KR20230066940A - Fog detection device - Google Patents

Abstract

Disclosed are a fog detection device and a fog detection method. The fog detection device of the present invention sets two or more areas on a road to measure the presence or absence of fog as regions of interest (ROI) and uses a coordinate system to detect the presence or absence of fog and visibility distance by using images of the corresponding regions of interest. The fog detection device of the present invention comprises: a mobile means having a camera unit that captures images of a set region of interest in real time while driving on the road; a fog measurement unit extracting an image of a region of interest (ROI) from the image captured by the camera unit of the means of transportation to measure the presence or absence of fog and visibility distance in the region of interest; and a control server receiving the presence or absence of fog and visibility distance detected by the fog measurement unit to display the same on an electronic signboard or situation room of the relevant road or transmit the same as weather information. Accordingly, the presence or absence of fog in the area and visibility distance can be accurately provided in real time as fog analysis information.

Description

Fog detection device {FOG DETECTION DEVICE}

The present invention relates to a fog detection technology, and more particularly, to a fog detection device using distribution map rearrangement capable of increasing the accuracy of fog determination by additionally enlarging the ROI used for fog determination to the center, left and right sides of the screen. will be.

Weather information is information about weather that greatly affects daily life.

Recently, the Korea Meteorological Administration has opened weather forecasting to private weather forecasting operators, and as the weather fluctuates greatly due to climate change, interest in weather information is further increasing.

In order to accurately monitor and predict weather information, weather data must be acquired through the installation of weather equipment.

Meteorological conditions (fog, rain, snow) are a major factor in causing traffic accidents by interfering with the driver's vision, and so far, safety facilities in preparation for fog have been safety signs, fog blocking nets, LED gaze guide lights, fog lights, and speeding. Installation and operation of enforcement equipment, etc.

These safety facilities are installed/operated confined to habitually occurring fog areas, so they cannot effectively respond to the fog that occurs randomly in time and space.

In particular, as the risk of traffic accidents due to fog has emerged as a social problem, installation projects for safety hazard display facilities in preparation for fog occurrence are actively being carried out during road design. As one method for this, a fog warning system is being developed and installed to measure the occurrence of fog and visibility and warn the driver through it, but the method of measuring the visibility distance using auxiliary facilities requires the installation of a separate target. There is a problem in that a separate cost is generated according to this. In addition, the conventional visibility distance measuring method has a problem in that it is difficult to calculate visibility when the distinction between day and night is ambiguous, such as at dawn. Accordingly, a method capable of measuring the visibility distance over a relatively wide area and measuring the visibility distance at low cost is required.

In addition, when the intensity of the fog increases in a part of the screen, a problem arises in that the presence or absence of fog cannot be accurately determined by the fog analysis of the existing region of interest (ROI) set in the center of the screen.

KR Registration Patent Publication No. 10-0946749 (2010.03.11)

An object of the present invention to solve these problems is to provide a fog detection device capable of accurately detecting the presence or absence of fog and a visibility distance in an image obtained by photographing the central and left and right regions of interest set on a road.

Another object of the present invention is to provide a fog detection device capable of detecting the presence or absence of fog and a visibility distance in real time by capturing an image of a region of interest set for a fixed camera.

In addition, the present invention is to provide a fog detection device capable of detecting the presence or absence of fog and the visibility distance in real time by attaching a camera to a vehicle that travels on the road at all times and taking an image of a set region of interest while driving, for another purpose. do.

Another object of the present invention is to provide an apparatus for detecting fog in which a fog detection function is improved by using a plurality of fog detection methods in each image obtained by taking a region of interest by distance.

Fog using a coordinate system that sets two or more areas to measure the presence or absence of fog on the road as a region of interest (ROI) and detects the presence or absence of fog and the visibility distance using an image of the corresponding region of interest. The detection device extracts an image of a region of interest (ROI) from an image captured by a moving means equipped with a camera unit that captures an image of a set region of interest while driving on a corresponding road in real time, and a camera unit of the moving means to capture the corresponding region of interest. A fog measurement unit that measures the presence or absence of fog and the visibility distance, and a weather information providing server that receives the presence or absence of fog and the visibility distance detected by the fog measurement unit and displays them on the electric signboard or situation room of the road or transmits them as weather information. It can be achieved by configuring

Therefore, according to the fog detection device of the present invention, since the presence or absence of fog is measured by dividing the image of the region of interest into the center and left and right, a similar phenomenon such as fog occurs only in a certain portion of the screen, thereby improving the conventional problem of determining fog. There are effects that can be done.

