CN107730890B - Intelligent transportation method based on traffic flow speed prediction in real-time scene - Google Patents
Intelligent transportation method based on traffic flow speed prediction in real-time scene Download PDFInfo
- Publication number
- CN107730890B CN107730890B CN201711095733.8A CN201711095733A CN107730890B CN 107730890 B CN107730890 B CN 107730890B CN 201711095733 A CN201711095733 A CN 201711095733A CN 107730890 B CN107730890 B CN 107730890B
- Authority
- CN
- China
- Prior art keywords
- traffic
- light control
- comprehensive information
- information
- traffic light
- 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
Images
Classifications
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Abstract
The invention discloses an intelligent traffic method based on implementation of scene leaving stream speed prediction, which comprises the following steps: collecting video information of a traffic lane intersection; analyzing the traffic comprehensive information according to the collected video information, and loading the traffic comprehensive information into historical traffic comprehensive information; constructing a traffic model according to the historical traffic comprehensive information, and predicting the predicted traffic comprehensive information of the traffic crossing at a node of a predetermined time in the future; generating a traffic light control signal of the traffic crossing according to the predicted traffic comprehensive information; and controlling the execution of the traffic lights at the traffic crossing according to the traffic light control signals. The traffic light monitoring system acquires traffic data through the existing monitoring system, formulates a traffic light control scheme of a future time point through modeling, and timely corrects the traffic light control scheme, so that the traffic light is controlled by a simple structure, the timeliness is high, the traffic control effect is good, the real-time matching degree is high, and the congestion condition of a traffic crossing can be effectively avoided.
Description
Technical Field
The invention relates to the field of traffic control, in particular to an intelligent traffic method based on traffic flow speed prediction in a real-time scene.
Background
With the high-speed development of national economy and the acceleration of urbanization process, the motor vehicle ownership and road traffic volume in China are increased rapidly. Especially in large cities, traffic congestion and congestion, and the increase of traffic accidents and the aggravation of environmental pollution caused by the traffic congestion and congestion are one of the very serious problems facing cities in China, and the traffic congestion and the aggravation of environmental pollution are the bottleneck problems of further development of national economy. Based on the above, the intelligent traffic system has come and its essence is to utilize the existing traffic infrastructure and potential to the maximum extent and guide reasonable traffic behaviors through the effective application of information technology. The detection of the speed of the traffic flow and the detection of real-time traffic scenes are the basis and the core of an intelligent traffic system. There are various methods for detecting the speed of a vehicle, such as: electromagnetic induction device methods, acoustic detection system methods, laser radar detection methods, and ultrasonic detection methods of traffic information. They all have the characteristics of high performance, high precision, small volume, convenient operation and the like. However, in practice, or because the speed and type of the vehicle in the process of advancing are constantly changed, the reflected signal is unstable, and the measurement error is large; or because the cost is high, the structure construction is needed, the road surface is damaged, and the like.
With the development of computer technology, image processing technology, artificial intelligence and mode recognition, automatic control technology, electronic sensor technology and other technologies, the intelligent traffic capable of effectively detecting and predicting the traffic flow speed in real-time scene becomes possible. The use of image detection methods has many advantages: for example, the coverage of detection is large, and the detected parameters are many; the installation is simple, the maintenance is convenient, the pavement is not damaged, and the construction cost is low; the application range is wide, and the method can be applied to road sections, intersections and the like; and all-weather detection can be realized.
At present, there are two main methods of the existing image detection technology in the aspect of detecting the speed of a traffic flow by intelligent traffic, which are based on time information in an image sequence or spatial information in the image sequence, such as:
1) in the optical flow method, when an object moves, luminance information (optical flow) of the corresponding object on an image also moves accordingly. Therefore, the size and the direction of the motion of each pixel point can be calculated according to several adjacent frames of images in time, so that the motion field is used for distinguishing the background and the motion target. Most computational methods are quite complex and computationally expensive, depending on the accuracy of the optical flow estimation, so that real-time detection is difficult to achieve unless special hardware support is available.
2) Background subtraction, which is to compare the gray value of the image pixel in the real-time video stream with the corresponding value in the video background model stored in advance or obtained in real time, and the pixel which does not meet the requirement is considered as a motion pixel, which is the most commonly used motion detection method in video monitoring. This approach is too sensitive to environmental changes caused by lighting and external conditions, often falsely detecting shadows of moving objects as part of itself.
