time humidity, and real-time temperature of the target area are existing technologies and will not be described in detail here.

[0025] As one embodiment of the present invention, the formula is as follows: ; The calculation number is The actual road surface complexity of the cleaning unit ; in, For the judgment function, when hour, ;when hour, ; This is the pavement complexity adjustment coefficient for the pavement material corresponding to this cleaning unit; Based on the complexity of the road surface; This represents the duration from the last time rainfall stopped to the current time. Preset drying time; The duration of a unit of time; The rainfall impact coefficient is the road surface material corresponding to this cleaning unit; This is the first preset constant; Through the above technical solution, this embodiment The pavement complexity of the pavement material corresponding to this cleaning unit; The formula is the difference between the preset dry period and the time from the end of the last rainfall to the current time. In the context of judgment functions In It refers to This is used to determine whether the preset drying time exceeds the time from the end of the last rainfall to the current time. This indicates that the time elapsed since the last rainfall ended has not yet reached the preset drying time, and the road surface is still wet. The larger the value, the longer the remaining time required to reach the preset dry state, and therefore the higher the actual road surface complexity; at this time... ;when This indicates that the time elapsed since the last rainfall has ended has reached or exceeded the preset drying time, and the road surface has reached the preset dry state. ;pass Assess the actual pavement complexity of the pavement material corresponding to the cleaning unit in its current state; In this embodiment, the basic road surface complexity P0 is set to 1.0; the first preset constant The value is 24, used to convert the duration difference into a unit of days; the unit of time The value is 1 hour. The above value is an optimal value obtained through multiple field tests and optimizations. In other embodiments of the present invention, it can be adjusted according to the actual application scenario.

[0026] It should be noted that the method for determining the pavement complexity adjustment coefficient is as follows: Standard sample blocks of typical pavement materials, including asphalt pavement, cement pavement, gravel pavement, and dirt pavement, are selected. Under standard lighting conditions (illuminance of 50±5 lux), at least 10 workers with more than three years of experience in green waste disposal score the difficulty of identifying pavement at different humidity levels. Humidity levels are measured by mass moisture content and are set to four levels: 0%, 5%, 10%, and 15%. Scores range from 1 to 10, with 10 indicating the most difficult identification. The average score of each pavement material at each humidity level is taken. The average score of asphalt pavement in a dry state (0% mass moisture content) is used as the baseline value of 1.0. The ratio of the average score of other pavement materials at each humidity level to the baseline value is calculated. Then, the least squares method is used for fitting to obtain the pavement complexity adjustment coefficient of each pavement material at different humidity levels, forming a table of correspondence between this coefficient and pavement material type and humidity level. The pavement complexity adjustment coefficient actually used in the system is obtained by looking up the table based on the current pavement material type and humidity level. For example, the pavement complexity adjustment coefficient for asphalt pavement in a dry state is 1.0, and the pavement complexity adjustment coefficient for pavement with a moisture content of 15% is 1.05; the pavement complexity adjustment coefficient for gravel pavement in a dry state is 1.2, and the pavement complexity adjustment coefficient for pavement with a moisture content of 15% is 1.45.

[0027] The method for determining the rainfall impact coefficient is as follows: Standard sample blocks of road materials, namely asphalt pavement, cement pavement, gravel pavement, and dirt pavement, are selected with the same calibration as the aforementioned pavement complexity adjustment coefficient. Under the same standard illumination environment (illuminance value of 50±5 lux), the identification accuracy of each pavement material is tested in both dry (0% moisture content) and wet (15% moisture content) states. The testing method is as follows: Dark-colored circular targets with a diameter of 2 to 5 cm are randomly placed on each pavement sample block to simulate fallen leaves. At least 10 workers with more than three years of experience in green waste disposal identify the targets from a distance of 1.5 meters. The number of targets correctly identified within 30 seconds is recorded. The correct identification rate (number of correctly identified targets divided by the total number of targets multiplied by 100%) is used as the identification accuracy rate. The decrease in identification accuracy rate from dry to wet states for each pavement material is calculated, i.e., the identification accuracy rate in the dry state minus the identification accuracy rate in the wet state. Using the decrease in the identification accuracy of asphalt pavement as a baseline value of 1.0, the decrease in the identification accuracy of each pavement material is divided by the decrease in the asphalt pavement to obtain the normalized rainfall impact coefficient for each pavement material. A larger rainfall impact coefficient indicates a more significant increase in the difficulty of identification after rainfall. For example, the rainfall impact coefficient for asphalt pavement ranges from 0.02 to 0.05, for cement pavement from 0.01 to 0.03, for gravel pavement from 0.05 to 0.10, and for dirt pavement from 0.04 to 0.08. The specific values ​​within these coefficient ranges are determined by collecting multiple sets of sample data in actual operating scenarios using the above calibration method and then fitting the data using the least squares method.

