KR20100127074A - System for controlling vehicle transport signal of intersection using day and night integrated traffic image detector - Google Patents

Abstract

PURPOSE: A system for controlling the vehicle transport signal of intersection using a day and night integrated traffic image detector is provided to minimize the interference of external illumination by improving the performance of an image detector at an intersection. CONSTITUTION: A day and night control device(330) determines a day mode or a night mode. An image obtaining controller(320) generates the day mode or infrared ray mode of a camera and generates a camera operation control signal. The image obtaining controller collects the capture image of vehicle entering and exiting. A digital signal processing unit(340) generates a traffic information message which includes the number of the vehicle waiting at lanes.

Description

System for Controlling Vehicle Transport Signal of Intersection using Day and Night Integrated Traffic Image Detector}

The present invention relates to a system for traffic signal control, and in particular, to improve the performance of the intersection image detector to minimize the effects of external illumination, the optimal robustness to external environmental changes, such as day or night image changes or weather changes The present invention relates to a system capable of acquiring images, accurately estimating the vehicle's air length, the number of air vehicles, and collecting and monitoring traffic information wirelessly, and automatically controlling traffic signals to facilitate traffic flow.

The traffic information center operates an intelligent transport system (ITS) to grasp the flow of vehicles at intersections, collect traffic information, and guide traffic information through a broadcasting network, a satellite communication network, or a mobile communication network as shown in FIG. If necessary, it can be used to control vehicle traffic lights.

In particular, since the flow of the vehicle is greatly affected by the traffic lights, it is required to optimally control the vehicle traffic lights. In general ITS, the traffic volume of the vehicle is determined by a loop buried type or an image detecting type.

In the roof embedding method, a loop for detecting a change in geomagnetic energy is embedded in a road for identifying vehicle entry and exit to detect vehicle entry and exit and collect vehicle traffic. Such a roof buried type method allows to acquire reliable traffic information simply by embedding a loop on the road, but there is a problem that damages the road and hinders traffic flow when the roof is buried, and only detects the entry and exit of the vehicle. It does not make it possible to identify traffic information separately. In addition, in the roof buried type, the traffic volume may change during the prior collection and analysis of the traffic volume in the above manner. .

The video detection method installs a camera on the road to grasp the entrance and exit of the vehicle, such as an intersection, and collects the image related to the vehicle entrance on the road in real time. However, the installation cost is expensive. It is widely used because it can collect traffic information on multiple lanes by using pan / tilit and it is easy to cope with changes in traffic flow.

However, in such an image detection type, since the image is acquired from a camera installed on the road, the performance difference due to day and night illumination varies greatly, and there is a problem that the accuracy decreases due to weather such as rain or snow, and a traffic signal controller Since there is a wired connection between the and the image detector, there is a problem that an initial cable laying cost or management cost for this is required.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and an object of the present invention is to be robust to external environment changes such as daytime or nighttime image changes or weather changes so as to minimize the effects of external illumination by improving the performance of an intersection image detector. It is to provide a system that can automatically control traffic signals so as to obtain optimal images, accurately estimate the vehicle's air length, the number of air vehicles, and collect and monitor traffic information wirelessly, and facilitate traffic flow.

First, to summarize the features of the present invention, an image detector according to an aspect of the present invention for achieving the above object, based on the time information, ambient weather information, or contrast information on the captured image from the camera installed on the road Day and night mode control device to determine the day mode or night mode; Generate mode information on the daylight mode or infrared mode of the camera according to the determined day mode or night mode, and generate a camera operation control signal for controlling pan, tilt, zoom in, or zoom out of the camera according to an external input. An image acquisition device controller; An image acquisition device configured to control the camera based on the mode information and the camera operation control signal to collect the captured image of a vehicle entrance and exit on a road; And a digital signal processor configured to generate a traffic information message including the number of vehicles waiting for each lane based on the vehicle speed detected from the captured image, wherein the traffic information message is a wired or wireless communication system. Transmitted to a signal controller, the traffic information center guides the traffic volume information through a wired or wireless communication network according to the traffic information message, and the traffic signal controller controls the traffic light according to the traffic information message.

