A street lamp intelligent control method and device based on intelligent lighting

Abstract

The present invention discloses a method and device for intelligent control of street lamps based on intelligent lighting, the method comprising: obtaining target location information of the target street lamp, determining historical flow data related to the target street lamp, wherein the historical flow data includes historical flow data of multiple time periods; training a pre-built neural network model based on the historical flow data to obtain a target neural network model; determining the predicted flow data of the current time period based on the target neural network model; and controlling the target street lamp according to the predicted flow data of the current time period. It can be seen that the implementation of the present invention can control the brightness of the street lamp according to the flow conditions of the road, realize intelligent control of the street lamp, and is conducive to ensuring road safety. At the same time, it can realize energy saving of the street lamp, effectively delay the life of the street lamp, reduce the electricity cost of the street lamp, and reduce labor costs.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a street lamp intelligent control method and device based on intelligent lighting. Background Art

[0002] In the existing street light system, the switch control is generally carried out according to time, that is, the power is turned on at night and the lights are turned off in the morning, or the lights are manually set to be turned off at a certain time period in the middle of the night, so as to achieve energy saving and emission reduction. However, the existing street light system cannot perform intelligent control of street lights according to actual needs. For example, it cannot perform intelligent control of street lights according to the real-time traffic flow or pedestrian flow of the road, and cannot effectively ensure the safety of the road, nor can it achieve the effect of energy saving and emission reduction. Therefore, how to achieve intelligent control of street lighting is a technical problem that needs to be solved in this field. Summary of the invention

[0003] The technical problem to be solved by the present invention is how to realize the intelligent control of street lamp lighting, and to provide a method and device for intelligent control of street lamps based on intelligent lighting, which can control the brightness of street lamps according to the traffic conditions of the road, realize intelligent control of street lamps, and is beneficial to ensure road safety. At the same time, it can realize energy saving of street lamps, effectively extend the life of street lamps, reduce electricity expenses of street lamps, and reduce labor costs.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a street lamp intelligent control method based on intelligent lighting, the method comprising:

[0005] Obtain target location information of the target street lamp;

[0006] Determine historical traffic data related to the target street lamp according to the target location information, wherein the historical traffic data includes historical traffic data of multiple time periods;

[0007] Training a pre-built neural network model based on the historical traffic data to obtain a target neural network model;

[0008] Determining predicted traffic data for the current period based on the target neural network model;

[0009] The target street light is controlled according to the predicted traffic data of the current time period.

[0010] As an optional implementation manner, in the first aspect of the present invention, determining the historical traffic data related to the target street lamp according to the target location information includes:

[0011] According to the target location information, acquiring video data matching the target location information;

[0012] Splitting the video data matching the target location information into a plurality of sub-video data based on a preset time segmentation condition;

[0013] For each of the sub-video data, identifying a passing object in the sub-video data, wherein the passing object includes a vehicle and / or a pedestrian;

[0014] Annotating the identified passing object in the sub-video data to obtain passing object annotation data corresponding to the sub-video data, wherein the passing object annotation data includes vehicle annotation data and / or pedestrian annotation data;

[0015] Determine the traffic flow data corresponding to the sub-video data based on the traffic object labeling data corresponding to the sub-video data, wherein the traffic flow data includes vehicle flow data and / or pedestrian flow data;

[0016] A traffic data set is generated according to the traffic flow data corresponding to the plurality of sub-video data, and the traffic data set is determined as historical traffic data related to the target street lamp.

[0017] As an optional implementation manner, in the first aspect of the present invention, generating a traffic data set according to the traffic flow data corresponding to the plurality of sub-video data includes:

[0018] For each of the traffic flow data corresponding to the sub-video data, acquiring scenario information matching the traffic flow data corresponding to the sub-video data, wherein the scenario information includes one or more of time period information, working day information, and weather information;

[0019] The traffic flow data corresponding to each of the sub-video data and the scenario information matching the traffic flow data corresponding to each of the sub-video data are stored to generate a traffic data set.

[0020] As an optional implementation, in the first aspect of the present invention, after determining the historical traffic data related to the target street lamp according to the target location information, and before training the pre-built neural network model based on the historical traffic data to obtain the target neural network model, the method further includes:

[0021] Extracting characteristic data from the historical traffic data, wherein the characteristic data includes one or more of time period information, working day information, weather information, and traffic flow data;

[0022] Generate a feature matrix corresponding to the historical traffic data according to the feature data extracted from the historical traffic data;

[0023] The pre-built neural network model is trained based on the historical traffic data to obtain a target neural network model, including:

[0024] A pre-built neural network model is trained based on the feature matrix corresponding to the historical traffic data to obtain a target neural network model.

[0025] As an optional implementation manner, in the first aspect of the present invention, controlling the target street lamp according to the predicted traffic data of the current time period includes:

[0026] Determine whether the predicted flow data for the current period is greater than or equal to a first preset threshold;

[0027] If the predicted traffic data of the current time period is greater than or equal to a first preset threshold, controlling the brightness of the target street lamp to be at a normal brightness within the current time period;

[0028] If the predicted traffic data of the current time period is less than a first preset threshold, controlling the brightness of the target street lamp to be at the lowest brightness within the current time period;

[0029] After controlling the target street lamp to be at the lowest brightness within the current time period, the method further includes:

[0030] Acquire real-time video data matching the target location information of the target street lamp;

[0031] Identifying real-time passing objects in the real-time video data;

[0032] Determine whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold;

[0033] When the distance between the real-time passing object and the target streetlight is less than or equal to a second preset threshold, the brightness of the target streetlight is controlled to be adjusted from the minimum brightness to the normal brightness.

[0034] As an optional implementation, in the first aspect of the present invention, the real-time passing objects include real-time passing vehicles and real-time passing pedestrians;

[0035] After determining whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold, the method further includes:

[0036] When the distance between the real-time passing vehicle and the target street lamp is greater than a second preset threshold, obtaining the headlight illumination area of ​​the real-time passing vehicle;

[0037] Determining whether the real-time passing pedestrian is in the lighting area of ​​the headlights of the real-time passing vehicle;

[0038] When it is determined that the real-time pedestrian is not in the lighting area of ​​the headlights of the real-time passing vehicle, the lighting area of ​​the target streetlight is adjusted so that the real-time pedestrian is in the adjusted lighting area of ​​the target streetlight.