The patent numbers are: the patent of CN201520661277.9 (published: 2016.01.06) discloses a traffic flow detection system based on monitoring image analysis, which comprises an image acquisition end, a client, a server end and a traffic processing system, wherein the acquisition end is suspended at a traffic channel and a traffic intersection on a road traffic network, acquires road vehicle picture information and sends the road vehicle picture information to the client; the client receives the vehicle picture information, analyzes the vehicle comprehensive information and sends the vehicle comprehensive information to the server and the traffic processing system, wherein the vehicle comprehensive information comprises vehicle types, vehicle numbers, vehicle flows and vehicle speeds. The server side generates a control signal for controlling a traffic signal lamp according to the vehicle comprehensive information and sends the control signal to a traffic processing system; the traffic processing system controls the traffic signal lamp according to the control signal so as to dredge road traffic; and the traffic processing system sends an alarm to the server side when judging the traffic jam according to the vehicle comprehensive information. The system discloses a scheme for controlling the traffic light by monitoring video data, but the system needs to calculate the traffic data in real time, so that the calculation amount is huge, and the power consumption of corresponding calculation equipment is high; meanwhile, the patent does not specifically disclose a traffic light control scheme, and has obvious defects in the aspect of efficiently controlling traffic signal lights.
Disclosure of Invention
The invention aims to: aiming at the existing problems, the intelligent traffic method based on traffic flow speed prediction under a real-time scene is provided, and the problem of reasonable control of traffic lights on each road based on video images is solved through a small calculated amount.
In order to solve all or part of the problems, the technical scheme adopted by the invention is as follows:
an intelligent transportation method based on vehicle speed prediction of a traffic flow in an implementation scene comprises the following steps:
s100: collecting video information of a traffic lane intersection;
s200: analyzing traffic comprehensive information according to the collected video information, wherein the traffic comprehensive information comprises traffic flow and vehicle speed; preferably, the method also comprises the vehicle type;
s300: loading the traffic comprehensive information into historical traffic comprehensive information;
s400: constructing a traffic model according to the historical traffic comprehensive information, and predicting the predicted traffic comprehensive information of the traffic crossing at a node in the future preset time;
s500: generating a traffic light control signal of the traffic crossing according to the predicted traffic comprehensive information;
s600: and controlling the execution of the traffic light at the traffic crossing according to the traffic light control signal.
According to the scheme, the comprehensive traffic information is obtained through video acquisition and further processing, the scheme of obtaining the comprehensive traffic information through a simple structure is realized, and the condition that the ground induction coil or other inductors are used for destroying/reforming the surrounding environment of the road surface/road is avoided. Through modeling of historical traffic data, prediction of traffic comprehensive information of the traffic crossing at a future time node is achieved, and therefore a traffic light control scheme suitable for the future time node is formulated. According to the scheme, the traffic lights at the traffic crossing are reasonably controlled through historical traffic data, and the problems of manpower cost needing manual control and manual multi-crossing combined control which cannot be completed are solved.
Further, the step S400 specifically includes:
s4001: receiving the historical traffic comprehensive information, and constructing a traffic model according to the historical traffic comprehensive information; whether the current time point is a preset time node is also judged, if yes, S4002 is executed, and if not, S4004 is executed;
s4002: acquiring real-time traffic comprehensive information according to the method of S100-S200;
s4003: correcting the traffic model according to the real-time traffic comprehensive information;
s4004: and predicting the predicted traffic comprehensive information of the traffic crossing at a node of a future preset time according to the traffic model.
According to the scheme, the real-time traffic comprehensive information is acquired at the preset time node, the traffic model is further corrected, and the matching degree of the traffic light control rule and the real-time environment is guaranteed. Meanwhile, a real-time correction mode instead of a modeling mode is adopted, so that the calculation amount of prediction is reduced, and the timeliness of prediction is greatly improved.
Preferably, in S4001, the traffic model is constructed by a regression analysis method.
The traffic model construction process based on the scheme does not need huge data calculation amount, so that the timeliness of prediction is guaranteed; meanwhile, the goodness of fit between the traffic model and the actual scene is ensured, and therefore the prediction accuracy is improved.
Preferably, in S300, the traffic integration information is loaded into the historical traffic integration information in a circular storage mode. When the space for storing the historical traffic comprehensive information is full, the loaded new traffic comprehensive information is automatically covered in the original historical traffic comprehensive information, the traffic comprehensive information stored firstly is still insufficient in space, the traffic comprehensive information stored firstly is continuously covered, and the like.
According to the scheme, on one hand, the modeling data can be guaranteed to be the data closest to the real-time condition, and on the other hand, the storage of the traffic comprehensive information is met without configuring a huge data storage space, so that the structure is simplified, and the stability of the system is improved.
Preferably, the preset time node is: time points set at predetermined time intervals.
By the scheme, the traffic model is corrected once at intervals of preset time, so that on one hand, huge calculation amount caused by real-time correction is avoided, and the timeliness of prediction is improved; on the other hand, the matching degree of the traffic model and the real-time traffic road condition is also met, and the requirement of intelligent traffic control is met.
The predetermined time interval may be set as appropriate according to a specific use scenario, or may be set with reference to a set hardware processing speed.
Further, before S100, the method further includes:
s001: waiting for receiving a scene selection signal in real time; if a scene selection signal is received, executing S101, otherwise, executing S100;
s101: and selecting a preset traffic light control signal according to the scene selection signal, and executing S600.
