KR20220086043A - Smart Road Information System for Blind Spot Safety - Google Patents

Abstract

The present invention acquires a moving picture of a road using a camera, acquires information about a target object using a radar sensor, and provides clear and accurate visual information on road conditions and risk factors on the road to road users in real time. It relates to a "smart road information provision system for safety in blind spots" that can effectively prevent traffic accidents by allowing accurate recognition of road conditions even in the zone.

Description

Smart Road Information System for Blind Spot Safety

The present invention relates to a smart road information providing system for providing information on road safety while showing road conditions in real time to drivers and pedestrians ("road users") instead of a conventional road reflector installed on the road. Specifically, after acquiring a video of the road using a camera and acquiring information about a target object using a radar sensor, it provides clear and accurate visual information on road conditions and road hazards in real time to road users. It relates to a "smart road information provision system for safety in blind spots" that can effectively prevent traffic accidents by allowing accurate recognition of road conditions even in the zone.

The conventional road reflector provides the driver with information about other vehicles, pedestrians, and the road situation ahead in advance in the curved part of the road, in a place where visibility is not secured due to driving speed, or at an intersection where left and right visibility is not secured to ensure safe driving. It is responsible for the induction function. Korean Patent Registration No. 10-0382799 discloses an example of a road reflector according to the prior art.

However, the conventional road reflector delivers a distorted image due to the convex mirror to the road user, and accordingly, the road user suffers from an error in distance judgment, an error in recognizing the existence of a vehicle, and a mismatch with the actual vehicle location, In particular, in the case of night, road users experience considerable difficulties in recognizing the exact situation due to the light of vehicle headlights.

Republic of Korea Patent Publication No. 10-0382799 (2003. 05. 09. Announcement).

The present invention has been developed to solve and overcome the problems and limitations of the mirror distortion and the narrow field of view of the blind spot of the existing road reflector as described above. After solving the distortion problem of the road, it is visually provided to road users through the information display device to secure a stable view of the blind spots of the road, and at the same time, it recognizes objects on the road using the acquired video and radar sensor, and the control unit By analyzing image analysis and target object information, various risk factors on the road are automatically analyzed and the corresponding information is provided to road users in various forms to quickly and easily recognize dangerous situations on the road, thereby reducing the risk of traffic accidents. It aims to provide technology that can reduce it.

In the present invention, in order to achieve the above object, the support 4 installed at a fixed observation point on the road or the edge of the road, and a moving picture of the road condition including the target object and movement information of the target object are acquired and collected. A collection unit (1), a control unit (2) for generating moving images and display information to be provided to road users, and an information providing unit (3) installed on the support (4) and displaying information received from the control unit (2) consists of; A smart road information providing system is provided, characterized in that it provides road conditions to road users in real time in a blind spot of view.

In the smart road information providing system according to the present invention, the collecting unit 1 includes an image collecting device 10 that captures a road and acquires a moving picture of a road condition including a target object, and recognizes the existence of the target object and aims It may be configured to include a target object detection device 11 for acquiring a moving direction and a moving speed as movement information of an object, and the image collecting device 10 is a panoramic camera capable of acquiring a panoramic image, and a target object detecting device Reference numeral 11 may include a laser sensor, and the control unit 2 includes image information acquired and transmitted by the image collection device 10 of the collection unit 1 and movement information acquired and transmitted by the target object detection device 11 . The information receiving module 20 for receiving the information storage module 21 for storing the information received by the information receiving module 20, the region of interest in which the target object is included in the video acquired by the image collecting device 10 ROI image extraction module 22 that extracts only the important image part, the target object detection module that analyzes the important image part of the region of interest extracted by the ROI image extraction module 22, extracts only the target object, and identifies the type of the target object (26), by fusing the information on the identified target object extracted by the target object detection module 26 and the movement information about the target object through the target object detection device 11, The information fusion/expression information generation module 24 that automatically generates the expression information to be provided to the user, and the video and the information fusion/expression information generation module 24 provided from the ROI image extraction module 22. An information transmission module 25 for receiving information and transmitting the information to the information providing unit 3 may be included.

Furthermore, in the smart road information providing system according to the present invention, the control unit 2 corrects the image distortion for the image for the important image part including the target object extracted by the ROI image extraction module 22 A distortion correction module 23 that performs 31) may be included.

According to the present invention, it is possible to provide a video on a road condition in which a cigar is not secured and warning information (image, text) about a risk factor to a road user, and road driving such as vehicle entry into a conflicting area, occurrence of a traffic accident, etc. When a hazard is found, it generates a warning through sound or image to draw attention to road users such as drivers and pedestrians, effectively preventing traffic accidents.

