CN117116065B - Intelligent road traffic flow control method and system - Google Patents
Intelligent road traffic flow control method and system Download PDFInfo
- Publication number
- CN117116065B CN117116065B CN202311373397.4A CN202311373397A CN117116065B CN 117116065 B CN117116065 B CN 117116065B CN 202311373397 A CN202311373397 A CN 202311373397A CN 117116065 B CN117116065 B CN 117116065B
- Authority
- CN
- China
- Prior art keywords
- road
- congestion level
- road congestion
- traffic
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims description 43
- 230000011218 segmentation Effects 0.000 claims description 42
- 238000012544 monitoring process Methods 0.000 claims description 30
- 238000012937 correction Methods 0.000 claims description 24
- 238000003709 image segmentation Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 22
- 238000005206 flow analysis Methods 0.000 claims description 21
- 230000000903 blocking effect Effects 0.000 claims description 19
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 description 19
- 230000006870 function Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Abstract
The invention provides a method and a system for managing and controlling intelligent road traffic flow, which relate to the technical field of traffic management and comprise the following steps: collecting road images, acquiring a first vehicle type set and a second vehicle type set, acquiring an image sequence, performing head time distance recognition, acquiring a first head time distance and a second head time distance, performing road congestion analysis, acquiring a first road congestion level and a second road congestion level, comparing the larger road congestion level with a vehicle type congestion comparison table, acquiring a traffic flow dredging obstruction coefficient, correcting, acquiring a corrected road congestion level, acquiring a plurality of associated corrected road congestion levels, combining the corrected road congestion levels, calculating, acquiring a comprehensive road congestion level, performing a management and control scheme decision, acquiring a management and control scheme, and managing and controlling traffic lights. The invention solves the technical problem that the traffic light is not matched with the actual traffic demand because the traditional traffic management can not make timely adjustment according to the real-time road congestion condition.
Description
Technical Field
The invention relates to the technical field of traffic flow control, in particular to a method and a system for intelligent road traffic flow control.
Background
The conventional road traffic flow control method has a certain disadvantage, and the conventional traffic control method often depends on a static manually-set or periodically updated traffic signal control scheme, so that the actual traffic condition change cannot be timely acquired and adapted; the traditional road congestion analysis method is mainly based on traffic flow data, cannot comprehensively consider the influence of factors such as vehicle types, headway and the like on road congestion, is relatively fixed in traditional traffic signal lamp timing scheme, cannot make timely adjustment according to real-time road congestion conditions, and causes mismatching of traffic lamps and actual traffic demands.
Therefore, there is some liftable space for road traffic control.
Disclosure of Invention
The application provides a smart road traffic flow management and control method and system, which aim to solve the technical problems that the traditional traffic management method cannot acquire and adapt to actual traffic condition changes in time, the road congestion analysis method is not comprehensive enough, the timing scheme is relatively fixed, and timely adjustment cannot be made according to real-time road congestion conditions, so that traffic lights and actual traffic demands are not matched.
In view of the above, the present application provides a method and a system for intelligent road traffic control.
In a first aspect of the disclosure, a method for controlling a traffic flow of a smart road is provided, where the method is applied to a traffic flow control device of a smart road, the device includes a data processing module, a traffic flow analysis module, and a control module, and the method includes: the device is accessed into a traffic monitoring system, a first road image and a second road image of a relative straight lane at a specified intersection are collected and transmitted to a data processing module, and image segmentation and vehicle type recognition processing are carried out on the road images to obtain a first vehicle type set and a second vehicle type set; acquiring a first road image sequence and a second road image sequence of a relative straight lane in a preset time window at the specified intersection, transmitting the first road image sequence and the second road image sequence to a data processing module, and recognizing the headway of the road image sequence to obtain a first headway and a second headway; the traffic flow analysis module is used for carrying out road congestion analysis according to the first vehicle head time interval and the second vehicle head time interval, obtaining a first road congestion level and a second road congestion level, and taking the larger road congestion level as the road congestion level; according to the vehicle type set of the lane corresponding to the road congestion level, comparing the vehicle type congestion comparison table, and obtaining a vehicle flow dredging blocking coefficient through statistical calculation; correcting the road congestion level according to the traffic flow dredging blocking coefficient to obtain a corrected road congestion level; collecting a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with a relative straight lane in the specified intersection, and calculating to obtain a comprehensive road congestion level by combining the correction road congestion levels; and carrying out a control scheme decision according to the comprehensive road congestion level to obtain a control scheme, wherein the control scheme comprises traffic light adjustment parameters, and the traffic lights in the designated intersection are controlled by the control module.