The scene selection signal is: presetting corresponding traffic light control signals aiming at signals corresponding to a plurality of preset special scenes and also aiming at the special scenes; namely, a special scene is selected, a scene selection signal for selecting the special scene is sent out, and then a traffic light control signal corresponding to the special scene is selected.
The scheme comprehensively considers the application of the road in a special use scene, and generates a traffic light control signal corresponding to the special scene through presetting a corresponding traffic light control rule to complete the control of the corresponding traffic light. The scheme reliably solves the temporary calling problem of the corresponding scene by formulating the corresponding rule in advance and executing the rule with high priority during execution.
Further, after executing S600, the above S101 further includes: waiting for receiving a scene cancel signal in real time; if the scene cancel signal is received, S100 is performed.
By the scheme, timely conversion between the traffic light control rules of the normal scene after the special scene environment is eliminated is realized, so that the continuity and the real-time adaptability of traffic control are ensured.
Further, the step S500 is specifically:
s5001: generating traffic light control sub-signals in the relative direction according to traffic flow information in the relative direction contained in the predicted traffic comprehensive information; and in parallel
S5002: generating traffic light control sub-signals in the left-turning direction according to traffic flow information in the left-turning direction contained in the predicted traffic comprehensive information;
s5003: and combining the traffic light control sub-signals in the opposite direction and the traffic light control sub-signals in the left-turning direction to generate traffic light control signals.
The relative directions are from west to east and from east to west, or from south to north and from north to south, or from the front to the corresponding horizontal direction. The above-mentioned left turn is a turn from east to south, from south to west, from west to north or from north to east, or a turn on the corresponding level.
According to the scheme, corresponding traffic control rules are formulated respectively for traffic flows which are driven in a straight line and in a turning manner, on one hand, the formulation of the traffic control rules of a universal traffic intersection is integrally solved, on the other hand, the calculation is respectively carried out in all directions, the complexity of comprehensive calculation can be effectively reduced, and the accuracy and timeliness of calculation results are improved.
Preferably, the traffic flow information in the opposite direction includes: the traffic flow in the opposite direction and the traffic flow ratio in the opposite direction.
The reasonability of traffic light control can be improved by considering the traffic flow proportion in the opposite direction. For example, if the traffic flow from east to west is N and the traffic flow from west to east is M, the ratio of the west release time to the east release time is preferably 1 to M: and N is added. Therefore, the accumulation degree of the opposite traffic flows at the road junction can be effectively ensured within a reasonable range.
Further, the traffic light control sub-signals (i.e. the traffic light control sub-signals in the opposite direction and the traffic light control sub-signals in the left-turn direction) are provided with initial values, and the generation rule of each traffic light control sub-signal is as follows: and adjusting according to a preset rule on the basis of the initial value.
By adopting the scheme, the traffic light can normally run while the adjustment scheme is not started through corresponding adjustment on the initial value; meanwhile, through the adjustment of the preset rule, the system of the traffic light control rule is serious, the overall management is convenient, and the irregularity of the traffic light control sub-signals of each road in the process of adjusting according to the traffic flow is avoided.
Preferably, the predetermined rule is: the adjustment is made in multiples of a predetermined length of time.
The management of traffic light control is facilitated by performing integer multiplication/subtraction of the predetermined time length on the basis of the initial value, and meanwhile, the effectiveness of adjustment on the basis of the initial value is increased. If the initial value is K seconds, the integral multiple adjustment is regulated on the basis of 5 seconds, such as (K-5) seconds, (K + 10) seconds and the like, so that the condition that the score is calculated according to the real-time quantity or the adjustment quantity without practical significance is avoided.
Further, each traffic light control sub-signal is provided with a preset threshold value, and each generated traffic light control sub-signal is in the preset threshold value.
According to the scheme, the threshold value is set, so that the vehicles on all roads can run together within the preset time, and when the traffic volume in the direction with more traffic flow is ensured as much as possible, the condition that the traffic volume in one direction is more, so that the traffic of the vehicles on other roads is influenced, and the vehicles on other roads are accumulated is avoided.
In order to solve all or part of the problems, the invention provides an intelligent traffic system based on traffic flow speed prediction in a real-time scene, which comprises the following components:
the image acquisition module is used for acquiring video information of a traffic crossing;
the vehicle detection module is used for analyzing traffic comprehensive information according to the video information acquired by the image acquisition module, wherein the traffic comprehensive information comprises traffic flow and vehicle speed;
the data storage module is used for storing the traffic comprehensive information output by the vehicle retrieval module and generating historical traffic comprehensive information;
the model building module is used for building a traffic model according to the historical traffic comprehensive information generated by the data storage module and outputting predicted traffic comprehensive information of the traffic crossing at a node in a future preset time according to the traffic model;
the traffic strategy module is used for generating a traffic light control signal of the traffic crossing according to the predicted traffic comprehensive information output by the model prediction module;
and the traffic control module is used for controlling the execution of the corresponding traffic lights according to the traffic light control signals generated by the traffic strategy module.