In addition, according to the fog detection device of the present invention, since the presence or absence of fog and the visibility distance are analyzed by measuring images of the corresponding region of interest from a plurality of vehicles running on the road at all times, the effect of providing fog information in real time is obtained. there is.

In addition, according to the fog detection device method of the present invention, since the image of each distance for one region of interest is analyzed and/or the fog measurement unit determines the presence or absence of fog by two or more methods, reliable fog information can be obtained by increasing the recognition rate. There are effects that can be provided.

Also, according to the fog detecting device of the present invention, information on visibility as well as information on the presence or absence of fog can be provided, so that driving on the road can be performed more efficiently.

1 is a view for explaining the concept of fog detection according to an embodiment of the present invention;
2 is a main configuration diagram of a fog detection device according to an embodiment of the present invention;
3 is a reference diagram for explaining the setting of the region of interest of the present invention;
4 is a flowchart for explaining a fog detection method according to an embodiment of the present invention;
5 is a reference diagram for explaining a method for setting a region of interest and identifying fog presence;
6 is a diagram illustrating a case of determining the presence or absence of fog in an image measured by distance;
and
7 is a diagram illustrating a case of determining the presence or absence of fog by lightness.

The terms or words used in this specification and claims are not limited to the usual or dictionary meanings, and the inventor can properly define the concept of the term in order to explain his or her invention in the best way. Based on this, it should be interpreted as a meaning and concept consistent with the technical spirit of the present invention.

Throughout the specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated. In addition, terms such as “… unit”, “… unit”, “module”, and “device” described in the specification mean a unit that processes at least one function or operation, which is implemented as a combination of hardware and/or software. It can be.

Throughout the specification, the term "and/or" should be understood to include all possible combinations from one or more related items. For example, the meaning of “a first item, a second item and/or a third item” may be presented from two or more of the first, second or third item as well as the first, second or third item. A combination of all possible items.

Throughout the specification, identification codes (e.g., a, b, c, ...) for each step are used for convenience of explanation, and the identification code does not limit the order of each step, and each step Unless the specific order is clearly stated in context, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

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

1 is a diagram for explaining a fog detection concept using a coordinate system according to an embodiment of the present invention, and FIG. 2 is a main configuration diagram of a fog detection device according to an embodiment of the present invention.

An apparatus and method for detecting fog using a coordinate system of the present invention set a region of interest (ROI) in an image on a road to be checked for presence or absence of fog, and use a fixed camera that captures the region of interest (ROI). To determine the presence or absence of fog in the region of interest (ROI) by analyzing the image, or by analyzing two or more images of the region of interest (ROI) taken by distance from the moving means moving toward the region of interest (ROI) fog can be used to determine whether or not

Referring to FIG. 1, on a road 400, a region of interest (ROI) 200 is captured and analyzed by a fixed camera 220, or a region of interest (ROI; 200) set forward while the moving means 100 is driving. To analyze by taking an image in the image acquisition section 210 set for each approach distance.

The region of interest (ROI) 200 is an area of high importance that can easily determine the presence or absence of fog, and is within an area that can be photographed by a camera mounted on a moving means passing through the fixed camera 220 and the image acquisition section 210. set to include

Means of transportation refers to image capturing means that move on the road, such as a vehicle capable of capturing images of a set area while driving on one or more roads among high-speed national highways, general national highways, special metropolitan cities, metropolitan cities, local roads, cities and provinces, archipelagos, and districts. do it by doing

Referring to the reference drawing for explaining the setting of the region of interest of the present invention of FIG. 3, the region of interest (ROI) 200 of the present invention consists of a central ROI (200A), a left ROI (200B), and a right ROI (200C). Set up.