The day and night mode control apparatus includes a system clock generator for generating the time information by counting a predetermined system clock source; A detector configured to detect ambient humidity, illuminance, or heat based on a set value input to a humidity, illuminance, or heat sensor and generate the ambient weather information as a digital value; An image processor configured to generate contrast information of the captured image corrected according to color correction of the captured image; And determining the daytime mode at daytime and the nighttime mode at nighttime based on the time information. When the contrast information is less than a threshold when the ambient weather information indicates cloudy weather even in the daytime mode, the nighttime mode is determined. Includes day and night mode controller to determine.

The digital signal processor may include: an image updater configured to update a still image by selecting a predetermined period from the captured image; A lane detecting unit detecting a lane on a road from the still image; A shadow extracting unit which extracts an image excluding the vehicle and the lane from the still image, including a shadow of the vehicle on a road; An image subtractor configured to remove an image excluding the vehicle and the lane from the still image to determine a region of interest for each lane; A feature point information unit to extract a feature point vector of each vehicle in the ROI and store it in a memory; A vehicle speed detector for detecting a vehicle speed of each vehicle using the feature point vector stored in the memory; A waiting length estimating unit for estimating the number of waiting vehicles having the vehicle speed smaller than a predetermined value for each lane; And a traffic information updating unit generating the traffic information message for the number of waiting vehicles for each lane.

The feature point vector includes a shape, a length of the vehicle, or an edge change amount compared with the vehicle in the previous still image.

The traffic information updating unit updates the traffic information message at regular time intervals according to an operation of a timer, and transmits the updated traffic information message in response to a request from the traffic information center or the traffic signal controller. It can transmit to the traffic signal controller.

The digital signal processor may include a video encoder configured to generate encoded image data that encodes the captured image in a predetermined manner; And a format converter for converting the encoded image data into a bit stream to be transmitted to the wired or wireless communication network.

According to another aspect of the present invention, an image detecting method includes determining a day mode or a night mode based on time information, ambient weather information, or contrast information on a captured image from a camera installed on a road; Generating mode information on a daylight mode or an infrared mode of the camera according to the determined day mode or night mode; Collecting the captured image of the vehicle entry / exit on the road by controlling the camera based on a camera operation control signal and the mode information generated to control the pan, tilt, zoom in, or zoom out of the camera according to an external input. ; And generating a traffic information message including the number of vehicles waiting for each lane based on the vehicle speed detected from the captured image, wherein the traffic information message is transmitted to the traffic information center or the traffic signal controller in a wired or wireless communication manner. The traffic information center transmits traffic volume information through a wired or wireless communication network according to the traffic information message, and the traffic signal controller controls a traffic light according to the traffic information message.

According to the image detector for controlling the traffic signal according to the present invention, in order to minimize the influence of the external illumination, obtain an optimal image even in the day or night image or weather changes, and accurately estimates the air length of the vehicle traffic information Traffic signals can be automatically controlled to collect and monitor wirelessly and to facilitate traffic flow.

In order to fully understand the present invention, the operational advantages of the present invention, and the objects achieved by the practice of the present invention, reference should be made to the accompanying drawings which illustrate preferred embodiments of the present invention and the contents described in the accompanying drawings.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

2 is a view for explaining a system 100 for traffic signal control according to an embodiment of the present invention.

2, the system 100 for traffic signal control according to an embodiment of the present invention, DMB, DAB broadcasting network, satellite communication network, mobile communication network, wireless Internet, wired communication network (PSTN, wired Internet, etc.) Based on the traffic information from the network detector 110, the image detector 120, which collects camera images installed on the road such as an intersection, and the traffic detector 120, which may include all of the network information, guides the traffic information through the network 110. The traffic information center 130, and the traffic signal controller 140 is installed around the vehicle traffic lights to control the traffic flow by controlling the flashing of red, orange, green of the vehicle traffic lights.

As described above, the image detector 120, the traffic information center 130, and the traffic signal controller 140 may transmit and receive signals necessary for each other according to a wired or wireless communication method through the network 110, but preferably, a wired cable Considering the difficulty of the construction work and the management cost of the construction, it is ultimately necessary to send and receive the necessary signals by the wireless communication method such as broadcasting network, satellite communication network, mobile communication network, or wireless internet such as DMB and DAB.