Further, the above system further comprises: the model correction module is used for controlling the image acquisition module to acquire the video data of the traffic intersection at a preset time point and controlling the vehicle detection module to analyze real-time traffic comprehensive information according to the video data acquired by the image acquisition module; correcting the traffic model constructed by the model construction module according to the real-time traffic comprehensive information;
the model building module is also used for correcting the predicted traffic comprehensive information according to the correction of the traffic model by the model correction module, so that the correction of traffic light control signals is realized.
Further, the preset time node is: time points set at predetermined time intervals.
Further, the system further comprises: and the scene confirmation module is used for receiving a scene selection signal, selecting a preset traffic light control signal according to the scene selection signal, setting the selected preset traffic light control signal to be the highest priority, and sending the selected preset traffic light control signal to the traffic control module, so that the traffic control module controls the execution of the traffic light according to the selected preset traffic light control signal.
Further, the scene confirmation module is further configured to: and receiving a scene cancel signal, and withdrawing the traffic light control signal sent to the traffic control module so that the traffic control module receives the traffic light control signal sent by the traffic strategy module.
Further, the traffic policy module includes:
and the opposite traffic strategy unit is used for outputting the following information according to the model construction module: the traffic flow information in the relative direction contained in the predicted traffic comprehensive information generates traffic light control sub-signals in the relative direction;
and the steering traffic strategy unit is used for outputting the following data according to the model construction module: the traffic flow information in the left turning direction contained in the predicted traffic comprehensive information generates traffic light control sub-signals in the left turning direction;
a strategy combination unit, which is used for generating the opposite traffic strategy unit: the traffic light control sub-signal of the opposite direction and the steering traffic strategy unit generate: and the traffic light control sub-signals in the left turning direction are combined to generate traffic light control signals.
Further, the vehicle flow rate in the opposite direction is proportional to the vehicle flow rate in the opposite direction.
Further, each of the traffic light control sub-signals has an initial value, and the generation rules of the traffic light control sub-signals generated by the opposite traffic strategy unit and the turning traffic strategy unit (that is, the opposite traffic strategy unit generates the traffic light control sub-signals in the opposite direction, and the turning traffic strategy unit generates the traffic light control sub-signals in the left-turning direction) are as follows: and adjusting according to a preset rule on the basis of the initial value.
Further, the predetermined rule is: the adjustment is made in multiples of a predetermined length of time.
Furthermore, the opposite traffic strategy unit and the steering traffic strategy unit are provided with preset thresholds, and the two strategy units adjust corresponding traffic light control sub-signals within the preset thresholds.
Further, the model building module builds the traffic model through a regression analysis method.
Preferably, the data storage module stores the traffic information in a cyclic storage mode. When the space for storing the historical traffic comprehensive information is full, the stored new traffic comprehensive information is automatically covered in the original historical traffic comprehensive information, the traffic comprehensive information stored firstly is still insufficient, the traffic comprehensive information stored firstly is continuously covered, and the like.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
by the scheme provided by the invention, the condition that the road surface needs to be damaged during installation and maintenance due to the fact that the ground induction coil is adopted for counting the traffic flow speed can be avoided, and the existing monitoring network can be directly utilized without additionally installing data acquisition equipment; meanwhile, through the scheme of once modeling and timely correction, the matching degree of the predicted data and the real-time traffic is ensured, the data calculation amount required by modeling is obviously reduced, and the method is high in timeliness and good in accuracy; a special scene mode is preset to meet the requirements of various special environments, and timeliness is high; the traffic flow in each direction is taken as a main traffic control reference, and then the traffic control is carried out according to the preset rule, so that the traffic volume in each direction can be effectively increased, and the traffic jam in each direction is avoided.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of an intelligent transportation method based on traffic flow speed prediction in a real-time scenario.
Fig. 2 is a flowchart of a predictive traffic integrated information prediction method.
Fig. 3 is a flow chart of traffic light control signal generation.
FIG. 4 is a block diagram of an intelligent transportation system based on traffic speed prediction in a real-time scenario.
FIG. 5 is a traffic policy module structure tree diagram.
Detailed Description
All of the features disclosed in this specification, or all of the steps in any method or process so disclosed, may be combined in any combination, except combinations of features and/or steps that are mutually exclusive.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
As shown in fig. 1, the present embodiment discloses an intelligent transportation method based on traffic flow speed prediction in a real-time scene, including:
s001: waiting for receiving a scene selection signal in real time; if a scene selection signal is received, executing S101, otherwise, executing S100;
s101: selecting a preset traffic light control signal according to the scene selection signal, and executing S600; waiting for receiving a scene cancel signal in real time; if a scene cancel signal is received, executing S100;
s100: collecting video information of a traffic lane intersection; in order to save the construction cost, the step can acquire video information through the existing traffic monitoring network, and preferably, the monitoring point is arranged at the traffic crossing and arranged towards the direction of entering the traffic crossing;
s200: analyzing traffic comprehensive information according to the collected video information, wherein the traffic comprehensive information comprises traffic flow and vehicle speed; preferably, the method also comprises the vehicle type;
s300: loading the traffic comprehensive information into historical traffic comprehensive information in a cyclic storage mode;
s400: constructing a traffic model according to the historical traffic comprehensive information, and predicting the predicted traffic comprehensive information of the traffic crossing at a node in the future preset time;
s500: generating a traffic light control signal of the traffic crossing according to the predicted traffic comprehensive information;
s600: and controlling the execution of the traffic light at the traffic crossing according to the traffic light control signal.
