A smart city road lighting intelligent control method and system based on the Internet of Things

Abstract

The embodiment of the specification provides a smart city road lighting intelligent control method and system based on Internet of Things, the method is realized by a smart city road lighting intelligent control system based on Internet of Things, the Internet of Things system comprises a user platform, a service platform, a management platform, a sensing network platform and an object platform, the method is executed by the management platform, and comprises the following steps: receiving sensing information acquired by the object platform through the sensing network platform; judging whether a target exists on a road based on the sensing information; in response to the fact that the target does not exist on the road and that a time length during which the target does not exist satisfies a preset condition, determining the irradiation intensity of a street lamp on the road; wherein the preset condition is related to a predicted time of next occurrence of the target on the road, and the predicted time is determined based on a time prediction model, input of the time prediction model comprises a historical target occurrence sequence and a historical target speed sequence, and output of the time prediction model comprises the predicted time of next occurrence of the target.

Description

[0001] Divisional Statement

[0002] This application is a divisional application of the Chinese application with the application number 202211195298.7, the application date of September 29, 2022, and the invention name of "Intelligent control method and system for smart city street lamps based on Internet of Things". TECHNICAL FIELD

[0003] The present specification relates to the field of Internet of Things, in particular to an intelligent control method and system for smart city street lighting based on Internet of Things. BACKGROUND

[0004] Street lamps are distributed on roads of all sizes in the city to provide lighting when natural light is insufficient, facilitating the passage of pedestrians and vehicles, and are essential infrastructure for the city. However, current control of street lamps is mostly turned on at fixed periods, and the maximum brightness is maintained throughout the lighting period. However, in some periods or sections, the traffic and pedestrian flow is small, and it is not necessary to maintain a high lighting intensity at all times.

[0005] Therefore, it is necessary to provide an intelligent control method and system for smart city street lighting based on Internet of Things to realize intelligent control of street lamps. SUMMARY

[0006] One or more embodiments of the present specification provide an intelligent control method for smart city street lighting based on Internet of Things. The method is realized by an intelligent control system for smart city street lighting based on Internet of Things, which includes a user platform, a service platform, a management platform, a sensing network platform and an object platform. The method is executed by the management platform, which includes: receiving sensing information obtained by the object platform through the sensing network platform; determining whether there is a target on the road based on the sensing information; determining the irradiation intensity of the street lamp on the road in response to the absence of the target on the road and the duration of the absence of the target satisfying a preset condition; wherein the preset condition is related to the predicted time of the next occurrence of the target on the road, the predicted time is determined based on a time prediction model, the input of the time prediction model includes a historical target occurrence sequence and a historical target speed sequence, and the output of the time prediction model includes the predicted time of the next occurrence of the target.

[0007] One or more embodiments of the present specification provide an Internet of Things-based intelligent city road lighting intelligent control system. The system comprises a user platform, a service platform, a management platform, a sensing network platform and an object platform, the management platform is configured to perform the following operations: receiving sensing information obtained by the object platform through the sensing network platform; determining whether a target exists on the road based on the sensing information; in response to the absence of the target on the road, and the duration of the absence of the target satisfying a preset condition, determining the irradiation intensity of the street light on the road; wherein the preset condition is related to the predicted time of the next occurrence of the target on the road, the predicted time is determined based on a time prediction model, the input of the time prediction model includes a historical target occurrence sequence and a historical target speed sequence, and the output of the time prediction model includes the predicted time of the next occurrence of the target.

[0008] The above-mentioned Internet of Things-based intelligent city road lighting intelligent control method and system reasonably configure the irradiation intensity of the street light according to the road conditions, and at least have one of the following beneficial effects: 1) enhancing the intelligentization of street light control, and being capable of adjusting the lighting intensity of the street light in a targeted manner; 2) reasonably configuring the lighting intensity while ensuring the lighting effect, which is conducive to saving power resources. BRIEF DESCRIPTION OF DRAWINGS

[0009] The present specification will be further illustrated in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same numbers represent the same structures, wherein:

[0010] Figure 1 is an application scenario schematic diagram of an Internet of Things-based intelligent city street light intelligent control system according to some embodiments of the present specification;

[0011] Figure 2 is an exemplary structural diagram of an Internet of Things-based intelligent city street light intelligent control system according to some embodiments of the present specification;

[0012] Figure 3 is an exemplary flowchart of determining the irradiation intensity of the street light on the road according to some embodiments of the present specification;

[0013] Figure 4 is an exemplary flowchart of the method of adjusting the irradiation intensity of the street light according to some embodiments of the present specification;

[0014] Figure 5 is another exemplary flowchart of the method of adjusting the irradiation intensity of the street light according to some embodiments of the present specification;

[0015] Figure 6This is yet another exemplary flowchart of a method for adjusting the intensity of streetlight illumination according to some embodiments of this specification. Detailed Implementation

[0016] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0017] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0018] Unless the context clearly indicates otherwise, the words “a,” “an,” “an,” and / or “the” do not specifically refer to the singular and may also include the plural. Generally speaking, the terms “comprising” and “including” only indicate that the explicitly identified steps and components are included, and these steps and components do not constitute an exclusive list; the method or apparatus may also include other steps or components.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0020] Figure 1 This is a schematic diagram illustrating an application scenario of an IoT-based smart city street light intelligent control system, based on some embodiments of this specification.

[0021] like Figure 1 As shown, the application scenario 100 of the smart city street light intelligent control system based on the Internet of Things may include a server 110, a storage device 120, a network 130, a street light 140, and a user terminal 150.

[0022] In some embodiments, the smart city street lamp intelligent control system based on Internet of Things can determine the illumination intensity of the street lamps on the road according to the ambient light intensity and the road environment information. For example, the smart city street lamp intelligent control system based on Internet of Things can determine the lane and the direction of the target on the road according to the road image and adjust the illumination intensity of the street lamps in the area.