In another aspect of the disclosure, there is provided a smart road traffic control system, the system being applied to a smart road traffic control device, the device including a data processing module, a traffic analysis module, and a control module, the system being used in the above method, the system comprising: the road image acquisition unit is used for accessing the device into a traffic monitoring system, acquiring a first road image and a second road image of a corresponding straight lane at a specified intersection, transmitting the first road image and the second road image to the data processing module, and carrying out image segmentation and vehicle type recognition processing on the road images to obtain a first vehicle type set and a second vehicle type set; the image sequence acquisition unit is used for acquiring a first road image sequence and a second road image sequence of the relative straight lane in the preset time window at the specified intersection, transmitting the first road image sequence and the second road image sequence to the data processing module, and recognizing the headway of the road image sequence to obtain a first headway and a second headway; the road congestion analysis unit is used for carrying out road congestion analysis according to the first vehicle head time interval and the second vehicle head time interval through the vehicle flow analysis module, acquiring a first road congestion level and a second road congestion level, and taking the larger road congestion level as the road congestion level; the obstruction system acquisition unit is used for comparing the vehicle type set of the lane corresponding to the road congestion level with a vehicle type congestion comparison table, and obtaining a traffic flow dredging obstruction coefficient through statistical calculation; the congestion level correction unit is used for correcting the road congestion level according to the traffic flow dredging blocking coefficient to obtain a corrected road congestion level; the congestion level acquisition unit is used for acquiring a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with the corresponding straight lanes at the specified intersection, and calculating to obtain a comprehensive road congestion level by combining the correction road congestion levels; and the control scheme decision unit is used for making a control scheme decision according to the comprehensive road congestion level to obtain a control scheme, wherein the control scheme comprises traffic light adjustment parameters, and the traffic lights in the designated intersection are controlled by the control module.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
acquiring and processing a plurality of data sources, such as images, vehicle types, headway and the like, so as to obtain real-time accurate road traffic conditions and comprehensive road congestion levels; by analyzing and calculating parameters such as vehicle model collection, headway and the like, comprehensively considering the influence of factors such as different vehicle types, vehicle density, flow speed and the like on road congestion, and improving the accuracy and comprehensiveness of congestion evaluation; based on the comprehensive road congestion level and the traffic flow dredging blocking coefficient, a corresponding management and control scheme is formulated and embedded into the management and control module, so that dynamic traffic signal lamp adjustment aiming at real-time road conditions is realized, and the traffic smoothness and congestion conditions are optimized. By the intelligent road traffic flow management and control method, the road congestion degree can be estimated more accurately in real time, and a targeted management and control scheme is provided, so that the traffic congestion condition is effectively improved, and the efficiency and quality of road traffic operation are improved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow chart of a smart road traffic control method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an intelligent road vehicle flow control system according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a road image acquisition unit 10, an image sequence acquisition unit 20, a road congestion analysis unit 30, a congestion level correction unit 50, a congestion level acquisition unit 60 and a control scheme decision unit 70.
Detailed Description
The embodiment of the application solves the technical problems that the traditional traffic management method cannot acquire and adapt to actual traffic condition changes in time, the road congestion analysis method is not comprehensive enough, the timing scheme is relatively fixed, timely adjustment cannot be made according to real-time road congestion conditions, and traffic lights and actual traffic demands are not matched.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present application provides a method for controlling a traffic flow of an intelligent road, where the method is applied to a device for controlling a traffic flow of an intelligent road, and the device includes a data processing module, a traffic flow analysis module, and a control module, and the method includes:
The device is accessed into a traffic monitoring system, a first road image and a second road image of a relative straight lane at a specified intersection are collected and transmitted to a data processing module, and image segmentation and vehicle type recognition processing are carried out on the road images to obtain a first vehicle type set and a second vehicle type set;
the intelligent road traffic flow control method is applied to an intelligent road traffic flow control device, and the device comprises a data processing module, a traffic flow analysis module and a control module.
And establishing connection between the intelligent road vehicle flow control device and the traffic monitoring system through a related network protocol so as to acquire real-time traffic monitoring data. The method comprises the steps of installing cameras on relatively straight lanes in a designated intersection, acquiring a first road image and a second road image through a traffic monitoring system, capturing the images in the same time period and at the same visual angle, and transmitting the acquired first road image and second road image to a data processing module through a network. In the data processing module, a semantic segmentation method is adopted to segment the road image, therefore, in the training process, a historical road image set is used for training a road semantic segmentation path, and the identification information of the vehicle image is obtained through the road semantic segmentation path, so that a first vehicle type set and a second vehicle type set are obtained.
Further, image segmentation and vehicle type recognition processing are performed on the road image to obtain a first vehicle type set and a second vehicle type set, including:
training a road image segmentation path according to semantic segmentation in a data processing module; inputting the first road image and the second road image into the road image segmentation path, and performing image semantic segmentation to obtain a first segmentation result and a second segmentation result comprising a plurality of vehicle images; and obtaining the first vehicle type set and the second vehicle type set according to the identification information of the plurality of vehicle images in the first segmentation result and the second segmentation result.
In the data processing module, a road image segmentation path is trained through a machine learning method by using a historical road image set, and the path is mainly used for effectively segmenting the road image and distinguishing vehicle parts in the road image segmentation path.
The first road image and the second road image are input into a trained encoder part, the encoder extracts feature representation of the input image step by step, captures semantic information in the image, performs feature fusion operation, inputs feature vectors after feature fusion into a decoder part, and the decoder maps the features back to the original image size step by step through up-sampling operation. And performing thresholding operation on the image according to the segmentation result output by the decoder to obtain the segmentation result of the vehicle image, wherein the segmentation results are a first segmentation result and a second segmentation result, and comprise a plurality of areas of the vehicle image.
And traversing each vehicle image area of the first segmentation result and the second segmentation result, extracting identification information related to the vehicle, including vehicle type, brand, color and the like, for each vehicle image area, performing vehicle type identification operation based on the extracted vehicle identification information, for example, matching the vehicle identification information with a pre-trained vehicle type database based on a feature matching method, and obtaining a specific vehicle type of the vehicle. For the first segmentation result and the second segmentation result, the model information of each vehicle is added into a corresponding model set, so that a first model set and a second model set can be formed, wherein each set contains model information of all vehicles in a corresponding lane.
Further, training the road image segmentation path according to semantic segmentation includes:
according to the monitoring record data of the traffic monitoring system, extracting and obtaining a historical road image set; dividing and identifying vehicle images in road images in a historical road image set to obtain a historical segmentation result set; based on semantic segmentation, constructing an encoder and a decoder in a road image segmentation path; and training the encoder and the decoder by adopting the historical road image set and the historical segmentation result set until convergence to obtain the road image segmentation path.