Referring to fig. 2, the present embodiment specifically discloses a method for predicting traffic integrated information at a future time point, that is, S400 in the above embodiment:
s4001: receiving the historical traffic comprehensive information, and constructing a traffic model by a regression analysis method according to the historical traffic comprehensive information; whether the current time point is a time point set by a preset time interval is judged, if yes, S4002 is executed, and otherwise, S4004 is executed;
s4002: acquiring real-time traffic comprehensive information according to the method of S100-S200;
s4003: correcting the traffic model according to the real-time traffic comprehensive information;
s4004: and predicting the predicted traffic comprehensive information of the traffic crossing at a node of a future preset time according to the traffic model.
Referring to fig. 3, the present embodiment specifically discloses a process of generating a traffic light control signal, i.e., S500 in the above embodiment:
s5001: generating traffic light control sub-signals in the relative direction according to traffic flow information in the relative direction contained in the predicted traffic comprehensive information; and in parallel
S5002: generating traffic light control sub-signals in the left-turning direction according to traffic flow information in the left-turning direction contained in the predicted traffic comprehensive information;
s5003: and combining the traffic light control sub-signals in the opposite direction and the traffic light control sub-signals in the left-turning direction to generate traffic light control signals.
The traffic light control sub-signals (i.e. the traffic light control sub-signals in the opposite direction and the traffic light control sub-signals in the left-turn direction) are provided with initial values, and the generation rule of the traffic light control sub-signals is as follows: and adjusting according to the multiple of preset time length on the basis of the initial value, wherein each traffic light control sub-signal is provided with a preset threshold value, and each generated traffic light control sub-signal is in the preset threshold value. The traffic flow information in the relative direction includes: the traffic flow in the opposite direction and the traffic flow ratio in the opposite direction.
For example, the following steps are carried out: the traffic flow from east to west is X, the traffic flow from west to east is Y, the initial value is set to be 40 seconds, the corresponding traffic flow is N, the regulation is carried out by taking 5 seconds as unit time, and the range of the set threshold value is 30-50 seconds; when the specified traffic flow increases/decreases Z, the corresponding time increases/decreases by one unit time, and then: 0< X-N < Z, and the east-west direction time is adjusted to 40+5 (-1) =35 seconds, and is within the threshold range, and is effective adjustment data, and 2Z < Y-N <3Z, the west-east direction time is adjusted to 40+ 5X 3=55 seconds, and 55 seconds exceeds the threshold range, and the west-east direction time is adjusted to 50 seconds. Meanwhile, considering the vehicle flow ratio in the east-west direction, the ratio of the west release time to the east release time is preferably 1 to Y: a reasonable value between X, such as Y: x =1.5, the ratio of west release time to east release time can take a value between 1 and 1.5, and the above adjustment time (1 <50:35< 1.5) in this ratio is a desirable adjustment scheme.
Referring to fig. 4 and 5, the present embodiment discloses an intelligent transportation system based on traffic speed prediction under a real-time scene, including:
the image acquisition module 101 is used for acquiring video information of a traffic intersection; in order to save the construction cost, the image acquisition module 101 can be an existing traffic monitoring network, preferably, an acquisition point is arranged at a traffic intersection and is arranged towards the direction of entering the traffic intersection;
the vehicle detection module 102 is configured to analyze traffic comprehensive information according to the video information acquired by the image acquisition module 101, where the traffic comprehensive information includes traffic flow and vehicle speed;
the data storage module 103 is used for storing the traffic comprehensive information output by the vehicle retrieval module in a circulating storage mode to generate historical traffic comprehensive information;
a model building module 104, configured to build a traffic model through a regression analysis method according to the historical traffic comprehensive information generated by the data storage module 103, and output predicted traffic comprehensive information of a node of the traffic crossing at a predetermined time in the future according to the traffic model; the predicted traffic comprehensive information is corrected according to the correction of the traffic model by the model correction module 107;
the model correction module 107 is used for controlling the image acquisition module 101 to acquire the video data of the traffic intersection at time points set at preset time intervals, and controlling the vehicle detection module 102 to analyze real-time traffic comprehensive information according to the video data acquired by the image acquisition module 101; correcting the traffic model constructed by the model construction module 104 according to the real-time traffic comprehensive information;
a traffic strategy module 105, configured to generate a traffic light control signal of the traffic crossing according to the predicted traffic comprehensive information output by the model prediction module;
the scene confirmation module 108 is configured to receive a scene selection signal, select a preset traffic light control signal according to the scene selection signal, set the selected preset traffic light control signal to be the highest priority, and send the selected preset traffic light control signal to the traffic control module 106, so that the traffic control module 106 controls the traffic light to be executed according to the selected preset traffic light control signal; receiving a scene cancel signal, and withdrawing the traffic light control signal sent to the traffic control module 106, so that the traffic control module 106 receives the traffic light control signal sent by the traffic policy module 105;
a traffic control module 106, configured to control execution of corresponding traffic lights according to the traffic light control signal generated by the traffic policy module 105.