[0023] The server 110 can be a single server or a group of servers. In some embodiments, the server 110 can include a processing device 112, which can be used to process information and / or data related to the application scenario 100 of the smart city street lamp intelligent control system based on Internet of Things. For example, the processing device 112 can access the information and / or data stored in the user terminal 150 and / or the storage device 120 via the network 130.

[0024] In some embodiments, the processing device 112 can access the road information stored in the user terminal 150 via the network 130, and send control instructions to the street lamps 140 through the network 130 based on the processing of the road information to determine the illumination intensity of the street lamps 140 on the road.

[0025] The storage device 120 can be used to store data and / or instructions. In some embodiments, the storage device 120 can store the road information obtained by the user terminal 150. In some embodiments, the storage device 120 can store the data and / or instructions of the exemplary smart city street lamp intelligent control system based on Internet of Things described in this specification.

[0026] The network 130 can connect the components of the system and / or connect the system with external resource parts. The network 130 enables communication between the components and between the system and other parts outside the system, facilitating the exchange of data and / or information.

[0027] The street lamps 140 can include one or more street lamps 140-1, 140-2, …, 140-n. In some embodiments, the illumination intensity of the street lamps 140 can be changed.

[0028] The user terminal 150 can include one or more terminals or software used by the user. In some embodiments, the user can be the owner of the user terminal 150. In some embodiments, the user terminal 150 can include a mobile device, a tablet computer, a notebook computer, a wearable smart terminal, etc. or any combination thereof. In some embodiments, the user can obtain information related to street lamp management through the user terminal 150.

[0029] It should be noted that the application scenario 100 of the smart city street lamp intelligent control system based on the Internet of Things is provided only for the purpose of illustration and is not intended to limit the scope of the present application. Those of ordinary skill in the art can make various modifications or changes according to the description of the present specification. For example, the application scenario 100 of the smart city street lamp intelligent control system based on the Internet of Things can also include an information source. However, these changes and modifications will not depart from the scope of the present application.

[0030] Figure 2 is an exemplary structural diagram of the smart city street lamp intelligent control system based on the Internet of Things according to some embodiments of the present specification. As shown in Figure 2 The smart city street lamp intelligent control system based on the Internet of Things 200 can include a user platform 210, a service platform 220, a management platform 230, a sensing network platform 240, and an object platform 250. In some embodiments, the smart city street lamp intelligent control system based on the Internet of Things 200 can be part of or implemented by the server 110.

[0031] In some embodiments, the smart city street lamp intelligent control system based on the Internet of Things 200 can be applied to various application scenarios such as street lamp management. In some embodiments, the smart city street lamp intelligent control system based on the Internet of Things 200 can obtain road information. In some embodiments, the smart city street lamp intelligent control system based on the Internet of Things 200 can control the illumination intensity of the street lamp based on the processing of the road information.

[0032] Various scenarios of street lamp management can include control of street lamp illumination intensity on urban roads, urban communities, etc. It should be noted that the above scenarios are only examples and do not limit the specific application scenarios of the smart city street lamp intelligent control system based on the Internet of Things 200. Those skilled in the art can apply the smart city street lamp intelligent control system based on the Internet of Things 200 to any other suitable scenario based on the content disclosed in the present embodiment.

[0033] The smart city street lamp intelligent control system based on the Internet of Things 200 will be described in detail below.

[0034] The user platform 210 can be a user-oriented service interface configured as a terminal device. In some embodiments, the user platform 210 can receive information from a user. For example, the user platform 210 can receive a street lamp management strategy query instruction from a user. In some embodiments, the user platform 210 can feed back a street lamp management strategy to a user. In some embodiments, the user platform 210 can interact with the service platform 220. For example, the user platform 210 can send a street lamp management strategy query instruction to the service platform 220; for another example, the user platform 210 can receive a street lamp management strategy uploaded by the service platform 220. The street lamp management strategy can include distribution position information of street lamps.

[0035] The service platform 220 can be a platform for preliminary processing of street lamp data, configured as a first server. In some embodiments, the service platform 220 is usually arranged independently. The independent arrangement means that the service platform 220 includes a plurality of service sub-platforms, and different sub-platforms can be used for data storage, data processing and / or data transmission of street lamp data in different areas. In some embodiments, the service platform 220 can interact with the management platform 230. For example, the service platform 220 can send a street lamp management strategy query instruction to the management platform 230; for another example, the service platform 220 can receive a street lamp management strategy uploaded by the management platform 230. In some embodiments, the sub-platforms of the service platform can also be referred to as service sub-platforms.

[0036] The management platform 230 can be an Internet of Things platform for overall planning and coordination of contact and cooperation between functional platforms, providing perception management and control management. In some embodiments, the management platform 230 can be configured as a second server. In some embodiments, the management platform 230 can be used to execute a smart city street lamp management method. In some embodiments, the management platform 230 processes street lamp related data uploaded by the sensing network platform 240 to determine a street lamp management strategy in response to a street lamp management strategy query instruction sent by the service platform 220. The street lamp related data can include the number of street lamps in different areas, brightness adjustment strategies of street lamps, etc.

[0037] In some embodiments, the management platform 230 adopts a combined pre-division arrangement. The combined pre-division arrangement refers to that the management platform 230 is provided with one general platform and a plurality of division platforms (including self-owned databases), the plurality of division platforms respectively store and / or process the street lamp related data of different regions sent by the sensing network platform 240, the general platform stores and / or processes the data of the plurality of division platforms after summarizing the data of the plurality of division platforms, and transmits the data to the service platform 220. The management division platforms are set based on the street lamp related data of different regions, each management division platform has a corresponding sensing network division platform, the data obtained by the object platform is uploaded to the corresponding sensing network division platform, and after being processed by the corresponding sensing network division platform, the data is uploaded to the corresponding management division platform. For example, the management division platforms can include a city A region division platform, a city B region division platform, and a city C region division platform, etc.

[0038] In some embodiments, each management division platform receives the street lamp related data of each region from the corresponding sensing network division platform, and each management division platform processes and manages the street lamp related data of each region. For example, the related data of each street lamp in the city A region is uploaded to the city A region street lamp management division platform for management. In some embodiments, each management division platform (including a self-owned database) further uploads the processed data to the management general platform, and the management general platform uploads the summarized and processed data to the service platform. The data uploaded to the server can include a street lamp management strategy.

