KR102526969B1 - Smart safety mirror device - Google Patents

Abstract

The present invention relates to a smart reflector device, and relates to a base, a CCTV module installed at an end of the base and capturing a road image within a specific area, and an AI-based object analysis on the road image to perform object analysis in first and second directions. An edge computing module for determining road conditions of each of the base, a reflector module installed on a pillar of the base, and a first installed in the first and second directions based on the reflector and displaying road conditions generated in the corresponding direction. and second display modules.

Description

Smart reflector device {SMART SAFETY MIRROR DEVICE}

The present invention relates to a reflector technology, and more particularly, to a smart reflector device capable of conveying a dangerous situation by analyzing a road image taken near the smart reflector through an edge computing module based on artificial intelligence (AI).

A road reflector is a facility installed to induce safe driving by checking other vehicles, pedestrians, and road conditions in front in advance at a curved part of the road, a place where the visibility according to the driving speed is not secured, or an intersection where the visibility on the left and right is not secured. am.

The road reflector has a function of preventing an accident in advance by providing the driver with information about the road conditions ahead in a section where the driver's visibility is poor so that the driver can take appropriate action accordingly. The road reflector provides information to the driver in an indirect way through the image of the mirror surface.

Existing road reflectors use a convex mirror to secure a wider viewing angle, which causes distortion of the image and makes it difficult to determine the location and approaching speed of the subject. There is a problem that significant functional degradation occurs.

Due to the limited viewing angle and distortion of the existing road reflector, it is possible to check the subject image of the opposite approach only when it is close to the intersection where traffic conflicts occur, and the possibility of accidents is high due to the lack of free time for accident prevention.

In order to solve these problems, there are increasing attempts to present new "road and traffic safety facilities" that combine digital data and AI technology through deep learning for CCTV images in line with the era of the 4th industrial revolution.

Korean Patent Registration No. 10-1720163 (2017.03.21)

An embodiment of the present invention is to provide a smart reflector device capable of delivering a dangerous situation by analyzing a road image taken near the smart reflector through an edge computing module based on artificial intelligence (AI).

An embodiment of the present invention provides a smart reflector device capable of preparing with sufficient safety time in advance by quickly and effectively conveying dangerous situations by analyzing CCTV images to secure sight distance and providing road situation information visually and audibly. .

An embodiment of the present invention integrates a CCTV into a reflector at the same point and combines various peripheral devices such as a warning light, a speaker, and a display with the reflector to form an integral unit, thereby optimally combining information providing means according to road conditions. It is intended to provide a smart reflector device.

An embodiment of the present invention can directly show the road conditions to the driver by replacing the existing mirror-shaped reflector with a full replacement or partial combination using an LED display or monitor, and can give a warning through a screen and a speaker in case of illegal parking. It is intended to provide a smart reflector device with

Among the embodiments, the smart reflector device includes a base, a CCTV module installed at an end of the base and taking a road image within a specific area, and performing AI-based object analysis on the road image to determine first and second directions. An edge computing module for determining each road condition, a reflector module installed on a pillar of the base, and a first and second sensors installed in the first and second directions based on the reflector and displaying road conditions generated in the corresponding direction. It includes second display modules.

The edge computing module may calculate a driving risk of a vehicle traveling in the direction of the reflector based on the road conditions.

Among embodiments, the smart reflector device may further include a driving risk display module installed on the base under the reflector module and providing the driving risk.

The first and second display modules may be directly coupled to left and right directions of the reflector and fixed by coupling the reflector to the base.

The first and second display modules may be fixedly coupled to the base and positioned on upper left and right sides of the reflector.

The first and second display modules may be coupled to the left and right rear surfaces of the reflector so as not to protrude outside the reflector, and the left and right rear surfaces of the reflector may be designed to be transparent.

The disclosed technology may have the following effects. However, it does not mean that a specific embodiment must include all of the following effects or only the following effects, so it should not be understood that the scope of rights of the disclosed technology is limited thereby.

The smart reflector device according to an embodiment of the present invention may deliver a dangerous situation by analyzing a road image captured near the smart reflector through an edge computing module based on artificial intelligence (AI).