Further, the traffic policy module 105 includes:
a traffic strategy unit 105a for opposing traffic, according to the output of the model construction module 104: the traffic flow information in the relative direction contained in the predicted traffic comprehensive information generates traffic light control sub-signals in the relative direction; the ratio of the traffic flow in the opposite direction to the traffic flow in the opposite direction
A turn-by-turn traffic strategy unit 105b for, according to the output of the model construction module 104: the traffic flow information in the left turning direction contained in the predicted traffic comprehensive information generates traffic light control sub-signals in the left turning direction;
a policy combining unit 105c, configured to combine the following generated by the opposite traffic policy unit 105 a: the traffic light control sub-signal of the opposite direction, and the steering traffic strategy unit 105b generates: and the traffic light control sub-signals in the left turning direction are combined to generate traffic light control signals.
Further, each of the traffic light control sub-signals is provided with an initial value, and the generation rules of the opposite traffic strategy unit 105a and the turning traffic strategy unit 105b generating the corresponding traffic light control sub-signals (that is, the opposite traffic strategy unit 105a generates the traffic light control sub-signals in the opposite direction, and the turning traffic strategy unit 105b generates the traffic light control sub-signals in the left-turning direction) are as follows: and adjusting by a multiple of a preset time length on the basis of the initial value. Meanwhile, the opposite traffic strategy unit 105a and the steering traffic strategy unit 105b are provided with preset thresholds, and the two strategy units adjust corresponding traffic light control sub-signals within the preset thresholds.
The invention is not limited to the foregoing embodiments. The invention extends to any novel feature or any novel combination of features disclosed in this specification and any novel method or process steps or any novel combination of features disclosed.
Claims (7)
1. An intelligent transportation method based on traffic flow speed prediction in a real-time scene is characterized by comprising the following steps:
s100: collecting video information of a traffic lane intersection;
s200: analyzing traffic comprehensive information according to the collected video information, wherein the traffic comprehensive information comprises traffic flow and vehicle speed;
s300: loading the traffic comprehensive information into historical traffic comprehensive information;
s400: constructing a traffic model according to the historical traffic comprehensive information, and predicting the predicted traffic comprehensive information of the traffic crossing at a node in the future preset time;
s500: generating a traffic light control signal of the traffic crossing according to the predicted traffic comprehensive information;
s600: controlling the execution of the traffic light at the traffic crossing according to the traffic light control signal;
the S400 specifically comprises the following steps:
s4001: receiving the historical traffic comprehensive information, and constructing a traffic model according to the historical traffic comprehensive information by a regression analysis method; whether the current time point is set at a preset time interval is also judged, if yes, S4002 is executed, and otherwise, S4004 is executed;
s4002: acquiring real-time traffic comprehensive information according to the method of S100-S200;
s4003: correcting the traffic model according to the real-time traffic comprehensive information;
s4004: and predicting the predicted traffic comprehensive information of the traffic crossing at a node of a future preset time according to the traffic model.
2. The method of claim 1, further comprising, prior to S100:
s001: waiting for receiving a scene selection signal in real time; if a scene selection signal is received, executing S101, otherwise, executing S100;
s101: and selecting a preset traffic light control signal according to the scene selection signal, and executing S600.
3. The method according to claim 2, wherein S500 is specifically:
s5001: generating traffic light control sub-signals in the relative direction according to traffic flow information in the relative direction contained in the predicted traffic comprehensive information; and in parallel
S5002: generating traffic light control sub-signals in the left-turning direction according to traffic flow information in the left-turning direction contained in the predicted traffic comprehensive information;
s5003: and combining the traffic light control sub-signals in the opposite direction and the traffic light control sub-signals in the left-turning direction to generate traffic light control signals.
4. The method of claim 3, wherein the traffic flow information for the relative direction comprises: the traffic flow in the opposite direction and the traffic flow ratio in the opposite direction.
5. The method of claim 4, wherein each traffic light control sub-signal is provided with an initial value, and the generation rule of each traffic light control sub-signal is as follows: and adjusting according to a preset rule on the basis of the initial value.
6. The method of claim 5, wherein the predetermined rule is: the adjustment is made in multiples of a predetermined length of time.