[0039] In some embodiments, the management general platform can also be referred to as the general platform of the management platform, and the management division platform can also be referred to as the division platform of the management platform.

[0040] In some embodiments, the management platform 230 can interact with the sensing network platform 240. The management platform 230 can send an instruction for obtaining street lamp related data to the sensing network platform 240. In some embodiments, the management platform 230 can receive and process the street lamp related data of each region uploaded by the sensing network platform 240.

[0041] In some embodiments of the present specification, the street lamp related data of different regions is processed by the management division platform, and then summarized to the general database, which can reduce the data processing pressure of the whole management platform, and can also collect the data of each independent division platform for unified management. In addition, the division platform database and the general database belong to the government, which is convenient for the government to uniformly master the overall situation of the city street lamp management.

[0042] The sensing network platform 240 can be a platform that realizes the interaction between the management platform and the object platform. In some embodiments, the sensing network platform 240 adopts a standalone arrangement, including a plurality of sensing network sub-platforms corresponding to a plurality of management sub-platforms. In some embodiments, the sensing network sub-platforms can be divided according to urban areas. For example, the sensing network sub-platforms can include a city A area sub-platform, a city B area sub-platform, and a city C area sub-platform, etc.

[0043] In some embodiments, the sensing network platform 240 is configured as a communication network and a gateway, and each sensing network sub-platform can be configured with an independent gateway. In some embodiments, each sensing network sub-platform obtains the street lamp related data uploaded by the object platform and processes and manages the street lamp related data. For example, the street lamps and related sensing devices deployed in the city A area upload the data to the city A area sensing network sub-platform for processing. In some embodiments, the sensing network sub-platform uploads the processed street lamp related data to the database of the corresponding management sub-platform.

[0044] In some embodiments, the sensing network platform 240 can interact with the object platform 250. The sensing network platform 240 can send a street lamp related data acquisition instruction to the object platform 250. In some embodiments, the sensing network platform 240 can receive the street lamp related data uploaded by the object platform 250 and process the street lamp related data.

[0045] In some embodiments, the sensing network sub-platform can also be referred to as a sub-platform of the sensing network platform.

[0046] The object platform 250 can be a functional platform for generating sensing information and executing control information. In some embodiments, the object platform 250 can be configured as a functional platform composed of at least one street lamp and related sensing devices (such as a camera device, etc.). Each of the at least one street lamp and related sensing devices is configured with a unique number, which can be used for managing the street lamps deployed in different areas of a city. The related sensing devices can include a light sensor for acquiring environmental light intensity. The related sensing devices can also include a camera for acquiring road images.

[0047] In some embodiments, the object platform 250 can interact with the sensing network platform 240 to receive the street lamp related data acquisition instruction issued by the sensing network sub-platform, and upload the street lamp related data to the corresponding sensing network sub-platform.

[0048] For those skilled in the art, after understanding the principle of the system, the Internet of Things based smart city street lamp intelligent control system 200 can be applied to any other suitable scene without departing from the principle.

[0049] It should be noted that the above description of the system and its components is for convenience of description only and does not limit the scope of the present specification to the embodiments described. It will be appreciated by those skilled in the art that, after having understood the principles of the system, any combination of the components or connection of the components to other components can be made without departing from the principles of the system. For example, the components can share a storage device, or each component can have its own storage device. Such variations are within the scope of the present specification.

[0050] Figure 3 is an exemplary flowchart of determining the illumination intensity of a streetlight on a road according to some embodiments of the present specification. As shown in Figure 3 , the flow 300 includes the following steps. In some embodiments, the flow 300 can be performed by the management platform 230.

[0051] Step 310, receiving road information obtained by an object platform via a sensing network platform, the road information including environmental light intensity and a road image, the object platform including a first sensor.

[0052] The road information refers to information related to a road. In some embodiments, the road information can include environmental light intensity and a road image. The road information can be obtained based on a first sensor in an object platform, and the first sensor can include a light sensor and an image sensor. The first sensor can be deployed on a road, on a streetlight of a road, or elsewhere.

[0053] The environmental light intensity refers to the illumination intensity in the environment where the road is located. The environmental light intensity can be represented by the luminous flux (unit: Lux) of the visible light received per unit area or other ways. For example, the environmental light intensity on a road at a certain time is 100 Lux. The environmental light intensity can be obtained based on the environmental light data collected by a light sensor.

[0054] The road image refers to an image containing a road picture taken. The road image can be obtained based on a picture containing a road collected by an image sensor (e.g., a camera).

[0055] Step 320, determining road environment information based on the road image.

[0056] The road environment information refers to information related to the environment of a road that can affect driving. In some embodiments, the road environment information can include visibility, the number of obstacles (e.g., a malfunction warning sign on a certain lane) on a road that affect traffic.

[0057] In some embodiments, the management platform 230 can determine the road environment information based on the road image by a first image recognition model. The first image recognition model can be a machine learning model. The input of the first image recognition model is the road image, and the output is the road environment information. The first image recognition model can be obtained by training. The first training sample can be a historical road image, and the label of the first training sample is the road environment information corresponding to the historical road image. The first training sample can be obtained based on historical data. The label of the first training sample can be obtained by manual annotation.

[0058] In step 330, the illumination intensity of the street lamp on the road is determined based on the ambient light intensity and the road environment information.

[0059] The illumination intensity can refer to the intensity of the light emitted by the street lamp irradiating onto the road surface. The illumination intensity can be the average luminous flux (unit: Lux) irradiating onto the road surface. For example, the illumination intensity of a certain street lamp is 60 Lux.

[0060] In some embodiments, in response to the ambient light intensity being greater than or equal to a first threshold value, the illumination intensity of the street lamp on the road can be determined as 0 Lux, i.e., the illumination of the street lamp is turned off.

