KR102313634B1 - Lighting device that irradiates light indicating traffic information and intelligent transport system comprising the lighting device and method performed by the system for providing traffic information - Google Patents

Abstract

A real-time traffic information providing method, performed by a lighting device disposed on a road or a tunnel, according to one embodiment of the present invention includes the steps of: collecting information on at least one of an image, video, temperature, and humidity in a preset range through a plurality of sensors included in the lighting device or receiving weather information and road condition information from a traffic control server in real time; identifying traffic information based on the information collected through the plurality of sensors or the weather information and road condition information received from the traffic control server; extracting a text or image previously matched with the identified traffic information; and exposing the traffic information by controlling a light emitting part to emit light formed in the form of the extracted text or image to a floor surface.

Description

LIGHTING DEVICE THAT IRRADIATES LIGHT INDICATING TRAFFIC INFORMATION AND INTELLIGENT TRANSPORT SYSTEM COMPRISING THE LIGHTING DEVICE AND METHOD PERFORMED BY THE SYSTEM FOR PROVIDING TRAFFIC INFORMATION}

The present invention relates to a lighting device irradiating light for displaying traffic information, an intelligent traffic information providing system including the same, and a traffic information providing method performed on the system. It relates to a technology for displaying traffic information on a road in real time through a light emitting device capable of output and intensity control.

In recent transportation systems, Intelligent Transport Systems (ITS) have been introduced, which improve efficiency and stability by providing traffic information and services through transportation means and facilities incorporating technologies such as electronics, control and communication, and utilizing them. have.

Examples include a public transportation location guidance system that can be encountered in everyday life, a system that automatically changes vehicle signals depending on the amount of traffic, real-time traffic information provided by navigation, and high-pass.

In addition, such an intelligent transportation system is developing into a next-generation intelligent transportation system (Cooperative-Intelligent Transport Systems, C-ITS) in which a vehicle informs the driver of surrounding roads and traffic conditions in real time.

This is a linkage method that basically collects data from driving vehicles in real time and analyzes them to provide traffic information to each vehicle, and it means a paradigm shift from road management to user safety.

Specifically, equipment including sensors that detect vehicle movement are installed around the road to collect status information about the vehicle in motion, and based on this, traffic jams, frequent accidents, number and speed of driving vehicles, etc. data and manage it.

After that, the real-time traffic situation and unexpected situation are transmitted to the driving vehicle through the equipment installed on the road, and precise location information is provided. In addition, safety and mobility are improved by notifying the risk of sudden braking, stopping, and collision through communication between adjacent vehicles.

In this way, C-ITS enables the driver to take a proactive response and effectively prevents traffic accidents.

On the other hand, although equipment such as vehicle detectors constituting the intelligent transportation system is gradually being improved in performance, it is difficult to efficiently arrange and manage it because it is exposed to the outside. In addition, there is a limit to covering numerous roads due to spatial and economic problems.

In this regard, since a lighting device such as a street lamp in a road or a tunnel is an essential element, an arrangement space is allocated at a certain location, but an additional function other than the general function of illuminating the road is not considered.

The present invention discloses a lighting device for providing traffic information to a driver by identifying real-time traffic information and irradiating light formed as text or images representing the same on a road surface in order to solve the problems of the prior art.

In addition, through an embodiment of the present invention, an intelligent traffic information providing system including the lighting device and a real-time traffic information providing method performed on the system are disclosed.

According to an embodiment of the present invention, the method for providing real-time traffic information, performed by a lighting device disposed on a road or a tunnel, includes images, images, temperature and humidity in a preset range through a plurality of sensors included in the lighting device. Collecting at least one of the information or receiving weather information and road condition information from a traffic control server in real time; identifying traffic information based on the information collected through the plurality of sensors or weather information and road condition information received from the traffic control server; extracting text or images previously matched with the identified traffic information; and exposing the traffic information by controlling the light emitting unit to irradiate the light formed in the form of the extracted text or image to the floor surface.

According to an embodiment of the present invention, the step of recognizing the traffic information further includes the step of recognizing traffic information based on wheel state information received from a vehicle located within a preset distance from the lighting device, wherein the wheel The traffic information identified based on the state information includes road surface state information of a road on which the lighting device is installed.

According to an embodiment of the present invention, the light emitting unit includes at least one light emitting element, wherein the light emitting element is subdivided into a predetermined pixel unit, and text is turned off and dimming is controlled for each pixel. Alternatively, light in the form of an image is formed.

According to an embodiment of the present invention, the step of extracting the text or image matched with the identified traffic information may include: calculating a risk score for each traffic information when there are a plurality of the identified traffic information; and extracting a text or image matched to traffic information having the highest risk score as a result of comparing the calculated risk score, or extracting text or image matching traffic information in which the calculated risk score is equal to or greater than a preset reference value; Including, but, when a plurality of texts or images matching the traffic information equal to or greater than the reference value are extracted, the light formed by the plurality of extracted texts or images is divided into preset areas and irradiated simultaneously or in the order of a high risk score for irradiation time This is set to be long and sequentially irradiated.

