CN103377558A - System and method for managing and controlling traffic flow - Google Patents

Abstract

The invention provides a traffic flow management and control system, which is applied to a control host connected to a UAV and a traffic signal in communication. The UAV shoots real-time images of each road, detects the position coordinates of the shooting location of each real-time image and the shooting direction of the UAV when shooting the real-time image, and transmits the data such as the real-time image, position coordinates and shooting direction to Control host. The traffic flow control system analyzes the real-time images to obtain the number data of people and vehicles in the real-time images, and marks the numbers of people and vehicles in each real-time image on the electronic map according to the location coordinates and shooting directions. The corresponding position, and dynamically adjust the control status of the traffic signals of each road according to the human shape and the number of vehicles marked on the electronic map. The invention also provides a traffic flow control method.

Description

Traffic flow control system and method

technical field

The invention relates to an information monitoring system and method, in particular to a traffic flow control system and method.

Background technique

At present, the traffic control guidance method generally relies on the traffic police and other manpower to go to the scene to confirm the traffic flow and other conditions of the road section and give instructions during peak traffic hours or when passers-by report the road conditions, or the personnel go to the scene to manually control traffic signals. to assist in the flow of traffic. This method not only requires a large amount of manpower for traffic control personnel, but also relies on regular patrols by personnel or real-time notifications from passers-by for relevant road conditions.

Contents of the invention

In view of the above, it is necessary to provide a traffic flow control system and method, which can obtain traffic flow information in real time and dynamically adjust the control status of traffic signals according to the traffic flow information.

A traffic flow control system, which is applied to a control host for controlling the control state of traffic signals. The traffic flow control system receives the real-time images of the roads captured by the image capture unit of the unmanned aerial vehicle UAV, the position coordinate data of the shooting location of each real-time image detected by the global positioning system GPS, and the electronic compass to detect The shooting direction data of the image capture unit when shooting the real-time image. Afterwards, the system analyzes the real-time images using vehicle and human-type detection technology to obtain the image information of people and vehicles in the real-time images of each road; The number of people and vehicles in the middle is marked on the corresponding position of the electronic map according to the location coordinates of the shooting location of the real-time image and the shooting direction; and according to the data of the number of people and vehicles on each road marked on the electronic map Adjust the control status of traffic signals on each road.

A traffic flow control method is applied to a control host for controlling the control status of traffic signals. The method includes: (A) receiving the real-time images of each road taken by the image capture unit of the unmanned aerial vehicle UAV, utilizing the position coordinate data of the shooting location of each real-time image detected by the global positioning system GPS, and utilizing the electronic compass The shooting direction data of the image capture unit when the detected real-time image is taken; (B) analyze the real-time image by using vehicle and human type detection technology to obtain the image information of human type and vehicle in the real-time image of each road; (C) Count the number of people and vehicles in the real-time images of each road, and mark the numbers of people and vehicles in each real-time image on the corresponding position of the electronic map according to the location coordinates of the shooting location of the real-time images and the shooting direction and other information; And (D) dynamically adjust the control status of the traffic signals of each road according to the number data of people and vehicles on each road marked on the electronic map.

Compared with the prior art, the traffic flow control system and method provided by the present invention can acquire traffic flow information in real time and dynamically adjust the control status of traffic signals according to the traffic flow information.

Description of drawings

FIG. 1 is an application environment diagram of a preferred embodiment of the traffic flow control system of the present invention.

Fig. 2 is a flowchart of a preferred embodiment of the traffic flow control method of the present invention.

FIG. 3 is a schematic diagram of a UAV and an image capture unit installed on the UAV.

FIG. 4 is a schematic diagram of the UAV shown in FIG. 3 hovering over a road and shooting a real-time image of the road.

FIG. 5 is a schematic diagram of image information of human figures and vehicles in real-time images of a road at a certain moment.

FIG. 6 is a schematic diagram showing the number data of people and vehicles in each direction of each road on an electronic map.

Description of main component symbols

UAV 1 control host 2 Storage System 3 traffic signal 4 GPS 11 image capture unit 12 Electronic compass 13 network module 14, 21 processor twenty two traffic flow control system twenty three analysis module 231 marking module 232 control module 233 digital map twenty four

The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings.

Detailed ways

Referring to FIG. 1 , it is an application environment diagram of a preferred embodiment of the traffic flow control system 23 of the present invention. The traffic flow control system 23 is applied to the control host 2 that controls the control state of the traffic signal 4 . The traffic signal 4 is a traffic control facility for assigning the right of way to vehicle drivers and pedestrians to control their walking and turning with alternating light and color signals. The traffic signal 4 includes a traffic control signal, a pedestrian-only signal, and a special traffic signal (such as a prompt for the blind).

The control host 2 is connected to an unmanned aerial vehicle (Unmanned Aerial Vehicle, UAV) 1 through network communication. The UAV1 includes a global positioning system (global position system, GPS) 11 , an image capture unit 12 , an electronic compass 13 and a network module 14 .