The smart reflector device according to an embodiment of the present invention analyzes CCTV images to secure sight distance and provides road situation information visually and audibly, thereby quickly and effectively conveying dangerous situations so that sufficient safety time can be prepared in advance.

The smart reflector device according to an embodiment of the present invention integrates a CCTV into a reflector at the same point and combines various peripheral devices such as a warning light, a speaker, and a display with the reflector to form an integrated unit, thereby providing an optimal means of providing information according to road conditions. can be run in combination.

The smart reflector device according to an embodiment of the present invention can directly show the road conditions to the driver by replacing the existing mirror-shaped reflector with a front replacement or partial combination using an LED display or monitor, and can display the screen and speaker during illegal parking. attention can be given.

1 is a diagram illustrating the configuration of a smart reflector device according to the present invention.
2a-2c are diagrams illustrating a coupled state of first and second displace modules in FIG. 1 .
3 is a view showing a state in which the smart reflector device of FIG. 1 is installed on a road.
4 is a flowchart illustrating the operation of a smart reflector device according to an embodiment of the present invention.

Since the description of the present invention is only an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiment can be changed in various ways and can have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, the scope of the present invention should not be construed as being limited thereto.

Meanwhile, the meaning of terms described in this application should be understood as follows.

Terms such as "first" and "second" are used to distinguish one component from another, and the scope of rights should not be limited by these terms. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected to the other element, but other elements may exist in the middle. On the other hand, when an element is referred to as being "directly connected" to another element, it should be understood that no intervening elements exist. Meanwhile, other expressions describing the relationship between components, such as “between” and “immediately between” or “adjacent to” and “directly adjacent to” should be interpreted similarly.

Expressions in the singular number should be understood to include plural expressions unless the context clearly dictates otherwise, and terms such as “comprise” or “having” refer to an embodied feature, number, step, operation, component, part, or these. It should be understood that it is intended to indicate that a combination exists, and does not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

In each step, the identification code (eg, a, b, c, etc.) is used for convenience of explanation, and the identification code does not describe the order of each step, and each step clearly follows a specific order in context. Unless otherwise specified, it may occur in a different order than specified. 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.

The present invention can be implemented as computer readable code on a computer readable recording medium, and the computer readable recording medium includes all types of recording devices storing data that can be read by a computer system. . Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. In addition, the computer-readable recording medium may be distributed to computer systems connected through a network, so that computer-readable codes may be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless defined otherwise. Terms defined in commonly used dictionaries should be interpreted as consistent with meanings in the context of the related art, and cannot be interpreted as having ideal or excessively formal meanings unless explicitly defined in the present application.

1 is a diagram illustrating the configuration of a smart reflector device according to the present invention.

Referring to FIG. 1, the smart reflector device 100 includes a base 110 and a reflector module 120 as a basic configuration for a typical reflector function, and includes a CCTV module 130, an edge computing module 140, and a display module. 150, a speaker 160 and a warning light 170 may be implemented.

Base 110 may correspond to a support erected vertically from the ground. The base 110 may be erected in a fixed state to the ground. For example, the base 110 may be fixed with a lower end buried in the ground.

The reflector module 120 may be installed on a pole of the base 110 . Here, the reflector module 120 may include a reflector 121 and a rear support plate 123 coupled to and supported by a rear surface of the reflector 121 . If the reflector 121 can be manufactured and processed to perform a convex mirror function, it can be formed of glass, plastic, metal, etc., and the rear support plate 123 can be formed of a metal material such as stainless steel or aluminum. In one embodiment, the reflector 121 may be implemented as an LED display or monitor instead of a mirror so as to perform a function of displaying road conditions on the screen.

The CCTV module 130 may include a monitoring camera for capturing road images within a specific area, and may be installed at an end of the base 110 to minimize blind spots. The CCTV module 130 and the reflector module 120 may be physically integrated and installed at the same point. The smart reflector device 100 can be integrated and used with existing CCTV infrastructure, such as CCTV for crime prevention and illegal parking/stop control systems. Here, the CCTV module 130 may sense a vehicle approaching from another direction.

The CCTV module 130 may use a multi-sensor camera, a wide-angle lens, or a fisheye lens. A wide-angle lens causes distortion when used for portraits, but takes a larger picture of the same space when used for landscapes. A fisheye lens has more distortion than a wide angle lens, but can see up to 360 degrees depending on the angle of installation. The smart reflector device 100 may secure a wide viewing angle through the CCTV module 130 .