[0039] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0040] Determine whether the target street lamp is in an off state during the current time period;

[0041] If it is determined that the target street lamp is in the off state during the current time period, then obtaining in real time environmental data related to the target location information of the target street lamp, wherein the environmental data includes at least one of fog level, rainfall data, air index, and natural light illumination;

[0042] Determine whether the environmental data related to the target location information of the target street lamp obtained in real time meets the preset start-up conditions;

[0043] If the environmental data related to the target position information of the target street lamp obtained in real time meets the preset start-up conditions, the brightness of the target street lamp in the current time period is controlled to be normal brightness.

[0044] The second aspect of the present invention discloses a street lamp intelligent control device based on intelligent lighting, the device comprising:

[0045] An acquisition module, used to acquire target location information of a target street lamp;

[0046] A determination module, configured to determine historical traffic data related to the target street lamp according to the target location information, wherein the historical traffic data includes historical traffic data of multiple time periods;

[0047] A construction module, used for training a pre-constructed neural network model based on the historical traffic data to obtain a target neural network model;

[0048] A prediction module, used to determine the predicted traffic data for the current period based on the target neural network model;

[0049] A control module is used to control the target street light according to the predicted traffic data of the current time period.

[0050] As an optional implementation, in the second aspect of the present invention, the determining module includes:

[0051] An acquisition submodule, used for acquiring video data matching the target position information according to the target position information;

[0052] A segmentation submodule, configured to segment the video data matching the target location information into a plurality of sub-video data based on a preset time segmentation condition;

[0053] An identification submodule, configured to identify, for each of the sub-video data, passing objects in the sub-video data, wherein the passing objects include vehicles and / or pedestrians;

[0054] A labeling submodule, used to label the identified passing object in the sub-video data to obtain the passing object labeling data corresponding to the sub-video data, wherein the passing object labeling data includes vehicle labeling data and / or pedestrian labeling data;

[0055] A determination submodule, configured to determine traffic flow data corresponding to the sub-video data based on the traffic object labeling data corresponding to the sub-video data, wherein the traffic flow data includes vehicle flow data and / or pedestrian flow data;

[0056] A generating submodule is used to generate a traffic data set according to the traffic flow data corresponding to the plurality of sub-video data, and determine the traffic data set as historical traffic data related to the target street lamp.

[0057] As an optional implementation, in the second aspect of the present invention, the generation submodule generates a traffic data set according to the traffic data corresponding to the plurality of sub-video data, including:

[0058] For each of the traffic flow data corresponding to the sub-video data, acquiring scenario information matching the traffic flow data corresponding to the sub-video data, wherein the scenario information includes one or more of time period information, working day information, and weather information;

[0059] The traffic flow data corresponding to each of the sub-video data and the scenario information matching the traffic flow data corresponding to each of the sub-video data are stored to generate a traffic data set.

[0060] As an optional implementation, in the second aspect of the present invention, the device further includes: an extraction module;

[0061] The extraction module is used for extracting feature data from the historical traffic data after the determination module determines the historical traffic data related to the target street lamp according to the target location information, and before the construction module trains the pre-constructed neural network model based on the historical traffic data to obtain the target neural network model, wherein the feature data includes one or more of time period information, working day information, weather information, and traffic flow data; and generating a feature matrix corresponding to the historical traffic data according to the extracted feature data in the historical traffic data;

[0062] The construction module trains a pre-constructed neural network model based on the historical traffic data to obtain a target neural network model in the following manner:

[0063] A pre-built neural network model is trained based on the feature matrix corresponding to the historical traffic data to obtain a target neural network model.

[0064] As an optional implementation, in the second aspect of the present invention, the control module is used to control the target street lamp in accordance with the predicted traffic data of the current time period, including:

[0065] Determine whether the predicted flow data for the current period is greater than or equal to a first preset threshold;

[0066] If the predicted traffic data of the current time period is greater than or equal to a first preset threshold, controlling the brightness of the target street lamp to be at a normal brightness within the current time period;

[0067] If the predicted traffic data of the current time period is less than a first preset threshold, controlling the brightness of the target street lamp to be at the lowest brightness within the current time period;

[0068] After controlling the target street lamp to be at the lowest brightness within the current time period, acquiring real-time video data matching the target position information of the target street lamp;

[0069] Identifying real-time passing objects in the real-time video data;

[0070] Determine whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold;

[0071] When the distance between the real-time passing object and the target streetlight is less than or equal to a second preset threshold, the brightness of the target streetlight is controlled to be adjusted from the minimum brightness to the normal brightness.

[0072] As an optional implementation, in the second aspect of the present invention, the real-time passing objects include real-time passing vehicles and real-time passing pedestrians;

[0073] The control module is also used for:

[0074] After determining whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold, when determining that the distance between the real-time passing vehicle and the target street lamp is greater than the second preset threshold, obtaining the headlight illumination area of ​​the real-time passing vehicle;

[0075] Determining whether the real-time passing pedestrian is in the lighting area of ​​the headlights of the real-time passing vehicle;

[0076] When it is determined that the real-time pedestrian is not in the lighting area of ​​the headlights of the real-time passing vehicle, the lighting area of ​​the target streetlight is adjusted so that the real-time pedestrian is in the adjusted lighting area of ​​the target streetlight.

[0077] As an optional implementation, in the second aspect of the present invention, the control module is further used for:

[0078] Determine whether the target street lamp is in an off state during the current time period;

[0079] If it is determined that the target street lamp is in the off state during the current time period, then obtaining in real time environmental data related to the target location information of the target street lamp, wherein the environmental data includes at least one of fog level, rainfall data, air index, and natural light illumination;

[0080] Determine whether the environmental data related to the target location information of the target street lamp obtained in real time meets the preset start-up conditions;

[0081] If the environmental data related to the target position information of the target street lamp obtained in real time meets the preset start-up conditions, the brightness of the target street lamp in the current time period is controlled to be normal brightness.

[0082] The third aspect of the present invention discloses another intelligent control device for street lamps based on intelligent lighting, the device comprising:

[0083] A memory storing executable program code;

[0084] a processor coupled to the memory;

[0085] The processor calls the executable program code stored in the memory to execute the intelligent control method of street lamps based on intelligent lighting disclosed in the first aspect of the present invention.

[0086] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the intelligent control method of street lamps based on intelligent lighting disclosed in the first aspect of the present invention.