Referring to FIG. 3 , the image capture unit 12 is installed on the nose of the UAV1 , and the lens of the image capture unit 12 is aligned with the nose of the UAV1 . In this embodiment, the image capture unit 12 is a digital camera with a night shooting function. The UAV1 utilizes the image capture unit 12 to capture real-time images of each road. Referring to FIG. 4 , it is a schematic diagram of the UAV1 staying above a road to shoot real-time images of the road.

The GPS 11 detects the coordinate information of the shooting location of each real-time image, that is, the coordinate information of the location of the UAV 1 when the image capture unit 12 shoots each real-time image. The electronic compass 13 detects the direction of the image capture unit 12 when shooting each real-time image (hereinafter referred to as the shooting direction of each real-time image).

The UAV 1 transmits the captured real-time images of each road, the location coordinates of the shooting location of each image, and the shooting direction to the control host 2 through the network module 14 .

Referring to FIG. 1 , the control host 2 also includes a network module 21 , a processor 22 and an electronic map 24 . The control host 2 receives the real-time images of each road transmitted by the UAV 1 through the network module 21 , the location coordinates of the shooting location of each image, the shooting direction and other data, and stores them in the storage system 3 . The storage system 3 can be a storage device inside the control host 2, or an external storage device connected to the control host 2, such as a database server.

The traffic flow control system 23 analyzes the received data, analyzes the real-time images using vehicle and human shape detection technology, obtains the number data of people and vehicles in the real-time images of each road, and compares the numbers of people and vehicles in the real-time images The quantity data is marked on the corresponding position of the electronic map according to the location coordinates and shooting direction of the shooting location of the real-time image, and the traffic signs of each road are dynamically adjusted according to the number of people and vehicles on each road marked on the electronic map 4 control status.

Referring to FIG. 1 , the traffic flow control system 23 includes an analysis module 231 , a marking module 232 and a control module 233 . The modules 231 - 233 include computer programming codes, which are stored in the storage system 3 , and the processor 22 executes these computer programming codes to provide the above-mentioned functions of the traffic flow control system 23 . For the specific functions of the modules 231-233, please refer to the description of FIG. 2 below.

Referring to Fig. 2, it is a flow chart of a preferred embodiment of the traffic flow control method of the present invention.

Step S10 , the UAV1 uses the image capture unit 12 to capture real-time images of each road, and uses the GPS 11 and the electronic compass 13 to detect the location coordinates and shooting directions of the shooting locations of each real-time image. Referring to FIG. 4 , it is a schematic diagram of the UAV1 staying above a road to shoot real-time images of the road. When UAV1 is taking the real-time image of this road, GPS11 detects that the longitude coordinate of UAV1 is 152.6248, and the latitude coordinate is 25.8214. -W15°. Wherein, the first English letter N indicates that the main shooting direction of the image capture unit 12 is due north, the second English letter W indicates that the offset direction of the image capture unit 12 is the west, and the number 15° indicates that the image capture unit 12 starts from the true north. The angle by which the direction is offset west.

In step S20 , the UAV 1 transmits the captured real-time images of each road, the location coordinates of the shooting location of each image, and the shooting direction data to the control host 2 through the network module 14 .

In step S30, after the control host 2 receives the above data through the network module 21, the analysis module 231 analyzes the real-time images using the vehicle and human shape detection technology to obtain image information of human shapes and vehicles in the real-time images of each road. Referring to Fig. 5, it is a real-time image of a road at a certain moment, and the analysis module 231 analyzes the image information of the people and vehicles in the real-time image, and marks the people and vehicles in the real-time image in the form of a rectangle plus a digital number image area.

The shown human type detection techniques include, but are not limited to, human type feature information statistics method and feature sample comparison classification method (Template Matching Method).

Specifically, the statistical method of humanoid feature information includes the following steps:

(1) Simplify the real-time image background by image processing;

(2) Compare the real-time image data with more than 100,000 humanoid feature point data of each posture in the database;

(3) Statistically estimate whether humanoid information exists in the real-time image according to the feature point data in the real-time image.

The characteristic sample comparison classification method includes the following steps:

(1) First collect a certain number of humanoid feature samples of each posture and a certain number of non-humanoid feature samples, for example, collect a certain number of humanoid pictures in standing postures, frontal postures, sideways postures, and sitting postures;

(2) After completing the collection of a certain number of human-like feature samples in different poses and a certain number of non-human-like feature samples, start further continuous training (Training) with the artificial neural network (Artificial Neural Network) training method, and continue to correct errors. If you do not use the neural network training method, you can also use the Ada-Boost classification method for classification, and the trained humanoid feature template (Template) or Ada-Boost classifier can be used for subsequent humanoid detection (Testing) use.

In this embodiment, vehicle detection can use Adaboost cascade-based license plate detection technology, which will not be repeated here.