This is because the ROI used for normal fog judgment is located only in the center of the screen, so if there is a phenomenon similar to fog in the center, it can be misjudged as fog. is what you want to do,

In addition, in order to solve the problem of not being able to determine the presence or absence of fog even when there are obstacles at adjacent distances on the left and right when the ROI is normally located only in the center of the screen, three ROIs are set in the center and on the left and right to determine the presence or absence of fog. judge

To this end, the central ROI 200A divides the section from the short distance of the lower image to the far distance of the upper image into approximately 10 sections (from the bottom, "ROI:10 ~ ROI:1") in the captured image, and detects each section. quantify the concentration of the fog.

In addition, the left and right ROIs (200B, 200C) divide the section from the short distance of the lower image to the far distance of the upper image into approximately 4 sections (“ROI:4~ ROI:1” from the bottom) in the captured image, and The concentration of the star-detected fog is digitized.

Since the camera sets the measurement area by placing the road on which the vehicle will drive in the center, the center ROI sets the measurement area so that the road on which the vehicle travels is located in the center, so that all of the vehicle routes are included in the measurement area. Therefore, in the measurement area, it is set by dividing it into 10 long sections from the bottom to the top in the center of the screen, and the ROI on the left and right is used as an auxiliary analysis area to solve the above problems, so it is set by dividing it into approximately 4 sections. .

The left and right ROIs can be used by changing the left and right positions or sizes on the measurement screen according to the feature of the measurement area, so that more accurate measurement can be achieved.

The fixed camera 220 is configured to capture a set region of interest using a camera such as a CCTV capable of capturing images.

Referring to FIG. 5 , it can be seen that a central ROI is set at one upper side of the tunnel. For convenience of description, left and right ROIs are omitted.

Referring to FIG. 1, an image is acquired from a fixed camera 220 or an image acquisition section 210 is set, a first image acquisition point is set within the image acquisition section 210, and the GPS coordinates of the point are set to the first image. x1 point 211 as the acquisition GPS coordinates, x2 point 212 as the second image acquisition GPS coordinates, x3 point 213 as the third image acquisition GPS coordinates, and N points as the Nth image acquisition GPS coordinates ( N) is indicated.

The image acquisition section 210 is a position where the region of interest (ROI) 200 is to be photographed when the moving means passes through the area, set as GPS coordinates, and the moving means 100 detects it to pass the corresponding GPS coordinates. It is preferable to install two or more for each distance of the entire region of interest (ROI) in order to take an image at the same time.

For example, the image acquisition section 210 may be set to about 100 m before the region of interest (ROI), and the image acquisition GPS coordinates may be set to 150 m, 100 m, and 50 m before the region of interest (ROI).

Referring to FIG. 6, images are displayed when there is no fog and when there is fog for each distance. The upper part uses the fog concentration measurement method, and the lower part shows the case of determining the presence or absence of fog by the contour extraction method. It is an illustrated drawing.

For convenience of description, only the central ROI is set, but it goes without saying that the left and right ROIs can also be set identically.

In addition, the region of interest (ROI; 200) is any one or more roads among high-speed national roads, general national roads, special cities, metropolitan cities, local roads, cities and provinces, archipelagos, and districts that can capture surrounding images by mounting a camera such as a fixed camera or a vehicle. However, it is preferable to divide the road by section and set a plurality of them to detect fog and provide information throughout the road.

In addition, it goes without saying that regions with frequent fog and frequent fog should be included in the region of interest for special management.

Even in this case, the present invention analyzes by setting the central ROI and the left and right ROIs in the measured image.

In addition, the moving means 100 may measure the presence or absence of fog and the visibility distance of itself with the captured image, and may transmit the result to the weather information providing server 300 for analysis.

That is, in order to analyze the presence or absence of fog in real time, the fog detection device of the present invention first sets two or more areas to measure the presence or absence of fog on the road as a region of interest (ROI), and uses an image of the corresponding region of interest to determine the presence or absence of fog and the visibility distance. In order to detect a fixed camera 220 and a moving means 100 equipped with a camera unit 110 that captures an image of a set region of interest in real time while driving on a corresponding road, a fixed camera 220 and a moving means ( Fog measuring units 150 and 360 and fog measuring units 150 and 360 extract an image of a region of interest (ROI) 200 from an image captured by the camera unit 120 of 100) and measure whether or not there is fog and a visibility distance in the region of interest. It is configured to include a weather information providing server 300 that receives the presence or absence of fog and the visibility distance detected in and displays it on the electronic signboard or situation room of the road or transmits it as weather information.