The edge computing module 140 may be installed between the pillar of the base 110 and the rear support plate 123 of the reflector module 120 while being mounted on the control distribution box 180 . The edge computing module 140 may perform operations such as data collection, situation analysis, and recognition. The edge computing module 140 can apply information learned from a separate learning server to perform situational analysis and cognitive operations, and as a component for this, an internal independent inference system (eg, AI analysis device) ).

The edge computing module 140 uses the road image received from the CCTV module 130 that photographs the road within a specific area where the smart reflector device 100 is installed to determine whether pedestrians and vehicles are approaching, and the pedestrians and vehicles are approaching. The display module 150 may be controlled to indicate that it is in progress. In one embodiment, the edge computing module 140 may recognize an object from a road image generated by taking a picture by the CCTV module 130 . Here, information collected through the CCTV module 130 may be de-identified to protect personal information and intellectual property rights. The edge computing module 140 may detect an object in the road image as a bounding box using the COCO dataset format. The COCO dataset format is a JSON metadata format to be used as a dataset for neural networks to detect objects in images.

The edge computing module 140 may determine road conditions in each of the first and second directions by performing AI-based object analysis on the road image. The edge computing module 140 may classify moving objects based on road images. In an embodiment, the edge computing module 140 may generate object data for the moving object by calculating the movement of the moving object and the change in the distance between the moving objects and extracting a unique feature of the moving object. For example, when the moving objects are vehicles traveling in different directions, when the distance between the moving objects rapidly decreases, corresponding data may be extracted by detecting this. When extracting a unique feature of a moving object, the edge computing module 140 may adjust an extraction frame according to the speed of the moving object. For example, when the speed of the moving object is fast, the unique feature of the moving object may be extracted by setting the extraction frame value higher than when the speed of the moving object is slow. When a moving object (a driving vehicle) is detected, the edge computing module 140 may determine a road condition given to the object by calculating a movement of the moving object. The edge computing module 140 may calculate a driving risk of a vehicle traveling in the direction of the reflector 121 based on road conditions. In an embodiment, the edge computing module 140 may generate road situation scenarios by time-series analysis of road conditions and input the road situation scenarios into a dangerous situation model to determine a dangerous situation. Here, the edge computing module 140 may recognize a dangerous situation by calculating the movement of the moving object and the change in the distance between the moving objects and extracting a unique feature of the moving object. At this time, a dangerous situation notification event may be generated and transmitted according to the grade of the recognized dangerous situation.

The edge computing module 140 detects accessibility in the direction of the reflector 121 for pedestrians and vehicles in a specific area through object analysis, and when the accessibility approaches the direction of the reflector 121, the reflector for the driving vehicle. It is possible to calculate the approaching speed in the direction of (121) and determine the possibility of collision with a pedestrian or driving vehicle. More specifically, the edge computing module 140 classifies the dangerous section in stages based on the effective video radius of the CCTV module 130 installed at the end of the base 110, detects the location of objects such as vehicles and pedestrians for each section, and The driving risk may be calculated according to the driving speed of the entering vehicle. Here, the danger zone can be divided into stages of intersection, danger zone A, and danger zone B, and the risk level can increase from danger zone B to the intersection.

The control distribution box 180 may be equipped with an AI analysis device, a control device, and an IoT sensor. Here, the IoT sensor may correspond to a sensor installed in the smart reflector device 100, and may collect environmental information such as temperature, humidity, and illumination that affect function deterioration.

The display module 150 may be installed in first and second directions, respectively, with respect to the reflector 121 and display road conditions occurring in the corresponding directions. The display module 150 may display road conditions as text information. The first and second display modules 150 may be fixedly coupled to the pillars of the base 110 and may be positioned on the upper left and right sides of the reflector 121 . The positions of the first and second display modules 150 are not limited thereto, and may be directly coupled to the reflector 121 or may be coupled in a built-in form built into the rear surface of the reflector 121 .