Road images are extracted from the monitoring record data of the traffic monitoring system to form a set of historical road images, which are captured road images from different times and scenes, including different road conditions, traffic densities and vehicle types.
The road image is processed using an object detection algorithm that is capable of detecting and locating objects in the image and outputting their location and bounding box information to obtain vehicles therein. According to the result of target detection, the vehicle is divided into independent areas in each road image, and corresponding identification is added to each vehicle image, wherein the identification information comprises the position, the size and other key attributes of the vehicle. And integrating the obtained vehicle division and identification information for each historical road image to form a historical division result set, wherein the set comprises all vehicle areas in each image and the corresponding identification information.
Constructing an encoder and a decoder by adopting a deep learning model, such as a Convolutional Neural Network (CNN), wherein the encoder is mainly responsible for carrying out feature extraction and encoding operation on an input road image, and consists of a plurality of convolutional layers, pooling layers and activation functions, and the layer-by-layer overlapped convolutional operation gradually extracts low-level to high-level feature information of the image and represents the low-level to high-level feature information as a more abstract feature vector; the decoder is responsible for mapping the feature vector output by the encoder back to the original image space, recovering the detail and boundary information of the image, the structure of the decoder comprises upsampling, deconvolution, fusion layers and activation functions, and the decoder expands the feature vector into a feature map with the same size as the original image through layer-by-layer upsampling operation so as to reconstruct the detail and shape of the image.
The method comprises the steps of taking a historical road image set and a corresponding historical segmentation result set as training data, initializing network parameters of an encoder and a decoder, comparing an output result with a real segmentation result by using the historical road image as input, calculating a loss value by a loss function, updating the network parameters by using a back propagation algorithm to minimize the loss function, and adjusting the network parameters by using an optimization algorithm such as gradient descent to gradually optimize the network parameters. Through iterative training, network parameters are continuously updated, the change of loss values is observed, training is stopped when the model reaches a convergence state, and finally the obtained road image segmentation path can be used for segmenting a new road image so as to identify information of vehicles and other specific areas.
Acquiring a first road image sequence and a second road image sequence of a relative straight lane in a preset time window at the specified intersection, transmitting the first road image sequence and the second road image sequence to a data processing module, and recognizing the headway of the road image sequence to obtain a first headway and a second headway;
capturing an image sequence of a relative straight lane at a specified intersection through a camera, and continuously acquiring a first road image sequence and a second road image sequence according to the setting of a preset time window, so as to ensure that the image sequence contains enough frames and time intervals to cover the preset time window. And transmitting the image sequence to a data processing module, wherein in the data processing module, the received road image sequence is subjected to headway recognition, the headway is the time distance between vehicles and is used for evaluating the density and the safety of traffic flow, and the headway can be calculated by analyzing the position and the timestamp information of the vehicles in the road image sequence. And according to the identification result, obtaining a first vehicle head time interval and a second vehicle head time interval, wherein the vehicle head time interval refers to the time distance between vehicles on two continuous relatively straight lanes in the road image sequence.
Further, the step of performing headway recognition on the road image sequence comprises the following steps:
marking vehicles in the first road image sequence and the second road image sequence according to the first vehicle type set and the second vehicle type set; according to the marking information of the vehicles, calculating and obtaining time difference of the head passing through the target position of two adjacent vehicles in the first road image sequence and the second road image sequence, and obtaining a first head time interval set and a second head time interval set; and calculating the average value of the first vehicle head time interval set and the second vehicle head time interval set to obtain the first vehicle head time interval and the second vehicle head time interval.
And identifying and marking corresponding vehicles in the first road image sequence and the second road image sequence by using the obtained information of the first vehicle type set and the second vehicle type set through a target detection algorithm, and determining the position of each vehicle head in the images.
Determining a target position, for example, setting the target position as a fixed position on a road, such as a traffic sign, an intersection and the like, calculating the time difference that the heads of two adjacent vehicles pass through the target position in a first road image sequence and a second road image sequence according to the vehicle sign and the target position, obtaining a first vehicle head time interval and a second vehicle head time interval, traversing all vehicles in the graph sequence, and obtaining a first vehicle head time interval set and a second vehicle head time interval set.
Summing all time interval values in the first vehicle head time interval set, dividing the sum by the size of the set, namely the vehicle logarithm, to obtain an average value of the first vehicle head time interval, obtaining an average value of the second vehicle head time interval in the same way, and taking the average time interval values as the first vehicle head time interval and the second vehicle head time interval respectively for evaluating the average distance between vehicles, traffic flow characteristics and road congestion conditions.
The traffic flow analysis module is used for carrying out road congestion analysis according to the first vehicle head time interval and the second vehicle head time interval, obtaining a first road congestion level and a second road congestion level, and taking the larger road congestion level as the road congestion level;
further, by the traffic flow analysis module, road congestion analysis is performed according to the first vehicle head time interval and the second vehicle head time interval, and a first road congestion level and a second road congestion level are obtained, including:
the method comprises the steps of calling historical monitoring data of a traffic detection system, processing and obtaining a sample headway record, and evaluating and obtaining a sample road congestion level record; the method comprises the steps of adopting a sample headway record and a sample road congestion level record as training data, constructing and training a road congestion analysis path based on machine learning, and embedding the road congestion analysis path into the traffic flow analysis module; and inputting the first vehicle head time interval and the second vehicle head time interval into the vehicle flow analysis module for characteristic analysis, and obtaining the first road congestion level and the second road congestion level.