The fog measurement units 150 and 360 receive an image of a region of interest and measure the presence or absence of fog and the visibility distance. A method of constructing and self-analyzing and a second fog measuring unit 360 that transmits images taken by the moving means 100 and the fixed camera 220 and analyzes them in the weather information providing server 300 will be described.

First, the moving means 100 mounts the camera unit 120, and captures a region of interest (ROI) 200 while driving on a road, and the fixed camera 220 photographs the set region of interest.

The first fog measurement unit 150 detects the presence or absence of fog and the visibility distance, and transmits the analysis information as fog information to the weather information providing server 300 through the communication unit 110, or the first fog measurement unit 150 If there is no image, the image may be transmitted to the weather information providing server 300 and analyzed by the weather information providing server 300 .

The fixed camera 220 transmits images taken at all times to the first fog measuring unit 150 .

The camera unit 120 of the moving unit is fixed and receives a signal from the control unit 140 to record an image or continuously captures an image, and when the control unit 140 determines that the image is acquired GPS coordinates, the corresponding image is displayed in the first fog. It can be transmitted to the measuring unit 150.

Preferably, the fixed camera 220 and the camera unit 120 always take images and store them in the image storage unit 170 for each recording time so that the images are read like a black box if necessary, or the control unit 140 acquires images. When the image is determined to be the GPS coordinates 210, the GPS coordinates taken in the image storage unit 170 and the unique identification number of the means of transportation are stored together, and the image is analyzed in the first fog measuring unit 150 The presence or absence of fog and the visibility distance can be measured.

In addition, since the camera unit 120 can be mounted on multiple means of transportation, when an image is captured and transmitted, it is transmitted along with the owner of the means of transportation on which the camera unit 120 is mounted or a unique identification code and transmitted in any means of transportation. It is necessary to distinguish whether

Since the fixed camera 220 may also be installed in several places, when an image is photographed and transmitted, it is necessary to transmit it along with a unique identification code to distinguish where the image was transmitted from the camera installed.

Therefore, in the case of an IP camera, only the IP address needs to be transmitted, and in the case of a general camera, a unique identification code including the identification code of the owner can be transmitted.

In addition, in the present invention, although a specific means of transportation may be equipped with a camera and photographed while periodically driving on the road, a unique identification code and Since images can be collected in real time by mounting a camera unit together, more accurate information can be provided by receiving an identification code for a video sender and paying a predetermined price to obtain real-time images.

When the camera unit 120 of the moving means reaches the set image acquisition GPS coordinates under the control of the control unit 140, it operates to capture a forward image.

To this end, the moving means 100 uses the GPS receiving unit 130 that receives the current GPS location of the moving means to extract the coordinates and the camera unit 120 to capture an image of the surroundings, and stores two or more GPS coordinates for measurement. A controller that includes a coordinate unit 160 and controls the camera unit 120 to capture an image when the GPS coordinates received through the GPS receiver 130 match the image acquisition GPS coordinates registered in the measurement coordinate unit 160 (140) is included.

In addition, as described above, the image storage unit 170 divides the captured images by time like a black box and stores the images, and stores the images acquired from the image acquisition GPS coordinates together with a unique identification code.

The first fog measurement unit 150 detects the presence or absence of fog and the visibility distance by transmitting or receiving an image captured by the fixed camera 220 or the camera unit 120 of the moving means.

As an example, looking at the reference drawing for explaining the setting of the region of interest and the method of identifying the presence or absence of fog in FIG. It is a picture that means a state, and if the outline is not visible when the color is removed, as shown in the bottom picture, it can be determined that there is fog.

Alternatively, an image obtained by storing an image in the case of fog and an image in the case of no fog, or an image for each visibility distance according to the intensity of fog in the first fog measurement unit 150 for each GPS coordinate, and then capturing the image. It may be detected by comparing the presence or absence of fog and the visibility distance by comparing with the stored image.