According to an embodiment of the present invention, the process of recognizing the road surface state information of the road on which the lighting device is installed may include detecting an identification signal of a vehicle located within the preset distance, and detecting the vehicle one included in the detected identification signal. Receives at least one of an acceleration signal, a geomagnetic signal, a pneumatic signal, a temperature signal, and a gyro sensing signal for the wheel on the side of the side, converts the received signal into a signal in the frequency domain, and converts the converted signal in the frequency domain to a preset signal It divides into sections, extracts representative data for each section, calculates a feature vector, performs size scaling on each calculated feature vector, and applies each size-scaled feature vector to a classification model. is applied to extract road surface condition information, and the classification model uses at least one of a wheel acceleration signal, a geomagnetic signal, a pneumatic signal, a temperature signal, and a gyroscope sensing signal as an input value, and one of the road surface condition information classified according to a preset standard It is pre-trained by a predetermined artificial neural network model designed to output .

According to an embodiment of the present invention, the step of recognizing traffic information based on the weather information and road condition information received from the traffic control server includes converting the weather information and road condition information received in real time into a risk score. step; and transmitting weather information and road condition information in which the converted risk score is equal to or greater than a preset reference value to a vehicle located within a preset distance from the lighting device; Transmitting a retransmission request signal of the weather information and road condition information together with the identification information of the lighting device to the traffic control server when the traffic information identified based on the information collected through the sensor and a preset error range are shown further includes

According to an embodiment of the present invention, the step of recognizing traffic information based on information collected through the plurality of sensors or weather information and road condition information received from the traffic control server may include: extracting road surface characteristic information of an area in which the lighting device is installed based on the image and image information; extracting a road friction coefficient estimation function by applying at least one of the road surface characteristic information and the temperature and humidity information collected through the plurality of sensors to a road friction coefficient estimation model; By applying at least one weather state value among the weather information received from the traffic control server as a parameter to the extracted road friction coefficient estimation function, a preset probability calculation indicating the correlation between the road friction coefficient and the weather is performed. estimating a road friction coefficient value; extracting one of the road surface condition information classified according to a preset criterion corresponding to the estimated road surface friction coefficient value; and transmitting the estimated road friction coefficient value or the extracted road surface condition information to a vehicle located within a preset distance; wherein the road friction coefficient estimation model collects and accumulates road surface characteristic information for a preset period; It is pre-trained by a predetermined machine learning model designed to take temperature information, humidity information, and weather information as input values, and output a road friction coefficient estimation function representing a road friction coefficient value according to the weather information.

In one embodiment of the present invention, by exposing various traffic information such as weather, traffic volume, congestion status, accident status, speed limit, road surface condition, etc. related to the current road situation in the form of lighting on the road surface, the driver can visually recognize it easily This can lead to safe driving.

In addition, by selectively outputting light according to the detected traffic information, it is possible to reduce excessive light pollution and create a comfortable driving environment.

The lighting device according to an embodiment of the present invention may contribute to the sophisticated operation of a traffic system and to secure traffic analysis data by providing traffic-related data collected in a corresponding section through communication linkage with a traffic control server.

In addition, traffic information can be provided dually through communication linkage with the vehicle, thereby inducing a driver's proactive response more effectively, thereby strengthening accident prevention.

As such, a general function of a lighting device disposed on a road or a tunnel is further improved as a function of identifying and displaying traffic information, thereby overcoming the spatial limitation of the intelligent traffic system. In addition, it does not require any other equipment, so it provides a solution to the economic problem.

In other words, since the equipment constituting the intelligent transportation system is implemented in the form of street lights or tunnel lights, it can be precisely placed at the intended location, enabling more effective management.

1 is a structural diagram of an intelligent traffic information providing system according to an embodiment of the present invention.
2 is a block diagram illustrating a configuration of a lighting device according to an embodiment of the present invention.
3 is a flowchart of a method for providing real-time traffic information according to an embodiment of the present invention.
4 is a flowchart of a first embodiment of a process in which the lighting device extracts road surface condition information.
5 is a flowchart of a second embodiment of a process in which the lighting device extracts road surface condition information.
6 is an exemplary view for explaining the characteristics of a light emitting device in a lighting device according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, this means that other components may be further included rather than excluding other components unless otherwise stated.

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' is not limited to software or hardware, and '~ unit' may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, '~' denotes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

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

1 is a structural diagram of an intelligent traffic information providing system according to an embodiment of the present invention.

The intelligent traffic information providing system according to an embodiment of the present invention may include a lighting device 100 and a traffic control server 200, and is linked to a vehicle 300 traveling on a road on which the lighting device 100 is disposed. so it can work.

First, the lighting device 100 according to an embodiment of the present invention may be a device in the form of a street lamp that is disposed at a preset position in a road or a tunnel and illuminates the surroundings by irradiating light on the road floor. That is, the basic lighting function is naturally performed, and an example is given in the form of a street lamp, but depending on the location where it is arranged, the shape manufactured or the area for irradiating light (eg, the inner wall of the tunnel) may vary, and these contents provide the present invention It is not limiting.