Accessing a traffic detection system, calling required historical monitoring data, calculating the time difference between adjacent vehicles passing through a target position, obtaining a sample headway record, setting a threshold according to the sample headway record and other related indexes such as speed, flow and the like, and evaluating and recording the congestion degree of a sample road.
The method comprises the steps of adopting a sample headway record and a sample road congestion level record as training data sets, constructing a road congestion analysis path based on a neural network, training the road congestion analysis path by using the training data sets, continuously optimizing parameters and weights of a model by using a training process of a machine learning algorithm to minimize the difference between a prediction result and an actual road congestion level until the required road congestion analysis path is obtained, and embedding the road congestion analysis path into a traffic flow analysis module.
Preparing the numerical values of the first vehicle head time interval and the second vehicle head time interval as input data, inputting the numerical values into a vehicle flow analysis module, and converting the first vehicle head time interval and the second vehicle head time interval into corresponding first road congestion level and second road congestion level according to a pre-constructed road congestion analysis path in the vehicle flow analysis module.
And comparing the first road congestion level with the second road congestion level, and taking the larger road congestion level as the road congestion level.
According to the vehicle type set of the lane corresponding to the road congestion level, comparing the vehicle type congestion comparison table, and obtaining a vehicle flow dredging blocking coefficient through statistical calculation;
further, according to the vehicle type set of the lane corresponding to the road congestion level, the vehicle type congestion comparison table is compared, and the traffic flow guiding and blocking coefficient is obtained through statistical calculation, including:
constructing a vehicle type congestion comparison table, wherein the vehicle type congestion comparison table comprises mapping relations of various vehicle types and various congestion coefficients, and the congestion coefficient of the mapping of the small car is 1; and according to the vehicle type set of the lane corresponding to the road congestion level, mapping and matching are carried out in the vehicle type congestion comparison table to obtain a congestion coefficient set, and an average value is calculated to obtain the traffic flow dredging obstruction coefficient.
Creating a vehicle type congestion comparison table, and recording mapping relations between different vehicle types and corresponding congestion coefficients, wherein the table contains information of various vehicle types and corresponding congestion coefficients, for example, a small car can be mapped into a congestion coefficient 1, other vehicle types possibly have different congestion coefficients, and the larger vehicle congestion coefficient is, for example, a large truck.
Determining a vehicle type set of a selected lane according to the road congestion level, matching each vehicle type from the vehicle type congestion comparison table by using the constructed vehicle type congestion comparison table, and finding out the congestion coefficient corresponding to each vehicle type according to the mapping relation in the comparison table. And (3) forming the obtained congestion coefficients into a congestion coefficient set, carrying out summation operation on each congestion coefficient in the congestion coefficient set, dividing the congestion coefficient set by the set size, namely the number of vehicle types, to calculate an average value, and taking the average value as a traffic flow dredging blocking coefficient.
Correcting the road congestion level according to the traffic flow dredging blocking coefficient to obtain a corrected road congestion level;
and correcting the original road congestion level by using the traffic flow dredging blocking coefficient, for example, calculating the product of the traffic flow dredging blocking coefficient and the road congestion level, and taking the calculation result as the corrected road congestion level, wherein the level reflects the actual road congestion condition taking the traffic flow dredging capability into consideration.
Collecting a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with a relative straight lane in the specified intersection, and calculating to obtain a comprehensive road congestion level by combining the correction road congestion levels;
Further, collecting a plurality of associated corrected road congestion levels on a plurality of lanes within a preset range of relative straight lane connection at the specified intersection, and calculating to obtain a comprehensive road congestion level in combination with the corrected road congestion levels, including:
collecting a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with a relatively straight lane in the specified intersection; according to the distances between the lanes and the designated intersection, weight distribution is carried out to obtain a plurality of weights, and the sum of the weights is 0.5; and adopting the plurality of weights to calculate the plurality of associated corrected road congestion levels and the corrected road congestion level in a weighting manner to obtain the comprehensive road congestion level, wherein the weight of the corrected road congestion level is 0.5.
Setting a preset range to cover a plurality of lanes connected with the relatively straight lanes, wherein the range comprises other lanes with direct association connectivity with the relatively straight lanes, disposing corresponding cameras on each lane within the determined preset range, and acquiring a plurality of association correction road congestion levels.
And determining the distance between each lane and the designated intersection through measurement, carrying out weight distribution on a plurality of lanes according to the distance, wherein the sum of all weights is 0.5, generating weight values corresponding to the lanes according to the weight distribution result, and each lane has a corresponding weight value to represent the importance of the lane in the comprehensive road congestion level.
And (3) using the multiple weights (sum is 0.5) of the multiple associated corrected road congestion levels obtained in the previous step and the weight (0.5) of the corrected road congestion level, carrying out weighted summation operation on the corrected road congestion level and the multiple associated corrected road congestion levels according to the corresponding weights to obtain a comprehensive road congestion level, and providing a more comprehensive and comprehensive index for describing road section congestion conditions.
And carrying out a control scheme decision according to the comprehensive road congestion level to obtain a control scheme, wherein the control scheme comprises traffic light adjustment parameters, and the traffic lights in the designated intersection are controlled by the control module.
Further, according to the comprehensive road congestion level, making a control scheme decision to obtain a control scheme, including:
according to historical traffic monitoring data of a designated intersection, processing and obtaining a sample comprehensive road congestion level set; according to historical traffic monitoring data of a designated intersection, according to different sample comprehensive road congestion levels, adjusting preset control time of traffic signal lamps to obtain a sample traffic lamp adjustment parameter set; taking the sample comprehensive road congestion level as a decision feature, adopting a sample comprehensive road congestion level set and a sample traffic light adjustment parameter set to construct a control scheme decision path, and embedding the control scheme decision path into the control module; and inputting the comprehensive road congestion level into a control scheme decision path to make a decision, and obtaining the control scheme.