In addition, since fog can change rapidly depending on weather conditions depending on road conditions, the first fog measurement unit 150 measures the presence or absence of fog in the image measured by distance, but accurately using a plurality of fog detection methods. It works so that it can be detected.

In addition, since fog has a significant effect on road safety depending on the start time and dissipation time as well as the frequency of occurrence, it is necessary to proceed with different fog detection times and cycles in consideration of the characteristics of each time, season, and region. can provide information.

As for the normal start time of fog, 201% of the fog with a visibility of 500 m or less occurs at 5:00, and 237% or more occurs at 6:00.

The frequency of fog starting from around 10:00 to 24:00 is very low at 3.3%, and the dissipation time is the highest between 6:00 and 7:00, and the fog begins to dissipate after sunrise and around 10:00 am. It appears that most of the fog is dissipated (Source: Journal of the Korean Geographical Society, Vol. 38, No. 4, 2003 (478-489))

That is, when it is determined that there is fog in all of the images received in two or more image acquisition sections 210 for each distance to the same region of interest (ROI), it is determined that there is fog, and it is determined that there is no fog at any one location. If so, it is determined that there is no fog in the area.

In addition, the presence or absence of fog is determined by the case where the same result is obtained by three methods, that is, the fog concentration measurement method, the contour extraction method, and the brightness analysis method, for the image at one location. That is, if the analysis result by one method is different from the other analysis result, it is determined that there is no fog.

Specifically, if it is determined that there is fog in the analysis by the fog concentration measurement method, there is fog in the outline extraction method, and there is fog in the brightness analysis method, it is determined that there is fog in the final area of interest, and it is determined that there is fog In this case, the visibility distance is calculated using the presence or absence of fog for each visibility distance analyzed in the fog concentration measurement method and the contour extraction method.

Looking at the upper figure in the diagram illustrating the case of determining the presence or absence of fog by the fog concentration measurement method and the contour extraction method in FIG. It is divided into approximately 10 sections, and the concentration of fog detected for each section is digitized and displayed in a graph.

Looking at the good case in the upper figure, the values of each section are similarly graphed, but in the case of fog, the concentration of fog is low in the area near the screen, but it is gradually accumulated and the value increases as the distance increases. there is.

The fog concentration measurement method analyzes each region of interest (ROI) that requires analysis, and calculates the measured value using the variance formula for the color value of each pixel.

When there is no fog feature, the measured variance value is 200 or more, and when there is fog feature, the value is low depending on the concentration.

In particular, when the fog is thick, a value of 2 or less is shown.

The dispersion equation used in the fog concentration measurement method is shown in Equation 1.

는 분산,

는 평균,

는 가중치이다.here

is the variance,

is the mean,

is the weight.

The contour extraction method analyzes the region of interest (ROI) that needs analysis, and uses a general edge extraction technique. Edge refers to the boundary of an object in the image, and the edge is a point where the change in contrast is large based on the contrast of the image, and a differential method is used to detect the rate of change in contrast and brightness, that is, the slope.

The threshold value for edge extraction is used as 10.

In addition, if the image is expressed as an edge, information about the shape of an object in the image can be maintained as it is. In order to detect such an edge, operators such as roberts, prewitt, and sobel are used. These operators can be performed with the concept of using a gradient operator for image differentiation.

Since this contour extraction method can use various publicly available methods, a detailed description thereof will be omitted.

That is, the present invention uses the contour extraction method as one of the methods for measuring the presence or absence of fog.

Looking at the bottom figure in the drawing illustrating the case of determining the presence or absence of fog by the fog concentration measurement method and the contour extraction method of FIG. Classification, and looking at the right screen where the outlines for each section are extracted, it can be seen that the outlines are extracted with red lines in the case of good weather without fog and that the outlines are not identifiable in the case of fog.

In addition, if the contour extraction method is used, the visibility distance can be estimated according to the degree of extraction of the contour in each stage.

For example, if the red picture on the upper right side scales down the step-by-step box on the left to correspond to the corresponding position, the starting point of the position where the red outline is visible can be converted into the visual distance in the image.