Referring to FIG. 2 , the lighting device 100 according to an embodiment of the present invention may be represented as detailed components according to functions performed, which include the control unit 110 , the sensing unit 120 , and the light emitting unit ( 130), a communication unit 140, and a database (not shown).

The detection unit 120 may be composed of a plurality of sensors, among a camera sensor that captures an image or an image within a preset range around the lighting device 100 , a temperature sensor that detects temperature, and a humidity sensor that detects humidity At least one may be included.

The location at which each sensor is installed in the lighting device 100 is not limited, but, for example, in the case of a camera sensor that takes an image or an image on the floor (road surface), it is installed in a protruding area to be incident perpendicularly to the floor surface. Therefore, it may be desirable to generate an accurate road surface image without an error according to an angle. In addition, a rotatable camera sensor may be configured for the purpose of determining whether there is a traffic jam or an accident, thereby securing a wider shooting area. In addition, a plurality of camera sensors, including fixed and rotary type, may be configured to collect various image or image information according to the type of traffic information to be grasped.

Meanwhile, various methods may be adopted for the camera sensor according to the purpose and characteristics of the road on which the lighting device 100 is disposed. For example, in order to precisely analyze the condition of the road surface, a CCD method that transmits the electric charge generated by light energy as it is may be used in consideration of excellent quality such as low noise and high magnification.

Alternatively, the CMOS method may be used in consideration of low power, processing speed, and economical aspects, and it may be desirable to configure a sensor of the corresponding method in order to determine road conditions such as traffic jams and accidents.

In addition, a multi-sensor in which several sensors are included in one camera may be adopted. This is a format in which the sensor is configured for each wavelength region of the collected light, and may include one or more of a color (Bayer) and monochrome (Mono) sensor, an RGB sensor, and an infrared region sensor to enable more sophisticated image analysis. For example, this method may be preferable in the case of a road that is greatly affected by weather or where cracks, black ice, and the like frequently occur.

The controller 110 according to an embodiment of the present invention may control the overall function of the lighting apparatus 100 and perform a preset operation.

Specifically, by collecting at least one of an image, an image, a temperature, and a humidity from the sensing unit 120 , traffic information may be identified based on the collected information. For example, by analyzing a road surface image received from a camera sensor, road surface condition information such as snow, ice, and wet conditions may be identified. Alternatively, traffic jam or accident occurrence information may be grasped based on image information captured by the camera sensor. Alternatively, weather-related traffic information may be identified based on information received from the temperature and humidity sensors.

Also, the controller 110 may determine traffic information based on weather information and road condition information received from the traffic control server 200 . For example, in a general case in which no unusual occurrence occurs, speed limit information received from the traffic control server 200 may be set as traffic information.

In addition, traffic information may be identified based on wheel state information received from the lighting device 100 and the vehicle 300 traveling at a preset distance. For example, the received wheel acceleration information may be pre-processed according to a preset algorithm and applied to a pre-learned and constructed classification model to determine road surface condition information.

According to an embodiment of the present invention, the control unit 110 may grasp traffic information at every preset period. You can set the priority through the set operation.

The controller 110 may extract text or an image previously matched with the identified traffic information. According to an embodiment, traffic information may be classified according to its type, such as weather, road surface condition, road condition, etc., text or image indicating the condition of each type is matched in a table format and stored in advance in a database (not shown). there may be

Thereafter, the controller 110 may control the light emitting unit 130 to irradiate the light in the form of an extracted text or image to the floor surface to expose the traffic information to the driver. That is, by controlling the light emitting element included in the light emitting unit 130 to turn off and dimming on a pixel-by-pixel basis, a message indicating traffic information may be output in a lighting format.

Meanwhile, according to an embodiment of the present invention, the controller 110 may control the communication unit 140 to transmit the identified traffic information to the traffic control server 200 or the vehicle 300 traveling within a preset distance.

The light emitting unit 130 according to an embodiment of the present invention may include at least one light emitting device. Although the type of the light emitting device is not limited here, an LED white device may be preferable in consideration of performance and price.

Each light emitting device (LED white device) may be subdivided into predetermined pixel units. 6 shows a state in which a conventional LED device is subdivided into multiple pixels through microfabrication.

As a specific example of this state, each pixel may have a square shape with a length of 40 μm. In addition, an interval between each pixel may be formed to be very small as 1 μm. The LED device may include a semiconductor layer having an active region for generating light for each pixel, and the semiconductor layer may be formed on a predetermined silicon substrate separated from the main substrate of the LED device. The semiconductor layer is completely isolated between adjacent pixels, between which it can be filled with an optically isolating layer, such as titanium dioxide scattering particles. In addition, a light emitting material is deposited on the semiconductor layer, and an optical isolation layer may be interposed therebetween. A control unit capable of integrated control of one pixel or a predetermined number or all of the pixels may be included in the silicon substrate configured with the semiconductor layer, and preferably, the control unit may be configured for each pixel.