7. The method of claim 6, wherein each traffic light control sub-signal is provided with a predetermined threshold, and wherein each generated traffic light control sub-signal is within the predetermined threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711095733.8A CN107730890B (en) | 2017-11-09 | 2017-11-09 | Intelligent transportation method based on traffic flow speed prediction in real-time scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711095733.8A CN107730890B (en) | 2017-11-09 | 2017-11-09 | Intelligent transportation method based on traffic flow speed prediction in real-time scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107730890A CN107730890A (en) | 2018-02-23 |
| CN107730890B true CN107730890B (en) | 2021-04-20 |
Family
ID=61214269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711095733.8A Active CN107730890B (en) | 2017-11-09 | 2017-11-09 | Intelligent transportation method based on traffic flow speed prediction in real-time scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107730890B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109637135A (en) * | 2018-12-29 | 2019-04-16 | 江苏工程职业技术学院 | A kind of circumstance video monitoring early warning system based on computer network |
| CN112614443A (en) * | 2020-12-24 | 2021-04-06 | 玺美车众数字传媒科技(上海)有限公司 | Intelligent lamp box capable of carrying out vehicle flow statistics and capturing and analyzing images of vehicle owner groups |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662141B2 (en) * | 1995-01-13 | 2003-12-09 | Alan R. Kaub | Traffic safety prediction model |
| CN101038700A (en) * | 2007-04-20 | 2007-09-19 | 东南大学 | Mixed controlling method of single dot signal controlling crossing |
| CN101783075A (en) * | 2010-02-05 | 2010-07-21 | 北京科技大学 | System for forecasting traffic flow of urban ring-shaped roads |
| CN102737513A (en) * | 2011-04-07 | 2012-10-17 | 张谞博 | Novel signalized intersection delay model calculation method |
| CN103050016A (en) * | 2012-12-24 | 2013-04-17 | 中国科学院自动化研究所 | Hybrid recommendation-based traffic signal control scheme real-time selection method |
| CN103247177A (en) * | 2013-05-21 | 2013-08-14 | 清华大学 | Large-scale road network traffic flow real-time dynamic prediction system |
| CN103383816A (en) * | 2013-07-01 | 2013-11-06 | 青岛海信网络科技股份有限公司 | Method and device for controlling traffic signals of multipurpose electronic police mixed traffic flow detection |
| EP2478508B1 (en) * | 2009-09-16 | 2014-12-17 | Road Safety Management Ltd | Traffic signal control system and method |
| CN106530762A (en) * | 2016-12-26 | 2017-03-22 | 东软集团股份有限公司 | Traffic signal control method and device |
| CN106600993A (en) * | 2017-02-17 | 2017-04-26 | 重庆邮电大学 | Intersection vehicle branch traffic flow prediction method based on RFID data |
| CN106663373A (en) * | 2014-08-19 | 2017-05-10 | 高通股份有限公司 | Systems and methods for traffic efficiency and flow control |
| CN106875702A (en) * | 2017-04-11 | 2017-06-20 | 冀嘉澍 | A kind of crossroad access lamp control method based on Internet of Things |
| CN106971567A (en) * | 2017-05-18 | 2017-07-21 | 上海博历机械科技有限公司 | A kind of the intensive traffic section vehicle queue video detection system |
| CN106971545A (en) * | 2017-05-16 | 2017-07-21 | 青岛大学 | A kind of bus arrival time Forecasting Methodology |
| CN106997670A (en) * | 2017-06-02 | 2017-08-01 | 攀枝花学院 | Real-time sampling of traffic information system based on video |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101206801B (en) * | 2007-12-17 | 2011-04-13 | 青岛海信网络科技股份有限公司 | Self-adaption traffic control method |
| TW201115518A (en) * | 2009-10-27 | 2011-05-01 | hui-de Cai | Symmetric chain control method for regional traffic signal to improve city traffic jam |
| CN102087794B (en) * | 2009-12-02 | 2014-04-16 | 丁靖宇 | Intelligent traffic signal lamp and network forming technology |
| WO2011126215A2 (en) * | 2010-04-09 | 2011-10-13 | 고려대학교 산학협력단 | Traffic flow control and dynamic path providing system linked with real-time traffic network structure control based on bidirectional communication function-combined vehicle navigation, and method thereof |
| CN101976510A (en) * | 2010-10-26 | 2011-02-16 | 隋亚刚 | Method for optimally controlling crossing vehicle signal under high definition video detection condition |
| CN102074117B (en) * | 2010-12-28 | 2013-07-17 | 同济大学 | Regional short range synchronous road control method |
| CN102063794B (en) * | 2011-01-14 | 2012-09-26 | 隋亚刚 | Urban expressway automatic even detecting and synergetic command dispatching system based on occupation ratio data |
| CN102142197B (en) * | 2011-03-31 | 2013-11-20 | 汤一平 | Intelligent traffic signal lamp control device based on comprehensive computer vision |
| US10121370B2 (en) * | 2014-09-20 | 2018-11-06 | Mohamed Roshdy Elsheemy | Comprehensive traffic control system |
| CN104637317B (en) * | 2015-01-23 | 2017-01-04 | 同济大学 | A kind of crossing based on real-time vehicle track actuated signal control method |
