WO2019151704A1

WO2019151704A1 - Method and system for measuring three-dimensional visibility using traffic monitoring camera

Info

Publication number: WO2019151704A1
Application number: PCT/KR2019/000927
Authority: WO
Inventors: 오원영; 양승환
Original assignee: 공간정보기술(주)
Priority date: 2018-01-31
Filing date: 2019-01-22
Publication date: 2019-08-08
Also published as: KR101893368B1

Abstract

Disclosed is a method and system for measuring three-dimensional visibility using a traffic monitoring camera. In the method, a depth map is generated through a first and a second image acquired by a first and a second camera; a contour line is formed according to the depth map; continuity of the contour line is examined; and visible distance information is extracted according to a certain level of continuity thereof or information on a visible distance to an object is calculated. By the method, more accurate visible distance information can be provided to a driver through a display unit, or when the visible distance information falls within a certain distance, a safety display device or the like operates or alarm information can be provided to the driver.

Description

3D visibility measurement method and system using traffic monitoring camera

An embodiment of the present invention relates to a three-dimensional visibility measurement method using a traffic monitoring camera, and more particularly, a three-dimensional visibility measurement method using a traffic monitoring camera that can calculate the visibility information of visibility measurement while performing traffic monitoring. And a system using the same.

There are now a number of closed circuit televisions (CCTVs) installed worldwide for various purposes. There are CCTVs for simple monitoring, CCTVs for preventive purposes, and CCTVs for analysis and tracking for certain purposes.

There is also a CCTV to monitor the weather. Weather monitoring CCTVs can also be used to prevent drivers from facing the risk of traffic accidents in the event of visibility disturbances such as haze, fog and fog.

For example, CCTV combined weather monitoring system is installed weather measurement equipment on the side of the road to prevent accidents caused by fog, to measure the visibility at all times, and to maintain the proper driving speed when the visible distance decreases. It is also used to guide.

In Korea, many weather stations are installed and operated to measure the weather conditions of the whole country. However, since most weather stations are not adjacent to roads, there are problems that road users cannot easily access or use observation data from weather stations. To overcome these limitations, municipal governments are installing and operating municipal roadsides as part of countermeasures against fog accidents.

The visibility system currently used is an optical visibility system that calculates visibility based on light scattering or transmission. However, this type of visibility system has a disadvantage in that accuracy is poor when there is a visibility disorder phenomenon.

In particular, due to the characteristics of the optical visibility system, it is not a whole area to be measured, but is a method of representing the visibility of the area by the measured value at a single point, so it is only 1 m away from the location of the visibility system. Even if fog occurs, there is a serious problem that can not determine the fog itself. For this reason, when the visibility system is installed, the CCTV system is installed in the same place to perform monitoring or reflect the observation result obtained by the person's direct visit. Can be.

In order to solve this problem, a conventional visual distance measuring system using CCTV has been released. However, due to the limitation of the mono image method, there are very few cases where the accuracy and reliability are practically used.

As an example, the weather observation system and method of the Republic of Korea Patent Publication No. 10-2009-0051785 is known. The prior art measures visibility using a visual line and a road model obtained from the moving area of the vehicle.

In addition, the road visibility measurement system and method using a camera of the Republic of Korea Patent Publication No. 10-2011-0037180 is known. The related art is a communication unit for receiving an image signal from a camera installed on a road and transmitting a result, an image of extracting a moving region of the vehicle from the received image signal and determining a visual line using the extracted moving region. And a processing unit, and a control unit for calculating visibility corresponding to the determined line of sight using the correction calculation function.

As described above, since the prior art uses the line of sight and the road model obtained in the vehicle moving area, there is a problem in that accuracy and reliability of the visibility distance calculated according to the vehicle speed or the curvature of the lane are inferior.

The present invention has been made to solve the problems of the prior art, and by adding only one camera to the existing traffic monitoring system, a three-dimensional visibility measurement method and system that can accurately perform two functions of monitoring and visibility measurement The purpose is to provide.