According to an embodiment of the present invention, as in the above-described example, the light emitting device can be turned off and dimmed for each pixel manufactured by microfabrication, so that in addition to simply emitting white light to brighten the surroundings, a specific shape can be obtained. The branch can be irradiated with light. That is, light in the form of text or images can be formed by being individually controlled for each pixel, and thus, a function of delivering a kind of message to the driver can be performed.

The communication unit 140 according to an embodiment of the present invention may include a predetermined wireless communication module, and functions to connect the lighting device 100, the traffic control server 200, and the vehicle 300 through a wireless network. carry out Here, the wireless communication module may include, but is not limited to, Bluetooth (Bluetooth Low Energy), NFC, RFID, Ultrasonic, Infrared, Wi-Fi, LiFi, and the like. In addition, the wireless network includes a local area network (LAN), a wide area network (WAN), the Internet (WWW: World Wide Web), a wireless data communication network, and an example of a wireless data communication network includes 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, ultrasonic communication, visible light communication (VLC: Visible) Light Communication), LiFi, etc., but are not limited thereto.

Referring back to FIG. 1 , the traffic control server 200 according to an embodiment of the present invention may refer to a server operated by the ITS center in charge of the intelligent traffic information providing system. The traffic control server 200 may receive traffic information from each of the lighting devices 100 to determine the traffic condition of each road section and update it in real time. In addition, identification information of each lighting device 100 and a specific area such as a road, a section, and a region associated with each lighting device 100 can be matched in advance and set, and there is a change in the traffic condition of a preset standard in the matched area In this case, it may be immediately notified to the corresponding lighting device 100 . For example, when weather state values such as temperature, humidity, precipitation, and snowfall in the matched area show a difference in a preset range from the current value, the updated weather information may be transmitted to the corresponding lighting device 100 . Alternatively, when road condition values such as average vehicle speed, traffic volume, and area transit time in the matched area show a difference between preset ranges and when an accident is detected, the lighting device 100 corresponding to the updated road condition information can be sent to Of course, when the lighting device 100 receives the weather information and road condition information, it may update the traffic information based thereon.

Of course, the traffic control server 200 may directly exchange information with each vehicle 300 . For example, based on the GPS system, the position, speed, etc. of each vehicle 300 can be determined, and according to an embodiment of the present invention, wheel state information transmitted by each vehicle 300 at a preset period is displayed. can receive Here, the wheel state information may include at least one of an acceleration signal, a geomagnetic signal, an air pressure signal, a temperature signal, and a gyroscope sensing signal of the wheel according to time.

According to an embodiment of the present invention, the traffic control server 200 may include a plurality of cloud servers (not shown) for each preset area. Here, the cloud server may perform learning to extract the road surface friction coefficient or road surface condition information of the corresponding area through a predetermined machine learning model. Also, the cloud server may be in a state of being connected to the lighting devices 100 disposed in the corresponding area. An embodiment related thereto will be described later.

Hereinafter, an embodiment of a method of providing real-time traffic information performed by the lighting device 100 will be described with reference to FIG. 3 . A common description is intended to replace the above-mentioned content.

3 is a flowchart of a method for providing real-time traffic information according to an embodiment of the present invention.

In step S310 , the lighting device 100 may collect at least one information of an image, an image, a temperature, and a humidity in a preset range through the sensing unit 120 . In addition, it is possible to receive weather information and road condition information from the traffic control server 200 in real time.

In step S320 , the control unit 110 of the lighting device 100 may determine traffic information based on information collected through the sensing unit 120 or weather information and road condition information received from the traffic control server 200 . . Here, the traffic information may be information on situations such as traffic congestion, congestion, and accidents ahead, or may be weather-related information such as snow and rain, or information related to driver operation such as speed limit and road surface conditions, and traffic information The configuration of does not limit the present invention.

In addition, the initial information of the traffic information may be set in advance. For example, in normal times, speed limit or road surface condition information may be set as traffic information. Thereafter, when the information on a sudden situation such as the occurrence of an accident ahead is grasped, it can be set as additional traffic information or the traffic information can be changed. That is, as described above, traffic information may be identified and set in single or plural pieces at the same time.

In addition, when the place where the lighting device 100 is disposed is a tunnel, the detected traffic information may be road condition information outside the tunnel. In other words, it is possible to induce safe driving by detecting heavy snowfall, accidents, congestion, black ice, etc. outside the tunnel in advance and providing it to the driver.

Hereinafter, with reference to FIGS. 4 and 5 , embodiments in which the lighting device 100 detects road surface state information among traffic information will be introduced.

4 is a flowchart of a first embodiment of a process in which the lighting device extracts road surface condition information.

Before step S410 , a classification model for extracting road surface condition information may be previously built in the lighting device 100 , or may be connected to a cloud server including the classification model.