The speaker 160 and the warning light 170 are installed at the end of the base 110 and may provide a warning signal and notification voice about a dangerous situation according to a dangerous situation notification event of the edge computing module 140 . Here, the speaker 160 may include a waterproof speaker so as not to be affected by the external environment. The speaker 160 and the warning light 170 display road conditions on the first and second display modules 150, and when a dangerous situation is predicted, they warn pedestrians and vehicles to prevent accidents and protect pedestrians. . The warning light 170 may be implemented as an LED warning light lamp and may be installed at the distal end of the base 110 to give visual attention when a vehicle or pedestrian needs attention. A speaker 160 may also be installed on the base 110 to notify an emergency situation. For example, when illegal parking occurs, an illegal parking screen may be displayed on the first and second display modules 150 and a warning voice may be output through the speaker 160 .

In one embodiment, the smart reflector device 100 may process an operation of performing data transmission and reception with the control center through wireless communication such as WiFi and LoRa.

In one embodiment, the smart reflector device 100 may install an emergency bell to connect with the control center when emergency situations and assistance are required.

2a-2c are diagrams illustrating a coupled state of first and second displace modules in FIG. 1 .

Referring to FIGS. 2A to 2C , first and second display modules 150 are installed in first and second directions with respect to the reflector module 120 and display road conditions occurring in the corresponding directions. Here, the first and second display modules 150 may display a road situation illuminated by the reflector module 120 using light emitting diodes (LEDs), for example, a pedestrian approaching or a vehicle approaching. Each of the first and second display modules 150 may display the same or different information. For example, when there is a pedestrian on the road and a vehicle is approaching, “Pedestrian crossing caution” is displayed on one of the first and second display modules 150 in one direction and “vehicle approach warning” is displayed on the display module in the other direction. ” can be displayed.

In FIG. 2A , the first and second display modules 150 include a first display module 151 coupled to the left side of the reflector module 120 and a second display module coupled to the right side of the reflector module 120 ( 152) may be included. The first display module 151 and the second display module 152 are directly coupled to the reflector module 120 and fixed by coupling the reflector module 120 to the base 110 . In one embodiment, the first and second display modules 150 may be coupled to the reflector module 120 via connection members 210 fixed to both sides of the reflector module 120 . At this time, the frame is fixedly installed on the rear support plate 123 of the reflector module 120, the bracket is fixedly installed on the pillar of the base 110, and the reflector module 120 is coupled to the base 110 by connecting the frame and the bracket. can The first display module 151 and the second display module 152 are located on the same horizontal line as the center of the reflector module 120, so that the driver of the road visually checks the road projected on the reflector module 120. The display module 151 or the second display module 152 is first secured in the driver's field of view, so that road conditions can be quickly recognized.

In FIG. 2B, the first and second display modules 150 include a first display module 153 located on the upper left side of the reflector module 120 and a second display module (located on the upper right side of the reflector module 120). 154) may be included. The first display module 153 and the second display module 154 are fixedly coupled to the pillar of the base 110 . The first display module 153 and the second display module 154 are installed on the top of the reflector module 120 in both directions relative to the base 110 to widen the display size, so that more diverse and detailed It can display information related to road conditions.

In FIG. 2C, the first and second display modules 150 include a first display module 155 coupled to the rear left side of the reflector module 120 and a second display module coupled to the right rear side of the reflector module 120 ( 156) may be included. The first display module 155 and the second display module 156 may be coupled to the reflector module 120 in a built-in form. The first display module 155 and the second display module 156 are disposed between the reflector 121 and the rear support plate 123 of the reflector module 120 and do not protrude outside the reflector module 120 . At this time, the reflector 121 is designed to be transparent at the part where the first display module 155 and the second display module 156 are combined to be displayed on the first display module 155 and the second display module 156. Make things visible from the outside.

The smart reflector device 100 may further include a driving risk level display module 230 providing a driving risk level below the reflector module 120 .

The driving risk display module 230 is installed on the base 110 at the lower part of the reflector module 120 and may provide the driving risk of the driving vehicle entering in the direction of the reflector calculated by the edge computing module 140. In one embodiment, the driving risk display module 230 may display a dangerous state by varying the light emitting color and flashing speed of the LED according to the driving risk of the driving vehicle.

The smart reflector device 100 according to an embodiment is implemented by replacing the existing mirror-shaped reflector with a front replacement or partial combination, as shown in FIGS. 2A to 2C using an LED display or monitor, to provide a road to the driver It can show the situation directly, allowing the driver to quickly and accurately recognize the road conditions.