Another object of the present invention is to create a depth map through the first image and the second image, create an iso-depth line connecting the same depth in the depth map, and then connect the iso-depth lines. Read the continuity to calculate the visible distance, provide the calculated visibility information to the driver through the display device, operate the safety indicator, etc. when the visible distance is less than a certain distance, or display the image to the driver through various display devices inside and outside the vehicle To provide a three-dimensional visibility measurement method and system that can provide.

It is still another object of the present invention to provide a three-dimensional visibility measurement method and system, which is more economical than a conventional visibility system and can provide more accurate visibility information to a driver, thereby contributing to reducing traffic accidents caused by fog.

The three-dimensional visibility measurement system according to an aspect of the present invention for solving the above technical problem, the first camera to shoot the first image and the second camera to shoot a second image from a different angle from the first camera And a controller configured to calculate visible distance information from an input of a first image photographed by the first camera and a second image photographed by the second camera; A storage unit which stores the first image, the second image, and the visible distance information in association with the controller; And a communication module for supporting network interworking between the controller, the first camera, the second camera, and the control server, wherein the controller is configured to generate a depth map using the first image and the second image. An image conversion module, and a visibility measurement module for generating an iso-depth line from the depth map, and detects the connection continuity of the iso-depth line to determine whether there is a certain level or more of continuity.

According to another aspect of the present invention, there is provided a three-dimensional visibility measurement method, comprising: acquiring a stereo image from two cameras and generating a depth map; Creating a depth line in a manner similar to a contour line from the depth map; Determining the connection continuity at the equi-depth line; And when the connection continuity of the iso-depth line has a certain level or more of continuity, acquiring a maximum value of the iso-depth line among the images having the continuity, wherein the maximum value corresponds to a current viewing distance.

In one embodiment, the three-dimensional visibility measurement method may further comprise determining the authenticity of the image in the acquiring step.

In an embodiment, the 3D visibility measurement method may further include extracting an edge from an original image and analyzing the edge by overlapping the depth line in order to increase the accuracy of the continuity. have.

In one embodiment, the three-dimensional visibility measurement method, because it is impossible to extract the edge (edge) in the area when the image (image) due to the visibility obstacles, such as fog, overlapping the depth line of the plurality of images And further analyzing the data. In this case, the error of matching due to the fog can be eliminated, so that the more accurate viewing distance can be determined.

According to another aspect of the present invention, there is provided a method for measuring 3D visibility according to another aspect of the present invention, including a first image photographed by a first camera and a second image photographed by a second camera photographed at a different angle from the first camera. Obtaining a first step; Generating a depth map based on the first image and the second image; Generating a depth line from the depth map; A fourth step of determining whether the connection continuity of the equal depth line has a certain level or more of continuity; A fifth step of acquiring a maximum value of the equal depth lines having the continuity and calculating the maximum value as the visible distance information when the iso-depth line has a predetermined level or more of continuity; And a sixth step of calculating the minimum value of the iso-depth lines as the visible distance information when the iso-depth line does not have a predetermined level or more of continuity.

Using the three-dimensional visibility measurement method and system using the traffic monitoring camera of the present invention, by using a zoom lens having a variable focal length and a pan / tilt device that can be rotated up, down, left, and right, it is possible to measure 360 ° omni-directional, while traffic monitoring is possible 3 Dimensional visibility measurement systems and methods can be provided.

In addition, according to the present invention, a depth map is generated through the first image and the second image, the visible distance to the object is calculated, the visible distance is provided to the driver through the display, and the visible distance is If the distance is less than a certain distance to turn on the safety indicator light and provide an image through the display, it is more economical than the conventional visibility system can provide more accurate visibility information to the driver, thereby contributing to reducing traffic accidents caused by fog.

In addition, according to the present invention, by installing only one camera in the existing traffic monitoring system, it is possible to perform two functions of monitoring and visibility measurement.

1 is a block diagram of a three-dimensional visibility measurement system using a traffic monitoring camera according to an embodiment of the present invention.

2 is a diagram illustrating normal images of the first and second cameras and images at the time of fog generation that may be used in the 3D visibility measurement system according to an exemplary embodiment of the present invention.