Specifically, the traffic control server 200 may collect a vast amount of wheel state information from vehicles 300 traveling within a specific area. Alternatively, wheel state information collected by the lighting devices 100 arranged in the corresponding area may be received from the lighting devices 100 . The wheel state information may include an acceleration signal for the wheel, a geomagnetic signal, an air pressure signal, a temperature signal, and a gyroscope sensing signal. Thereafter, the collected wheel state information can be transmitted to a cloud server corresponding to the corresponding area, and the cloud server receives wheel state information, that is, wheel acceleration, geomagnetism, air pressure, temperature and When the gyroscope sensing signal is input, it can be learned to output one of the road surface condition information classified according to a preset criterion. The road surface condition classification criterion may be, for example, ICE/SNOW/WET/DRY, but is not limited thereto.

The artificial neural network applied here is not limited in its composition such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), etc., but CNN (Convolution Neural Network) is adopted according to the characteristics of the input value. This is desirable to avoid learning speed and overfitting problems. For example, since a tire has characteristics of deformation or air pressure change at the moment it comes into contact with the ground and falls, such characteristics can be extracted first and set as an input value. In this way, when the CNN model is applied, since it does not require wheel state information for all time periods, the layers of the artificial neural network can be reduced, and accordingly, it can be designed relatively simply to reduce errors and reduce learning speed and road surface conditions. The extraction rate can be improved.

By such learning, a classification model for extracting road surface condition information may be built in the cloud server. According to an embodiment of the present invention, the built classification model may be stored in advance in each lighting device 100 connected to the corresponding cloud server. Alternatively, when the lighting apparatuses 100 receive wheel state information from the vehicle 300 , it may be of a type in which it is transmitted to a cloud server to receive road surface state information. Of course, even after the classification model is constructed, since wheel state information is continuously collected, the classification model can be continuously updated accordingly. That is, as the new wheel state information is applied again as an input value, the number of hidden layers and nodes of the artificial neural network may increase, and accordingly, the activation function connecting each node and the applied weight may be updated.

Thereafter, in step S410 , the lighting device 100 may detect an identification signal of the vehicle 300 traveling within a preset distance through the communication unit 140 . For example, the communication unit 140 may include a Bluetooth module, and a beacon mode may be possible. Through this, the communication unit 140 may continuously output the beacon signal within a preset distance, and when the vehicle 300 enters within the corresponding distance, it may receive the beacon signal. The request signal of the vehicle 300 by the received beacon signal is an identification signal and may include wheel state information. Here, the wheel state information may be at least one of an acceleration signal, a geomagnetic signal, an air pressure signal, a temperature signal, and a gyroscope sensing signal for a wheel on one side of the vehicle 300 .

In step S420, the received wheel state information signal may be converted into a frequency domain. For example, the received wheel acceleration signal according to time may be converted into a tire deformation signal according to frequency through fast Fourier transform (FFT).

Next, the converted frequency domain signal may be divided into preset sections. Tire deformation data indicating the extent to which the tire is deformed for each section may be extracted.

A feature vector may be calculated by extracting representative data for each segment divided in step S430. That is, the tire deformation strength for each frequency can be vectorized, and the tire deformation strength corresponding to one rotation of the tire including the moment the tire comes into contact with the ground and falls is dimensionalized. For example, when a section corresponding to one rotation is divided into n pieces, an n-dimensional feature vector may be calculated. In addition, a feature vector for wheel rotation from when the lighting device 100 receives the wheel state information until the vehicle 300 goes out of a communication range with the lighting device 100 may be calculated. Accordingly, a plurality of feature vectors may be calculated.

Next, size scaling may be performed on each feature vector. For example, in order to remove a momentary abnormal deformation caused by a piece of asphalt, filtering can be performed to quantize the value of the feature vector to remove data in the ultra-high frequency region. Alternatively, in order to mainly determine the deformation at the moment when the tire comes into contact with the ground and falls during each rotation, preset maximum and minimum values may be applied to the feature vector to reduce the size. In this way, when the wheel state information is characterized based on the CNN algorithm, the processing speed can be increased and the accuracy in extracting the road surface state information can be improved.

In step S440, each of the size-scaled feature vectors may be applied as an input value to a classification model built in advance according to the above-described process. Accordingly, road surface condition information of one of ICE/SNOW/WET/DRY is output, and the controller 110 may set it as traffic information.

5 is a flowchart of a second embodiment of a process in which the lighting device extracts road surface condition information.

Before step S510, a road friction coefficient estimation model may be built. This may be used to extract more sophisticated road surface condition information by grafting the weather information received from the traffic control server 200 to the information collected by the lighting device 100 itself through the sensor unit 120 in real time. Here, the road friction coefficient estimation model is obtained by inputting a vast amount of road surface images, temperature and humidity information accumulated by the lighting device 100 for a preset period, and weather information of various criteria previously collected by the traffic control server 200. , may be pre-trained by a predetermined machine learning model to output a road friction coefficient estimation function representing a road friction coefficient value according to weather information. The cloud server may construct a road friction coefficient estimation model by performing such learning, and the built model may be pre-stored in the lighting device 100 . Alternatively, the lighting apparatus 100 may transmit information collected at the time to the cloud server and receive the road friction coefficient estimation function.