[0061] In some embodiments, in response to the ambient light intensity being less than the first threshold value, the illumination intensity of the street lamp on the road can be determined based on the ambient light intensity and the road environment information by a preset rule. For example, the preset rule can be: the lower the ambient light intensity, the lower the visibility, and the more the number of obstacles, the greater the illumination intensity of the street lamp.

[0062] In some embodiments, the management platform can obtain historical traffic accident data of the road, and determine the illumination time and the corresponding illumination intensity of the street lamp based on the historical traffic data. The historical traffic data can at least include the road section with high traffic accidents and the corresponding time period. The management platform can control the street lamp of the road section to be always on and increase the illumination intensity in the time period based on the road section and the time period with high traffic accidents at night, so as to reduce the occurrence frequency of traffic accidents at night and improve the safety of vehicles driving at night.

[0063] In some embodiments, the management platform can also adjust the illumination intensity of the street lamps in other manners. For example, the management platform can determine the lane and the direction of the target based on the road image, determine a first target area based on the lane and the direction, and adjust the illumination intensity of the street lamps in the first target area. The management platform can determine the turn signal state of the target on the road based on the road image, determine a second target area based on the turn signal state, and adjust the illumination intensity of the street lamps in the second target area. The management platform can adjust the illumination intensity of the street lamps based on whether there is a target on the road, and reduce the illumination intensity of the street lamps when there is no target in a certain time range. The management platform can also determine the illumination intensity of the street lamps according to historical traffic accident data, and increase the illumination intensity of the street lamps in the time and / or location where accidents frequently occur.

[0064] Further details about adjusting the illumination intensity of the street lamps can be found in other parts of this specification (e.g., Figure 4 , Figure 5 and Figure 6 .

[0065] After the management platform 230 calculates the illumination intensity of the street lamps, it can send adjustment instructions to the object platform through the corresponding regional sensor network platform to adjust the illumination intensity of the relevant street lamps in the region.

[0066] In some embodiments of this specification, the road environment information is obtained by the first sensor, the illumination of the street lamps can be turned off when the ambient light intensity is high (e.g., during the day), and the illumination intensity of the street lamps can be intelligently increased in poor road conditions. By reasonably configuring the illumination intensity of the street lamps according to the road conditions, the illumination effect can be ensured while effectively saving power resources.

[0067] Figure 4 is an exemplary flowchart of the method for adjusting the illumination intensity of the street lamps according to some embodiments of this specification. As Figure 4 shown, the flowchart 400 includes the following steps. In some embodiments, the flowchart 400 can be performed by the management platform 230.

[0068] Step 410: determining the lane and the direction of the target on the road based on the road image.

[0069] The target on the road can include a vehicle, a pedestrian, etc. on the road. The lane indicates a lane on the road where the target is currently located. The lane can include a motor lane, a non-motor lane, a pedestrian lane, etc. The lane can be represented by a number (e.g., lane 1, lane 2, etc.) or other manners based on a preset rule (e.g., from left to right). In some embodiments, the lane can be segmented based on a preset distance (e.g., 10 m), and each segment of the lane can be represented by a number (e.g., segment 1, segment 2, etc.) or other manners. In some embodiments, the lane can also include the lane and the segment where the target is currently located. For example, the lane of a target on the road is (1, 2), which can indicate that the target is currently located in the second segment of lane 1.

[0070] The forward direction indicates a direction in which the target on the road is moving. The forward direction can be represented by a number (e.g., 1 for a direction in which a lane extends, and 0 for the opposite direction) or other manners based on a preset rule.

[0071] In some embodiments, the management platform can determine the lane and the forward direction of the target on the road based on the road image by using a second image recognition model.

[0072] The second image recognition model can be a machine learning model. The input of the second image recognition model is the road image, and the output is the lane and the forward direction of the target on the road. In some embodiments, the output of the second image recognition model can include the lane and the forward direction of multiple targets on the road. In some embodiments, the output of the second image recognition model can also include the number of targets on the road. In some embodiments, the input of the second image recognition model can be a road image sequence composed of multiple frames of the current time and the previous and subsequent time, and the output can also include the forward speed of the target on the road.

[0073] In some embodiments, the second image recognition model can be obtained by training. The second training sample for training the second image recognition model can be a historical road image (or a historical road image sequence), and the label is the lane, the forward direction, the number of targets, and the forward speed of the target in the historical road image. The second training sample can be obtained based on historical data, and the label can be obtained by manual labeling.

[0074] At step 420, a first target region is determined based on the lane and the forward direction of the target.

[0075] The first target region indicates a region determined based on a preset extension segment of the lane and the forward direction of the target on the road. The preset extension segment indicates at least one segment of the lane determined based on the forward direction. For example, the target is currently located in the third segment of a lane, and the forward direction is 1, and the preset extension segment can be the fourth segment and the fifth segment of the lane.

[0076] In some embodiments, the region formed by the lane where the at least one target on the road is located and the preset extension of the direction of the at least one target can be determined as the first target region. For example, through the aforementioned image recognition, there are currently two targets on the road, and the vectors formed by the lanes where the targets are located and the directions of the targets are (1, 4, 1) and (2, 5, 0) in turn. Therefore, the first target region includes the 4th, 5th and 6th segments of the 1st lane and the 5th, 4th and 3rd segments of the 2nd lane.

[0077] In step 430, the illumination intensity of at least the street lamps in the first target region is adjusted.

[0078] In some embodiments, adjusting the illumination intensity of the street lamps in the first target region can include determining a first illumination intensity adjustment value based on the first target region, and adjusting the illumination intensity of at least the street lamps in the first target region based on the first illumination intensity value.

[0079] The illumination intensity adjustment value refers to the absolute value of the difference between the adjusted illumination intensity and the illumination intensity before adjustment. The illumination intensity adjustment value can be represented by a value greater than 0 or in other ways. For example, the illumination intensity adjustment value can be 10 Lux.

[0080] In some embodiments, the first illumination intensity adjustment value can be determined based on the first target region by a preset rule. For example, the preset rule can be that the more lanes the first target region contains, the greater the first illumination intensity adjustment value.