That is, since the distance of each section can be calculated in the 10 sections of the left screen, the corresponding distance information can be stored and then the section from which the outline is extracted can be detected and converted into a distance.

The brightness analysis method refers to a graph showing the frequency distribution of colors. Referring to the drawing exemplifying the case of determining the presence or absence of fog by brightness in FIG. While the value (pixel value) is digitized and displayed, it can be seen that when there is fog, the color value (pixel value) for the corresponding region of interest (ROI) is displayed as “0”.

This brightness analysis method analyzes the region of interest (ROI) that requires analysis and uses the HSL extraction technique.

First of all, the RGB color of the region of interest is converted to HSL (Hue Saturation Lightness), and then only the H (Hue) color is extracted. After that, it goes through a process of converting the extracted H (Hue) color into a histogram. In the general case without fog, the measured value appears at the position of 100 to 150, and in the case of fog, it is distributed only at the position of 0.

Fog analysis has been described as analyzing the presence or absence of fog and visibility distance in each moving means in the present invention to provide rapid data, but the image captured by the camera unit 120 is input from the weather information providing server 300 It can also determine the presence or absence of fog and the visibility distance.

Therefore, according to set conditions, the control unit 140 transmits the image or fog analysis information captured by the weather information providing server 300 through the communication unit 110 and at the same time receives a video transmission request from the weather information providing server 300. It can operate to transmit the corresponding data to the weather information providing server 300 .

That is, when the weather information providing server 300 designates an identification code and requests a photographed image or an analysis result, the control unit of each moving means transmits the photographed image or fog analysis information with the corresponding identification code.

In addition, the control unit 140 may store images taken by time by date or fog analysis information in its own memory and transmit it to the weather information providing server 300 if necessary.

In addition, when the fog analysis information or captured image is transmitted to the weather information providing server 300, the control unit 140 transmits an identification code, and when displaying the image, the region name of the corresponding image is displayed so that it can be easily distinguished.

The weather information providing server 300 may be a terminal installed in a meteorological person, a control center, a weather center, or a road traffic center, and by installing an application related to the present invention, analysis of a photographed image or fog of a corresponding area of interest or a corresponding road from each camera information can be received.

In particular, in the case of applying for emergency text notification in a set area, when the weather information providing server 300 suddenly changes in fog in the area, the stored application is automatically driven when the corresponding information is received from the weather information providing server 300. and displays the received information on the screen so that the terminal manager or owner can check it.

The weather information providing server 300 receives and stores the photographed image, fog analysis information, and identification code received from the means of transportation, and operates to display or transmit the corresponding information if necessary.

Referring to FIG. 2, the weather information providing server 300 sequentially displays images of regions with different identification codes along with road names according to the order set by the multi-screen 2350, and regions where rapid changes are expected are other You can pay special attention by flashing the screen or generating a warning sound.

In this case, the weather information providing server 300 sends an emergency notification to a management agency such as a regional control center, weather center, or road traffic center, and if there are terminals requesting information by identification code, the corresponding information is sent to each It is transmitted to the terminal so that terminal holders can share emergency information.

To this end, the weather information providing server 300 manages the authentication of the terminal holder requesting information reception for installing the app, and the user authentication unit 320 that manages the authentication of the administrator's access to the server, and the information through the electronic display board or the administrator's terminal. A data providing unit 330 that transmits, and a camera DB 340 that stores the identification code of each moving means 100, image acquisition GPS coordinates, and GPS coordinates of the region of interest (ROI), photographed images for each identification code, and A storage unit 380 that stores fog analysis information and an image indicating the presence or absence of fog and visibility distance for each image acquisition GPS coordinate, and a second fog measurement that analyzes the received image to detect the presence or absence of fog and the visibility distance. It may include a server communication unit 370 that communicates with the unit 360, the means of transportation, and the terminal, respectively.

The data providing unit 330 is configured to display the data stored in the storage unit 380 or the data on the presence or absence of fog and the visibility distance on an electric signboard for each road or a situation room, or to transmit weather information.

When a sudden change in fog is detected, the server control unit 310 generates a warning sound, provides emergency information on a corresponding area, and issues an alert to vehicles passing through the corresponding area.