In the system 100 for controlling traffic signals according to an embodiment of the present invention, the image detector 120 includes the surroundings based on time information, ambient weather information, or contrast information on captured images from a camera installed on a road. Determines the mode information of the camera's daylight mode or infrared mode according to the brightness to control the camera to collect the captured image of the entrance and exit of the vehicle on the road, and the number of vehicles waiting for each lane based on the vehicle speed detected from the captured image. The traffic information message may be generated and transmitted to the traffic information center 130 or the traffic signal controller 140 through a network 110 in a wired or wireless communication manner. Accordingly, the traffic information center 130 may guide the traffic volume information through the wired or wireless communication network of the network 110 according to the traffic information message, and the traffic signal controller 140 may control the traffic light according to the traffic information message. have.

In the system 100 for controlling a traffic signal according to an embodiment of the present invention, in order to minimize the influence of the external illumination as described above, it was intended to obtain an optimal camera image even in a day or night image or a change in the weather. Therefore, it is possible to accurately estimate the waiting length of vehicles at intersections, to collect and monitor traffic information wirelessly, and to automatically control traffic signals, that is, vehicle traffic lights, to facilitate traffic flow.

For detailed operation of the system 100 for controlling traffic signals according to an embodiment of the present invention, a detailed block diagram of the image detector 120 of FIG. 3 and a specific block diagram of the digital signal processor 340 of FIG. 5, and the data format of the traffic information message of FIG. 6.

Referring to FIG. 3, the image detector 120 according to an embodiment of the present invention may include an image acquisition device 310, an image acquisition device controller 320, a day / night mode control device 330, and a digital signal processor 340. And a wireless communication module 350. Here, the day and night mode control device 330 is a day and night mode controller 331, the image processor 332, the image color coordinate means 333, the detector 334, the sensor input unit 335, the system clock generator 336 And a system clock source 337.

First, the operator may input predetermined settings from the outside to the image capturing device controller 320 to control an operation such as pan, tilt, zoom in, or zoom out of the camera, and thus the image capturing device controller 320 The camera operation control signal associated with the operation of the camera may be generated (S510). Setting values input to the image capturing device controller 320 may be input from a computer or a dedicated device such as a notebook PC through RS-232 serial communication, and the image capturing device controller 320 generates a corresponding camera operation control signal. In operation S520, the image capturing apparatus 310 may control a camera installed on a road such as an intersection to collect a captured image of the vehicle entrance and exit on the road.

In addition, the day and night mode control device 330 determines the day mode or the night mode based on time information, ambient weather information, or contrast information on captured images from a camera installed on a road, and thus obtains an image acquisition device controller 320. It can be notified (S510). Accordingly, the image capturing apparatus controller 320 may generate mode information on the daylight mode or the infrared mode of the camera according to the day mode or the night mode determined by the day / night mode control apparatus 330, and the image obtaining apparatus 310 ) Controls the camera to the daylight mode or the infrared mode according to the mode information to collect the captured image of the vehicle entrance and exit on the road (S520).

The camera, which is installed on a road with vehicle entry and exit, such as an intersection, has a wide pan and a tilt, for example, pan 0 to 350 degrees and tilt -70 to 20. It can be operated to move left and right or up and down by degrees (± 5 degrees error), and it is also possible to periodically repeat the operation with a certain pan and tilt according to the camera motion control signal set above for the road. In addition, the camera may capture an image of a vehicle on a road using the illumination of the external environment in the daylight mode according to the above mode information, and detect the infrared ray in the infrared mode corresponding to the fall of the illumination. To capture a corresponding image of a vehicle on the road. Such a camera may be in the form of a digital camera, or may be a CCTV camera that supports an infrared mode.

Referring to the operation of the day and night mode control device 330 in more detail, first, the system clock generator 336 may generate the time information by counting the system clock source (337). As the system clock source 337, current time information carried on a predetermined channel through a broadcasting network such as DMB or DAB, or a satellite communication network can be utilized. In addition, the use of an oscillator such as a crystal oscillator as the system clock source 337 is not limited.