[0087] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0088] In the embodiment of the present invention, the target location information of the target street lamp is obtained to determine the historical traffic data related to the target street lamp, wherein the historical traffic data includes historical traffic data of multiple time periods; a pre-built neural network model is trained based on the historical traffic data to obtain a target neural network model; the predicted traffic data of the current time period is determined based on the target neural network model; and the target street lamp is controlled according to the predicted traffic data of the current time period. It can be seen that the implementation of the present invention can control the brightness of the street lamp according to the traffic conditions of the road, realize intelligent control of the street lamp, and is conducive to ensuring road safety. At the same time, it can realize energy saving of street lamps, effectively delay the life of street lamps, reduce street lamp electricity expenses, and reduce labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0090] Figure 1 It is a flowchart of a street lamp intelligent control method based on intelligent lighting disclosed in an embodiment of the present invention;

[0091] Figure 2 It is a flowchart of another intelligent control method of street lamps based on intelligent lighting disclosed in an embodiment of the present invention;

[0092] Figure 3 It is a structural schematic diagram of a street lamp intelligent control device based on intelligent lighting disclosed in an embodiment of the present invention;

[0093] Figure 4 is a schematic diagram of the structure of the determination module disclosed in the embodiment of the present invention;

[0094] Figure 5 It is another intelligent street lamp control device based on intelligent lighting disclosed in an embodiment of the present invention;

[0095] Figure 6 It is a structural schematic diagram of another intelligent control device for street lamps based on intelligent lighting disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0096] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0097] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0098] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0099] The present invention discloses a street lamp intelligent control method and device based on intelligent lighting, which can control the brightness of street lamps according to the traffic conditions of the road, realize intelligent control of street lamps, and help ensure road safety. At the same time, it can achieve energy saving of street lamps, effectively extend the life of street lamps, reduce street lamp electricity expenses, and reduce labor costs. The following are detailed descriptions.

[0100] Embodiment 1

[0101] See also Figure 1 , Figure 1 : is a flow chart of a street lamp intelligent control method based on intelligent lighting disclosed in an embodiment of the present invention. Figure 1 The described intelligent control method for street lamps based on intelligent lighting can be applied to a street lamp system including an intelligent control system for LED street lamps. The exemplary LED street lamp control system integrates intelligent devices such as LED street lamps, street lamp intelligent controllers, road surface video monitoring, air quality monitoring, temperature sensors, rainfall sensors, and communication networks. It can also be applied to other street lamp systems, which is not limited in the embodiments of the present invention. Figure 1 As shown, the intelligent street lamp control method based on intelligent lighting may include the following operations:

[0102] S101. Obtain target location information of a target street lamp.

[0103] In an embodiment of the present invention, the target street light can be a street light system including an LED street light intelligent control system (hereinafter referred to as the LED street light system). The unique ID number of the LED street light system is obtained, and the position of the LED street light system is determined based on the unique ID number, thereby obtaining the target position information of the LED street light system.

[0104] S102. Determine historical traffic data related to the target street lamp according to the target location information, wherein the historical traffic data includes historical traffic data of multiple time periods.

[0105] In the embodiment of the present invention, historical traffic data refers to the number of vehicles or pedestrians that have passed or arrived at a certain section of road or a certain location near the target street lamp in one or more past periods of time. In the embodiment of the present invention, historical traffic data related to the target street lamp can be obtained by video image processing. For example, the lighting time of the street lamp is divided into hours, and the video data collected by the road surface video monitoring set up in the LED street lamp system is processed to extract the vehicle flow data and pedestrian flow data in each divided time period, and then annotate according to the scenario information to form historical traffic data information. The scenario information may include the time period, whether it is a working day, the weather conditions, etc.

[0106] S103: Train a pre-built neural network model based on historical traffic data to obtain a target neural network model.

[0107] In an embodiment of the present invention, a preset neural network model is constructed, and relevant training work is performed so that the trainer can achieve a preset prediction effect. Exemplarily, the pre-constructed neural network model can be a deep neural network model. Before training the deep neural network model, corresponding processing is required, namely, node compression processing of the deep neural network model and update processing of the loss function. The node compression processing method is to divide the nodes of all layers in the deep neural network model by 2 and round down; through node compression, the model training convergence can be achieved using less sample data, and the probability of overfitting during the training process can be reduced; then the loss function is updated in a regularized manner, that is, all layer nodes of the deep neural network model are regularized to form a regularization term, and the regularization term is added to the original loss function to form an updated loss function to obtain an updated deep neural network model.

[0108] It should be noted that when training a pre-built neural network model based on historical traffic data, the historical traffic data is divided into training historical traffic data and test historical traffic data, and then the training historical traffic data is used to input the updated deep neural network model for training processing. After the training is completed, the test historical traffic data is used to input the trained deep neural network model for testing to verify whether the test results are within an acceptable range. If so, the training is terminated. If not, the back propagation algorithm is used to update the parameters of each node of the trained deep neural network model, and retrain until the test results are within an acceptable range.

[0109] S104. Determine the predicted traffic data for the current period based on the target neural network model.

[0110] In an embodiment of the present invention, a trained deep neural network model is used to predict the flow data of the current time period. The current time period can be one time period or multiple time periods within a day. Exemplarily, whether the current day is a working day and the weather conditions of each time period to be predicted are obtained by real-time collection (for example, the weather condition information of the corresponding location is crawled on the weather forecast website by a crawler algorithm), and then the data to be predicted is constructed based on the collected data, and the data to be predicted is input into the converged deep neural network model, and the predicted flow data for each time period of the day is output.

[0111] S105. Control the target street lights according to the predicted traffic data of the current time period.

[0112] In the embodiment of the present invention, after the predicted traffic data of the current period is obtained, the target street lamps can be controlled according to the predicted traffic data of the current period, thereby realizing controlling the brightness of the street lamps according to the traffic conditions of the road.

[0113] It can be seen that the implementation Figure 1 The intelligent control method of street lamps based on intelligent lighting shown can control the brightness of street lamps according to the traffic conditions of the road, realize intelligent control of street lamps, which is conducive to ensuring road safety. At the same time, it can achieve energy saving of street lamps, effectively extend the life of street lamps, reduce electricity expenses of street lamps, and reduce labor costs.

[0114] In the embodiment of the present invention, optionally, step S102 determines historical traffic data related to the target street lamp according to the target location information, including:

[0115] According to the target position information, video data matching the target position information is acquired;

[0116] Splitting the video data matching the target location information into a plurality of sub-video data based on a preset time segmentation condition;

[0117] For each sub-video data, identifying a passing object in the sub-video data, wherein the passing object includes a vehicle and / or a pedestrian;

[0118] Annotating the identified passing objects in the sub-video data to obtain passing object annotation data corresponding to the sub-video data, wherein the passing object annotation data includes vehicle annotation data and / or pedestrian annotation data;

[0119] Determine the traffic flow data corresponding to the sub-video data based on the traffic object labeling data corresponding to the sub-video data, wherein the traffic flow data includes vehicle flow data and / or pedestrian flow data;

[0120] A traffic data set is generated according to the traffic flow data corresponding to the plurality of sub-video data, and the traffic data set is determined as historical traffic data related to the target street lamp.