3 is a diagram illustrating a depth map during normal and fog generation that can be used in a three-dimensional visibility measurement system according to an embodiment of the present invention.

4 is an exemplary view of an image extracted from the depth lines of the normal and the fog occurs that can be used in the three-dimensional visibility measurement system according to an embodiment of the present invention,

FIG. 5 is an exemplary diagram of boundary image extraction images during normal and fog generation that can be used in a 3D visibility measurement system according to an exemplary embodiment of the present invention.

FIG. 6 is an exemplary view of an image obtained by superimposing an extracted depth line image and a boundary line extracted image during normal and fog generation that can be used in a 3D visibility measurement system according to an exemplary embodiment of the present invention.

7 is a view showing the operation of the display unit and the safety display device according to an embodiment of the present invention.

8 is a flowchart illustrating a three-dimensional visibility measurement method according to an embodiment of the present invention.

The terms or words used in this specification and claims are not to be construed as limiting in their usual or dictionary meanings, and the inventors may appropriately define the concept of terms in order to best explain their invention in the best way possible. It should be interpreted as meaning and concept corresponding to the technical idea of the present invention based on the principle that the present invention.

Therefore, the embodiments described in the specification and the drawings shown in the drawings are only the most preferred embodiments of the present invention and do not represent all of the technical idea of the present invention, various equivalents that may be substituted for them at the time of the present application It should be understood that there may be water and variations.

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

Referring to FIG. 1, the 3D visibility measuring system 100 according to the present exemplary embodiment includes a first image receiving unit 111, a second image receiving unit 112, an infrared light transmitting unit 114, and a pan / tilt driving unit 116. The controller 120 may include a storage unit 130, a communication unit 140, and a display unit 150.

The first image receiver 111 is connected to the first camera to obtain a first image from the first camera. The first image receiving unit 111 may include a receiving port that receives the first image from the first camera, or may be connected to the first camera according to a preset configuration or under the control of the controller 120 to display the first image of the first camera. It may include a means for reading or a component for performing an operation corresponding to the means.

The second image receiver 112 is connected to the second camera similarly to the first image receiver 111 to obtain a second image from the second camera. The second image receiving unit 112 includes a receiving port that receives the second image from the second camera, or connects to the second camera according to a preset configuration or under the control of the controller 120 to store the second camera. It may include a means for reading the stored second image or a component for performing an operation corresponding to the means.

The first camera and the second camera may be spaced apart by a predetermined interval to generate a stereo image. The first camera and the second camera may be stereo cameras depending on the implementation.

The first and

second image receivers

111 and 112 may be separate components, but are not limited thereto and may be implemented as a single image receiver.

The infrared light emitter 114 may include an infrared light emitter, and may be coupled to the first camera and the second camera so that the first camera and the second camera may be used for photographing at night or during fog. In addition, the infrared light emitter 114 may include an infrared light emitter driver for controlling the operation of the infrared light emitter. In this case, the infrared light emitter driver may be controlled by the controller 200.

The pan / tilt drive unit 116 includes a pan / tilt drive unit, which is a single hardware installed in a single housing of the first camera and the second camera, and includes a first image and a second image in the first and second cameras. It is made to obtain a stereo image. To this end, the pan / tilt driver 116 may include a single drive shaft coupled to the housing such that a pan operation or a tilt operation of the first camera and the second camera is interlocked with each other. In addition, the pan / tilt driver 116 may include a driving circuit or a software driving module for controlling the pan / tilt driving unit.

In addition, the pan / tilt driver 116 may include a first zoom driver coupled to the first camera and a second zoom driver coupled to the second camera.

The controller 120 controls the operation of each component of the 3D visibility measurement system. The controller 120 may include a processor or a microprocessor. The controller 120 may include a stereo image conversion module 121, a visibility measurement module 122, and a PTZ control module 123.