The detection unit 334 includes various sensors for detecting ambient weather related information such as humidity, illuminance, or heat sensor, and a set value input to the humidity, illuminance, or heat sensor through the sensor input unit 335. The ambient weather information may be generated as a digital value by detecting weather related information such as humidity, illuminance, or heat of the air. The operator may input a predetermined set value such as zero adjustment, gain adjustment, etc. to properly operate the humidity, illuminance, or heat detection sensor through the sensor input unit 335.

The image processor 332 may correct a color of the captured image acquired by the image capturing apparatus 310 by using image color coordinate means 333, and apply corresponding contrast information to the corrected captured image. Can be generated. If the color of the captured image is not appropriate, the operator can change the table value managed by the image color coordinate means 333. Accordingly, the image processor 332 according to the table value R (Red), G ( Green), B (Blue) color correction, gamma correction, etc., and contrast information is calculated according to a predetermined algorithm that calculates the maximum brightness (contrast ratio) to the lowest brightness for the color-corrected captured image. Output to the controller 331.

Accordingly, the day and night mode controller 331 classifies a predetermined time zone for distinguishing day and night, such as sunrise and sunset, according to the time information generated by the system clock generator 336, and operates the camera in daylight mode at day time. It is possible to determine the day mode for the camera and to determine the night mode for operating the camera in the infrared mode at night time. At this time, even in the daytime mode as described above, the day and night mode controller 331 is a night mode if the contrast information from the image processor 332 is also below the threshold when the ambient weather information generated by the detector 334 indicates cloudy weather. It is possible to determine that.

As described above, the day and night mode control device 330 is based on the time information from the system clock generator 336, the ambient weather information from the sensor 334, or the contrast information from the image processor 332, or The night mode may be determined, and the image acquisition device controller 320 may be notified.

In this way, based on the camera operation control signal and the mode information from the image acquisition device controller 320, the image acquisition device 310 properly controls the camera in the required direction and operates in the daylight / infrared mode, so that As the captured image is collected, the digital signal processor 340 encodes the captured image in a predetermined manner and transmits the captured image to the traffic information center so that the operator can monitor the traffic state of the dogo from the video (S530). On the basis of the vehicle speed detected from the captured image as described above, a traffic information message including the number of vehicles waiting for each lane may be generated (S540 to S590).

Referring to FIG. 4, the digital signal processor 340 according to an embodiment of the present invention may include an image updater 410, an image subtractor 420, a lane detector 421, a shadow extractor 422, and a feature point. Information unit 430, memory 431, vehicle speed detector 432, air length estimator 440, traffic information update unit 450, timer 451, video encoder 460, and format converter 470 It includes.

First, the video encoder 460 may generate encoded image data by encoding a captured image from the image capturing apparatus 310 in a predetermined manner. Accordingly, the format converter 470 may convert the data format into a predetermined bit stream according to a wireless communication method (or wired communication method) to be transmitted to the network 110. The wireless communication module 350 may transmit the bit stream of the captured image generated by the format converter 470 to the traffic information center 130 wirelessly through the network 110 such as a broadcasting network or a mobile communication network (S530). When using a predetermined wired communication module, it is also possible to transmit a bit stream of the captured image generated by the format converter 470 to the traffic information center 130 through a predetermined dedicated wired network.

Meanwhile, the image updater 410 may update and output a still image by selecting a predetermined period, for example, in units of 1 second, 10 seconds, etc., from the captured images collected by the image capturing apparatus 310. .

The lane detecting unit 421 may detect a lane on a road from the still image output from the image updating unit 410 (S540). The shadow extractor 422 may extract an image excluding the vehicle and the lane from the still image, including the shadow of the vehicle on the road (S540). For example, the lane detector 421 and the shadow extractor 422 may perform preprocessing such as low pass filtering, Gaussian filtering, and median filtering on the input image to remove unnecessary images such as noise. -processing, and analyze the corresponding still image according to histogram algorithm, edge algorithm, labeling algorithm, etc. to detect lanes, or to separate and extract vehicles and non-lane images. Can be.

The image subtractor 420 removes the vehicle extracted by the shadow extractor 422 and the image except the lane from the still image from the image updater 410, thereby waiting for the vehicle based on the lane detected by the lane detector 421. The region of interest for each lane for estimating the length may be determined (S550).