1 is a schematic block diagram showing the configuration of a smart road information providing system according to the present invention.
2 is a schematic diagram showing the smart road information providing system according to the present invention in a shape that can be installed at an observation point.
3 is a schematic block diagram for explaining the configuration of a control unit provided in the smart road information providing system according to the present invention.
4 is a schematic diagram conceptually showing that the image of the region of interest is extracted and the distortion is corrected by the ROI image extraction module and the distortion correction module provided in the present invention.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings. Although the present invention has been described with reference to the embodiment shown in the drawings, which is described as one embodiment, the technical idea of the present invention and its core configuration and operation are not limited thereby. For convenience, in this specification, vehicles, pedestrians, personal transportation means (kickboards, etc.) using a road are collectively referred to as “purpose object”. In addition, both the moving speed and the moving direction of the target object are collectively described as "moving information". In the disclosure of this specification, including the claims, like reference numerals refer to like elements.

In the description of the embodiments of the present invention, if it is determined that a detailed description of a well-known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description will be omitted, and the terms to be described later are used in the embodiments of the present invention. As terms defined in consideration of the function of Therefore, the definition should be made based on the content throughout this specification. Each block in the accompanying block diagram and combinations of steps in the flowchart may be executed by computer program instructions (execution engine), which may be executed by a processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment. It may be mounted so that the instructions, which are executed by the processor of a computer or other programmable data processing equipment, create means for performing the functions described in each block of the block diagram or in each step of the flowchart. These computer program instructions may also be stored in a computer-usable or computer-readable memory that may direct a computer or other programmable data processing equipment to implement a function in a particular manner, and thus the computer-usable or computer-readable memory. It is also possible to produce an article of manufacture containing instruction means for performing the functions described in each block of the block diagram or each step of the flowchart, the instructions stored in the block diagram. It is also possible to provide steps for performing the functions described in each block of the block diagram and in each step of the flowchart, such that a series of operational steps are performed on a computer or other programmable data processing equipment. Also, each block or step may represent a module, segment, or portion of code comprising one or more executable instructions for executing specified logical functions, and in some alternative embodiments referred to in blocks or steps. It should be noted that it is also possible for the specified functions to occur out of sequence. For example, it is possible that two blocks or steps shown one after another may be performed substantially simultaneously, and also the blocks or steps may be performed in the reverse order of the corresponding functions, if necessary.

1 is a schematic block diagram showing the configuration of the smart road information providing system 100 according to the present invention, and in FIG. 2, the smart road information providing system 100 according to the present invention can be installed at the observation point. A schematic diagram showing the state shaped in the present form is shown.

The smart road information providing system 100 according to the present invention acquires a moving picture of a road condition including a support 4 installed at a fixed observation point on a road or a road edge, and a target object, and movement information of the target object. A collection unit (1) that collects the data, a control unit (2) that generates a moving picture and display information to be provided to road users, and an information providing unit installed on the support (4) and expressing the information received from the control unit (2) (3) is included.

The collection unit 1 includes an image collection device 10 that captures a road and acquires a moving picture of a road condition including a target object, recognizes the existence of the target object, and determines the moving direction and speed as movement information of the target object. It is configured to include a target object detection device 11 to acquire. The image collecting device 10 is composed of a camera capable of acquiring a moving picture, and it is preferable to minimize the blind spot and obtain a wide range of images for the road in each direction. It is preferable to be configured as a "panoramic camera" having a wide horizontal field of view (eg, a horizontal angle of view of 180 degrees). In the case of a panoramic camera, only one may be installed on the upper portion of the support 4 . However, the image collecting device 10 is not limited to a panoramic camera, and may be installed on the support 4 by being composed of a plurality of independent cameras so as to acquire individual moving pictures for each road in each direction.

The target object detection device 11 is a device for recognizing whether a target object exists on the road, and measuring and acquiring a moving direction and a moving speed as moving information about the target object. When a vehicle, a person, or other various types of target objects simply exist or are moving on the road within the detection range, the target object detection device 11 recognizes the existence of the target object itself and measures the moving speed of the moving object. to obtain it as movement information. The target object detecting device 11 may be a radar sensor or a LiDAR sensor, and a radar sensor or a lidar sensor operated in various methods such as a microwave method or a Doppler method may be used. The target object detection device 11 is installed toward each road so that the target object can be measured for each road in each direction. It may be installed on a separate support from the image collecting device 10 .