Historical traffic monitoring data is collected from traffic monitoring systems of specified intersections, the data are grouped according to different comprehensive road congestion levels according to the historical traffic monitoring data, similar traffic conditions are classified into sample sets, and each sample set represents a specific comprehensive road congestion level. For each sample comprehensive road congestion level, adjusting the preset control time of the traffic signal lamp based on the analysis result of the historical data, for example, increasing or decreasing the duration of specific stages such as red light, green light and yellow light according to the characteristics and the needs of different comprehensive road congestion levels so as to optimize the traffic smoothness and reduce the congestion, and arranging the adjusted preset control time of the traffic signal lamp corresponding to each comprehensive road congestion level into a set to form a sample traffic light adjustment parameter set.
Based on the sample comprehensive road congestion level as decision feature, adopting the feature and the corresponding traffic light adjustment parameter to construct a decision path of the management and control scheme, wherein the decision path is trained based on historical data and the corresponding adjustment parameter, and can make decisions according to the real-time comprehensive road congestion level to guide the control of traffic signal lamps, thereby optimizing traffic flow and reducing congestion.
The constructed decision path is embedded into the management and control module to become a part of a management and control scheme, and the appropriate traffic signal lamp adjustment parameters can be determined and selected according to the decision path and the current comprehensive road congestion level in the management and control module.
The obtained comprehensive road congestion level is used as input data, the input data is used as a decision path of a management and control scheme, based on the pre-constructed decision path, the system can carry out decision process according to different conditions of the comprehensive road congestion level, and after decision, the management and control scheme is obtained, wherein the scheme comprises traffic management and control measures which are made for the current comprehensive road congestion level, and the traffic management and control measures comprise traffic light adjustment parameters.
The obtained control scheme is issued to a traffic signal lamp control system in the designated intersection through a control module, and the control module can correspondingly adjust the traffic signal lamps in the designated intersection according to the control strategy and parameters in the control scheme, for example, adjust the duration of red lights and green lights, change the signal timing of different lanes and the like. The control module can also continuously monitor traffic conditions in the appointed intersection, dynamically adjust the traffic signal lamp according to the real-time data, and realize real-time response, thereby ensuring traffic smoothness and safety.
In summary, the intelligent road traffic flow control method and system provided by the embodiment of the application have the following technical effects:
1. acquiring and processing a plurality of data sources, such as images, vehicle types, headway and the like, so as to obtain real-time accurate road traffic conditions and comprehensive road congestion levels;
2. by analyzing and calculating parameters such as vehicle model collection, headway and the like, comprehensively considering the influence of factors such as different vehicle types, vehicle density, flow speed and the like on road congestion, and improving the accuracy and comprehensiveness of congestion evaluation;
3. based on the comprehensive road congestion level and the traffic flow dredging blocking coefficient, a corresponding management and control scheme is formulated and embedded into the management and control module, so that dynamic traffic signal lamp adjustment aiming at real-time road conditions is realized, and the traffic smoothness and congestion conditions are optimized.
In summary, by the intelligent road traffic flow management and control method, the road congestion degree can be estimated more accurately and in real time, and a targeted management and control scheme is provided, so that the traffic congestion condition is effectively improved, and the efficiency and quality of road traffic operation are improved.
Based on the same inventive concept as the intelligent road traffic control method in the foregoing embodiments, as shown in fig. 2, the present application provides an intelligent road traffic control system, where the system is applied to an intelligent road traffic control device, and the device includes a data processing module, a traffic analysis module, and a control module, and the system includes:
The road image acquisition unit 10 is used for accessing the device into a traffic monitoring system, acquiring a first road image and a second road image of a relative straight lane at a specified intersection, transmitting the first road image and the second road image to the data processing module, and carrying out image segmentation and vehicle type recognition processing on the road images to obtain a first vehicle type set and a second vehicle type set;
the image sequence acquisition unit 20 is used for acquiring a first road image sequence and a second road image sequence of the relative straight traffic lane in the specified intersection within a preset time window, transmitting the first road image sequence and the second road image sequence to the data processing module, and recognizing the headway of the road image sequence to obtain a first headway and a second headway;
the road congestion analysis unit 30 is configured to perform road congestion analysis according to the first head time interval and the second head time interval through the traffic flow analysis module, obtain a first road congestion level and a second road congestion level, and use the larger road congestion level as the road congestion level;
a blocking coefficient obtaining unit 40, where the blocking coefficient obtaining unit 40 is configured to obtain a traffic flow guiding blocking coefficient by performing statistical calculation according to a vehicle type set of the lane corresponding to the road congestion level and a vehicle type congestion comparison table;
A congestion level correction unit 50, where the congestion level correction unit 50 is configured to correct the road congestion level according to the traffic flow congestion blocking coefficient, to obtain a corrected road congestion level;
the congestion level obtaining unit 60 is configured to collect a plurality of associated corrected road congestion levels on a plurality of lanes within a preset range of connection with respect to the straight lanes at the specified intersection, and calculate and obtain a comprehensive road congestion level in combination with the corrected road congestion levels;
the control scheme decision unit 70 is configured to perform a control scheme decision according to the comprehensive road congestion level, so as to obtain a control scheme, where the control scheme includes traffic light adjustment parameters, and the control module is configured to control traffic lights in the specified intersection.