The stereo image conversion module 121 is a combination of the first image of the first camera and the second image of the second camera or stereo vision image data (hereinafter, simply referred to as 'image data', 'source data' or 'first image data' ) Can be pre-processed side by side or in pairs, vertical errors of pre-processed image data can be removed, geometric correction can be performed, or depth maps can be generated using geometrically corrected image data.

In addition, the stereo image conversion module 121 extracts a boundary line corresponding to an edge in the image and generates image data (hereinafter, 'correction measurement image data' or 'second image data') overlapping the depth line and the boundary line. Can be.

In addition, the stereo image conversion module 121 may extract the depth map from the first image and the second image and convert the depth information into the RGB value from the depth map.

The visibility measurement module 122 may calculate or obtain a visible distance from the second image data. The information calculated or acquired by the visibility measurement module 122 may be used to operate a safety display device installed as a traffic support device or provide safety driving information to a roadside display device or an in-vehicle display device when fog occurs. . The information may include visibility information.

The PTZ control module 123 is a means for controlling the operation of the first camera and the second camera. The PTZ control module 123 may capture a detailed view of the target or the target area through the pan, tilt, and zoom functions. The PTZ control module 123 may control a pan or tilt operation of the pan / tilt driver 116 coupled to the first camera and the second camera so as to focus a desired position in the target area where the first camera and the second camera are set. Can be.

That is, the PTZ control module 123 controls the pan / tilt driver 116 to rotate the first camera and the second camera up, down, left, and right to perform 360-degree omnidirectional measurements from the point where the camera is installed. In addition, the PTZ control module 123 may simultaneously control the zoom magnifications of the first camera and the second camera at the same magnification or individually adjust the zoom magnifications to different magnifications.

In this case, the visibility measurement module 122 may automatically operate the zoom lens of the pan / tilt driver 116 and the camera at a predetermined time interval through the PTZ control module 123, but is not limited thereto. It may be implemented to operate as.

The stereo image conversion module 121, the visibility measurement module 122, and the PTZ control module 123 described above may be implemented in at least a part of hardware in the controller 120 or the controller 120 may be stored in the storage 130. The module may be implemented to mount at least one of the stereo image conversion module 121, the visibility measurement module 122, and the PTZ control module 123 and execute a function thereof.

The storage unit 130 may include storage means such as a semiconductor memory such as a RAM or a ROM, a flash memory, a hard disk, an optical disk, or the like. The storage unit 130 may store at least one or more of the stereo image conversion module 121, the visibility measurement module 122, and the PTZ control module 123 in the form of a software module.

The communication unit 140 may support transmission and reception of signals and data between the control unit 120 and each component in the 3D visibility measurement system. That is, the communication unit 140 may include a means or a component for providing or supporting a connection for interworking between the input terminal and the output terminal between the process units in the system.

In addition, the communication unit 140 may include at least one communication subsystem for supporting a wired communication network, a wired network, a wireless communication network, a wireless network, or a combination thereof, and the control unit 120 may include the safety display device 160, It may support transmitting and receiving signals and data with the control server 170 or the display device 180.

The safety display device 160 may include a fog generation warning device using sound, light, and the like, a vehicle induction lamp, a flashing light, or the like installed in a center line, a lane, a guide rail, and the like in a fog area. The safety display device 160 interlocks with the 3D visibility measurement system 100 and may operate according to the control signal of the system.

The control server 170 may collect and monitor the signals or information produced or output from the 3D visibility measurement system 100 and the status of peripheral devices operating in accordance with the signals or information. The control server 170 may classify a fog area or detect a change in a fog area or spread or reduce the fog area based on information of a plurality of adjacent three-dimensional visibility measurement systems, and based on the obtained information. An additional traffic safety system can be operated.

The control server 170 may receive the visibility information, the first and

second images

201, 201a, 202, 202a or the information of the safety display device 160, and the first and second cameras, the safety. The display device 160 or the display device 180 may be controlled.

The display device 180 may include a device installed at a roadside and displaying only text or both text and an image. In addition, the display device 180 may include all image display devices operating in an intelligent traffic system (ITS). For example, the display device 180 may include various image display devices that are located on a road or installed in a vehicle driving a road.