[0028] It should be noted that the variable X in the judgment function f(X) refers to different physical quantities in different formulas of this invention, but the judgment rule remains consistent: when the physical quantity it refers to is greater than 0, the function takes the value of the physical quantity itself; when the physical quantity it refers to is less than or equal to 0, the function takes the value of 0. This function is used to quantify the positive deviations from the benchmark value in each formula, avoiding the unreasonable reverse influence of negative values ​​on the calculation results.

[0029] As one embodiment of the present invention, the formula is as follows: ; Calculate the preset drying time ; in, The current time; To ensure effective statistical duration, its value is determined by the following rule: when... hour, ;when hour, ,in, The preset minimum positive duration, and ; The preset duration was previously known; The function represents the change in real-time rainfall intensity over time in the target area. This is the preset cumulative rainfall; The function represents the real-time humidity variation of the target area over time. Preset humidity; The real-time temperature change function of the target area over time; Preset temperature; This is the first weighting coefficient; This is the second weighting coefficient; This is the third weighting coefficient; This is the second preset constant; This is the third preset constant; This is the fourth preset constant; The baseline drying time is used to characterize the baseline time required for a road surface to go from a wet state to a preset dry state under preset baseline environmental conditions. Through the above technical solution, this embodiment This represents the cumulative rainfall within a preset time period prior to the last rainfall stop time. It is the difference between the cumulative rainfall within a preset time period prior to the last rainfall stop time and the preset cumulative rainfall; when This indicates that the cumulative rainfall within the preset time period prior to the last rainfall stop time exceeded the preset cumulative rainfall amount. More rainfall meant more water was absorbed by the road surface, requiring more time to dry. Therefore, the difference between the cumulative rainfall within the preset time period prior to the last rainfall stop time and the preset cumulative rainfall amount is [value missing]. The larger the size, the longer the preset drying time. The longer; conversely, when This indicates that the cumulative rainfall within the preset time period prior to the last rainfall stop time did not exceed the preset cumulative rainfall amount. The rainfall was relatively low, resulting in less water absorption on the road surface and a shorter drying time. Therefore, the difference between the cumulative rainfall within the preset time period prior to the last rainfall stop time and the preset cumulative rainfall amount is [not specified]. The larger the absolute value, the longer the preset drying time. The shorter; The average humidity from the time the last rainfall ended to the current time; The difference between the average humidity from the time the last rainfall ended to the current time and the preset humidity. This indicates that the average humidity from the time the last rainfall ended to the current time exceeds the preset humidity level. The high water vapor content in the air slows down the evaporation of moisture from the road surface, thus slowing down the drying process. Therefore, the difference between the average humidity from the time the last rainfall ended to the current time and the preset humidity level is significant. The larger the size, the longer the preset drying time. The longer; conversely, when This indicates that the average humidity from the time the last rainfall ended to the current time has not exceeded the preset humidity. The water vapor content in the air is low, leading to faster evaporation of moisture from the road surface and a faster drying process. Therefore, the difference between the average humidity from the time the last rainfall ended to the current time and the preset humidity is [missing information]. The larger the absolute value, the longer the preset drying time. The shorter; The average temperature from the time the last rainfall ended to the current time; The difference between the average temperature from the time the last rainfall ended to the current time and the preset temperature. This indicates that the average temperature from the time the last rainfall ended to the current time exceeds the preset temperature, resulting in faster evaporation and quicker road surface drying. Therefore, the difference between the average temperature from the time the last rainfall ended to the current time and the preset temperature is significant. The larger the size, the longer the preset drying time. The shorter; conversely, when This indicates that the average temperature from the time the last rainfall stopped to the current time has not exceeded the preset temperature, the evaporation rate is slow, and the road surface drying rate is slow. Therefore, the difference between the average temperature from the time the last rainfall stopped to the current time and the preset temperature is... The larger the absolute value, the longer the preset drying time. The longer; It should be noted that, in this embodiment, the specific values ​​of each parameter are as follows: the basic drying time The value is 6 hours, which is the measured average time required for an asphalt pavement to go from a saturated wet state (moisture content >15%) to a preset dry state (moisture content <2%) under standard environmental conditions (temperature 25℃, relative humidity 60%, no wind). The preset cumulative rainfall... The value is 5 millimeters, and the preset humidity is... The value is set to 80%, and the preset temperature T0 is set to 25℃. The first weighting coefficient... The value is 0.2, the second weighting coefficient. The value is 0.15, the third weighting coefficient. The value is 0.1. The second preset constant. The value is 100, the third preset constant. The value is 10, the fourth preset constant. The value is 10.