Further, the road image acquisition unit 10 further comprises the following operation steps:
training a road image segmentation path according to semantic segmentation in a data processing module;
inputting the first road image and the second road image into the road image segmentation path, and performing image semantic segmentation to obtain a first segmentation result and a second segmentation result comprising a plurality of vehicle images;
And obtaining the first vehicle type set and the second vehicle type set according to the identification information of the plurality of vehicle images in the first segmentation result and the second segmentation result.
Further, the road image acquisition unit 10 further comprises the following operation steps:
according to the monitoring record data of the traffic monitoring system, extracting and obtaining a historical road image set;
dividing and identifying vehicle images in road images in a historical road image set to obtain a historical segmentation result set;
based on semantic segmentation, constructing an encoder and a decoder in a road image segmentation path;
and training the encoder and the decoder by adopting the historical road image set and the historical segmentation result set until convergence to obtain the road image segmentation path.
Further, the image sequence acquisition unit 20 further comprises the following operation steps:
marking vehicles in the first road image sequence and the second road image sequence according to the first vehicle type set and the second vehicle type set;
according to the marking information of the vehicles, calculating and obtaining time difference of the head passing through the target position of two adjacent vehicles in the first road image sequence and the second road image sequence, and obtaining a first head time interval set and a second head time interval set;
And calculating the average value of the first vehicle head time interval set and the second vehicle head time interval set to obtain the first vehicle head time interval and the second vehicle head time interval.
Further, the road congestion analysis unit 30 further includes the following operation steps:
the method comprises the steps of calling historical monitoring data of a traffic detection system, processing and obtaining a sample headway record, and evaluating and obtaining a sample road congestion level record;
the method comprises the steps of adopting a sample headway record and a sample road congestion level record as training data, constructing and training a road congestion analysis path based on machine learning, and embedding the road congestion analysis path into the traffic flow analysis module;
and inputting the first vehicle head time interval and the second vehicle head time interval into the vehicle flow analysis module for characteristic analysis, and obtaining the first road congestion level and the second road congestion level.
Further, the blocking coefficient obtaining unit 40 further includes the following operation steps:
constructing a vehicle type congestion comparison table, wherein the vehicle type congestion comparison table comprises mapping relations of various vehicle types and various congestion coefficients, and the congestion coefficient of the mapping of the small car is 1;
and according to the vehicle type set of the lane corresponding to the road congestion level, mapping and matching are carried out in the vehicle type congestion comparison table to obtain a congestion coefficient set, and an average value is calculated to obtain the traffic flow dredging obstruction coefficient.
Further, the congestion level obtaining unit 60 further includes the following operation steps:
collecting a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with a relatively straight lane in the specified intersection;
according to the distances between the lanes and the designated intersection, weight distribution is carried out to obtain a plurality of weights, and the sum of the weights is 0.5;
and adopting the plurality of weights to calculate the plurality of associated corrected road congestion levels and the corrected road congestion level in a weighting manner to obtain the comprehensive road congestion level, wherein the weight of the corrected road congestion level is 0.5.
Further, the control scheme decision unit 70 further comprises the following operation steps:
according to historical traffic monitoring data of a designated intersection, processing and obtaining a sample comprehensive road congestion level set;
according to historical traffic monitoring data of a designated intersection, according to different sample comprehensive road congestion levels, adjusting preset control time of traffic signal lamps to obtain a sample traffic lamp adjustment parameter set;
taking the sample comprehensive road congestion level as a decision feature, adopting a sample comprehensive road congestion level set and a sample traffic light adjustment parameter set to construct a control scheme decision path, and embedding the control scheme decision path into the control module;
And inputting the comprehensive road congestion level into a control scheme decision path to make a decision, and obtaining the control scheme.
In the foregoing detailed description of a method for controlling intelligent road traffic, those skilled in the art can clearly understand that the method and system for controlling intelligent road traffic in this embodiment, for the apparatus disclosed in the embodiments, the description is relatively simple, and the relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. The intelligent road traffic flow control method is applied to an intelligent road traffic flow control device, and the device comprises a data processing module, a traffic flow analysis module and a control module, and comprises the following steps:
The device is accessed into a traffic monitoring system, a first road image and a second road image of a relative straight lane at a specified intersection are collected and transmitted to a data processing module, and image segmentation and vehicle type recognition processing are carried out on the road images to obtain a first vehicle type set and a second vehicle type set;
acquiring a first road image sequence and a second road image sequence of a relative straight lane in a preset time window at the specified intersection, transmitting the first road image sequence and the second road image sequence to a data processing module, and recognizing the headway of the road image sequence to obtain a first headway and a second headway;
the traffic flow analysis module is used for carrying out road congestion analysis according to the first vehicle head time interval and the second vehicle head time interval, obtaining a first road congestion level and a second road congestion level, and taking the larger road congestion level as the road congestion level;
according to the vehicle type set of the lane corresponding to the road congestion level, comparing the vehicle type congestion comparison table, and obtaining a vehicle flow dredging blocking coefficient through statistical calculation;
correcting the road congestion level according to the traffic flow dredging blocking coefficient to obtain a corrected road congestion level;
collecting a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with a relative straight lane in the specified intersection, and calculating to obtain a comprehensive road congestion level by combining the correction road congestion levels;
According to the comprehensive road congestion level, a control scheme decision is made to obtain a control scheme, wherein the control scheme comprises traffic light adjustment parameters, and traffic lights in the designated intersection are controlled through the control module;
the method for acquiring the multiple associated correction road congestion levels on multiple lanes in a preset range of relative straight lane connection at the specified intersection, and calculating to obtain the comprehensive road congestion level by combining the correction road congestion levels comprises the following steps:
collecting a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with a relatively straight lane in the specified intersection;
according to the distances between the lanes and the designated intersection, weight distribution is carried out to obtain a plurality of weights, and the sum of the weights is 0.5;
the multiple weight values are adopted to calculate the multiple associated correction road congestion levels and the correction road congestion levels in a weighting mode, and the comprehensive road congestion level is obtained, wherein the weight of the correction road congestion level is 0.5;
and carrying out control scheme decision according to the comprehensive road congestion level to obtain a control scheme, wherein the method comprises the following steps of:
according to historical traffic monitoring data of a designated intersection, processing and obtaining a sample comprehensive road congestion level set;
According to historical traffic monitoring data of a designated intersection, according to different sample comprehensive road congestion levels, adjusting preset control time of traffic signal lamps to obtain a sample traffic lamp adjustment parameter set;
taking the sample comprehensive road congestion level as a decision feature, adopting a sample comprehensive road congestion level set and a sample traffic light adjustment parameter set to construct a control scheme decision path, and embedding the control scheme decision path into the control module;
and inputting the comprehensive road congestion level into a control scheme decision path to make a decision, and obtaining the control scheme.