| CN204440651U (en) * | 2015-02-15 | 2015-07-01 | 南京信息工程大学 | A kind of intelligent traffic light control system based on vehicle flowrate |
-
2017
- 2017-11-09 CN CN201711095733.8A patent/CN107730890B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662141B2 (en) * | 1995-01-13 | 2003-12-09 | Alan R. Kaub | Traffic safety prediction model |
| CN101038700A (en) * | 2007-04-20 | 2007-09-19 | 东南大学 | Mixed controlling method of single dot signal controlling crossing |
| EP2478508B1 (en) * | 2009-09-16 | 2014-12-17 | Road Safety Management Ltd | Traffic signal control system and method |
| CN101783075A (en) * | 2010-02-05 | 2010-07-21 | 北京科技大学 | System for forecasting traffic flow of urban ring-shaped roads |
| CN102737513A (en) * | 2011-04-07 | 2012-10-17 | 张谞博 | Novel signalized intersection delay model calculation method |
| CN103050016A (en) * | 2012-12-24 | 2013-04-17 | 中国科学院自动化研究所 | Hybrid recommendation-based traffic signal control scheme real-time selection method |
| CN103247177A (en) * | 2013-05-21 | 2013-08-14 | 清华大学 | Large-scale road network traffic flow real-time dynamic prediction system |
| CN103383816A (en) * | 2013-07-01 | 2013-11-06 | 青岛海信网络科技股份有限公司 | Method and device for controlling traffic signals of multipurpose electronic police mixed traffic flow detection |
| CN106663373A (en) * | 2014-08-19 | 2017-05-10 | 高通股份有限公司 | Systems and methods for traffic efficiency and flow control |
| CN106530762A (en) * | 2016-12-26 | 2017-03-22 | 东软集团股份有限公司 | Traffic signal control method and device |
| CN106600993A (en) * | 2017-02-17 | 2017-04-26 | 重庆邮电大学 | Intersection vehicle branch traffic flow prediction method based on RFID data |
| CN106875702A (en) * | 2017-04-11 | 2017-06-20 | 冀嘉澍 | A kind of crossroad access lamp control method based on Internet of Things |
| CN106971545A (en) * | 2017-05-16 | 2017-07-21 | 青岛大学 | A kind of bus arrival time Forecasting Methodology |
| CN106971567A (en) * | 2017-05-18 | 2017-07-21 | 上海博历机械科技有限公司 | A kind of the intensive traffic section vehicle queue video detection system |
| CN106997670A (en) * | 2017-06-02 | 2017-08-01 | 攀枝花学院 | Real-time sampling of traffic information system based on video |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107730890A (en) | 2018-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110376594B (en) | Intelligent navigation method and system based on topological graph | |
| WO2018217806A1 (en) | Road traffic control system, method, and electronic device | |
| CN111613070B (en) | Traffic signal lamp control method, traffic signal lamp control device, electronic equipment and computer storage medium | |
| CN108932470B (en) | Image processing system, image processing method, information processing apparatus, and recording medium | |
| CN113807270A (en) | Road congestion detection method and device and electronic equipment | |
| US11798408B2 (en) | Green wave speed determination method, electronic device and storage medium | |
| CN113077626B (en) | Lane selection guiding method, device, system, equipment and storage medium | |
| CN112462774A (en) | Urban road supervision method and system based on unmanned aerial vehicle navigation following and readable storage medium | |
| CN107730890B (en) | Intelligent transportation method based on traffic flow speed prediction in real-time scene | |
| CN113276874B (en) | Vehicle driving track processing method and related device | |
| Gloudemans et al. | Interstate-24 motion: Closing the loop on smart mobility | |
| US20210088340A1 (en) | Inferring lane boundaries via high speed vehicle telemetry | |
| CN114322799A (en) | Vehicle driving method and device, electronic equipment and storage medium | |
| KR20090090049A (en) | Apparatus and method for real-time traffic information service | |
| CN109767339A (en) | A kind of Claims Resolution data determination method, the apparatus and system of accident vehicle | |
| CN113593221A (en) | Information value evaluation type driving system, internet vehicle system and data transmission method | |
| US20230394694A1 (en) | Methods and apparatus for depth estimation using stereo cameras in a vehicle system | |
| KR20180068462A (en) | Traffic Light Control System and Method | |
| CN116935631A (en) | Abnormal traffic situation detection method, device and system based on radar fusion | |
| Mishra et al. | Adaptive traffic light cycle time controller using microcontrollers and crowdsource data of google apis for developing countries | |
| CN114024997B (en) | Intelligent equipment based on automatic driving and AIOT Internet of things platform method | |
| CN115359671A (en) | Intersection vehicle cooperative control method and related equipment | |
| CN110556000A (en) | Artificial intelligence traffic detection system | |
| KR100999416B1 (en) | Providing system of driving information by simulating with cctv's shooting information | |
| CN112526477B (en) | Method and device for processing information |
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 |