As an additional embodiment in relation to the construction of the above-described road friction coefficient estimation model, in order to increase the learning speed of the road friction coefficient estimation model and to increase the relationship between weather and road surface conditions, the traffic control server 200 or the cloud server may perform the accumulated weather Pre-processing can be performed on the information. The more diverse the criteria of weather information applied as input values to the road friction coefficient estimation model, the higher the accuracy.

The preprocessing process may, for example, first select a specific road that is greatly affected by the weather. And last year's state information (ICE/SNOW/WET/DRY) of the corresponding road is stored in the traffic control server 200 or the cloud server. Thereafter, with respect to the area including the road, the weather information collected from the weather prediction server (eg, the Meteorological Administration server) up to last year is classified into preset criteria such as topography, temperature, humidity, precipitation, snow load, wind direction, and wind speed. can do. Since weather information (=problem) and road condition information (=answer) according to the classification criteria up to last year have been prepared, it is possible to construct a primary road surface condition estimation model using these as learning data. That is, when each of the weather information of last year classified according to the above is input, supervised learning can be performed to output last year's state information (= primary road surface state value) of the corresponding road, and the decision tree map It can be implemented as a learning algorithm. Accordingly, new weather information applied as an input value to learning the road friction coefficient estimation model is first preprocessed as the primary road surface state value, so the seven input values of topography, temperature, humidity, precipitation, snow load, wind direction, and wind speed are one By replacing the input value, it can alleviate the complicated learning process of building the road friction coefficient estimation model.

In step S510 , the control unit 110 in the lighting device 100 may extract characteristic information on the road surface of the area where the lighting device 100 is installed based on the image and image information collected from the sensor 110 . For example, the controller 110 may perform image processing for calculating an average of gray levels of all pixels for each road image collected during a preset period. Thereafter, an average value of the average of the gray levels calculated for each image may be calculated. That is, the average gray level for a preset period may be calculated, and this may be set as road surface characteristic information.

Here, the average gray level represents the average brightness of the road surface, and the gray level of the road is stored in advance as a reference value in the database. For example, if it deviates from the reference value, it may be an indicator that snow, black ice, and other objects that interfere with driving exist on the road surface. It is of sufficient value as a single source of information.

In step S520, the control unit 110 may extract a road friction coefficient estimation function by applying at least one of the extracted road surface feature information and the temperature and humidity information collected from the sensor 120 to the road friction coefficient estimation model. have. The road friction coefficient estimation model is previously learned and constructed as described above.

Here, the extracted road friction coefficient estimation function is a function representing the correlation between the road friction coefficient and the weather, and is a probability calculation for estimating the road friction coefficient value when a specific weather state value is input using the weather state value as a parameter. In addition, even if the road surface friction coefficient estimation function is extracted, it needs to be adjusted as the friction coefficient of the corresponding road surface changes, so it may mean that a predetermined statistical pattern analysis operation model is applied. A Markov model can be given as an example, and preferably, a regression calculation is grafted based on the Hidden Markov Model, and the road surface friction coefficient estimation function according to the change (result) of the estimated friction coefficient The algorithm of (state) can be adjusted.

In step S530 , the controller 110 may calculate an estimated road friction coefficient by inputting at least one weather state value among the weather information received from the traffic control server 200 into the extracted road friction coefficient estimation function. .

Thereafter, road surface condition information corresponding to the calculated road surface friction coefficient value may be extracted. Here, the database may match and store the road surface conditions of ICE/SNOW/WET/DRY for each preset road friction coefficient value range. For example, when the estimated friction coefficient value is 0.8 and 0.7 or more is matched with DRY, road surface condition information of DRY may be set as traffic information.

Apart from irradiating the extracted road surface condition information with light, in step S540 , when the vehicle 300 approaches the lighting device 100 and is located within a preset distance, the lighting device 100 sends the vehicle 300 to the vehicle 300 . By transmitting road surface condition information, it is possible to double the driver's safety. In addition, in S530 , the estimated road friction coefficient value may also be transmitted to the vehicle 300 .

Meanwhile, the lighting device 100 may transmit the road friction coefficient value and road surface condition information identified in the present embodiment to the traffic control server 200 . Accordingly, the traffic control server 200 can induce continuous safe driving by updating the road surface condition of the corresponding road and transmitting it to the lighting device disposed on the next path.

In a further embodiment, the controller 110 of the lighting apparatus 100 may analyze a road image captured by a camera sensor to determine whether there is snow or black ice on the road.

For example, the controller 110 may receive a photographed road image and divide it into R, G, and B regions. Thereafter, a gray level value and a range corresponding to each region may be calculated, and the number of pixels corresponding to each gray level value may be determined.

)을 산출할 수 있다. 이는 레드(R)영역 평균값과 블루(B)영역의 평균값의 차이를 의미할 수 있다.Thereafter, an average of gray level values for all pixels of the road image may be calculated. This may mean the luminance (L*) of the road image. In addition, the difference value (

) can be calculated. This may mean a difference between the average value of the red (R) region and the average value of the blue (B) region.