The three-dimensional visibility measurement system 100 according to the present embodiment is implemented to further include a first camera, a second camera, a safety display device 160, a control server 17 and an external display device 180 in a broad sense. Can be.

The operation principle of the above-described three-dimensional visibility measurement system 100 will be described in more detail as follows.

As shown in (a) and (b) of FIG. 2, the first camera photographs the first image 201 and the second camera photographs the second image 202. In addition, as shown in (c) and (d) of FIG. 2, when fog occurs, the first camera may photograph the first image 201a and the second camera may photograph the second image 202a.

If the camera used in the existing traffic monitoring system is the first camera, it can be implemented to perform two functions of monitoring and visibility measurement by adding only one camera like the second camera.

The first camera and the second camera may be configured to capture an image in 360 ° by using a zoom lens having a variable focal length and a pan / tilt device capable of rotating up, down, left, and right.

The first camera and the second camera may simultaneously provide a first image and a second image of roads and streets to monitor traffic at different zoom magnifications. Here, each of the first image and the second image may be an enlarged image including an object such as a vehicle. In this case, the first camera may be zoomed in and the second camera may be operated in the same manner as the zoom out. Also, the first camera may be implemented to display a general image and the second camera may display an image to which the fog removing function is applied.

The controller 120 interoperates with the first camera and the second camera and acquires, as an input,

first images

201 and 201a captured by the first camera and

second images

202 and 202a captured by the second camera. As illustrated in (a) and (b) of FIG. 3,

images

203 and 204 including depth map information may be generated. The depth map can be used to calculate the line of sight information.

To this end, the controller 120 may include a stereo image conversion module 121, a visibility measurement module 122, and a PTZ (pan / tilt / zoom) control module 123.

The stereo image conversion module 121 generates a depth map by using the first image photographed by the first camera and the second image photographed by the second camera, and creates a depth line from the depth map (205 of FIG. 4). And 206, a boundary line may be extracted from the original image (source data) (see 207 and 208 of FIG. 5).

In this case, the stereo image conversion module 121 may correct the first and

second images

201 or 201a, 202 or 202a, and then generate a depth map using the corrected first and second images. By performing the calibration process, a more accurate depth map of the data can be generated.

In the above-described process, the stereo image conversion module 121 determines a conjugate point from the intersection of the projection center and the reference point on the position plane of the first and

second images

201, 201a, 202, and 202a, and uses the conjugate point to determine the three-dimensional image. It is implemented to generate a depth map using Epipolar Geometry which generates.

The visibility measurement module 122 is implemented to detect the connection continuity using the depth line and the boundary line, and determine whether the connection continuity has a certain level or more of continuity.

That is, the visibility measurement module 122 extracts an edge from the original image of the first image photographed by the first camera and the second image photographed by the second camera, and extracts an edge and the iso-depth line. The analysis can be superimposed (see

images

209 and 210 of FIG. 6).

In addition, the visibility measurement module 122 may be implemented to be optimized by additionally applying a method of extracting a plurality of consecutive images and a statistical method in order to reduce a determination error at a boundary where visibility is unclear when fog occurs.

The depth line means a line connecting a point representing a distance and a closeness of a distance on the depth map, similar to a contour line connecting a point having the same height based on the average surface of the sea. If an image is formed so that one object is accurately distinguished from the surrounding background, it may be determined that the image has continuity between contiguous image elements (pixels).

Therefore, the visibility measurement module 122 may examine the continuity in the iso-depth line, and may determine that the value is the visible distance only when the maximum value is acquired only when the continuity is higher than a predetermined level.

In other words, if there is no visibility deterioration due to fog, the visibility distance at that time can be said to be the theoretical maximum that can be obtained from stereo images. At this time, in the visibility measurement module 122, if the iso-depth line has a continuity of a predetermined level or more, the maximum value in the iso-depth line having continuity is obtained, and the maximum value is calculated as the visible distance information.

In addition, when visibility decreases due to fog or the like, an image is not formed from the farthest point, and if an image is not formed, the matching point may not have regularity. At this time, if the iso-depth line in the visibility measurement module 122 does not have a continuity of a predetermined level or more, the minimum value of the iso-depth line is calculated as visual distance information.