[0121] In an optional embodiment of the present invention, a road video surveillance device that matches the target position information of the LED street light system is determined, and video data collected by the road video surveillance device is obtained. When processing the video data collected by the road video surveillance that matches the LED street light system, the video data needs to be segmented according to a preset time period, and then the video data in each time period is framed to obtain the video frame data in each time period. Foreground and background separation processing is performed on each video frame data in each time period, and the separated foreground image is identified as a passing object, and the identified passing objects are marked, specifically vehicles or pedestrians are used for target marking. After the marking is completed, counting processing is performed to obtain the vehicle flow data and pedestrian flow data in each segmented time period, and then the historical flow data related to the target street light is obtained.

[0122] In an optional embodiment of the present invention, further optionally, generating a traffic data set according to the traffic flow data corresponding to the plurality of sub-video data includes:

[0123] For each traffic flow data corresponding to the sub-video data, acquiring scenario information matching the traffic flow data corresponding to the sub-video data, wherein the scenario information includes one or more of time period information, working day information, and weather information;

[0124] The traffic flow data corresponding to each sub-video data and the scenario information matching the traffic flow data corresponding to each sub-video data are stored to generate a traffic data set.

[0125] In an optional embodiment of the present invention, a traffic data set can be formed by extracting the vehicle flow data and pedestrian flow data in each divided time period, and then labeling the vehicle flow data and pedestrian flow data in each divided time period according to scenario information such as the time period, whether it is a weekday, and the weather conditions.

[0126] It can be seen that the implementation of this optional embodiment can identify the vehicle and / or pedestrian images contained in the video data, and then realize the process of vehicle and / or pedestrian identification and labeling, effectively avoiding the technical problem of inaccurate vehicle and / or pedestrian identification in the prior art, and can automatically complete the collection of historical traffic data, thereby improving the accuracy and efficiency of historical traffic data collection.

[0127] In the embodiment of the present invention, optionally, step S105, controlling the target street light according to the predicted traffic data of the current time period, includes:

[0128] Determine whether the predicted traffic data for the current period is greater than or equal to a first preset threshold;

[0129] If the predicted traffic data for the current period is greater than or equal to the first preset threshold, the brightness of the target street lamp is controlled to be at a normal brightness during the current period;

[0130] If the predicted traffic data for the current period is less than the first preset threshold, the brightness of the target street lamp is controlled to be at the lowest brightness within the current period;

[0131] After controlling the target street lamp to be at the lowest brightness in the current period, the method further includes: acquiring real-time video data matching the target position information of the target street lamp;

[0132] Identify real-time passing objects in real-time video data;

[0133] Determine whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold;

[0134] When the distance between the real-time passing object and the target street lamp is less than or equal to the second preset threshold, the brightness of the target street lamp is controlled to be adjusted from the minimum brightness to the normal brightness.

[0135] In an optional embodiment of the present invention, if the predicted flow data in a certain time period is within a preset range, the brightness of the street lamp in the time period is controlled to be normal brightness, but if the predicted flow data is less than a certain value range, the brightness value of the street lamp is controlled to be the lowest brightness. At the same time, monitoring video data can also be collected according to real-time road video monitoring, and moving target recognition can be performed on the monitoring video data. When a target is identified approaching the street lamp, the lighting brightness of the LED street lamp is controlled to increase to a normal range, and after the target disappears in the monitoring video data for a preset time, the lighting brightness of the LED street lamp is controlled to be adjusted to the lowest.

[0136] It can be seen that the implementation of this optional embodiment can control the brightness of the street lamp according to the traffic conditions of the road, thereby achieving energy saving of the street lamp.

[0137] In an optional embodiment of the present invention, further optionally, the real-time passing object includes a real-time passing vehicle and a real-time passing pedestrian. After determining whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold, the method further includes:

[0138] When the distance between the real-time passing vehicle and the target street lamp is greater than a second preset threshold, obtaining the headlight illumination area of ​​the real-time passing vehicle;

[0139] Determine whether the real-time pedestrian is in the lighting area of ​​the real-time vehicle;

[0140] When it is determined that the real-time pedestrian is not in the lighting area of ​​the headlights of the real-time passing vehicle, the lighting area of ​​the target street lamp is adjusted so that the real-time pedestrian is in the adjusted lighting area of ​​the target street lamp.

[0141] In an optional embodiment of the present invention, if the monitoring video data identifies that the vehicle and / or pedestrian is far away from the LED street lamp, the LED street lamp is at the lowest brightness. At this time, in order to ensure road traffic safety, it is necessary to obtain whether the vehicle headlight lighting area can cover the pedestrian currently passing. If the vehicle headlight lighting area cannot cover the pedestrian currently passing, the lighting area of ​​the LED street lamp is adjusted so that the pedestrian passing is in the adjusted lighting area of ​​the target street lamp, so that the vehicle driver can see the pedestrian passing, thereby ensuring traffic safety.

[0142] It can be seen that implementing this optional embodiment can effectively avoid traffic accidents caused by vehicles not being able to see pedestrians, and can also achieve energy conservation and emission reduction.

[0143] Embodiment 2

[0144] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of another method for intelligently controlling street lamps based on intelligent lighting disclosed in an embodiment of the present invention. Figure 2 As shown, the intelligent street lamp control method based on intelligent lighting may include the following operations:

[0145] S201. Obtain target location information of a target street lamp.

[0146] S202. Determine historical traffic data related to the target street lamp according to the target location information, wherein the historical traffic data includes historical traffic data of multiple time periods.

[0147] In the embodiment of the present invention, for other detailed descriptions of step S201 - step S202, please refer to the detailed description of step S101 - step S102 in the first embodiment, and the embodiment of the present invention will not be repeated here.

[0148] S203: extracting characteristic data from the historical traffic data, where the characteristic data includes one or more of time period information, weekday information, weather information, and traffic flow data.

[0149] S204: Generate a feature matrix corresponding to the historical traffic data according to the feature data extracted from the historical traffic data.