In addition, the server control unit 310 operates to extract and transmit field images or fog analysis information of a corresponding camera when an image or data for an identification code of a region of interest is requested from a terminal having installed an application related to the present invention.

Since the second fog measurement unit 360 measures the presence or absence of fog and the visibility distance in the same manner and configuration as the first fog measurement unit 150, a description thereof will be omitted.

The fog detection method using the coordinate system of the present invention using the above configuration will be described.

4 is a flowchart for explaining a fog detection method according to an embodiment of the present invention. As shown, the fog detection method of the present invention acquires images from a fixed camera and a camera mounted on a moving means, and the acquired image The presence or absence of fog and visibility are detected from

Since the process of analyzing the captured image is the same, the fog detection method using a moving means will be described below.

The fog detection method sets GPS coordinates for capturing images and stores them as image acquisition GPS coordinates (S100), captures images (S110), analyzes the captured images (S120), and analyzes the data as standard. It may include a step of determining the presence or absence of fog and a visibility distance (S130), and a step of transmitting fog analysis information to the outside if necessary (S140).

The image acquisition GPS coordinates in step S100 are set and stored as GPS coordinates of a place where an image is to be captured in order to calculate the presence or absence of fog and the visibility distance of a vehicle driving on the road.

Preferably, a region of interest is set first, and the front of the region of interest is set as an image acquisition section, but an area where the region of interest can be accurately photographed should be set.

When the image acquisition section is set, two or more image acquisition points are set in consideration of the conditions of the region, and the GPS coordinates of the corresponding points are set as the image acquisition GPS coordinates.

As described above, a plurality of regions of interest (ROIs) can be set on a corresponding road, and two or more image acquisition GPS coordinates are set in front of one region of interest (ROI) to acquire images for each distance.

When two or more image acquisition GPS coordinates are set, the corresponding GPS coordinates are stored in the measurement coordinate unit 160 of the moving means 100 and the camera DB 340 of the weather information providing server 300, respectively.

For these image acquisition GPS coordinates 210, the manager inputs the corresponding coordinates in the weather information providing server 300 and transmits the inputted coordinates to the transportation means 100 through communication to change the data of the measurement coordinate unit 160 or Of course, it is possible to add and delete.

That is, the communication unit 110 of the means of transportation 100 and the server communication unit 370 of the weather information providing server 300 may exchange information through mutual communication.

The step of capturing an image in step S110 is to capture an image using a camera when the moving means arrives at the image acquisition GPS coordinates set in step S100.

To this end, while the means of transportation 100 is driving on the road, the control unit 140 determines that the GPS coordinates received by the GPS receiver 130 and the image acquisition GPS coordinates 210 registered in the measurement coordinate unit 160 match. (S111), the camera unit 120 is controlled to capture an image including the region of interest (ROI) (S112), and the captured image is analyzed by itself or transmitted to the weather information providing server 300 for analysis. may proceed (S113).

Step S120 is a step of analyzing the image to detect the presence or absence of fog and the visibility distance using the received image, and may be configured in four steps.

First, it must be determined that there is fog in all of the images received from two or more image acquisition GPS coordinates (S121).

As described above, since fog is variable depending on time and surrounding weather conditions, it is necessary to determine that all images taken by distance from the front of one ROI have fog before proceeding to the next stage of the fog analysis method. .

For example, if the image acquisition GPS coordinates are set at 150m, 100m, and 50m before the region of interest (ROI), it should be determined that there is fog in the region of interest (ROI) extracted from three images taken at that point.

Of course, if it is determined that there is no fog from the image for each distance in step S121, the corresponding area may be determined to be free of fog (S132).

At this time, the presence or absence of fog can be performed by any one of the fog concentration measurement method, the outline extraction method, or the brightness analysis method.

In other words, when the three fog analysis methods (fog concentration measurement method, contour extraction method, and brightness analysis method) are analyzed for each image for each distance, all of them are equally foggy. If any of them is analyzed to be free of fog, it is determined that there is no fog at that distance.

Preferably, if it is analyzed that there is fog by applying each of the three fog analysis methods, it can be determined that there is fog.