The control unit 2 tracks and analyzes the target object on the road based on the information acquired and transmitted by the collection unit 1 to form a real-time video and display information about the road condition to be provided to the road user, and It performs the function of storing video and information. 3 is a schematic block diagram for explaining the configuration of the control unit 2 is shown. As shown in FIG. 3, the control unit 2 includes an information receiving module 20, an information storage module 21, an ROI (Region of Interest) image extraction module 22, an information fusion/expression information generating module 24, information It is configured to include a transmission module 25 and a target object detection module 26 . If necessary, the distortion correction module 23 and the collision risk analysis module 27 may be further provided in the control unit 2 .

The information receiving module 20 receives the image information acquired and transmitted by the image collection device 10 of the collection unit 1 and movement information acquired and transmitted by the target object detection device 11, such as when an accident occurs. When it is necessary to preserve information, the received video and information are stored using the information storage module 21 .

Among the images acquired by the image collecting device 10, content that is not necessary for road users may be included. In particular, what the road user needs is an image of a target object that affects the passage of the road. Therefore, the control unit 2 is provided with an ROI image extraction module 22 that extracts only the image part necessary for the road user, that is, the important image part including the target object, from among the videos acquired and transmitted by the image collecting device 10 . In the ROI image extraction module 22, only the important image portion of the region of interest (ROI) (blind zone) including the target object is extracted from the video acquired by the image collection device 10 by using a known method.

On the other hand, distortion may exist in the image acquired by the image collecting device 10 . In particular, when the image acquired by the image collecting device 10 is a wide-angle image having a wide horizontal angle of view, significant distortion exists. For this purpose, if necessary, the distortion correction module 23 may be provided in the control unit 2, and when it is necessary to remove distortion for the acquired image, the distortion correction module 23 includes the ROI image extraction module 22 For the image of "important image part containing the target object" extracted by 4 is a schematic diagram conceptually showing that the image of the region of interest (ROI) is extracted and the distortion is corrected by the ROI image extraction module 22 and the distortion correction module 23 provided in the present invention.

The target object detection module 26 extracts and identifies only target objects such as vehicles, pedestrians, bicycles, and kickboards (including various personal transportation means) from the extracted important image portion. That is, the target object detection module 26 performs image analysis on the important image part to extract only the target object to determine the type of target object, such as whether the target object is a vehicle, a pedestrian, a bicycle, or other personal mobile equipment. will be identified In extracting and identifying only the target object from the important image portion through the target object detection module 26, the present invention can utilize the conventional object detection method. In particular, as the object detection method, a known technique for automatically identifying an object of interest in an image in an image by using deep learning can be used to identify a background and a part, and a detailed description thereof will be omitted.

In the information fusion/expression information generation module 24, information on the target object extracted and identified by the target object detection module 26, and movement information about the target object through the target object detection device 11, that is, By fusing the moving direction and moving speed of the target object, the expression information to be provided to the road user is automatically generated for each road in each direction. Specifically, in the information fusion/expression information generation module 24, the number of the target object extracted and identified previously through the target object detection module 26 is present in the region of interest (ROI). In addition, the information fusion/expression information generation module 24 identifies and grasps movement information on the target object existing in the region of interest among the information acquired through the target object detection device 11 . In the information fusion/expression information generation module 24, the target object in the region of interest identified in this way and its movement information are combined with each other to determine the movement status of the target object. And the information fusion/expression information generation module 24 generates the expression information set in advance according to the movement status of the target object identified in this way. In order to generate the expression information in the information fusion/expression information generation module 24, first, the information fusion/expression information generation module 24 first determines whether a vehicle enters the region of interest. If it is determined that a vehicle is approaching, it is determined whether the vehicle's speed is above the speed limit. If it is determined that the vehicle enters the region of interest over the speed limit, display information warning of overspeed is generated. When the speed of the vehicle is less than the speed limit, it is determined whether there are pedestrians in the area of interest, and display information corresponding thereto is generated. At this time, it is determined whether there are users who use other personal means of transportation such as bicycles and kickboards as well as pedestrians. For example, if the speed of the vehicle is less than the speed limit and there is a pedestrian in the area of interest, the information to be provided to the vehicle is information to warn the pedestrian, and the information to be provided to the pedestrian is information to the effect that the vehicle is entering. It is possible to create expression information.

In this way, in generating the expression information in the information fusion/expression information generation module 24, for example, the target object is extracted by the operation of the target object detection module 26, and the target object is identified as a pedestrian and a vehicle, respectively, and a vehicle. When it is determined that the pedestrian is approaching, the expression information of the content that can inform the situation of such a road is generated. That is, in the information fusion/expression information generation module 24, when it is determined that the target object approaches each other by grasping the movement of the moving target object, the expression information notifying the approach is generated.