[0081] In some embodiments, the first illumination intensity adjustment value can be related to the number of targets in the first target region. In some embodiments, the number of targets in the first target region can be obtained by the second image recognition model. For example, the number of targets on the road output by the second image recognition model is determined as the number of targets in the first target region. For example, the first illumination intensity adjustment value can be determined by the following formula:

[0082] L1 = k1n1 + k2n2

[0083] Wherein, L1 is the first illumination intensity adjustment value, n1 is the number of lanes covered by the first target region, n2 is the number of targets in the first region, and k1 and k2 are preset parameters for adjusting the size of the first illumination intensity adjustment value. k1 and k2 can be determined based on experience, for example, k1 and k2 can both be 1.

[0084] In some embodiments of the present specification, by introducing the number of targets when calculating the first illumination intensity adjustment value, the increase in illumination intensity can be increased in the case of road congestion, thereby more intelligently reducing the risk of potential traffic accidents.

[0085] In some embodiments, the first irradiation intensity adjustment value can also be related to the advancing speed of the target of the first target region.

[0086] In some embodiments, the advancing speed of the target of the first target region can be obtained by the second image recognition model. For example, the advancing speed of the target on the road output by the second image recognition model is determined as the advancing speed of the target of the first target region. For example, the first irradiation intensity adjustment value can be determined by the following formula:

[0087]

[0088] wherein, L1 is the first irradiation intensity adjustment value, n is the number of lanes covered by the first target region, m is the number of targets of the first region, v i is the advancing speed of the i-th target, k1, k2, k3 are preset parameters for adjusting the size of the first irradiation intensity adjustment value, and k1, k2, k3 can be determined based on experience, for example, k1, k2, k3 can all be 1.

[0089] In some embodiments of the present specification, by introducing the advancing speed of the target when calculating the first irradiation intensity adjustment value, the increase range of the irradiation intensity can be increased in the case that the speed of the vehicle on the road is relatively fast, so as to more intelligently reduce the risk of potential traffic accidents.

[0090] In some embodiments, the management platform can send an adjustment instruction to the object platform through the sensor network sub-platform of the corresponding region, so as to increase the irradiation intensity of the street lamp in the first target region, wherein the increase value of the irradiation intensity is the first irradiation intensity adjustment value.

[0091] In some embodiments, the management platform can also send an adjustment instruction to the object platform through the sensor network sub-platform of the corresponding region, so as to decrease or maintain the irradiation intensity of the street lamp outside the first target region, wherein, in response to decreasing the irradiation intensity outside the first target region, the decrease value of the irradiation intensity can be the first irradiation intensity adjustment value or other numerical value.

[0092] In some embodiments of the present specification, based on the road image, the lane and the advancing direction of the target on the road are determined, and finally the irradiation intensity is adjusted, so that the irradiation intensity of the street lamp can be increased in the road section where the vehicle or the pedestrian exists, the visual field condition of the vehicle on the lane is improved, and the occurrence of traffic accidents is reduced.

[0093] Figure 5 is another exemplary flowchart of the method for adjusting the irradiation intensity of the street lamp according to some embodiments of the present specification. As Figure 5 shown, the flow 500 includes the following steps. In some embodiments, the flow 500 can be executed by the management platform 230.

[0094] At step 510, a turn light state of the target on the road is determined based on the road image.

[0095] The turn light state refers to a state of a turn light of the target (e.g., a vehicle) on the road. For example, the turn light state includes: a left turn light being on, a right turn light being on, and no turn light being on. The turn light state can be represented by a digital number or in other ways. For example, the turn light state of “1” represents the left turn light being on, the turn light state of “2” represents the right turn light being on, and the turn light state of “0” represents no turn light being on.

[0096] In some embodiments, the management platform can determine the turn light state of the target on the road based on the road image by a third image recognition model.

[0097] The third image recognition model can be a machine learning model. The input of the third image recognition model is the road image, and the output is the turn light state of the target on the road. In some embodiments, the output of the third image recognition model can include the turn light states of multiple targets on the road.

[0098] In some embodiments, the third image recognition model can be obtained by training. The third training sample for training the third image recognition model can be a historical road image, and the label of the third training sample is the turn light state of the target in the historical road image. The third training sample can be obtained based on historical data. The label of the third training sample can be obtained by manual annotation.

[0099] At step 520, a second target region is determined based on the turn light state.

[0100] The second target region refers to a lane that the target can possibly enter, which is determined based on the lane where the target is located on the road and the turn light state. For example, the turn light state of the target is “1” (e.g., representing the right turn light being on), and the possible driving route of the target is: changing lanes to the right to the right lane, turning right to enter the next road, etc. Therefore, the possible lanes that the target can enter include: all lanes to the right of the lane where the target is currently located, and all lanes to the right of the next road after the right turn.

[0101] In some embodiments, at least one of the possible lanes that the at least one target on the road can enter can be determined as the second target region. For example, all the possible lanes that the target can enter can be determined as the second target region. For another example, only one of the possible lanes that the target can enter can be determined as the second target region.

[0102] At step 530, the illumination intensity of at least the street lamp in the second target region is adjusted.

[0103] In some embodiments, the adjusting the illumination intensity of at least the street lamps in the second target area can comprise: determining a second illumination intensity adjustment value based on the second target area; and adjusting the illumination intensity of at least the street lamps in the second target area based on the second illumination intensity adjustment value.

[0104] In some embodiments, the second illumination intensity adjustment value of different lanes and lane segments in the second target area can be determined based on the current distance of the different lanes and lane segments to the nearest target in the second target area by a preset rule. For example, the preset rule can be that the closer the distance, the greater the second illumination intensity adjustment value of the corresponding lane segment.

[0105] In some embodiments, the second illumination intensity adjustment value can be related to a red light waiting time. The red light waiting time refers to the waiting time caused by a red light.

[0106] In some embodiments, in response to a lane segment in the second target area being a target passing through lane segment by changing lanes or right turn, the red light waiting time corresponding to the lane segment of the lane can be 0.