This is because when the image is not formed due to visibility obstacles such as fog, it is impossible to extract the edges from the corresponding area. This is because the error can be eliminated, so that a more accurate view distance can be determined.

Meanwhile, the captured first image 201 and the second image 202 are stored in the storage 130. The display 150 or the display device 180 may display the visual distance calculated by the controller 120 as an image, and display the captured

first image

201 and 201a or the

second image

202 and 202a. You may.

The safety display device 160 may perform a preset operation or output preset information or a screen corresponding to the visible distance information calculated by the controller 120. The safety display device 160 may include a device for providing a safety display function installed on a road such as a road electric light display (VMS), a fog display device, a variable speed limit display device, a directional speaker, and a fog lamp.

For example, when the safety display device 160 is a fog light, when the visible distance information is a predetermined distance or more and does not correspond to the safety distance, it is not lit when the visible distance information is a certain distance or less to notify the driver on the road. Can be operated. In addition, according to the implementation, the visible distance may be set in a predetermined range so that the brightness and the flashing speed may be adjusted in stages.

Therefore, as illustrated in FIG. 7, the display device 180 may provide a visual distance as a numerical value, and may also provide an image of a road taken by the first camera or the second camera.

To this end, the control server 170 displays the visible distance information through the display device 180, when the visibility information calculated by the visibility measurement module 122 is 50m, and at the same time provide an image of the road One or more safety indicators 160 may be activated.

In this case, the storage unit 130 may store the first image and the second image, and the control unit 120 may operate the display device 180 and the safety display device 160 through the communication unit 140. Control their behavior.

8 is a flowchart illustrating a control method of a 3D visibility measurement system according to an embodiment of the present invention.

Referring to FIG. 8, the three-dimensional visibility measurement method according to the present embodiment includes a series of steps performed by the above-described three-dimensional visibility measurement system. First, a first image of the first camera is acquired, and the first A second image of the second camera photographed at an angle different from that of the camera may be acquired (S802).

Here, the first camera and the second camera simultaneously provide a first image and a second image photographing a road and a street for monitoring traffic from different angles. The first image and the second image may be images including an object such as a vehicle.

Next, a first image photographed by the first camera and a second image photographed by the second camera are acquired as inputs, and a depth map is generated using three-dimensional coordinates in the first image and the second image. (S804).

In operation S804, after correcting the first image and the second image, the depth map may be generated using the 3D coordinates obtained from the corrected first image and the second image. The step S804 may include generating a depth map using Epipolar Geometry for generating a stereoscopic image through the conjugate point determined from the first image and the second image. According to this method, a more accurate depth map of the data can be generated.

Next, an equal depth line is generated or extracted from the depth map (S806).

Next, it is determined whether the continuity of the equal depth line is detected to have a continuity of a predetermined level or more (S808). This step (S808) extracts an edge from the original image of the first image taken by the first camera and the second image taken by the second camera, and analyzes by overlapping the edge and the iso-depth line. It may include the process of doing.

Next, if the iso-depth line has a continuity of a predetermined level or more, the maximum value is obtained among the iso-depth lines having continuity, that is, the minimum parallax value is calculated as the visible distance information (S810).

On the other hand, when the iso depth line does not have a continuity of a predetermined level or more in step S808, it may be determined whether the photographing center point by the camera is the minimum distance measuring point (S812). If the photographing center point is the minimum distance measuring point, the minimum value or the lowest value among the depth lines may be calculated or applied as the visible distance information (S814).

On the other hand, if it is determined in the determination step (S812) that the photographing center point is not the minimum distance measuring point, the control unit or the visibility measurement module of the controller may move the photographing center point step by step (S816). In this case, the controller may move the photographing center point to a minimum distance measuring point or a position adjacent thereto from a distance to a near distance by a preset step-by-step zoom out method. Then, when the photographing center point is located at a predetermined minimum distance measuring point or the area, the process may return to obtaining the images of the first and second cameras.