3 is a view showing a state in which the smart reflector device of FIG. 1 is installed on a road.

Referring to FIG. 3, the smart reflector device 100 may be installed in a place where it is difficult for the vehicle driver to easily recognize pedestrians and vehicles approaching from different directions due to blind spots such as road intersections, back roads, and sharp curves. there is.

At the intersection as shown in FIG. 3, the smart reflector device 100 is installed at a position facing the bicycle 330 traveling on the road in the opposite direction, and the CCTV module 130 can be installed to photograph a specific area of the road. there is. The CCTV module 130 may transmit a video to the edge computing module 140 by capturing a specific area including each road in a different direction. At this time, the reflector module 120 illuminates the road to be illuminated by the reflector 121. Since the driver of the bicycle 330 traveling on the road can confirm that the vehicle 310 traveling on the road in the other direction has come to at least the “P” point, the safety margin is short.

The smart reflector device 100 determines the road conditions of each of the different directions by performing artificial intelligence-based object analysis on the road images captured by the CCTV module 130 through the edge computing module 140, and the road conditions are It can be displayed on the first and second display modules 150 . When the object of the vehicle 310 approaching from the road in the second direction is recognized, the edge computing module 140 reports “vehicle approaching” to the display module installed in the second direction among the first and second display modules 150. By displaying letters, the driver of the bicycle 330 can recognize in advance that a vehicle is approaching on the road in the second direction before the vehicle 330 arrives at the “P” point, so that an additional safety margin can be secured. Here, an additional safety margin distance may be determined according to the category of the shooting area of the CCTV module 130 .

4 is a flowchart illustrating the operation of a smart reflector device according to an embodiment of the present invention.

Referring to FIG. 4 , the smart reflector device 100 may capture a road image within a specific area through the CCTV module 130 (step S410).

The smart reflector device 100 performs artificial intelligence (AI)-based object analysis on the road image captured by the CCTV module 130 through the edge computing module 140, and the road conditions in each of the first and second directions. can be determined (step S430).

The smart reflector device 100 measures road conditions occurring in first and second directions, respectively, with respect to the reflector module 120 at the center, and the first and second display modules installed in the corresponding first and second directions ( 150) as text information (step S450).

The smart reflector device 100 may calculate the driving risk of a driving vehicle entering the direction of the reflector based on road conditions in the edge computing module 140 and provide the driving risk through the driving risk display module 230 ( Step S470).

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the claims below. You will understand that it can be done.

100: smart reflector device
110: base 120: reflector module
130: CCTV module 140: edge computing module
150: first and second display modules
160: speaker 170: warning light
180: control distribution box
210: connecting member 230: driving risk display module

Claims (6)

Base;
CCTV module installed at the end of the base and taking a road image in a specific area;
a reflector module installed on the pillar of the base;
An edge for determining a road condition in each of the first and second directions by performing artificial intelligence-based object analysis on the road image, and calculating a driving risk of a driving vehicle entering the direction of the reflector based on the road condition computing module;
first and second display modules installed in the first and second directions based on the reflector and displaying road conditions generated in the corresponding directions; and
Including a driving risk display module installed on the base at the bottom of the reflector module and providing the driving risk,
The edge computing module
The road situation is time-series analyzed to generate a road situation scenario, and a dangerous situation is determined by inputting the road situation scenario into a risk situation model;
A smart reflector device, characterized in that for generating a risk notification event according to the determined dangerous situation and providing a notification voice or warning signal related to the dangerous situation through a speaker or a warning light installed on the base.
delete delete The method of claim 1, wherein the first and second display modules are
Smart reflector device, characterized in that directly coupled to the left and right directions of the reflector and fixed by coupling the reflector to the base.
The method of claim 1, wherein the first and second display modules are
Smart reflector device, characterized in that fixedly coupled to the base and located on the upper left and right sides of the reflector.
The method of claim 1, wherein the first and second display modules are
The smart reflector device, characterized in that coupled to the rear left and rear right sides of the reflector and disposed so as not to protrude out of the reflector, and the rear left and rear right sides of the reflector are designed to be transparent.

Images