 The feature point information unit 430 may extract the feature point vector of each vehicle in the ROI and store it in the memory 431 (S560). Here, the feature point vector may be a shape of a vehicle (a contour shape for distinguishing a car, a bus, a truck, etc.), a length (the length of a vehicle to be measured for a vehicle size), or an edge compared with a corresponding vehicle in a previous still image. The amount of change (the amount of movement of the contour edge for grasping the movement of the vehicle) may be included.

The vehicle speed detector 432 may detect the vehicle speed of each vehicle by using the feature point vector stored in the memory 431 as described above (S570). For example, the vehicle speed of each vehicle may be detected based on the edge change amount for each vehicle length of a car, a bus, a truck, and the like.

The waiting length estimating unit 440 may estimate the number of waiting vehicles for which the vehicle speed is smaller than a predetermined value for each lane (S580). The traffic information updater 450 may generate a traffic information message about the waiting length of the vehicle for each lane and the number of waiting vehicles. The traffic information updater 450 may update the traffic information message generated as described above at a predetermined time interval according to the operation of the timer 451, and transmit the updated traffic information message to the traffic information center 130. In addition, the traffic information message updated as described above may be transmitted to the traffic signal controller 140 according to a radio request from the traffic signal controller 140 (S590). Alternatively, when the traffic information center 130 receives the traffic information message, the traffic information center 130 transmits the corresponding traffic information message to the traffic signal controller 140 in response to a radio request from the traffic signal controller 140. It is possible.

The data format of the traffic information message generated by the traffic information updater 450 is shown in FIG. 6. In FIG. 6, 'Number' represents a number of a corresponding video detector assigned to a corresponding direction of an intersection, and 'Video Image Detector Name' represents an alias of a detector assigned to an image detector. In addition, 'Valid Time' refers to the valid time available when transmitting a message wirelessly, 'Extended Header' is used when there is an extended header or data, and 'Flag', which indicates the presence of additional header or data, The length of the data consists of 'Length', and the 'Flag' indicating the type of the data. 'N-Length' indicates the number of information as many lanes as detected, 'Intersection's Locate' means the area name of the intersection where the detector is installed, and when the wireless data transmitted in free space reaches the neighboring intersection, This allows you to distinguish and share information from neighboring intersections. 'Camera Position' indicates the angle or height at which the camera is installed. 'Que-Length' The waiting length of the lane, 'Average Vehicle Speed' is the average vehicle speed in the lane, and 'Number of a vehicle' is the number of waiting vehicles included in the lane's waiting length. #. Small ',' #. Middle ',' #. Big 'means the number of vehicles by size of each vehicle. 'Error Redundancy Code' refers to an error detection or correction code of the remaining data except for the extended header. In addition, additional data 'Extended Data' is included as long as 'Length' defined in 'Extended Header', and the entire error correction or detection code can be inserted into the 'Total Packet Error Redundancy Code'.

The traffic information message having the data format as described above is transmitted to the traffic information center 130 or the traffic signal controller 140 in a wired or wireless communication manner, and the traffic information center 130 according to the traffic information message according to the wired or wireless communication network. Traffic volume information may be guided to a web server, a mobile communication terminal, and the like, and the traffic signal controller 140 may appropriately control a vehicle traffic signal according to the corresponding traffic information message so that the traffic flow may be smoothly maintained (S600). ). For example, if the number of waiting vehicles is greater than or equal to a certain size, the turn-on holding time of the green light of the traffic light may be longer than the usual setting value, otherwise the green light of the traffic light may be changed according to the usual setting value. It is possible to maintain the turn-on holding time at the same time as the traffic lights in the other direction.

As described above, optimal embodiments have been disclosed in the drawings and the specification. Although specific terms have been used herein, they are used only for the purpose of describing the present invention and are not intended to limit the scope of the invention as defined in the claims or the claims. Therefore, those skilled in the art will understand that various modifications and equivalent other embodiments are possible from this. Therefore, the true technical protection scope of the present invention will be defined by the technical spirit of the appended claims.

1 is a view for explaining a general operation diagram of the ITS.