[0150] In the embodiment of the present invention, the data in the historical flow data is feature extracted according to the time period, flow data, whether it is a working day, and weather conditions (including temperature data, whether it is a windy and rainy day and other weather information), forming a feature matrix information with one row and multiple columns. When extracting the features, the time period, flow data, whether it is a working day, weather conditions and LED brightness conditions are converted into digital representations. Whether it is a working day, 0 indicates not a working day, and 1 indicates a working day; in the weather conditions, 0 indicates a windy and rainy day, and 1 indicates a non-windy and rainy day. For example, 25 degrees Celsius in the temperature data is directly represented by 25; the time period, such as 6-7 o'clock, is represented by 6, 7-8 o'clock is represented by 7, and so on; the flow data is represented by a specific flow; after feature extraction, it is converted into a digital matrix with one row and multiple columns, that is, the feature matrix information corresponding to the historical flow data is obtained.

[0151] S205. Train a pre-built neural network model based on a feature matrix corresponding to historical traffic data to obtain a target neural network model.

[0152] In an embodiment of the present invention, feature matrix information is divided into training feature matrix information and test feature matrix information, and then the training feature matrix information is used to input the updated deep neural network model for training processing. After the training is completed, the test feature matrix information is used to input the trained deep neural network model for testing to verify whether the test result is within an acceptable range. If so, the training is terminated. If not, the back propagation algorithm is used to update the parameters of each node of the trained deep neural network model, and retrain until the test result is within an acceptable range.

[0153] S206. Determine the predicted traffic data for the current period based on the target neural network model.

[0154] S207: Control the target street lights according to the predicted traffic data of the current time period.

[0155] In the embodiment of the present invention, for other detailed descriptions of step S206-step S207, please refer to the detailed description of step S104-step S105 in the first embodiment, and the embodiment of the present invention will not be repeated here.

[0156] S208, determining whether the target street lamp is in the off state during the current period; if it is determined that the target street lamp is in the off state during the current period, executing step S209;

[0157] S209, acquiring in real time environmental data related to the target location information of the target street lamp, wherein the environmental data includes at least one of fog level, rainfall data, air index, and natural light illumination;

[0158] S210, determining whether the environmental data meets the preset start-up condition; if the environmental data related to the target location information of the target street lamp obtained in real time meets the preset start-up condition, executing step S211;

[0159] S211. Control the brightness of the target street lamp to be normal brightness during the current time period.

[0160] In an embodiment of the present invention, during the time period when the street lights are not normally turned on, the conditions are collected in real time by the air quality monitoring sensors and rainfall monitoring sensors arranged on the street light system. When the air quality monitoring sensor detects that the fog situation reaches a certain threshold, or the rainfall data collected by the rainfall monitoring sensor reaches a certain threshold, it is also necessary to control the LED street light system to work, that is, to control the LED street lights to perform lighting work, and the brightness is normal lighting brightness, so as to ensure road traffic safety.

[0161] It can be seen that the implementation Figure 1 The intelligent control method of street lamps based on intelligent lighting shown can perform corresponding intelligent control on street lamps while ensuring road safety as much as possible. It can control the brightness of street lamps according to the traffic conditions of the road, and control street lamps according to the corresponding weather conditions, so as to ensure road safety, realize energy saving of street lamps, effectively extend the life of street lamps, reduce electricity expenses of street lamps, and reduce labor costs.

[0162] Embodiment 3

[0163] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a street lamp intelligent control device based on intelligent lighting disclosed in an embodiment of the present invention, such as Figure 3 As shown, the intelligent street lamp control device based on intelligent lighting includes: an acquisition module 301, a determination module 302, a construction module 303, a prediction module 304 and a control module 305.

[0164] in:

[0165] The acquisition module 301 is used to acquire the target position information of the target street lamp.

[0166] In an embodiment of the present invention, the target street light can be a street light system including an LED street light intelligent control system (hereinafter referred to as the LED street light system). The unique ID number of the LED street light system is obtained, and the position of the LED street light system is determined based on the unique ID number, thereby obtaining the target position information of the LED street light system.

[0167] The determination module 302 is used to determine the historical traffic data related to the target street lamp according to the target location information, wherein the historical traffic data includes historical traffic data of multiple time periods.

[0168] In the embodiment of the present invention, historical traffic data refers to the number of vehicles or pedestrians that have passed or arrived at a certain section of road or a certain location near the target street lamp in one or more past periods of time. In the embodiment of the present invention, historical traffic data related to the target street lamp can be obtained by video image processing. For example, the lighting time of the street lamp is divided into hours, and the video data collected by the road surface video monitoring set up in the LED street lamp system is processed to extract the vehicle flow data and pedestrian flow data in each divided time period, and then annotate according to the scenario information to form historical traffic data information. The scenario information may include the time period, whether it is a working day, the weather conditions, etc.

[0169] The construction module 303 is used to train the pre-constructed neural network model based on the historical traffic data to obtain the target neural network model.

[0170] In an embodiment of the present invention, a preset neural network model is constructed, and relevant training work is performed so that the trainer can achieve a preset prediction effect. Exemplarily, the pre-constructed neural network model can be a deep neural network model. Before training the deep neural network model, corresponding processing is required, namely, node compression processing of the deep neural network model and update processing of the loss function. The node compression processing method is to divide the nodes of all layers in the deep neural network model by 2 and round down; through node compression, the model training convergence can be achieved using less sample data, and the probability of overfitting during the training process can be reduced; then the loss function is updated in a regularized manner, that is, all layer nodes of the deep neural network model are regularized to form a regularization term, and the regularization term is added to the original loss function to form an updated loss function to obtain an updated deep neural network model.

[0171] It should be noted that when training a pre-built neural network model based on historical traffic data, the historical traffic data is divided into training historical traffic data and test historical traffic data, and then the training historical traffic data is used to input the updated deep neural network model for training processing. After the training is completed, the test historical traffic data is used to input the trained deep neural network model for testing to verify whether the test results are within an acceptable range. If so, the training is terminated. If not, the back propagation algorithm is used to update the parameters of each node of the trained deep neural network model, and retrain until the test results are within an acceptable range.

[0172] The prediction module 304 is used to determine the predicted traffic data for the current period based on the target neural network model.

[0173] In an embodiment of the present invention, a trained deep neural network model is used to predict the flow data of the current time period. The current time period can be one time period or multiple time periods within a day. Exemplarily, whether the current day is a working day and the weather conditions of each time period to be predicted are obtained by real-time collection (for example, the weather condition information of the corresponding location is crawled on the weather forecast website by a crawler algorithm), and then the data to be predicted is constructed based on the collected data, and the data to be predicted is input into the converged deep neural network model, and the predicted flow data for each time period of the day is output.