[0030] The specific methods for obtaining the preset thresholds, weighting coefficients, and preset constants, excluding those mentioned above, are as follows: Meteorological data (including hourly rainfall intensity, temperature, and humidity) and road surface condition data for the target area over the past year are collected. The actual time it takes for the road surface to reach a preset dry state (moisture content below 2%) is used as the dependent variable, and the aforementioned parameters are used as independent variables. Multiple nonlinear regression analysis is employed to fit the parameters, yielding the preset constants and preset values ​​applicable to the target area. In the initial stage of system deployment, the preset values ​​adopt default values ​​under typical temperate climate conditions. During actual operation, rolling corrections are made based on the collected meteorological and road surface dryness data to adapt to the microclimate characteristics of different target areas.

[0031] It should be noted that the function representing the change in real-time rainfall intensity in the target area over time... The function of real-time humidity change over time in the target area and the real-time temperature change function of the target area over time The method of obtaining it is based on existing technology and will not be described in detail here.

[0032] As one embodiment of the present invention, numbered as The method for obtaining the garbage collection complexity of the cleaning unit includes the following steps: S10: The analysis module will process the code numbered... The waste in the pre-operation image information data of the cleaning unit is divided into two categories: other waste and green waste; S20: Identify other debris in the pre-operation image information data of the cleaning unit; when other debris exists, determine the location of each piece of debris, and obtain the minimum coverage circle that covers all other debris locations based on the location of each piece of debris; when no other debris exists, set the pixel area of ​​the minimum coverage circle that covers all other debris locations to 0. It should be noted that the location of other waste refers to the centroid position of the corresponding other waste instance region output by the image recognition model. The analysis module calculates the minimum coverage circle that can cover all the centroid coordinates of all other waste instance regions. S30: The analysis module identifies all green waste from the pre-operation image information data of the cleaning unit and obtains the pixel area of ​​each piece of green waste; when the pixel area of ​​green waste is greater than or equal to the preset pixel area threshold, it is identified as large green waste, and when the pixel area of ​​green waste is less than the preset pixel area threshold, it is identified as small green waste. S40: The garbage cleaning complexity of this cleaning unit is obtained by analyzing the minimum coverage circle that covers all other garbage locations, as well as the number and pixel area of ​​large green garbage. Through the above technical solution, this embodiment uses the analysis module to analyze the numbered... The waste in the pre-operation image information data of the cleaning unit is divided into two categories: other waste and green waste. Then, other waste is identified in the pre-operation image information data of the cleaning unit. When other waste is present, the location of each piece of other waste is determined, and the minimum coverage circle covering all other waste locations is obtained based on the location of each piece of other waste. When no other waste is present, the pixel area of ​​the minimum coverage circle covering all other waste locations is set to 0. Next, the analysis module identifies all green waste from the pre-operation image information data of the cleaning unit and obtains the pixel area of ​​each piece of green waste. When the pixel area of ​​green waste is greater than... If the pixel area of ​​the green waste is equal to or equal to a preset pixel area threshold, it is identified as large green waste; if the pixel area of ​​the green waste is less than the preset pixel area threshold, it is identified as small green waste. Finally, the waste cleaning complexity of the cleaning unit is obtained by analyzing the minimum coverage circle covering all other waste locations, as well as the number and pixel area of ​​large green waste. Large green waste includes branches, trunks, and large plant remains, which are large in area, irregular in shape, require cutting, and pose a greater risk during transportation, making cleaning more complex. Small green waste includes leaves, grass clippings, and twigs, which are small in area and easy to clean. It should be noted that the minimum coverage circle of other waste reflects the spatial dispersion of other waste within the cleaning unit, which affects the frequency with which workers need to sort and avoid waste when cleaning green waste; while the quantity and average pixel area of ​​large green waste reflect the workload of cleaning large-volume green waste that needs to be cut and manually transported. Both factors affect the complexity of waste cleaning from the dimensions of 'operational complexity' and 'operational intensity', respectively, and there is no significant interaction between them. Therefore, a weighted summation method is used to calculate the overall complexity of waste cleaning.