2 is a view for explaining a system for traffic signal control according to an embodiment of the present invention.

3 is a detailed block diagram of an image detector according to an embodiment of the present invention.

4 is a detailed block diagram of a digital signal processing unit according to an embodiment of the present invention.

5 is a flowchart illustrating an operation of a system for controlling traffic signals according to an embodiment of the present invention.

6 is a diagram for describing a data format of a traffic information message according to one embodiment of the present invention.

Claims (7)

Day and night mode control device for determining the day or night mode based on the time information, ambient weather information, or contrast information on the captured image from the camera installed on the road; Generate mode information on the daylight mode or infrared mode of the camera according to the determined day mode or night mode, and generate a camera operation control signal for controlling pan, tilt, zoom in, or zoom out of the camera according to an external input. An image acquisition device controller; An image acquisition device configured to control the camera based on the mode information and the camera operation control signal to collect the captured image of a vehicle entrance and exit on a road; And A digital signal processor configured to generate a traffic information message including the number of vehicles waiting for each lane based on the vehicle speed detected from the captured image; The traffic information message is transmitted to a traffic information center or a traffic signal controller in a wired or wireless communication manner, and the traffic information center guides traffic volume information through a wired or wireless communication network according to the traffic information message, and in the traffic signal controller And the traffic light is controlled according to the traffic information message. According to claim 1, The day and night mode control device, A system clock generator for generating the time information by counting a predetermined system clock source; A detector configured to detect ambient humidity, illuminance, or heat based on a set value input to a humidity, illuminance, or heat sensor and generate the ambient weather information as a digital value; An image processor configured to generate contrast information of the captured image corrected according to color correction of the captured image; And The day mode is determined based on the time information, and the night mode is determined at night time. When the contrast information is less than a threshold when the ambient weather information indicates cloudy weather even in the daytime mode, the night mode is determined. Day and night mode controller to determine Image detector comprising a. The method of claim 1, wherein the digital signal processing unit, An image updater configured to update the still image by selecting the captured image at regular intervals; A lane detecting unit detecting a lane on a road from the still image; A shadow extracting unit which extracts an image excluding the vehicle and the lane from the still image, including a shadow of the vehicle on a road; An image subtractor configured to determine a vehicle selection region of interest by removing an image excluding the vehicle and the lane from the still image; A feature point information unit to extract a feature point vector of each vehicle in the ROI and store it in a memory; A vehicle speed detector for detecting a vehicle speed of each vehicle using the feature point vector stored in the memory; A waiting length estimating unit for estimating the number of waiting vehicles having the vehicle speed smaller than a predetermined value for each lane; And Traffic information updating unit for generating the traffic information message for the number of waiting vehicles for each lane Image detector comprising a. The method of claim 3, wherein the feature point vector, An image detector comprising a shape, a length of a vehicle, or an edge change amount compared with a corresponding vehicle in a previous still image. The method of claim 3, wherein the traffic information update unit, The traffic information message is updated at regular time intervals according to the operation of a timer. And the updated traffic information message is transmitted to the traffic information center or the traffic signal controller in response to a request from the traffic information center or the traffic signal controller. The method of claim 3, wherein the digital signal processing unit, A video encoder for generating encoded image data encoding the captured image in a predetermined manner; And A format converter for converting the encoded image data into a bit stream to be transmitted to the wired or wireless communication network Image detector, characterized in that it further comprises. Determining a day mode or a night mode based on time information, ambient weather information, or contrast information on captured images from a camera installed on a road; Generating mode information on a daylight mode or an infrared mode of the camera according to the determined day mode or night mode; Collecting the captured image of the vehicle entry / exit on the road by controlling the camera based on a camera operation control signal and the mode information generated to control the pan, tilt, zoom in, or zoom out of the camera according to an external input. ; And Generating a traffic information message including the number of vehicles waiting for each lane based on the vehicle speed detected from the captured image; The traffic information message is transmitted to a traffic information center or a traffic signal controller in a wired or wireless communication manner, and the traffic information center guides traffic volume information through a wired or wireless communication network according to the traffic information message, and in the traffic signal controller And a traffic light in accordance with the traffic information message.

Images