[0174] The control module 305 is used to control the target street light according to the predicted traffic data of the current time period.

[0175] In the embodiment of the present invention, after the predicted traffic data of the current period is obtained, the target street lamps can be controlled according to the predicted traffic data of the current period, thereby realizing controlling the brightness of the street lamps according to the traffic conditions of the road.

[0176] It can be seen that the implementation Figure 3 The street lamp intelligent control device based on intelligent lighting shown can control the brightness of the street lamp according to the traffic conditions of the road, realize intelligent control of the street lamp, which is conducive to ensuring road safety. At the same time, it can achieve energy saving of street lamps, effectively extend the life of street lamps, reduce electricity expenses of street lamps, and reduce labor costs.

[0177] In the embodiment of the present invention, optionally, please refer to Figure 4 , Figure 4 is a schematic diagram of the structure of the determination module disclosed in the embodiment of the present invention, such as Figure 4 As shown, the determination module 302 includes:

[0178] The acquisition submodule 3021 is used to acquire video data matching the target position information according to the target position information;

[0179] A segmentation submodule 3022, configured to segment the video data matching the target location information into a plurality of sub-video data based on a preset time segmentation condition;

[0180] The identification submodule 3023 is used to identify, for each sub-video data, a passing object in the sub-video data, wherein the passing object includes a vehicle and / or a pedestrian;

[0181] The labeling submodule 3024 is used to label the identified passing objects in the sub-video data to obtain the passing object labeling data corresponding to the sub-video data, wherein the passing object labeling data includes vehicle labeling data and / or pedestrian labeling data;

[0182] A determination submodule 3025 is used to determine the traffic flow data corresponding to the sub-video data based on the traffic object labeling data corresponding to the sub-video data, wherein the traffic flow data includes vehicle flow data and / or pedestrian flow data;

[0183] The generating submodule 3026 is used to generate a traffic data set according to the traffic flow data corresponding to the plurality of sub-video data, and determine the traffic data set as the historical traffic data related to the target street lamp.

[0184] In an optional embodiment of the present invention, a road video surveillance device that matches the target position information of the LED street light system is determined, and video data collected by the road video surveillance device is obtained. When processing the video data collected by the road video surveillance that matches the LED street light system, the video data needs to be segmented according to a preset time period, and then the video data in each time period is framed to obtain the video frame data in each time period. Foreground and background separation processing is performed on each video frame data in each time period, and the separated foreground image is identified as a passing object, and the identified passing objects are marked, specifically vehicles or pedestrians are used for target marking. After the marking is completed, counting processing is performed to obtain the vehicle flow data and pedestrian flow data in each segmented time period, and then the historical flow data related to the target street light is obtained.

[0185] In an optional embodiment of the present invention, further optionally, the generation submodule 3026 generates a traffic data set according to the traffic flow data corresponding to the plurality of sub-video data, in a manner including:

[0186] For each traffic flow data corresponding to the sub-video data, acquiring scenario information matching the traffic flow data corresponding to the sub-video data, wherein the scenario information includes one or more of time period information, working day information, and weather information;

[0187] The traffic flow data corresponding to each sub-video data and the scenario information matching the traffic flow data corresponding to each sub-video data are stored to generate a traffic data set.

[0188] In an optional embodiment of the present invention, a traffic data set can be formed by extracting the vehicle flow data and pedestrian flow data in each divided time period, and then labeling the vehicle flow data and pedestrian flow data in each divided time period according to scenario information such as the time period, whether it is a weekday, and the weather conditions.

[0189] It can be seen that the implementation of this optional embodiment can identify the vehicle and / or pedestrian images contained in the video data, and then realize the process of vehicle and / or pedestrian identification and labeling, effectively avoiding the technical problem of inaccurate vehicle and / or pedestrian identification in the prior art, and can automatically complete the collection of historical traffic data, thereby improving the accuracy and efficiency of historical traffic data collection.

[0190] In the optional embodiment of the present invention, optionally, please refer to Figure 5 , Figure 5 is a schematic diagram of the structure of another intelligent control device for street lamps based on intelligent lighting disclosed in an embodiment of the present invention, such as Figure 5 As shown, the intelligent lighting-based street lamp intelligent control device further includes: an extraction module 306;

[0191] The extraction module 306 is used to extract feature data from the historical traffic data after the determination module 302 determines the historical traffic data related to the target street lamp based on the target location information, and before the construction module 303 trains a pre-constructed neural network model based on the historical traffic data to obtain the target neural network model, the feature data includes one or more of time period information, weekday information, weather information, and traffic flow data; and generates a feature matrix corresponding to the historical traffic data based on the feature data extracted from the historical traffic data.

[0192] In an optional embodiment of the present invention, the data in the historical flow data is feature extracted according to the time period, flow data, whether it is a working day, and weather conditions (including temperature data, whether it is a windy and rainy day and other weather information) to form a feature matrix information with one row and multiple columns. When extracting the features, the time period, flow data, whether it is a working day, weather conditions and LED brightness conditions are converted into digital representations. Whether it is a working day, 0 represents a non-working day, and 1 represents a working day; in the weather conditions, 0 represents a windy and rainy day, and 1 represents a non-windy and rainy day. In the temperature data, for example, 25 degrees Celsius is directly represented by 25; the time period, such as 6-7 o'clock, is represented by 6, 7-8 o'clock is represented by 7, and so on; the flow data is represented by a specific flow; after feature extraction, it is converted into a digital matrix with one row and multiple columns, that is, the feature matrix information corresponding to the historical flow data is obtained.

[0193] In an optional embodiment of the present invention, further optionally, the construction module 303 trains a pre-constructed neural network model based on historical traffic data to obtain a target neural network model, including: training a pre-constructed neural network model based on a feature matrix corresponding to the historical traffic data to obtain a target neural network model.

[0194] In an optional embodiment of the present invention, the feature matrix information is divided into training feature matrix information and test feature matrix information, and then the training feature matrix information is used to input the updated deep neural network model for training processing. After the training is completed, the test feature matrix information is used to input the trained deep neural network model for testing to verify whether the test result is within an acceptable range. If so, the training is terminated. If not, the back propagation algorithm is used to update the parameters of each node of the trained deep neural network model, and retrain until the test result is within an acceptable range.