As such, in the information fusion/expression information generation module 24, the operation of grasping the moving speed/moving direction information of the target object using the important image part, and the moving speed/moving direction of the target object derived from the important image part, and , by fusing the moving speed/moving direction of the target object acquired by the target object detection device 11 to generate the correct moving speed/moving direction of the target object, grasp the road situation and obtain appropriate expression information will create At this time, it is possible to set the display scenario for each situation that may occur on the road in advance, and to generate and transmit the appropriate expression information.

Meanwhile, in the present invention, if necessary, the control unit 2 may further include a collision risk analysis module 27. The collision risk analysis module 27 analyzes the movement information of the target object to analyze whether there is a collision risk. do.

The information transmission module 25 receives the video provided from the ROI image extraction module 22 and the expression information provided from the information fusion/expression information generation module 24 and provides it to the information providing unit 3 . When the distortion correction module 23 is provided, the moving image from the ROI image extraction module 22 is provided to the image transmission module 25 in a state in which the distortion is corrected through the distortion correction module 23 .

The information providing unit 3 includes an image display device 30 such as a monitor capable of displaying moving images and text information on the screen, and if necessary, a warning lamp that emits light and a voice such as a speaker that emits a sound. An expression device 31 may be further included. First, the moving images for each road in each direction transmitted from the image transmission module 25 are continuously displayed through the image display device 30 of the information providing unit 3 . Therefore, road users such as vehicle drivers and pedestrians can visually check the real-time image of the actual situation for each road in each direction in an optimized state or without distortion. The advantage of being able to grasp the condition of the road in real time with the naked eye is demonstrated.

In addition, the information providing unit 3 is provided with a voice expression device 31 to display information generated from the information fusion/expression information generation module 24 and transmitted through the image transmission module 25 to an image, text, light, etc. It is expressed in various forms and delivered to road users. For example, if a pedestrian and a vehicle are present, a voice notifying the pedestrian of the approach of the vehicle is emitted, and even if interference by direction occurs or the vehicle is driving at a speed (above a preset speed), a warning broadcast sound is issued. Through this, it can be displayed to pedestrians and vehicles.

As such, the smart road information providing system 100 according to the present invention is established as "user-centered" "corner safety" and provides road users with superior performance than the existing road reflectors "Securing field of view" and "Accident risk prevention" By providing services, it is possible to prevent traffic accidents in advance, thereby reducing social costs.

1: Collector
2: Control
3: Information provision department
4: support
10: image acquisition device
11: Target object detection device
20: information receiving module
21: information storage module
22: ROI image extraction module
23: distortion correction module
24: Information fusion/expression information generation module
25: information transmission module
26: target object detection module
27: Collision risk analysis module
100: smart road information providing system

Claims (6)

A support installed at a fixed observation point on the road or the edge of the road;
A collection unit that acquires and collects moving images of the road conditions including the target object and the movement information of the target object;
A control unit for generating video and expression information to be provided to road users;
It is installed on the support and is configured to include an information providing unit that displays information received from the control unit;
A smart road information providing system, characterized in that it provides real-time road conditions to road users in blind spots where visibility is not secured. According to claim 1,
The collecting unit includes an image collecting device that captures a road and acquires a video of the road condition including the target object;
Smart road information providing system, characterized in that it comprises a target object detection device for recognizing the existence of the target object and acquiring the moving direction and moving speed as the moving information of the target object. 3. The method of claim 2,
The image collecting device is a panoramic camera capable of acquiring a panoramic image,
The target object detection device is a smart road information providing system, characterized in that it consists of a laser sensor. 4. The method according to any one of claims 1 to 3,
In the control unit,
an information receiving module for receiving image information acquired and transmitted by the image collecting device of the collecting unit and movement information acquired and transmitted from the target object detection device;
an information storage module for storing the information received by the information receiving module, an ROI image extraction module for extracting only the important image portion of the region of interest including the target object from the video acquired by the image collecting device;
a target object detection module for extracting only the target object by analyzing the important image part of the region of interest extracted by the ROI image extraction module and identifying the type of the target object;
By fusing the information on the identified target object extracted and identified by the target object detection module and the movement information about the target object through the target object detection device, the displayed information to be provided to road users for each road in each direction is automatically provided. information fusion/expression information generation module to generate; and
Smart road information providing system, characterized in that it includes an information transmission module that receives the video provided from the ROI image extraction module and the expression information provided from the information fusion/expression information generation module and transmits it to the information providing unit. 5. The method of claim 4,
Smart road information providing system, characterized in that the control unit further comprises a distortion correction module for correcting the image distortion for the image part containing the target object extracted by the ROI image extraction module. 5. The method of claim 4,
The information providing unit, a smart road information providing system, characterized in that it comprises a video display device capable of displaying video and text information on the screen, and a voice expression device that emits a sound.

Images