[0107] In some embodiments, in response to a lane segment in the second target area being a target passing through lane segment by left turn, U-turn or straight driving, the red light waiting time corresponding to the lane segment of the lane can be determined based on the schedule of the traffic light obtained by the management platform, and the current speed of the target, the distance to the traffic light, etc.

[0108] For example, the second illumination intensity value of a lane segment of a lane in the second target area can be determined by the following formula:

[0109]

[0110] wherein L2 is the second illumination intensity adjustment value, d is the distance of the nearest target to the lane segment of the lane, t is the red light waiting time, k1 and k2 are preset parameters for adjusting the size of the second illumination intensity adjustment value, and k1 and k2 can be determined based on experience, for example, k1 and k2 can both be 1.

[0111] In some embodiments, the illumination intensity of the street lamps in the second target area can be increased, wherein the increase value of the illumination intensity is the second illumination intensity adjustment value.

[0112] In some embodiments, the illumination intensity of the street lamps outside the second target area can also be reduced or maintained, wherein in response to reducing the illumination intensity outside the second target area, the reduction value of the illumination intensity can be the second illumination intensity adjustment value or other numerical value.

[0113] In some embodiments of the present disclosure, by introducing the red light waiting time of the target when calculating the second illumination intensity adjustment value, the increase in the illumination intensity can be reduced in the case that the red light waiting time of the vehicle on the road is long, thereby avoiding the ineffective illumination of the street lamp and effectively saving the power resource.

[0114] In some embodiments of the present disclosure, the turn signal state of the target on the road is determined based on the road image, and the illumination intensity is finally adjusted, so that the illumination intensity of the corresponding area street lamp can be increased in advance according to the possible tendency (turning, straight driving, U-turn) of the vehicle on the road, the road driving experience is optimized, and the occurrence of traffic accidents is reduced.

[0115] In some embodiments, the management platform can also communicate with the navigation system of the vehicle through the Internet of Things technology, obtain the navigation route of the vehicle, determine the road section where the vehicle will come from and the estimated time when the vehicle arrives at the road section based on the navigation route, determine the third illumination intensity adjustment value, and adjust the illumination intensity of the street lamp of the road section by a preset time in advance according to the estimated time. The third illumination intensity adjustment value can be one of a system preset value, an artificially input adjustment value, or an adjustment value determined according to the actual road condition.

[0116] In some embodiments of the present disclosure, by obtaining the navigation route of the vehicle within the preset range, the road section where the vehicle is likely to come from can be determined in advance, so that the illumination intensity of the specified road section can be adjusted in advance, and the intelligentization of the street lamp illumination intensity control can be improved.

[0117] Figure 6 is another exemplary flowchart of the method for adjusting the illumination intensity of the street lamp according to some embodiments of the present disclosure. As shown in Figure 6 , the flowchart 600 includes the following steps. In some embodiments, the flowchart 600 can be executed by the management platform 230.

[0118] Step 610: determining whether there is a target on the road based on the sensing information obtained by the second sensor.

[0119] The second sensor can include a pressure sensor. The second sensor can be located in the object platform. In some embodiments, the management platform can receive the sensing information obtained by the second sensor in different areas from different sensing network sub-platforms, and the sensing information can include a pressure value. The second sensor can be deployed on the road surface or other places. In some embodiments, at least one second sensor can be deployed on each lane section of each lane on the road to determine whether there is a target on the lane section of the lane.

[0120] In some embodiments, the presence of the target on the road can be determined based on the pressure values obtained by the at least one second sensor on the road. For example, the pressure values of each lane segment can be compared with a preset pressure value to determine whether the target is present on the lane segment.

[0121] In some embodiments, the management platform can further receive the sensing information obtained by the second sensors and / or the road images obtained by the first sensors in different regions from different sensing network sub-platforms to determine whether the target is present on the road.

[0122] In response to the absence of the target on the road and the duration of the absence satisfying a preset condition, the illumination intensity reduction value of the street lamp on the road is determined in step 620.

[0123] In some embodiments, the preset condition can refer to the duration of the absence being greater than or equal to a duration preset value. The duration preset value can be determined based on experience, for example, 5 seconds, 10 seconds, etc.

[0124] In some embodiments, the preset condition can be related to a predicted time 623 of the next occurrence of the target on the road. The predicted time can be determined based on a time prediction model 622.

[0125] The time prediction model 622 can be a machine learning model. The input of the time prediction model 622 is a historical target occurrence time sequence 621, and the output is the predicted time 623 of the next occurrence of the target.

[0126] The historical target occurrence time refers to the time of the occurrence of a target on the road before the current time. For example, a historical target occurrence time of 20 seconds can indicate that a target occurred on the road 20 seconds ago. The historical target occurrence time sequence can include at least one historical target occurrence time. For example, the historical target occurrence time sequence (250, 210, 100, 40, 10) indicates that a target occurred on the road 250 seconds ago, a target (which can not be the same as the aforementioned target) occurred on the road 210 seconds ago, and so on, and a target occurred on the road 10 seconds ago.

[0127] In some embodiments, the management platform can receive the information obtained by the first and / or second sensors in different regions from different sensing network sub-platforms to obtain the historical target occurrence time sequence 621.

[0128] In some embodiments, the input of the time prediction model 622 can further include a historical target speed sequence 624, and the output can further include the speed 625 of the next occurrence of the target.

[0129] The historical target speed refers to the forward speed of a target appearing on the road at a certain time before the current time. The historical target speed sequence can include at least one historical target speed. In some embodiments, the historical target speeds in the historical target speed sequence can correspond to the same target in sequence with the historical target appearance times in the historical target appearance time sequence. For example, the historical target appearance time sequence (250, 210, 100, 40, 10) and the historical target speed sequence (60, 40, 80, 20, 10) represent that a target appeared on the road at 250 seconds ago at a speed of 60 km / h, a target appeared on the road at 210 seconds ago at a speed of 40 km / h, and so on, and a target appeared on the road at 10 seconds ago at a speed of 10 km / h.