[0195] In the embodiment of the present invention, optionally, the control module 305 is used to control the target street lamp according to the predicted traffic data of the current period, including:

[0196] Determine whether the predicted traffic data for the current period is greater than or equal to a first preset threshold;

[0197] If the predicted traffic data for the current period is greater than or equal to the first preset threshold, the brightness of the target street lamp is controlled to be at a normal brightness during the current period;

[0198] If the predicted traffic data for the current period is less than the first preset threshold, the brightness of the target street lamp is controlled to be at the lowest brightness within the current period;

[0199] After controlling the target street lamp to be at the lowest brightness in the current period, the method further includes: acquiring real-time video data matching the target position information of the target street lamp;

[0200] Identify real-time passing objects in real-time video data;

[0201] Determine whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold;

[0202] When the distance between the real-time passing object and the target street lamp is less than or equal to the second preset threshold, the brightness of the target street lamp is controlled to be adjusted from the minimum brightness to the normal brightness.

[0203] In an optional embodiment of the present invention, if the predicted flow data in a certain time period is within a preset range, the brightness of the street lamp in the time period is controlled to be normal brightness, but if the predicted flow data is less than a certain value range, the brightness value of the street lamp is controlled to be the lowest brightness. At the same time, monitoring video data can also be collected according to real-time road video monitoring, and moving target recognition can be performed on the monitoring video data. When a target is identified approaching the street lamp, the lighting brightness of the LED street lamp is controlled to increase to a normal range, and after the target disappears in the monitoring video data for a preset time, the lighting brightness of the LED street lamp is controlled to be adjusted to the lowest.

[0204] It can be seen that the implementation of this optional embodiment can control the brightness of the street lamp according to the traffic conditions of the road, thereby achieving energy saving of the street lamp.

[0205] In an optional embodiment of the present invention, further optionally, the real-time passing objects include real-time passing vehicles and real-time passing pedestrians; the control module 305 is further used to:

[0206] After determining whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold, when determining that the distance between the real-time passing vehicle and the target street lamp is greater than the second preset threshold, obtaining the headlight illumination area of ​​the real-time passing vehicle;

[0207] Determine whether the real-time pedestrian is in the lighting area of ​​the real-time vehicle;

[0208] When it is determined that the real-time pedestrian is not in the lighting area of ​​the headlights of the real-time passing vehicle, the lighting area of ​​the target street lamp is adjusted so that the real-time pedestrian is in the adjusted lighting area of ​​the target street lamp.

[0209] In an optional embodiment of the present invention, if the monitoring video data identifies that the vehicle and / or pedestrian is far away from the LED street lamp, the LED street lamp is at the lowest brightness. At this time, in order to ensure road traffic safety, it is necessary to obtain whether the vehicle headlight lighting area can cover the pedestrian currently passing. If the vehicle headlight lighting area cannot cover the pedestrian currently passing, the lighting area of ​​the LED street lamp is adjusted so that the pedestrian passing is in the adjusted lighting area of ​​the target street lamp, so that the vehicle driver can see the pedestrian passing, thereby ensuring traffic safety.

[0210] It can be seen that implementing this optional embodiment can effectively avoid traffic accidents caused by vehicles not being able to see pedestrians, and can also achieve energy conservation and emission reduction.

[0211] In the embodiment of the present invention, optionally, the control module 305 is further configured to:

[0212] Determine whether the target street light is in the off state during the current period;

[0213] If it is determined that the target street lamp is in an off state during the current period, environmental data related to the target location information of the target street lamp is obtained in real time, wherein the environmental data includes at least one of fog level, rainfall data, air index, and natural light illumination;

[0214] Determine whether the environmental data related to the target location information of the target street lamp obtained in real time meets the preset start-up conditions;

[0215] If the environmental data related to the target position information of the target street lamp obtained in real time meets the preset start-up conditions, the brightness of the target street lamp in the current time period is controlled to be normal brightness.

[0216] In an optional embodiment of the present invention, during the time period when the street lights are not normally turned on, the conditions are collected in real time by the air quality monitoring sensors and rainfall monitoring sensors arranged on the street light system. When the air quality monitoring sensor detects that the fog situation reaches a certain threshold, or the rainfall data collected by the rainfall monitoring sensor reaches a certain threshold, it is also necessary to control the LED street light system to work, that is, to control the LED street lights to perform lighting work, and the brightness is normal lighting brightness, so as to ensure road traffic safety.

[0217] It can be seen that the implementation of this optional embodiment can control the brightness of street lamps according to the traffic conditions of the road, and control the street lamps accordingly according to the corresponding weather conditions, thereby ensuring road safety and achieving energy saving of street lamps.

[0218] Embodiment 4

[0219] See also Figure 6 , Figure 6 FIG. 1 is a schematic diagram of the structure of another intelligent control device for street lamps based on intelligent lighting disclosed in an embodiment of the present invention. Figure 6 As shown, the intelligent street lamp control device based on intelligent lighting may include:

[0220] A memory 601 storing executable program codes;

[0221] a processor 602 coupled to the memory 601;

[0222] The processor 602 calls the executable program code stored in the memory 601 to execute the steps in the intelligent control method of street lamps based on intelligent lighting described in the first embodiment of the present invention or the second embodiment of the present invention.

[0223] Embodiment 5

[0224] An embodiment of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps in the intelligent control method of street lamps based on intelligent lighting described in Embodiment 1 or Embodiment 2 of the present invention.

[0225] Embodiment 6

[0226] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the intelligent control method of street lamps based on intelligent lighting described in Example 1 or Example 2.