[0033] It should be noted that in this embodiment, the preset pixel area threshold is set to 2500 pixels². This value is determined based on the pixel area occupied by a piece of green waste with an actual size of 0.5 meters × 0.5 meters in the image when the image acquisition module has a resolution of 1920×1080 pixels, an installation height of 3 meters, and a shooting tilt angle of 45°. When the installation parameters of the image acquisition module change, this threshold should be recalibrated accordingly.

[0034] It should be noted that the garbage image recognition model adopts a YOLOv5-based object detection network architecture. The training process of the model is as follows: First, collect no less than 5000 images of green areas containing various types of garbage, with a uniform image resolution of 640×640 pixels; Second, use the LabelImg image annotation tool to annotate garbage instances in each image, with annotation categories divided into three types: "twigs / trunks", "fallen leaves / grass clippings", and "other garbage"; Third, randomly divide the annotated dataset into training and validation sets at a ratio of 8:2; Fourth, set the initial learning rate to 0.001, the batch size to 16, and use the SGD optimizer for iterative training for 300 rounds; Fifth, stop training when the average accuracy of the model on the validation set reaches above 90%, and use the trained model as the garbage image recognition model of this system. The analysis module calculates the geometric center of the bounding box as the centroid of the garbage based on the bounding box information of each garbage instance output by the model, and calculates the number of pixels covered by the bounding box as the pixel area of ​​the garbage. The analysis module uses the Welzl algorithm to calculate the minimum covering circle. This algorithm determines the minimum circle covering all points in O(n) time complexity through random increment, where n is the number of centroid points.

[0035] As one embodiment of the present invention, the formula is as follows: ; The calculation number is The complexity of garbage collection in the cleaning unit ; in, The complexity of basic waste cleanup; The pixel area of ​​the smallest coverage circle that the cleaning unit can cover all other garbage locations; The total pixel area of ​​the image information data before the operation; The total quantity of large green waste in this cleaning unit; h is the serial number of the large green waste, h=1, 2, ..., H; For this cleaning unit The pixel area of ​​a large piece of green waste; To remove the unit coefficient; This is the first major complexity weighting coefficient; This is the second largest complexity weighting coefficient; This is the first garbage collection complexity weighting coefficient; This is the second garbage collection complexity weighting coefficient; This is the first preset constant; This is the second preset constant; It should be noted that, in the formula calculation, the average pixel area term for large-scale green waste is considered. Follow these rules for setting values: When H=0, set the overall value of this item to 0; when H>0, the value of this item is calculated normally according to the ratio of the sum of the pixel areas of H large green wastes to H. Through the above technical solution, this embodiment The ratio of the pixel area of ​​the minimum coverage circle of the cleaning unit covering all other waste locations to the total pixel area of ​​the image information data before the operation. The larger the size, the more dispersed the other waste is within the cleaning unit. When processing green waste, workers must separate the other waste from the green waste; therefore, the complexity of waste handling in this unit is high. The larger the quantity of large green waste, the more likely it is to be cut into pieces. Furthermore, large waste is prone to slipping, falling, or causing injuries during transport. Therefore, the total quantity of large green waste in this cleaning unit should be considered. The more garbage there is, the more complex the garbage collection process becomes in this unit. The larger; The average pixel area of ​​large green waste in this cleaning unit. The larger the value, the larger the volume of large-scale green waste, thus increasing the complexity of waste disposal in this unit. The larger; It should be noted that in this embodiment, the basic garbage collection complexity X0 is 1.0; the first preset constant Z1 is 30, and the second preset constant Z2 is 100; the de-unit coefficient ε is 1, and its dimension is the same as that of pixel area. The first garbage collection complexity weight coefficient σ1 is 0.5, and the second garbage collection complexity weight coefficient σ2 is 0.5; the first large complexity weight coefficient θ1 is 0.6, and the second large complexity weight coefficient θ2 is 0.4. The above weight coefficients are optimized through the analytic hierarchy process and combined with on-site measured data.