Thereafter, the whiteness (index of whiteness, lw) of the road surface image can be calculated by applying the following equation (1).

- (1)

- (One)

In the database of the lighting device 100 , reference values of a first whiteness for determining a state in which snow is distributed on a road surface and a second whiteness for determining a state in which black ice is included may be preset and stored. Accordingly, when the calculated whiteness is equal to or greater than the first whiteness, the controller 110 may determine that the road surface is snowy, and when the calculated whiteness is less than the second whiteness, it may determine that the road surface has black ice.

According to the above-described embodiments, the intelligent traffic information providing system of the present invention can accurately estimate road surface condition information. That is, the lighting apparatus 100 may use the road surface state information as traffic information and irradiate the text or image with light. For safe driving, weather information is only for reference, and the most closely related to driving operation is the current road surface condition, so the driver can visually recognize more practical and direct traffic information.

Referring back to FIG. 2 , according to an embodiment related to step S320 , when traffic information is identified based on the weather information and road condition information received from the traffic control server 200 , the controller 110 controls the weather information and Road condition information can be converted into risk scores. When the converted risk score is determined to be greater than or equal to the preset reference value, it is determined that the risk of driving is large, and the corresponding weather information and road condition information can be transmitted to the lighting device 100 and the vehicle 300 located within a preset distance. . Accordingly, the driver can fully focus on driving by receiving the double warning message.

In addition, in the lighting device 100 , the traffic information detected based on the weather information and road condition information received from the traffic control server 200 is different from the traffic information detected by itself according to the information collected by the sensing unit 120 . I may have a case. For example, when each traffic information shows a preset error range, the lighting device 100 requests retransmission of weather information and road condition information along with identification information to the traffic control server 200 to determine which traffic information is more accurate. signal can be transmitted. In addition, it is also possible to request a comparison determination from the traffic control server 200 by transmitting the traffic information grasped by itself.

In step S330 , the control unit 110 of the lighting device 100 may extract text or an image previously matched with the identified traffic information. For example, in the case of an accident in the front, texts such as 'identity' and 'occurrence of accident' or a mark symbolizing the same may be stored in the database by matching it.

In step S340 , the controller 110 may control the light emitting unit 130 to irradiate the light formed in the form of the extracted text or image to the floor surface. A feature of the light emitting unit 130 is that by inserting a micro-processed light emitting device, the light emitting device can be individually controlled for each pixel, and thus a specific type of light can be formed. A detailed description related thereto is provided in place of the above description with reference to FIG. 1 .

6 shows an example in which light of an image symbolizing the eye is formed when traffic information related to the eye is identified. In this way, the lighting apparatus 100 according to an embodiment of the present invention may also serve to deliver a message to the driver in addition to the existing lighting function. Therefore, it is possible to economically operate an intelligent transportation system without spatial restrictions even if separate intelligent transportation equipment is not placed on a road or tunnel.

In a further embodiment, the controller 110 may determine the luminance of the floor based on information collected through a camera sensor in the detector 120 . Thereafter, the intensity of the irradiated light may be adjusted according to the determined brightness (luminance) of the floor surface. For example, brightness is continuously detected in real time, and accordingly, dimming control may be continuously performed for each output pixel to maintain a preset light intensity. Accordingly, it is possible to prevent driver fatigue due to excessive light and prevent unnecessary power loss.

Meanwhile, according to an embodiment of the present invention as disclosed in step S320, a plurality of pieces of traffic information may be identified in the same period in the process of identifying traffic information. For example, the presence of black ice is detected by the information collected by the sensing unit 120 , the occurrence of an accident is detected based on the information received from the traffic control server 200 , and the Based on the information, the road surface condition of 'SNOW' may be simultaneously grasped.

According to an embodiment of the present invention, in this case, in step S330, a risk score may be calculated for each traffic information. Here, the process of calculating the risk score is to be performed based on a predetermined arithmetic expression in which the distance between the location corresponding to the corresponding traffic information and the vehicle 300, the speed of the vehicle, the direction of travel, and a predetermined risk index for each traffic information are taken into account. can For example, even if the risk index of the forward accident occurrence information is greater than the black ice, when the location where the black ice exists is closer to the vehicle 300 , a higher risk score may be calculated.

Thereafter, the controller 110 may compare and calculate the calculated risk score, and as a result, may extract text or an image matched with traffic information having the highest risk score. Alternatively, the risk score may be compared and calculated with a preset reference value, and text or images matched with traffic information determined to be greater than that may be extracted.

According to an embodiment, it does not matter if the highest risk score is determined, but there may be a plurality of traffic information corresponding to a risk score greater than or equal to a reference value. In this case, since each traffic information is closely related to safety, it may be desirable to display and expose all of them on the floor. In this case, the controller 110 may control the light emitting unit 130 to extract text or images matched with each traffic information, and simultaneously or sequentially irradiate the respective lights displaying them.