Next, the safety display device may be operated in correspondence with the visual field information selectively calculated in the above steps (S810 and S814) (S818). In this step, it is determined whether the visible distance is greater than or equal to a certain distance, and when the visible distance information is a reference value less than or equal to the predetermined distance, the safety display device or the like can be operated.

In addition, the controller may display the viewing distance through the display device or store the first image, the second image, and the viewing distance information in the storage unit (S820).

According to the present embodiment, a depth map is generated based on the first image and the second image, an iso-depth line is formed according to the depth map, the connection continuity of the iso-depth line is examined, and continuity of a predetermined level or more is determined. In accordance with the present invention, the visible distance information may be extracted or the visible distance information to an object may be calculated. The calculated information is used to provide visibility information to the driver through the display device, or to provide various safe driving environments such as operating a safety display device and providing an image through the display device when the visible distance information is below a certain distance. It can be used, and by such a configuration and action effect is more economical than the conventional visibility system, there is an effect that can provide more accurate visibility information to the driver.

The above-described three-dimensional visibility measurement method may be implemented as a submodule in the form of a software module of the controller, in particular, the visibility measurement module. Here, the visibility measurement module may include a plurality of submodules that perform each function in response to steps S802 to S820, and for example, the plurality of submodules may correspond to an acquisition module (corresponding to an acquisition submodule, which is the same below). ), A generation module, an extraction module, a first determination module, a second determination module, a view distance calculation module, an optimum value applying module, a moving module, an operation module, a display module, and a storage module.

As described above, in the detailed description of the present invention has been described with respect to preferred embodiments, those skilled in the art without departing from the spirit and scope of the invention described in the claims below It will be appreciated that various modifications and variations can be made in the present invention. Therefore, the technical spirit of the present invention should not be limited to the above-described embodiments, but should be defined by the appended claims and equivalents thereof.

Claims

A first image photographed by the first camera and a second image photographed by the second camera in conjunction with a first camera photographing the first image and a second camera photographing the second image at a different angle from the first camera; A controller configured to calculate the visible distance information from the input of the image;

A storage unit which stores the first image, the second image, and the visible distance information in association with the controller; And

And a communication module supporting network interworking between the control unit, the first camera, the second camera, and the control server.

The control unit,

A stereo image conversion module for generating a depth map using the first image and the second image, and

And a visibility measurement module for generating an iso-depth line from the depth map, and detecting a connection continuity of the iso-depth line to determine whether there is a continuity of a predetermined level or more.
According to claim 1,

The visibility measurement module,

When the iso-depth line has a continuity of a predetermined level or more, the maximum value is obtained among the iso-depth lines having continuity and the maximum value is calculated as visual distance information,

3D visibility measurement system using a traffic monitoring camera to analyze the lowest value of the visible distance by overlapping the equi-depth line, if there is no boundary extraction from the first image and the second image.
According to claim 1,

The stereo image conversion module is a three-dimensional visibility measurement using a traffic monitoring camera for generating the depth map using Epipolar Geometry for generating a three-dimensional image through the conjugate point determined from the first image, the second image system.
According to claim 1,

The controller may output one or more of the first image, the second image, and the viewing distance information to a display device, operate a safety display device according to the viewing distance information, or operate the first image and the first image. A three-dimensional visibility measurement system using a traffic monitoring camera that provides two images and the visible distance information or a combination thereof to the control server.
A first step of acquiring a first image photographed by a first camera and a second image photographed by a second camera photographed at an angle different from that of the first camera;

Generating a depth map based on the first image and the second image;

Generating a depth line from the depth map;

A fourth step of determining whether the connection continuity of the equal depth line has a certain level or more of continuity;

A fifth step of acquiring a maximum value of the equal depth lines having the continuity and calculating the maximum value as the visible distance information when the iso-depth line has a predetermined level or more of continuity; And

A sixth step of calculating the minimum value of the iso-depth lines as visual distance information when the iso-depth line does not have a continuity of a predetermined level or more.

3D visibility measurement method using traffic monitoring camera.