2. The method of claim 1, wherein performing image segmentation and model recognition processing on the road image to obtain a first model set and a second model set, comprises:
training a road image segmentation path according to semantic segmentation in a data processing module;
inputting the first road image and the second road image into the road image segmentation path, and performing image semantic segmentation to obtain a first segmentation result and a second segmentation result comprising a plurality of vehicle images;
and obtaining the first vehicle type set and the second vehicle type set according to the identification information of the plurality of vehicle images in the first segmentation result and the second segmentation result.
3. The method according to claim 2, characterized in that the method comprises:
according to the monitoring record data of the traffic monitoring system, extracting and obtaining a historical road image set;
dividing and identifying vehicle images in road images in a historical road image set to obtain a historical segmentation result set;
based on semantic segmentation, constructing an encoder and a decoder in a road image segmentation path;
and training the encoder and the decoder by adopting the historical road image set and the historical segmentation result set until convergence to obtain the road image segmentation path.
4. The method of claim 1, wherein performing headway recognition on the sequence of road images comprises:
marking vehicles in the first road image sequence and the second road image sequence according to the first vehicle type set and the second vehicle type set;
according to the marking information of the vehicles, calculating and obtaining time difference of the head passing through the target position of two adjacent vehicles in the first road image sequence and the second road image sequence, and obtaining a first head time interval set and a second head time interval set;
and calculating the average value of the first vehicle head time interval set and the second vehicle head time interval set to obtain the first vehicle head time interval and the second vehicle head time interval.
5. The method of claim 1, wherein the obtaining, by the traffic flow analysis module, the first road congestion level and the second road congestion level according to the first headway and the second headway comprises:
the method comprises the steps of calling historical monitoring data of a traffic detection system, processing and obtaining a sample headway record, and evaluating and obtaining a sample road congestion level record;
the method comprises the steps of adopting a sample headway record and a sample road congestion level record as training data, constructing and training a road congestion analysis path based on machine learning, and embedding the road congestion analysis path into the traffic flow analysis module;
and inputting the first vehicle head time interval and the second vehicle head time interval into the vehicle flow analysis module for characteristic analysis, and obtaining the first road congestion level and the second road congestion level.
6. The method according to claim 1, wherein the obtaining the traffic flow guiding obstruction coefficient by statistical calculation according to the vehicle type set of the lane corresponding to the road congestion level against the vehicle type congestion comparison table comprises:
constructing a vehicle type congestion comparison table, wherein the vehicle type congestion comparison table comprises mapping relations of various vehicle types and various congestion coefficients, and the congestion coefficient of the mapping of the small car is 1;
And according to the vehicle type set of the lane corresponding to the road congestion level, mapping and matching are carried out in the vehicle type congestion comparison table to obtain a congestion coefficient set, and an average value is calculated to obtain the traffic flow dredging obstruction coefficient.