[0036] It should be noted that other waste includes all waste other than green waste.

[0037] As one embodiment of the present invention, the formula is as follows: ; The calculation number is The overall cleaning complexity of the cleaning unit ; Through the above technical solution, the complexity of garbage cleaning in this embodiment is reduced. The larger the size, the greater the overall complexity of the cleanup. The larger the volume, the more complex the actual road surface becomes in the cleaning unit. The larger the size, the greater the overall complexity of the cleanup. the greater.

[0038] As an embodiment of the present invention, through the formula: ; calculate the illumination brightness of the lighting module of the cleaning unit numbered ; wherein, is the unit complexity, which is set to 1.0 in this embodiment, and is used to dimensionlessize the complexity difference; is the basic illumination brightness; which is set to 50 lux in this embodiment, this value is the minimum illuminance standard that meets the basic safety requirements of night green waste treatment operations, and can be preset and adjusted according to the light conditions of the actual working environment; Through the above technical solution, this embodiment is the basic comprehensive cleaning complexity of the cleaning unit; is the difference between the comprehensive cleaning complexity of the cleaning unit numbered and the basic comprehensive cleaning complexity of the cleaning unit; in the formula , in the judgment function refers to , which is used to judge whether the comprehensive cleaning complexity of the cleaning unit numbered exceeds the basic comprehensive cleaning complexity; when , it indicates that the comprehensive cleaning complexity of the cleaning unit numbered exceeds the basic comprehensive cleaning complexity ; therefore, it is necessary to increase the brightness of the cleaning unit to facilitate the staff to see the road surface clearly, the difference between the comprehensive cleaning complexity of the cleaning unit numbered and the basic comprehensive cleaning complexity of the cleaning unit the larger, the illumination brightness of the lighting module of the cleaning unit numbered the greater; when , it indicates that the comprehensive cleaning complexity of the cleaning unit numbered does not exceed the basic comprehensive cleaning complexity, ; therefore, there is no need to increase the brightness of the cleaning unit, and the basic illumination brightness can be maintained; the illumination brightness of the lighting module of the cleaning unit is adjusted according to the comprehensive cleaning complexity of the cleaning unit; increasing the illumination brightness at the cleaning unit with higher comprehensive cleaning complexity is beneficial to reduce the visual blind area formed by insufficient illumination, improve the staff's ability to identify road surface garbage and potential obstacles, and is beneficial to improve operation safety.

[0039] ​​The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A following lighting system for nighttime green waste disposal, characterized in that, The lighting system includes: The partitioning module is used to divide the target area into several cleaning units and number each cleaning unit, wherein the number is denoted as . n ; The road surface information module is used to store road surface information data for each cleaning unit; Multiple image acquisition modules, one for each cleaning unit, are used to collect image information data of the corresponding cleaning unit before the operation. Multiple lighting modules, one for each cleaning unit, are used for illumination; The environmental information module is used to acquire environmental information data for the target area. The analysis module is used to analyze the road surface information data, environmental information data and pre-operation image information data of each corresponding cleaning unit to obtain the comprehensive cleaning complexity of each cleaning unit, and to obtain the lighting parameters of each cleaning unit based on the comprehensive cleaning complexity. The control module is used to control the corresponding lighting module to start working lighting according to the lighting parameters of the corresponding cleaning unit after detecting that the target object performing the green waste disposal operation has entered the corresponding cleaning unit, and to predict the movement trend of the target object in adjacent cleaning units and adjust the lighting modules of the adjacent cleaning units to the pre-set lighting parameters in advance. The control module is also used to reduce the lighting brightness of the current cleaning unit to the standby lighting brightness when it is detected that the target object leaves the current cleaning unit and enters the adjacent cleaning unit.