This process is repeated to determine the presence or absence of fog by distance. If it is determined that there is fog in the same analysis result for each distance, there is fog. is to determine that there is no

Detailed description of the presence or absence of fog and the visibility distance calculation by the fog concentration measurement method in step S122, the presence or absence of fog and visibility distance calculation by the contour extraction method in step S123, and the method of determining the presence or absence of fog by the lightness measurement method in step S124. Since is the same as the determination method of the fog measurement unit described in the above-described fog detection device, it will be omitted.

When the presence or absence of fog is detected in the corresponding region of interest (ROI) in step S120, the control unit 140 of the moving means 100 determines whether there is fog or no fog (S130).

When it is determined that there is fog in step S130, the control unit 140 determines the visibility distance analyzed at the time of analyzing the presence or absence of fog by the fog concentration measurement method in step S122 when the first fog measuring unit 150 analyzes the fog, and at step S123. When analyzing the presence or absence of fog by the contour extraction method, the analyzed visibility distance is calculated and the common calculated distance is determined as the visibility distance. When it is determined that there is fog, the visibility distance is also transmitted as fog data (S140).

In step S140, if the analysis is performed in the means of transportation, the weather information providing server 300 transmits the fog data including the presence or absence of fog and the visibility distance to the weather information providing server 300. It is displayed on the electronic display board or control room, or transmitted as weather information.

As described above, according to the fog detection device and method using the coordinate system of the present invention, since the presence or absence of fog and the visibility distance can be measured and guided in real time without errors, fog information can be accurately transmitted.

Although the present invention has been described in detail with respect to the specific embodiments described above, it is obvious to those skilled in the art that various changes and modifications are possible within the scope of the technical idea of the present invention, and it is natural that these changes and modifications fall within the scope of the appended claims.

100: means of movement 120: camera unit
130: GPS receiver 150: first fog measuring unit
160: measurement coordinate unit 200: region of interest (ROI)
210: image acquisition GPS coordinates 300: weather information providing server
360: second fog measuring unit 400: road

Claims (5)

In the fog detection device for setting an area to measure the presence or absence of fog on a road as a region of interest (ROI) and detecting the presence or absence of fog and a visibility distance using an image of the region of interest,
The area of interest is
The fog detection device, characterized in that the region to be measured is set to three regions of a central region of interest and a left and right region of interest.
The method of claim 1,
a camera unit that captures an image surrounding the set region of interest in real time;
A fog measurement unit for extracting an image of a region of interest (ROI) from an image captured by the camera unit and measuring the presence or absence of fog and a visibility distance in the region of interest; and
a weather information providing server that receives the presence or absence of fog and the visibility distance detected by the fog measuring unit and displays them on an electric signboard or situation room of the road or transmits them as weather information;
Fog detection device comprising a.
The method of claim 1,
a moving means equipped with a camera unit that captures images around the set region of interest in real time while driving on the corresponding road;
A fog measurement unit that extracts an image of a region of interest (ROI) from an image captured by the camera unit of the moving means and measures whether or not there is fog and a visibility distance in the region of interest; and
a weather information providing server that receives the presence or absence of fog and the visibility distance detected by the fog measuring unit and displays them on an electric signboard or situation room of the road or transmits them as weather information;
Fog detection device comprising a.
According to claim 2 or 3,
The fog measuring unit
The central region of interest is divided into 10 sections, and the concentration of fog detected for each section is digitized and displayed as a graph. At the same time, each region of interest on the left and right is divided into 4 sections and the concentration of fog detected for each section is displayed as fog. A fog detection device that digitizes the concentration and displays it as a graph.
The method of claim 3,
The means of transportation is
a camera unit that captures an image of the surrounding area including the set region of interest (ROI);
a GPS receiving unit for extracting coordinates by receiving the current GPS location of the means of transportation;
a measurement coordinate unit storing two or more image acquisition GPS coordinates to capture an image of the surroundings using the camera unit;
a control unit controlling the camera unit to capture an image when the GPS coordinates received through the GPS receiver match the image acquisition GPS coordinates registered in the measurement coordinate unit;
Fog detection device using a coordinate system comprising a.

Images