That is, it may be divided into preset areas and simultaneously irradiated or sequentially irradiated with a long irradiation time set in the order of a high risk score. For example, if the 'M' and 'N' images matching the 'M' and 'N' images are extracted because the risk scores of 'A' and 'B' traffic information are all higher than the reference value, the Light indicating 'N' may be irradiated together. Alternatively, when the control unit 110 compares the risk scores of 'A' and 'B' with each other, when the risk score of 'A' is high, the irradiation time of 'M' is 3 seconds, followed by the irradiation time of 'N' It is possible to control the light emitting unit 130 to sequentially irradiate by setting to 1 second.

Although the methods and systems of the present invention have been described with reference to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The description of the present invention described above is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

100: lighting device
200: traffic control server
300: vehicle

Claims (5)

A method for providing real-time traffic information, performed by a lighting device disposed on a road or a tunnel,
Collecting at least one of an image, temperature, and humidity in a preset range through a plurality of sensors included in the lighting device or receiving weather information and road condition information from a traffic control server in real time;
identifying traffic information based on information collected through the plurality of sensors or weather information and road condition information received from the traffic control server;
extracting text or images previously matched with the identified traffic information; and
exposing the traffic information by controlling the light emitting unit to irradiate the light formed in the form of the extracted text or image on the floor;
including,
The step of recognizing the traffic information further includes the step of recognizing the traffic information based on the wheel state information received from the vehicle located within a preset distance from the lighting device,
Traffic information identified based on the wheel state information includes road surface state information of a road on which the lighting device is installed,
The light emitting unit includes at least one light emitting element, wherein the light emitting element is subdivided into a predetermined pixel unit, and light in the form of text or image is formed by controlling turning off and dimming for each pixel. ,
The process of identifying the road surface condition information of the road on which the lighting device is installed,
Detects an identification signal of a vehicle located within the preset distance,
Receive at least one of an acceleration signal, a geomagnetic signal, a pneumatic signal, a temperature signal, and a gyroscope sensing signal for a wheel on one side of the vehicle included in the detected identification signal,
converting the received signal into a signal in the frequency domain,
dividing the converted frequency domain signal into preset sections,
Extracting representative data for each divided section to calculate a feature vector,
performing size scaling on each of the calculated feature vectors,
To extract road surface condition information by applying each of the size-scaled feature vectors to a classification model,
The classification model uses at least one of an acceleration signal, a geomagnetic signal, a pneumatic signal, a temperature signal, and a gyro sensing signal of the wheel as an input value and outputs one of the road surface condition information classified according to a preset criterion. previously learned by
How to provide real-time traffic information. The method of claim 1,
The step of extracting the text or image matched with the identified traffic information is,
calculating a risk score for each piece of traffic information when there are a plurality of the identified traffic information; and
extracting a text or image matched with traffic information having the highest risk score as a result of comparing the calculated risk scores, or extracting text or images matched with traffic information in which the calculated risk score is equal to or greater than a preset reference value;
including,
When a plurality of texts or images matched with traffic information equal to or greater than the reference value are extracted, the light formed from the plurality of extracted texts or images is divided into a preset area and irradiated simultaneously, or the irradiation time is set to be long in the order of a high risk score sequentially investigated,
How to provide real-time traffic information. delete The method of claim 1,
The step of identifying traffic information based on the weather information and road condition information received from the traffic control server includes:
converting the weather information and road condition information received in real time into a risk score; and
transmitting weather information and road condition information in which the converted risk score is equal to or greater than a preset reference value to a vehicle located within a preset distance from the lighting device;
including,
When the identified traffic information shows traffic information and a preset error range based on information collected through a plurality of sensors in the lighting device, the traffic control server sends the weather information together with identification information of the lighting device and transmitting a retransmission request signal of road condition information.
How to provide real-time traffic information. The method of claim 1,
The step of identifying traffic information based on information collected through the plurality of sensors or weather information and road condition information received from the traffic control server,
extracting road surface characteristic information of an area in which the lighting device is installed based on the image information collected through the plurality of sensors;
extracting a road friction coefficient estimation function by applying at least one of the road surface characteristic information and the temperature and humidity information collected through the plurality of sensors to a road friction coefficient estimation model;
By applying at least one weather state value among the weather information received from the traffic control server as a parameter to the extracted road friction coefficient estimation function, a preset probability calculation indicating the correlation between the road friction coefficient and the weather is performed. estimating a road friction coefficient value;
extracting one of the road surface condition information classified according to a preset criterion corresponding to the estimated road surface friction coefficient value; and
transmitting the estimated road friction coefficient value or the extracted road surface condition information to a vehicle located within a preset distance;
including,
The road friction coefficient estimation model takes as input values accumulated road surface characteristic information, temperature information, humidity information, and weather information collected for a preset period, and outputs a road friction coefficient estimation function representing a road friction coefficient value according to the weather information which has been previously learned by a predetermined machine learning model designed to
How to provide real-time traffic information.

Images