[0227] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0228] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0229] Finally, it should be noted that the intelligent control method and device for street lamps based on intelligent lighting disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A street lamp intelligent control method based on intelligent lighting, characterized in that: The method comprises: Obtain target location information of the target street lamp; Determine historical traffic data related to the target street lamp according to the target location information, wherein the historical traffic data includes historical traffic data of multiple time periods; Training a pre-built neural network model based on the historical traffic data to obtain a target neural network model; Determining predicted traffic data for the current period based on the target neural network model; Controlling the target streetlight according to the predicted traffic data of the current time period; And, the method further comprises: Extracting characteristic data from the historical traffic data, wherein the characteristic data includes one or more of time period information, working day information, weather information, and traffic flow data; Generate a feature matrix corresponding to the historical traffic data according to the feature data extracted from the historical traffic data; The pre-built neural network model is trained based on the historical traffic data to obtain a target neural network model, including: Training a pre-built neural network model based on a feature matrix corresponding to the historical traffic data to obtain a target neural network model; And, controlling the target street lamp according to the predicted traffic data of the current time period includes: Determine whether the predicted flow data for the current period is greater than or equal to a first preset threshold; If the predicted traffic data of the current time period is greater than or equal to a first preset threshold, controlling the brightness of the target street lamp to be at a normal brightness within the current time period; If the predicted traffic data of the current time period is less than a first preset threshold, controlling the brightness of the target street lamp to be at the lowest brightness within the current time period; After controlling the target street lamp to be at the lowest brightness within the current time period, the method further includes: Acquire real-time video data matching the target location information of the target street lamp; Identifying real-time passing objects in the real-time video data; Determine whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold; When the distance between the real-time passing object and the target streetlight is less than or equal to a second preset threshold, controlling the brightness of the target streetlight to be adjusted from the minimum brightness to the normal brightness; And, the real-time passing objects include real-time passing vehicles and real-time passing pedestrians; After determining whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold, the method further includes: When the distance between the real-time passing vehicle and the target street lamp is greater than a second preset threshold, obtaining the headlight illumination area of ​​the real-time passing vehicle; Determining whether the real-time passing pedestrian is in the lighting area of ​​the headlights of the real-time passing vehicle; When it is determined that the real-time pedestrian is not in the lighting area of ​​the headlights of the real-time passing vehicle, the lighting area of ​​the target streetlight is adjusted so that the real-time pedestrian is in the adjusted lighting area of ​​the target streetlight.

2. The intelligent control method for street lamps based on intelligent lighting according to claim 1 is characterized in that: The determining, according to the target location information, historical traffic data related to the target street lamp includes: According to the target location information, acquiring video data matching the target location information; Splitting the video data matching the target location information into a plurality of sub-video data based on a preset time segmentation condition; For each of the sub-video data, identifying a passing object in the sub-video data, wherein the passing object includes a vehicle and / or a pedestrian; Annotating the identified passing object in the sub-video data to obtain passing object annotation data corresponding to the sub-video data, wherein the passing object annotation data includes vehicle annotation data and / or pedestrian annotation data; Determine the traffic flow data corresponding to the sub-video data based on the traffic object labeling data corresponding to the sub-video data, wherein the traffic flow data includes vehicle flow data and / or pedestrian flow data; A traffic data set is generated according to the traffic flow data corresponding to the plurality of sub-video data, and the traffic data set is determined as historical traffic data related to the target street lamp.

3. The intelligent control method for street lamps based on intelligent lighting according to claim 2 is characterized in that: The generating a traffic data set according to the traffic flow data corresponding to the plurality of sub-video data includes: For each of the traffic flow data corresponding to the sub-video data, acquiring scenario information matching the traffic flow data corresponding to the sub-video data, wherein the scenario information includes one or more of time period information, working day information, and weather information; The traffic flow data corresponding to each of the sub-video data and the scenario information matching the traffic flow data corresponding to each of the sub-video data are stored to generate a traffic data set.

4. The intelligent control method for street lamps based on intelligent lighting according to any one of claims 1 to 3, characterized in that: The method further comprises: Determine whether the target street lamp is in an off state during the current time period; If it is determined that the target street lamp is in the off state during the current time period, then obtaining in real time environmental data related to the target location information of the target street lamp, wherein the environmental data includes at least one of fog level, rainfall data, air index, and natural light illumination; Determine whether the environmental data related to the target location information of the target street lamp obtained in real time meets the preset start-up conditions; If the environmental data related to the target position information of the target street lamp obtained in real time meets the preset start-up conditions, the brightness of the target street lamp in the current time period is controlled to be normal brightness.

5. A street lamp intelligent control device based on intelligent lighting, characterized in that: The device comprises: An acquisition module, used to acquire target location information of a target street lamp; A determination module, configured to determine historical traffic data related to the target street lamp according to the target location information, wherein the historical traffic data includes historical traffic data of multiple time periods; A construction module, used for training a pre-constructed neural network model based on the historical traffic data to obtain a target neural network model; A prediction module, used to determine the predicted traffic data for the current period based on the target neural network model; A control module, used for controlling the target street lamp according to the predicted traffic data of the current time period; And, the device further comprises: an extraction module; The extraction module is used for extracting feature data from the historical traffic data after the determination module determines the historical traffic data related to the target street lamp according to the target location information, and before the construction module trains the pre-constructed neural network model based on the historical traffic data to obtain the target neural network model, wherein the feature data includes one or more of time period information, working day information, weather information, and traffic flow data; and generating a feature matrix corresponding to the historical traffic data according to the extracted feature data in the historical traffic data; The construction module trains a pre-constructed neural network model based on the historical traffic data to obtain a target neural network model in the following manner: Training a pre-built neural network model based on a feature matrix corresponding to the historical traffic data to obtain a target neural network model; And, the control module is used to control the target street lamp according to the predicted traffic data of the current period, including: Determine whether the predicted flow data for the current period is greater than or equal to a first preset threshold; If the predicted traffic data of the current time period is greater than or equal to a first preset threshold, controlling the brightness of the target street lamp to be at a normal brightness within the current time period; If the predicted traffic data of the current time period is less than a first preset threshold, controlling the brightness of the target street lamp to be at the lowest brightness within the current time period; After controlling the target street lamp to be at the lowest brightness within the current time period, acquiring real-time video data matching the target position information of the target street lamp; Identifying real-time passing objects in the real-time video data; Determine whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold; When the distance between the real-time passing object and the target streetlight is less than or equal to a second preset threshold, controlling the brightness of the target streetlight to be adjusted from the minimum brightness to the normal brightness; And, the real-time passing objects include real-time passing vehicles and real-time passing pedestrians; The control module is also used for: After determining whether the distance between the real-time passing object and the target street lamp is less than or equal to a second preset threshold, when determining that the distance between the real-time passing vehicle and the target street lamp is greater than the second preset threshold, obtaining the headlight illumination area of ​​the real-time passing vehicle; Determining whether the real-time passing pedestrian is in the lighting area of ​​the headlights of the real-time passing vehicle; When it is determined that the real-time pedestrian is not in the lighting area of ​​the headlights of the real-time passing vehicle, the lighting area of ​​the target streetlight is adjusted so that the real-time pedestrian is in the adjusted lighting area of ​​the target streetlight.

6. A street lamp intelligent control device based on intelligent lighting, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent control method for street lamps based on intelligent lighting as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are called, they are used to execute the intelligent control method for street lamps based on intelligent lighting as described in any one of claims 1-4.

Images