[0130] In some embodiments, the management platform can receive information of the second sensor from different sensor network platforms to obtain the historical target speed sequence 624.

[0131] In some embodiments of the present specification, by introducing the historical target speed sequence, the influence of the speed on the appearance time is fully considered when predicting the next appearance time of the target, and the prediction accuracy can be improved.

[0132] In some embodiments, the time prediction model can be trained by training or other methods. The fourth training sample for training the time prediction model can be a historical arrival time sequence, and the label is the time of the next appearance of the target corresponding to the historical arrival time sequence. The fourth training sample can obtain the label based on historical data, and the label can be obtained by manual labeling.

[0133] For example, the time length preset value in the preset condition can be determined by the following formula:

[0134]

[0135] Wherein, T is the time length preset value, t is the predicted time of the next appearance of the target, k1 and k2 are preset parameters for adjusting the size of the time length preset value, and k1 and k2 can be determined based on experience, for example, k1 and k2 can both be 1.

[0136] In some embodiments, the irradiation intensity reduction value can be determined based on the time length preset value and the predicted time of the next appearance of the target. For example, the irradiation intensity reduction value can be determined by the following formula:

[0137] L3=k1t1+k2t2

[0138] Wherein, L3 is the irradiation intensity reduction value, t1 is the time length preset value, t2 is the predicted time of the next appearance of the target, k1 and k2 are preset parameters for adjusting the size of the irradiation intensity reduction value, and k1 and k2 can be determined based on experience.

[0139] After the management platform 230 calculates the illumination intensity reduction value of the street lamp, the management platform 230 can send an adjustment instruction to the object platform through the corresponding regional sensor network sub-platform to adjust the illumination intensity of the street lamp in the region.

[0140] In some embodiments, the illumination intensity reduction value of the street lamp can be determined based on a gradient reduction value sequence, and the gradient reduction value sequence can be related to the predicted time of the next appearance of the target.

[0141] The gradient reduction value sequence refers to a sequence composed of at least one illumination intensity reduction value. For example, the gradient reduction value sequence can be (20, 20, 20, 20). In some embodiments, the gradient reduction value sequence can be sequentially assigned to the illumination intensity reduction value of the street lamp, and when the management platform controls the street lamp to reduce the illumination intensity based on the illumination intensity reduction value, the illumination intensity reduction value can be cleared to wait for the next assignment, so that the illumination intensity of the street lamp can be reduced in segments. For example, the current illumination intensity of the street lamp is 100 Lux, and the gradient reduction value sequence is (20, 20, 20, 20), then the element value in the gradient reduction value sequence can be sequentially assigned to the illumination intensity reduction value of the street lamp at certain intervals, so that the illumination intensity of the street lamp can be reduced by 20 Lux at certain intervals.

[0142] In some embodiments, a minimum intensity value of the illumination intensity of the street lamp can be set, and when the illumination intensity of the street lamp is controlled to be reduced by the illumination intensity reduction value, if the illumination intensity of the street lamp has been reduced to the minimum intensity value, the reduction will not continue.

[0143] In some embodiments, the gradient reduction value sequence can be related to the predicted time of the next appearance of the target. For example, the longer the predicted time of the next appearance of the target, the fewer the number of elements in the gradient reduction value sequence and the larger the sum of the elements (but will not make the illumination intensity of the street lamp reduced below the minimum intensity value), so that the illumination intensity of the street lamp is quickly reduced; the shorter the predicted time of the next appearance of the target, the more the number of elements in the gradient reduction value sequence and the smaller the sum of the elements, so that the illumination intensity of the street lamp is slowly reduced.

[0144] In some embodiments, the gradient reduction value sequence can also be related to the speed of the next appearance of the target. For example, the longer the predicted time of the next appearance of the target and the smaller the speed of the next appearance of the target, the fewer the number of elements in the gradient reduction value sequence and the larger the sum of the elements; the shorter the predicted time of the next appearance of the target and the greater the speed of the next appearance of the target, the more the number of elements in the gradient reduction value sequence and the smaller the sum of the elements.

[0145] In some embodiments of the present specification, by introducing the correlation of the speed when the target next appears when determining the gradient reduction value sequence, the situation that the speed of the next vehicle is fast and the illumination intensity of the street lamp has been rapidly reduced can be effectively prevented, thereby reducing the risk of traffic accidents.

[0146] In some embodiments of the present specification, by introducing the gradient reduction value sequence and sequentially assigning the elements in the gradient reduction value sequence to the illumination intensity reduction value, the step-by-step reduction of the illumination intensity of the street lamp can be realized, thereby realizing gradient control and helping to adapt to more variable and complex road scenes.

[0147] In some embodiments of the present specification, by acquiring sensing information through the second sensor to determine whether the target exists on the road, the illumination intensity of the street lamp is reduced when the target does not exist and the time length satisfies the preset condition, thereby saving power resources, and considering the time when the target next appears, the situation of sudden arrival of a vehicle can be prevented, thereby reducing the risk of accidents.

[0148] It should be noted that the above description of the method for adjusting the illumination intensity of the street lamp is only for example and illustration, and does not limit the scope of the present specification. Those skilled in the art can make various modifications and changes to the method for adjusting the illumination intensity of the street lamp under the guidance of the present specification. However, these modifications and changes are still within the scope of the present specification.

[0149] The above has described the basic concept, and it is obvious that the above detailed disclosure is only for example and does not constitute a limitation on the present specification for those skilled in the art. Although it is not explicitly stated here, those skilled in the art can make various modifications, improvements and corrections to the present specification. Such modifications, improvements and corrections are suggested in the present specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present specification.

[0150] At the same time, the present specification uses specific words to describe the embodiments of the present specification. As "one embodiment", "an embodiment", and / or "some embodiments" means a certain feature, structure or characteristic related to at least one embodiment of the present specification. Therefore, it should be emphasized and noted that the "an embodiment" or "one embodiment" or "one alternative embodiment" mentioned in different places in the present specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present specification can be properly combined.