Step S40, the marking module 232 counts the number of people and vehicles in the real-time images of each road, and marks the number data of people and vehicles in each real-time image on the computer according to the location coordinates and shooting directions of the shooting location of the real-time images. corresponding location on the map. Fig. 6 has shown the partial area of electronic map 24, and this electronic map 24 is except displaying the sign of road, building, also on the electronic map 24 and UAV1 shoots the corresponding position place mark analysis of this real-time image at the shooting location of each piece of real-time image. The data of the number of people and vehicles in each direction of the corresponding road obtained from the image. Assuming that the UAV1 captures one or more real-time images at each intersection, as shown in FIG. 6 , arrows indicating different directions are marked at each intersection displayed on the electronic map 24 . The arrows are used to indicate the shooting direction of the image capture unit 12 when shooting a certain real-time image, and two numbers are marked next to each arrow to indicate the number of people and vehicles on the road corresponding to the shooting direction obtained from the real-time image analysis. . In this embodiment, numbers placed in circles indicate the number of human figures, and numbers not placed in circles indicate the number of vehicles.

In step S50, the control module 233 dynamically adjusts the management and control status of the traffic signs 4 on each road according to the human shape and vehicle quantity data on each road marked on the electronic map 24 . For example, when the number of people and vehicles in a certain direction of a road exceeds a preset threshold, the control module 233 generates a control command to the traffic signal 4 on the road to prolong the time for people and vehicles in the direction of the road. .

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention without limitation. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent replacements can be made without departing from the spirit and scope of the technical solutions of the present invention.

Claims (8)

1. A traffic flow control system, which is applied to a control host controlling a traffic signal control state, is characterized in that the traffic flow control system comprises: The network module is used to receive the real-time images of each road taken by the image capture unit of the unmanned aerial vehicle UAV, the position coordinate data of the shooting location of each real-time image detected by the global positioning system GPS, and the electronic compass to detect The shooting direction data of the image capture unit when shooting the real-time image; The analysis module is used to analyze the real-time images using vehicle and human-type detection technology to obtain the image information of human-type and vehicles in the real-time images of each road; The marking module is used to count the number of people and vehicles in the real-time images of each road, and mark the numbers of people and vehicles in each real-time image on the electronic map according to the position coordinates of the shooting location of the real-time images and the shooting direction information the corresponding location; and The control module is used to dynamically adjust the control status of the traffic signals of each road according to the data of the number of people and vehicles on each road marked on the electronic map. 2. The traffic flow control system according to claim 1, characterized in that the traffic signal is an alternating light and color signal, which is set at a crossroad or other special location to assign the right of way to the vehicle Traffic control facilities for drivers and pedestrians to control their behavior and turn. 3 . The traffic flow control system according to claim 1 , wherein the human shape detection technology includes a statistical method of human shape characteristic information and a method of comparing and classifying characteristic samples. 4 . 4. The traffic flow management and control system as claimed in claim 1, characterized in that, the dynamic adjustment of the control state of the traffic signal of each road according to the figure of each road marked on the electronic map, the quantity data of vehicles comprises: When the number of people and vehicles in a certain direction of a road exceeds the preset threshold, a control command is generated to the traffic signal on the road to extend the time for people and vehicles in the direction of the road to pass. 5. A traffic flow control method, applied to a control host controlling a traffic signal control state, characterized in that the method comprises: Receive the real-time images of each road captured by the image capture unit of the unmanned aerial vehicle UAV, use the global positioning system GPS to detect the position coordinate data of the shooting location of each real-time image, and use the electronic compass to detect and shoot the real-time image shooting direction data of the image capture unit at the time; Analyze the real-time images by using vehicle and human shape detection technology to obtain the image information of human shapes and vehicles in the real-time images of each road; Count the number of people and vehicles in the real-time images of each road, and mark the numbers of people and vehicles in each real-time image on the corresponding position of the electronic map according to the location coordinates of the shooting location of the real-time images and the shooting direction information; and According to the data of the number of people and vehicles on each road marked on the electronic map, the control status of traffic signals on each road is dynamically adjusted. 6. The traffic flow control method according to claim 5, characterized in that the traffic signal is an alternating light and color signal, which is set at a crossroad or other special location to assign the right of way to the vehicle Traffic control facilities for drivers and pedestrians to control their behavior and turn. 7 . The traffic flow control method according to claim 5 , wherein the human shape detection technology includes a statistical method of human shape characteristic information and a method of comparing and classifying characteristic samples. 8 . 8. The traffic flow control method as claimed in claim 5, wherein the dynamic adjustment of the control state of the traffic signal of each road according to the human figure and vehicle quantity data of each road marked on the electronic map comprises: when When the number of people and vehicles in a certain direction of a road exceeds the preset threshold, a control command is generated to the traffic signal on the road to extend the time for people and vehicles in the direction of the road to pass.

Images