2. The following lighting system for nighttime green waste disposal according to claim 1, characterized in that, The process of obtaining the overall cleanup complexity is as follows: S1: The analysis module analyzes the environmental information data and the road surface information data of each cleaning unit to obtain the actual road surface complexity of each cleaning unit; S2: Collect image information data of each cleaning unit before operation through the image acquisition module of each cleaning unit at the preset acquisition time every day; S3: The analysis module analyzes the pre-operation image information data of each cleaning unit to obtain the garbage cleaning complexity of each cleaning unit; S4: The analysis module analyzes the actual road surface complexity and garbage cleaning complexity of each cleaning unit to obtain the comprehensive cleaning complexity of each cleaning unit.

3. The following lighting system for nighttime green waste disposal according to claim 2, characterized in that, Through the formula: ； The calculation number is The actual road surface complexity of the cleaning unit ; in, For the judgment function, when hour, ;when hour, ; This is the pavement complexity adjustment coefficient for the pavement material corresponding to this cleaning unit; Based on the complexity of the road surface; This represents the duration from the last time rainfall stopped to the current time. Preset drying time; The duration of a unit of time; The rainfall impact coefficient is the road surface material corresponding to this cleaning unit; This is the first preset constant.

4. A following lighting system for nighttime green waste disposal according to claim 3, characterized in that, Through the formula: ； Calculate the preset drying time ; in, The current time; To ensure effective statistical duration, its value is determined by the following rule: when... hour, ;when hour, ,in, The preset minimum positive duration, and ; The preset duration was previously known; The function represents the change in real-time rainfall intensity over time in the target area. This is the preset cumulative rainfall; The function represents the real-time humidity variation of the target area over time. Preset humidity; The real-time temperature change function of the target area over time; Preset temperature; This is the first weighting coefficient; This is the second weighting coefficient; This is the third weighting coefficient; This is the second preset constant; This is the third preset constant; This is the fourth preset constant; The baseline drying time is used to characterize the baseline time required for a road surface to go from a wet state to a dry state under preset baseline environmental conditions.

5. A following lighting system for nighttime green waste disposal according to claim 4, characterized in that, Number The method for obtaining the garbage collection complexity of the cleaning unit includes the following steps: S10: The analysis module will process the code numbered... The waste in the pre-operation image information data of the cleaning unit is divided into two categories: other waste and green waste; S20: Identify other debris in the pre-operation image information data of the cleaning unit; when other debris exists, determine the location of each piece of debris, and obtain the minimum coverage circle that covers all other debris locations based on the location of each piece of debris; when no other debris exists, set the pixel area of ​​the minimum coverage circle that covers all other debris locations to 0. S30: The analysis module identifies all green waste from the pre-operation image information data of the cleaning unit and obtains the pixel area of ​​each piece of green waste; when the pixel area of ​​green waste is greater than or equal to the preset pixel area threshold, it is identified as large green waste, and when the pixel area of ​​green waste is less than the preset pixel area threshold, it is identified as small green waste. S40: The garbage cleaning complexity of this cleaning unit is obtained by analyzing the minimum coverage circle that covers all other garbage locations, as well as the number and pixel area of ​​large green garbage.

6. A following lighting system for nighttime green waste disposal according to claim 5, characterized in that, Through the formula: ； The calculation number is The complexity of garbage collection in the cleaning unit ; in, The complexity of basic waste cleanup; The pixel area of ​​the smallest coverage circle that the cleaning unit can cover all other garbage locations; The total pixel area of ​​the image information data before the operation; Let h be the total number of large green waste items in this cleaning unit, and h be the serial number of the large green waste items, where h = 1, 2, ..., H; For this cleaning unit The pixel area of ​​a large piece of green waste; To remove the unit coefficient; This is the first major complexity weighting coefficient; This is the second largest complexity weighting coefficient; This is the first garbage collection complexity weighting coefficient; This is the second garbage collection complexity weighting coefficient; This is the first preset constant; This is the second preset constant.

7. A following lighting system for nighttime green waste disposal according to claim 6, characterized in that, Through the formula: ； The calculation number is The overall cleaning complexity of the cleaning unit .

8. A following lighting system for nighttime green waste disposal according to claim 7, characterized in that, Through the formula: ； The calculation number is The lighting brightness of the cleaning unit's lighting module ; in, The complexity is in units; Based on the brightness of the lighting.

Images