[0151] It should be appreciated that, for simplicity of illustration, the foregoing methodology can be illustrated or described in terms such as the following: in one embodiment, another embodiment, an implementation, or variations thereof, etc. Although described in one or more implementations, these teachings are hereby applied to any and all such variations. Where the description defines implementations by using such terms as "in one embodiment," "in another embodiment," or "in an implementation", such terminology is used for descriptive purposes only, and does not delimit the subject matter described. It is recognized that "in one embodiment" or "in an implementation" thereof is simply one example of an implementation and "in one embodiment" is not necessarily delineated each and every implementation. Further, the use of these terms is not intended to delimit the subject matter described, but the scope of the subject matter will be defined only by the claims. Further, these terms can be replaced with the phrases "in an embodiment," "in one embodiment," or "in at least one embodiment," depending on the context.

[0152] Finally, it should be appreciated that the foregoing description is by way of example only, and is not intended to limit the scope of the subject matter described herein. Other variations that are within the scope of the described subject matter can occur to those in the art upon reading or understanding the previous description. Accordingly, while the exemplary embodiments have been described above with particularity, the scope of the subject matter described herein should not be construed as limited to the embodiments described in the specification, but should be given the full breadth that comprises all of the aforementioned alternatives and their equivalents.

Claims

1. A smart city road lighting intelligent control method based on Internet of Things, characterized in that, The method is implemented by a smart city road lighting intelligent control system based on Internet of Things, the smart city road lighting intelligent control system based on Internet of Things comprises a user platform, a service platform, a management platform, a sensing network platform and an object platform, the method is executed by the management platform, and comprises: receiving sensing information acquired by the object platform through the sensing network platform; judging whether a target exists on the road based on the sensing information; in response to the target not existing on the road and a duration for which the target does not exist satisfying a preset condition, determining a radiation intensity reduction value of a street lamp on the road; wherein the preset condition is related to a predicted time of next occurrence of the target on the road determined based on a time prediction model, input of the time prediction model comprises a historical target occurrence sequence and a historical target speed sequence, and output of the time prediction model comprises a predicted time of next occurrence of the target. 2.The IoT-based smart city road lighting intelligent control method according to claim 1, wherein, The radiation intensity reduction value is determined based on a gradient reduction value sequence, and the gradient reduction value sequence is determined based on the predicted time of next occurrence of the target. 3.The IoT-based smart city road lighting intelligent control method of claim 1, wherein, The method further comprises: receiving road information acquired by the object platform through the sensing network platform, the road information comprising ambient light intensity and a road image, and the object platform comprising a first sensor; determining road environment information based on the road image; determining radiation intensity of a street lamp on the road based on the ambient light intensity and the road environment information. 4.The IoT-based smart city road lighting intelligent control method according to claim 1, wherein, Comprise: The service platform adopts an independent arrangement and comprises a plurality of service sub-platforms, different sub-platforms can be used to store, process and / or transmit street lamp data of different regions; The management platform adopts a front sub-arrangement and comprises a management total platform and a plurality of management sub-platforms, the plurality of management sub-platforms respectively store and / or process street lamp related data of different regions, the management total platform stores and / or processes data of the plurality of management sub-platforms after the data is aggregated, and transmits the data to the service platform; The sensing network platform adopts an independent arrangement and comprises a plurality of sensing network sub-platforms, the plurality of sensing network sub-platforms correspond to the plurality of management sub-platforms one by one. 5.The IoT-based smart city road lighting intelligent control method according to claim 3, wherein, The determination of the radiation intensity of the street lamp on the road further comprises: determining a lane and a forward direction of the target on the road based on the road image; determining a first target area based on the lane and the forward direction; adjusting radiation intensity of at least a street lamp in the first target area.

6. An Internet of Things-based intelligent control system for smart city road lighting, characterized in that, Comprise a user platform, a service platform, a management platform, a sensing network platform and an object platform, the management platform is configured to execute the following operations: receiving sensing information acquired by the object platform through the sensing network platform; judging whether a target exists on the road based on the sensing information; In response to the target not existing on the road and a duration of the target not existing satisfying a preset condition, a reduction value of an illumination intensity of a streetlight on the road is determined, wherein the preset condition is related to a predicted time of the target next appearing on the road, the predicted time being determined based on a time prediction model, an input of the time prediction model including a historical target appearance sequence and a historical target speed sequence, and an output of the time prediction model including the predicted time of the target next appearing. 7.The IoT-based smart city road lighting intelligent control system according to claim 6, wherein, The reduction value of the illumination intensity is determined based on a gradient reduction value sequence, the gradient reduction value sequence being determined based on the predicted time of the target next appearing.

8. The IoT based smart city road lighting intelligent control system as claimed in claim 6 wherein, The management platform is further configured to: receive, by the sensing network platform, road information acquired by the object platform, the road information including an ambient light intensity and a road image, the object platform including a first sensor; determine road environment information based on the road image; determine an illumination intensity of a streetlight on the road based on the ambient light intensity and the road environment information. 9.The IoT-based smart city road lighting intelligent control system according to claim 6, wherein, The service platform comprises: The service platform adopts a standalone arrangement and comprises a plurality of service sub-platforms, different sub-platforms being used to store, process and / or transmit streetlight data of different regions; The management platform adopts a front sub-arrangement and comprises a management general platform and a plurality of management sub-platforms, the plurality of management sub-platforms respectively storing and / or processing streetlight related data of different regions, the management general platform storing and / or processing data of the plurality of management sub-platforms after the data is aggregated, and transmitting the data to the service platform; The sensing network platform adopts a standalone arrangement and comprises a plurality of sensing network sub-platforms, the plurality of sensing network sub-platforms corresponding to the plurality of management sub-platforms one by one. 10.The IoT-based smart city road lighting intelligent control system according to claim 8, wherein, The management platform is further configured to: determine a lane and a forward direction of a target on the road based on the road image; determine a first target region based on the lane and the forward direction; adjust at least an illumination intensity of a streetlight in the first target region.

Images