7. A smart road traffic control system, wherein the system is applied to a smart road traffic control device, the device comprising a data processing module, a traffic analysis module and a control module for implementing a smart road traffic control method according to any one of claims 1-6, comprising:
the road image acquisition unit is used for accessing the device into a traffic monitoring system, acquiring a first road image and a second road image of a corresponding straight lane at a specified intersection, transmitting the first road image and the second road image to the data processing module, and carrying out image segmentation and vehicle type recognition processing on the road images to obtain a first vehicle type set and a second vehicle type set;
the image sequence acquisition unit is used for acquiring a first road image sequence and a second road image sequence of the relative straight lane in the preset time window at the specified intersection, transmitting the first road image sequence and the second road image sequence to the data processing module, and recognizing the headway of the road image sequence to obtain a first headway and a second headway;
The road congestion analysis unit is used for carrying out road congestion analysis according to the first vehicle head time interval and the second vehicle head time interval through the vehicle flow analysis module, acquiring a first road congestion level and a second road congestion level, and taking the larger road congestion level as the road congestion level;
the obstruction coefficient acquisition unit is used for comparing the vehicle type congestion comparison table with the vehicle type set of the lane corresponding to the road congestion level, and obtaining a traffic flow dredging obstruction coefficient through statistical calculation;
the congestion level correction unit is used for correcting the road congestion level according to the traffic flow dredging blocking coefficient to obtain a corrected road congestion level;
the congestion level acquisition unit is used for acquiring a plurality of associated correction road congestion levels on a plurality of lanes in a preset range connected with the corresponding straight lanes at the specified intersection, and calculating to obtain a comprehensive road congestion level by combining the correction road congestion levels;
and the control scheme decision unit is used for making a control scheme decision according to the comprehensive road congestion level to obtain a control scheme, wherein the control scheme comprises traffic light adjustment parameters, and the traffic lights in the designated intersection are controlled by the control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311373397.4A CN117116065B (en) | 2023-10-23 | 2023-10-23 | Intelligent road traffic flow control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311373397.4A CN117116065B (en) | 2023-10-23 | 2023-10-23 | Intelligent road traffic flow control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117116065A CN117116065A (en) | 2023-11-24 |
| CN117116065B true CN117116065B (en) | 2024-02-02 |
Family
ID=88800533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311373397.4A Active CN117116065B (en) | 2023-10-23 | 2023-10-23 | Intelligent road traffic flow control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117116065B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179615A (en) * | 2019-12-31 | 2020-05-19 | 宁波宁工交通工程设计咨询有限公司 | Traffic sign information indicating system and method |
| CN111462484A (en) * | 2020-03-31 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Congestion state determination method, device, equipment and computer readable storage medium |
| CN114639243A (en) * | 2022-03-31 | 2022-06-17 | 四川九洲视讯科技有限责任公司 | Intelligent traffic prediction and decision method, system and readable storage medium |
| CN114999161A (en) * | 2022-07-29 | 2022-09-02 | 河北博士林科技开发有限公司 | Be used for intelligent traffic jam edge management system |
| CN115762195A (en) * | 2022-11-09 | 2023-03-07 | 宁波宁工交通工程设计咨询有限公司 | Dynamic green wave signal control method, system, device and storage medium |
| CN116229707A (en) * | 2022-12-15 | 2023-06-06 | 智慧互通科技股份有限公司 | Congestion backtracking-based control method and system |
| CN116704771A (en) * | 2023-06-21 | 2023-09-05 | 中咨数据有限公司 | Real-time positioning command processing system based on traffic information of congested road section |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9076332B2 (en) * | 2006-10-19 | 2015-07-07 | Makor Issues And Rights Ltd. | Multi-objective optimization for real time traffic light control and navigation systems for urban saturated networks |
| CN112561146B (en) * | 2020-12-08 | 2023-04-18 | 哈尔滨工程大学 | Large-scale real-time traffic flow prediction method based on fuzzy logic and depth LSTM |
-
2023
- 2023-10-23 CN CN202311373397.4A patent/CN117116065B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179615A (en) * | 2019-12-31 | 2020-05-19 | 宁波宁工交通工程设计咨询有限公司 | Traffic sign information indicating system and method |
| CN111462484A (en) * | 2020-03-31 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Congestion state determination method, device, equipment and computer readable storage medium |
| CN114639243A (en) * | 2022-03-31 | 2022-06-17 | 四川九洲视讯科技有限责任公司 | Intelligent traffic prediction and decision method, system and readable storage medium |
| CN114999161A (en) * | 2022-07-29 | 2022-09-02 | 河北博士林科技开发有限公司 | Be used for intelligent traffic jam edge management system |
| CN115762195A (en) * | 2022-11-09 | 2023-03-07 | 宁波宁工交通工程设计咨询有限公司 | Dynamic green wave signal control method, system, device and storage medium |
| CN116229707A (en) * | 2022-12-15 | 2023-06-06 | 智慧互通科技股份有限公司 | Congestion backtracking-based control method and system |
| CN116704771A (en) * | 2023-06-21 | 2023-09-05 | 中咨数据有限公司 | Real-time positioning command processing system based on traffic information of congested road section |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117116065A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596129B (en) | Vehicle line-crossing detection method based on intelligent video analysis technology | |
| JP6570731B2 (en) | Method and system for calculating passenger congestion | |
| CN106599792B (en) | Method for detecting hand driving violation behavior | |
| CN110866430B (en) | License plate recognition method and device | |
| CN104134222A (en) | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion | |
| CN115995063A (en) | Work vehicle detection and tracking method and system | |
| CN113160575A (en) | Traffic violation detection method and system for non-motor vehicles and drivers | |
| CN117173913B (en) | Traffic control method and system based on traffic flow analysis at different time periods | |
| CN113034378B (en) | Method for distinguishing electric automobile from fuel automobile | |
| CN113313031B (en) | Deep learning-based lane line detection and vehicle transverse positioning method | |
| CN116030396B (en) | Accurate segmentation method for video structured extraction | |
| CN109034211A (en) | A kind of parking space state detection method based on machine learning | |
| CN113408550B (en) | Intelligent weighing management system based on image processing | |
| CN116901089B (en) | Multi-angle vision distance robot control method and system | |
| CN114332781A (en) | Intelligent license plate recognition method and system based on deep learning | |
| CN117116065B (en) | Intelligent road traffic flow control method and system | |
| CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
| CN116109986A (en) | Vehicle track extraction method based on laser radar and video technology complementation | |
| CN117593717B (en) | Lane tracking method and system based on deep learning | |
| CN110909670A (en) | Unstructured road identification method | |
| CN112395956A (en) | Method and system for detecting passable area facing complex environment | |
| CN114742975B (en) | Vehicle-mounted image rail curve modeling method | |
| CN113033352B (en) | Real-time mobile traffic violation detection method based on combination of improved target semantic segmentation and target detection model | |
| CN113449663B (en) | Collaborative intelligent security method and device based on polymorphic fitting | |
| CN116229409A (en) | Crosswalk line detection method introducing global features and multi-scale features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |