KR20230032335A - Information analysis system using image and method thereof - Google Patents

Abstract

An information analysis system using an image according to one embodiment disclosed herein may include a data processing unit configured to obtain identification information of a vehicle entering a reference area, adjust an irradiation angle of light by controlling an illumination unit based on the identification information of the vehicle, and determine whether the vehicle violates a traffic law by analyzing an image taken with light from the illumination unit when the vehicle passes through the reference area.

Description

Information analysis system using image and method thereof {INFORMATION ANALYSIS SYSTEM USING IMAGE AND METHOD THEREOF}

Embodiments disclosed in this document relate to an information analysis system using an image and a method therefor.

For the analysis of traffic information, a technology for analyzing an image of a road captured by a camera is being used. For example, such image analysis technology may capture images of vehicles violating various traffic laws, such as traffic violation vehicles, speeding vehicles, and parking violation vehicles, and conduct enforcement based on the captured images.

On the other hand, since the degree of risk in an accident can be significantly different depending on whether a seat belt is fastened during a traffic accident or a sudden stop on the road, it is important to induce a driver or occupant to wear a seat belt. However, today, it is unreasonable to determine whether a seat belt is worn by simply taking a vehicle image with a camera due to the coating of a vehicle window or the like.

Accordingly, there is a need for a technology for more reliably and easily determining whether a driver and a passenger are wearing seat belts based on image analysis technology.

Embodiments disclosed in this document control whether or not the driver and occupants of the vehicle are wearing seat belts by controlling the light irradiation angle of the light for capturing a vehicle image in consideration of the angle or height of different windshields according to the type or specification of the vehicle. An object of the present invention is to provide an information analysis system capable of acquiring a vehicle image that can be more accurately and easily determined and a method related thereto.

In addition, the embodiments disclosed in this document may be caused by not wearing a seat belt, a system error, or environmental factors (e.g., the position of the sun, the type of windshield coating film of the vehicle) when the seat belt is not detected in the image. An object of the present invention is to provide an information analysis system using an image that can secure reliability when analyzing an image for determining whether a seat belt is worn by determining whether the image itself is a problem, and a method related thereto.

Technical problems of the embodiments disclosed in this document are not limited to the above-mentioned technical problems, and other technical problems not mentioned above will be clearly understood by those skilled in the art from the description below.

An information analysis system using an image according to an embodiment disclosed in this document acquires identification information of a vehicle entering a reference area, adjusts an irradiation angle of light by controlling a lighting unit based on the identification information of the vehicle, and adjusts an irradiation angle of light to the vehicle. A data processing unit configured to determine whether the vehicle violates traffic laws by analyzing an image captured together with the light of the lighting unit when the vehicle passes through the reference area.

According to an embodiment, the data processing unit may be configured to select one of a plurality of light sources included in the lighting unit and having different light irradiation angles based on the identification information of the vehicle.

According to an embodiment, the data processing unit obtains specification information of the vehicle that matches the vehicle identification information, and a plurality of light sources included in the lighting unit and having different light irradiation angles based on the vehicle identification information. One of them may be selected, and an angle of the selected light source may be adjusted to correspond to the specification information of the vehicle.

According to an embodiment, the identification information of the vehicle may include at least one of a vehicle model and a license plate number of the vehicle.

According to an embodiment, the vehicle specification information may include information about an angle of a windshield provided in the vehicle.

According to an embodiment, the vehicle specification information may include at least one of information about a height of a windshield provided in the vehicle and information about a size of the vehicle.

According to an embodiment, the data processing unit causes an error that occurs when determining whether the vehicle violates traffic laws based on the position of the sun while the vehicle passes the reference area and the shadow generated by the vehicle. can determine

According to one embodiment, the information analysis system using an image may further include a sensor unit that detects a change in position of the sun over time.

According to an embodiment, the data processing unit may determine the type of film provided in the vehicle using the image of the vehicle, and determine the cause of the error based on the type of film.

A method of operating an information analysis system using an image according to an embodiment disclosed in this document includes obtaining vehicle identification information of a vehicle entering a reference area, and controlling a lighting unit based on the vehicle identification information to control an irradiation angle of light. and determining whether the vehicle violates traffic laws by analyzing an image captured together with the light of the lighting unit when the vehicle passes the reference area.

An information analysis system and method using an image according to an embodiment disclosed in this document control the light irradiation angle of lighting for taking a vehicle image in consideration of the angle or height of different windshields according to the type or specification of the vehicle. By doing so, it is possible to more accurately and easily determine whether the driver and passengers of the vehicle are wearing seat belts.

In addition, in the information analysis system and method using an image according to an embodiment disclosed in this document, the cause of seat belt non-detection in the image is whether the seat belt is not fastened, a system error, or the vehicle image itself due to environmental factors. Reliability can be secured when analyzing an image for determining whether a seat belt is worn or not by determining whether it is a problem of the seat belt.

In addition, the information analysis system and method using an image according to an embodiment disclosed in this document can provide various traffic-related services by collecting traffic information of vehicles and pedestrians, traffic law violation information, and crime prevention information. .

1 is a diagram for explaining the operation of an information analysis system using an image according to an embodiment disclosed in this document.
2 is a block diagram showing the configuration of an information analysis system using an image according to an embodiment disclosed in this document.
3 is a flowchart illustrating an entire operation of an information analysis system using an image according to an embodiment disclosed in this document.
4 is a flowchart illustrating an error determination operation of an information analysis system using an image according to an embodiment disclosed in this document.
5 is a diagram illustrating front glass images for each sun position of an object acquired by an information analysis system using images according to an embodiment disclosed in this document.
6 is a diagram showing front glass images for each type of film of an object acquired in an information analysis system using an image according to an embodiment disclosed in this document.
7 is a flowchart illustrating an information analysis method using an image according to an embodiment disclosed in this document.

Hereinafter, various embodiments disclosed in this document will be described in detail with reference to the accompanying drawings. In this document, the same reference numerals are used for the same components in the drawings, and redundant descriptions of the same components are omitted.

For various embodiments disclosed in this document, specific structural or functional descriptions are merely illustrated for the purpose of describing the embodiments, and various embodiments disclosed in this document may be implemented in various forms, and It should not be construed as limited to the described embodiments.

Expressions such as "first", "second", "first", or "second" used in various embodiments may modify various elements regardless of order and/or importance, and the elements Not limited. For example, a first component may be called a second component without departing from the scope of rights of the embodiments disclosed in this document, and similarly, the second component may also be renamed to the first component.

Terms used in this document are only used to describe a specific embodiment, and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly dictates otherwise.

All terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by a person of ordinary skill in the art of the embodiments disclosed in this document. Terms defined in commonly used dictionaries may be interpreted as having the same or similar meanings as those in the context of the related art, and unless explicitly defined in this document, they are not interpreted in ideal or excessively formal meanings. . In some cases, even terms defined in this document cannot be interpreted to exclude the embodiments disclosed in this document.

1 is a diagram for explaining the operation of an information analysis system using an image according to an embodiment disclosed in this document.

Referring to FIG. 1 , an information analysis system 100 using an image according to an embodiment disclosed in this document includes a lighting unit 110, a data processing unit 140, an object detection unit 160, and a photographing unit 170. can do. The lighting unit 110, the data processing unit 140, the object detection unit 160, and the photographing unit 170 are installed in units of specific areas (eg, intersections, alleys, tunnels, or highways) to capture and analyze images. It may also be referred to as an 'information acquisition unit'.

The photographing unit 170 may include a camera capable of capturing images. The object detecting unit 160 may include, for example, a sensor (eg, radar (radio detection) capable of measuring the location or moving distance of an object by detecting an object such as a vehicle (eg, 0b1) or a person and tracking the movement of the object). and ranging (RADAR), light detection and ranging (LIDAR), and laser detection and ranging (LADAR). According to embodiments, the information analysis system 100 may use the photographing unit 170 and the object detection unit 160 cooperatively. For example, the information analysis system 100 may preferentially use the object detection unit 160 to more accurately detect the moving position, distance, direction, or speed of the object, and if it is necessary to identify the shape of the object In this case, the photographing unit 170 may be used. According to the embodiment, the photographing unit 170 and the object detection unit 160 may be implemented as one integrated module.

The data processing unit 140 may obtain passage information through at least one of the photographing unit 170 and the object detection unit 160 . 'Traffic information' may include, for example, a road image. In addition, the traffic information includes vehicle image, number of vehicles, vehicle driving speed, vehicle driving direction, vehicle driving lane, vehicle moving distance, vehicle traffic volume, vehicle waiting length, vehicle occupancy rate, pedestrian image, and pedestrian traffic information. It may further include at least one of number, gait speed, or gait direction. In addition, the traffic information may include identification information including at least one of a vehicle type, type, color, size, driving lane, license plate number, or pedestrian appearance.

In addition to traffic information, the data processing unit 140 may obtain at least one of behavior information and crime prevention information through the photographing unit 170 . 'Act information' includes speed violations, signal violations, reversal, driving lane violations, cutting in, lane violations, stop line violations, obsolete diesel vehicle operating restrictions violations, heavy traffic restrictions, not wearing seat belts, illegal parking and stopping, pedestrian signal violations, or unauthorized It may mean an act that violates traffic laws, such as crossing, or an act that requires guidance from the driver, such as poor loading or violation of a truck break. 'Security information' may include at least one of life crime prevention information and traffic crime prevention information. In addition, the data processing unit 140 may detect events such as vehicle stop, vehicle accident, pedestrian/wild animal appearance, falling object, roadkill, landslide, fog, or pothole using traffic information.

Although not shown in FIG. 1 , the data processing unit 140 may detect an event through data obtained from at least one sensor in addition to the photographing unit 170 and the object detection unit 160 . For example, the data processing unit 140 may include an acceleration sensor for detecting an impact on the road, a positioning sensor for detecting a landslide on a slope adjacent to the road, a temperature/humidity sensor for detecting weather changes such as temperature/humidity, and a load An event may be detected based on data received from at least one of a motion sensor for detecting a kill and an acoustic sensor.

The data processing unit 140 applies artificial intelligence (AI)-based image analysis/processing algorithms such as deep learning or machine learning to provide traffic information, behavior information, crime prevention information, or event information. At least one of them can be obtained. In one embodiment, the data processing unit 140 analyzes the image acquired by the photographing unit 170 or the object Ob1 moving in the designated direction F through the object detection unit 160 enters the reference area AR. /can detect whether it has passed or not. When the data processing unit 140 detects, through the object detection unit 160, that the object Ob1 enters the reference area AR (that is, when it passes through L1 in FIG. 1), the object Ob1 passes through the object capturing unit 170. The traffic information of (Ob1) can be obtained. For example, the data processing unit 140 may use the image of the object Ob1, identification information, or driving information (eg, driving speed, driving direction of the vehicle, driving lane of the vehicle, moving distance of the vehicle, traffic volume of the vehicle, vehicle At least one of waiting length and vehicle occupancy) may be obtained. In addition, the data processing unit 140 according to an embodiment disclosed in this document may obtain specification information of the object Ob1 that matches the identification information of the object Ob1. For example, the specification information of the object Ob1 may include size information of the object Ob1 (eg, length, height, width, etc. of the object Ob1) and angle information of the windshield of the object Ob1. can Additionally, the specification information of the object Ob1 may further include height information of the front glass of the object Ob1. At this time, the specification information of the object Ob1 may be stored in the database of the information analysis system 100 using an image or may be received from an external server (eg, the operating device 50).

The lighting unit 110 may radiate light to the object Ob1. The lighting unit 110 may be implemented as a part of the photographing unit 170 or may be implemented as a device separate from the photographing unit 170 . The photographing unit 170 may control the lighting unit 110 to emit light when capturing an image. Due to the light irradiated during image capturing, the photographing unit 170 can capture an image of an object (eg, a vehicle) even at night. Transmittance may increase. When the transmittance increases, the photographing unit 170 may capture an image of the inside of the vehicle. Although the lighting unit 110 is illustrated as having one light source in FIG. 1 , the lighting unit 110 may include a plurality of light sources installed at different positions and at different angles. The lighting unit 110 may include a lighting driving unit (or lighting control unit) capable of adjusting an irradiation angle of light of the lighting unit 110 based on a signal received from the data processing unit 140 .

When the object Ob1 passes through the reference area AR (or passes through L2), the data processing unit 140 transmits an image of the object Ob1 to which light is irradiated through the lighting unit 110, such as not wearing a seat belt. It is possible to detect an act of violating traffic laws of the object 0b1. At this time, the data processor 140 may adjust the light irradiation angle by controlling the lighting unit 110 based on the identification information of the object 0b1 (for example, a vehicle type such as a large (bus)/small car (passenger car)). , The light irradiation angle may be more finely adjusted by additionally controlling the lighting unit 110 based on the specification information of the object Ob1. For example, the data processing unit 140 may select a light source (lighting unit) suitable for the identification information of the object Ob1 and adjust the angle of the selected light source according to the specification information. At this time, the lighting control unit of the lighting unit 110 may adjust the angle of the lighting unit 110 to correspond to the height of the object Ob1 and the angle of the front glass based on the signal received from the data processing unit 140 . Through this, the data processing unit 140 controls the lighting unit 110 to change the front glass of the object Ob1 when the object Ob1 passes through the reference area AR (that is, when it passes through L2 in FIG. 1 ). Angles may be controlled so that light may be irradiated to the driver and passengers. The photographing unit 170 may capture an image of the object Ob1 when light is irradiated to the object Ob1 by the lighting unit 110 . Accordingly, the user (eg, the operator of the operating device 50) may determine whether the driver and passengers of the object Ob1 are wearing seat belts based on the captured image of the object Ob1. In addition, the information analysis system 100 using an image according to an embodiment disclosed in this document determines whether the object Ob1 is speeding or violates a signal based on the image of the object Ob1 captured by the photographing unit 170. The back can be cracked together.

In addition, the data processing unit 140 according to an embodiment disclosed in this document may detect the cause of an error that may occur when determining a traffic law violation through an image. In this case, the data processing unit 140 may determine an error according to the position of the sun after measuring the exact position of the sun based on the length and direction of the sensor unit (eg, solar tracker) and the shadow. In addition, the data processing unit 140 may determine the type of film provided in the object Ob1 through the image, and based on this, determine an error according to the type of film.

In one embodiment, the information analysis system 100 using an image may further include an operating device 50 . The operating device 50 (eg, a control center) may be operated by a public organization such as a local government, road construction, facilities corporation, or the National Police Agency. The operating device 50 stores and manages the information obtained through the data processing unit 140 in a database, and uses the stored information to allow a user (eg, a control agent) of the operating device 50 to control road conditions in real time. You can output an interface that can do this. In addition, the operating device 50 may compensate for insufficient hardware performance of the data processing unit 140 . For example, the data processing unit of the operating device 50 may include hardware (eg, a GPU) capable of implementing higher-performance image processing than the data processing unit 140 . The data processing unit of the operating device 50 may perform the same functions as those of the data processing unit 140 including analyzing road conditions (eg, traffic information, crime prevention information, or event information). In this case, the data processor 140 included in the passage information acquisition unit may be removed or deactivated. The operating device 50 may transmit a command to the data processor 140 to control a signal or lighting unit or to provide a different route to the vehicle based on the analyzed road conditions.

2 is a block diagram showing the configuration of an information analysis system using an image according to an embodiment disclosed in this document. Components described below may be implemented as a hardware device or implemented as software such as instructions or programs. Referring to FIG. 2 , an information analysis system 100 using an image according to an embodiment disclosed in this document includes a lighting unit 110, a data processing unit 140, an object detection unit 160, a photographing unit 170, and a sensor unit. (180). Hereinafter, components having the same names and reference numerals as those of FIG. 1 may have the same or similar functions as the components described in FIG. 1 .

The lighting unit 110 may radiate light to an object passing through the reference area. In this case, the lighting unit 110 may have a tilt structure and may include one light source or a plurality of light sources installed at different locations to emit light to the object at different angles.

The data processing unit 140 may obtain passage information of an object entering the reference area. In this case, the data processing unit 140 may obtain at least one of object identification information and object specification information matching the identification information. At this time, the data processing unit 140 obtains specification information stored in a database (not shown) prepared in the information analysis system 100 using an image, or obtains object identification information and data from an external server (eg, the operating device 50). Matching specification information may be received. For example, the specification information of the object may include information about the size of the object (eg, length, height, width, etc. of the object) and information about the angle of a front glass provided in the object.

The data processing unit 140 may obtain an image of an object passing through the reference area, and determine whether the object violates traffic laws based on the obtained image. In this case, the data processing unit 140 may determine whether the object violates a signal, speeding, or wearing a seat belt based on the image of the object. When the lighting unit 110 emits light, the data processing unit 140 may control the light irradiation angle of the lighting unit 110 so that the light irradiation angle is suitable for the vehicle model or specification information.

Meanwhile, when the lighting unit 110 includes a plurality of light sources. The data processing unit 140 may select one of a plurality of light sources based on object identification information. For example, each of the plurality of light sources may include a light source for a large vehicle and a light source for a small vehicle, and since a vertical light incident angle with respect to a windshield is different between a large vehicle and a small vehicle, the data processing unit 140 A light source corresponding to the vehicle type can be selected. Since the angle or height of the windshield may be different depending on the specifications of the vehicle even for the same type of vehicle, in the embodiment, the data processing unit 140 adjusts the angle of the light source selected based on the identification information of the object in a tilt manner using the specification information. can be adjusted accordingly.

The data processing unit 140 may determine the cause of an error occurring when determining whether a traffic law is violated based on the position of the sun while the object passes through the reference area and the shadow generated by the object. In this case, the data processing unit 140 calculates the exact position of the sun by considering the position of the sun measured by the sensor unit 180 and the length and direction of the object in the image or the shadow of the driver or passenger riding on the object. can do. For example, the data processing unit 140 may determine whether an error occurs in the obtained image of the object due to the influence of backlight or direct light. Also, the data processing unit 140 may determine the type of film provided on the object using the image of the object. At this time, the data processing unit 140 may determine the cause of the error based on the type of film. For example, the data processor 140 may determine whether the film provided on the object is a reflective film or an absorption film based on the image of the object. As such, the data processing unit 140 may determine the cause of the image analysis error by considering factors according to the position of the sun or factors according to the type of film provided on the object. Therefore, it is possible to secure the accuracy and reliability of the information analysis system 100 using an image.

The object detection unit 160 may detect an object entering the reference area. For example, the object detection unit 160 may be a radar or lidar. Also, the number of object detection units 160 may be one or a plurality.

The photographing unit 170 may capture an object entering or passing through the reference area. At this time, the photographing unit 170 may capture an image of the object at the time of entering and passing through the reference area. In addition, the photographing unit 170 may include a light source (eg, the lighting unit 110) for photographing. For example, the photographing unit 170 may be a camera. When a light source installed at a light irradiation angle corresponding to a vehicle model is selected by the data processing unit 140, the photographing unit 170 may control the lighting unit 110 to emit light through the selected light source. Also, the photographing unit 170 may control the lighting unit 110 to emit light through the light source selected and finely adjusted by the data processing unit 140 .

The sensor unit 180 may detect a change in position of the sun over time. For example, the sensor unit 180 may be a solar tracker that tracks the position of the sun. In this case, the sensor unit 180 can predict the position of the sun by storing the sensed value of cadmium sulfide (CdS) every hour.

As such, the information analysis system 100 using an image according to an embodiment disclosed in this document controls the angle of lighting according to the specifications of the vehicle, thereby more accurately and easily determining whether the driver and occupants of the vehicle are wearing seat belts. can judge

In addition, the information analysis system 100 using an image according to an embodiment disclosed in this document determines an image analysis error based on the position of the sun and the type of vehicle coating film, thereby increasing reliability when analyzing an image related to a violation of wearing a seat belt. can be obtained.

3 is a flowchart illustrating an entire operation of an information analysis system using an image according to an embodiment disclosed in this document.

Referring to FIG. 3 , the data processing unit 140 may first detect the entry of an object into the reference area through the object detection unit 160 (S101). For example, the object may be a vehicle. In addition, the data processing unit 140 may detect identification information of the object through the photographing unit 170 when the object enters (S102).

Then, the data processing unit 140 may match the identification information of the detected object with previously stored object specification information (S103). For example, the data processing unit 140 may obtain vehicle specification information (eg, the length, height, width, and angle of the windshield of the vehicle) corresponding to the model or vehicle number of the object detected through the image. there is.

Next, the data processor 140 may adjust the angle of the lighting unit 110 to correspond to vehicle identification information or specification information (S104). For example, when the lighting unit 110 is composed of a plurality of light sources, the data processing unit 140 selects one light source from among the plurality of light sources based on identification information (eg, vehicle model), and then selects the selected light source based on specification information. You can control the angle of the light source. In another implementation, the data processing unit 140 may adjust the angle of the lighting unit 110 after the object passes through the reference area.

The data processing unit 140 may detect that an object passes through the reference area through the object detection unit 160 (S105). At this time, the data processing unit 140 may detect identification information of the object again based on the image of the object captured at the point of time when the object passes. When a light source installed at a light irradiation angle corresponding to a vehicle model is selected by the data processing unit 140, the photographing unit 170 may control the lighting unit 110 to emit light through the selected light source. Also, the photographing unit 170 may control the lighting unit 110 to emit light through the light source selected and finely adjusted by the data processing unit 140 .

The data processing unit 140 may analyze the image of the object (S106). In this case, the data processing unit 140 may determine whether the object violates traffic laws by analyzing whether the object is speeding, violating a signal, or wearing a seat belt through an image (S107).

On the other hand, if it is not determined whether traffic laws have been violated, the data processing unit 140 may perform error determination (S108). For example, when a seat belt is not detected through an image, the data processing unit 140 needs to confirm whether the driver is not actually wearing a seat belt or whether the seat belt is not detected due to a specific factor. In this case, the data processing unit 140 may determine whether an occupant is detected if the seat belt is not detected, and determine that an environmental factor exists if the occupant is not detected. Environmental factors may include, for example, a factor according to the position of the sun or a factor according to the type of film of an object.

The data processing unit 140 may generate data according to the result of determining whether traffic laws are violated (S109). For example, when seatbelt non-wearing is detected through image analysis including a windshield ('Yes' in operation S107), the data processing unit 140 identifies the violation information (seatbelt not wearing) and the vehicle corresponding to the violation information. Enforcement data including information (eg, at least one of a vehicle model and a license plate number) may be generated. For another example, if whether or not the seat belt is worn is not detected ('No' in operation S107), the data processing unit 140 may generate data related to the determined error through operation S108.

The data processing unit 140 may transmit the generated data to the operating device 50 . A user (or an operator) of the operating device 50 may determine whether or not a vehicle has been regulated based on the data received from the data processing unit 140 or may check details of errors appearing in the video analysis process.

4 is a flowchart illustrating an error determination operation of an information analysis system using an image according to an embodiment disclosed in this document.

Referring to FIG. 4 , the data processing unit 140 according to an embodiment disclosed in this document may track the position of the sun using the sensor unit 180 upon determining an error (S201). In this case, the sensor unit 180 may store the measurement value of the position of the sun for each time zone.

Also, the data processing unit 140 may detect the position of the sun based on the length and direction of the shadow appearing in the image (S202). In this case, the data processing unit 140 may predict the position of the sun through the length and direction of an object (eg, a vehicle) in the image or a shadow of a driver or occupant of the object. As such, the data processing unit 140 may accurately detect a factor (eg, backlight, direct light) caused by the position of the sun based on the sun position measurement value by the sensor unit 180 and the shadow analysis through the image.

Then, the data processing unit 140 may determine the type of film provided on the object based on the front glass image of the object (S203). For example, the data processing unit 140 may determine that the front glass in the image of the object is a reflective film if all light is reflected, and if all light is absorbed, it is an absorbing film.

Next, the data processing unit 140 may determine an error generated during image analysis by considering the factor due to the position of the sun and the factor due to the film type of the object (S204). Accordingly, the information analysis system 100 using an image according to an embodiment disclosed in this document may determine an environmental factor related to seat belt detection and perform error determination to secure accuracy and reliability of the system.

5 is a diagram showing front glass images for each sun position of an object acquired by an information analysis system using images according to an embodiment disclosed in this document. Also, FIG. 6 is a diagram showing front glass images for each type of film of an object acquired in an information analysis system using images according to an embodiment disclosed in this document.

5 (a) and (b) show backlight (for example, sunlight coming from the opposite side of the photographing unit 170) and direct light (eg, sunlight coming from the rear of the photographing unit 170), respectively. In case of input from ), it shows the video. In addition, (a) and (b) of FIG. 6 show images of a reflective film and an absorption film, respectively.

Referring to (a) and (b) of FIG. 5 , the sensor unit 180 (eg, a solar tracker) may store a sensing value of CdS every hour. In this way, the data processing unit 140 predicts the position of the sun based on the sensed value stored by the sensor unit 180 at the time when the corresponding object passes the reference area, and the object and the driver or occupant in the image of the object at that time. The exact position of the sun can be obtained by additionally detecting the length and direction of the shadow. Through this, it is possible to determine an error according to the position of the sun and determine the reason why image analysis is impossible (eg, backlight or direct light).

That is, the data processing unit 140 may determine an error due to backlight or direct light in the case of an image in which the outline or the inside is transmitted but the inside is not accurately seen, as in the images in (a) and (b) of FIG. 5 . In addition, the data processing unit 140 may perform learning for error determination by post-processing the determined image after determining an error according to the position of the sun. The data processing unit 140 may perform error determination according to the position of the sun based on the learned image.

Referring to (a) and (b) of FIG. 6 , the data processing unit 140 may determine the type of film provided on the object (eg, vehicle) from the obtained image. For example, in the case of a film for a vehicle, there are usually two types of a reflective film and an absorptive film, and these films each have different effects. That is, as shown in (a) of FIG. 6, in the case of the reflective film, all light is reflected so that the background affects the image of the windshield of the vehicle, and as shown in (b) of FIG. 6, the absorption type film In the case of , it can absorb light and affect the image of the front glass of the vehicle as black.

As such, the information analysis system 100 using an image according to an embodiment disclosed in this document determines the position of the sun based on the sensor unit 180 and the shadow analysis of the image, detects the type of film provided in the vehicle, It is possible to accurately analyze the cause of errors and secure reliability when analyzing images on whether drivers and passengers are wearing seat belts.

7 is a flowchart illustrating an information analysis method using an image according to an embodiment disclosed in this document.

Referring to FIG. 7 , the information analysis system 100 may acquire identification information of a vehicle entering a reference area (S310). In addition, the information analysis system 100 may further obtain specification information matching the identification information.

In addition, the information analysis system 100 may adjust the irradiation angle of light by controlling the lighting unit 110 based on the identification information of the vehicle (S320). In addition, the information analysis system 100 may adjust the irradiation angle of light by controlling the lighting unit 110 to correspond to the specification information of the object. Through this, the lighting unit 110 can accurately radiate light to the windshield of the vehicle passing through the reference area.

Meanwhile, in step S320, when the lighting unit 110 includes a plurality of light sources. The information analysis system (eg, the data processing unit 140) may select one of a plurality of light sources based on vehicle identification information and adjust an angle of the selected light source to correspond to vehicle specification information. For example, the plurality of light sources may be installed so that light incident angles to the windshields of large vehicles and small vehicles are perpendicular to each other. That is, in step S320, the information analysis system 100 may select a light source according to the obtained identification information and then finely adjust the angle of the selected light source to correspond to the specification information.

Next, the information analysis system 100 may determine whether the vehicle violates traffic laws by analyzing an image captured together with the light of the lighting unit 110 when the vehicle passes the reference area.

Meanwhile, although not shown in FIG. 7 , the information analysis system 100 according to an embodiment disclosed in this document may determine the cause of an error occurring in the process of determining a traffic law violation. In this case, the information analysis system 100 determines the cause of the error based on the type of film provided in the vehicle using the image of the vehicle and the shadow generated by the vehicle and the location of the sun while the vehicle passes through the reference area. can do. Since this has been described in FIGS. 5 and 6, a detailed description thereof will be omitted.

As such, the information analysis method using an image according to an embodiment disclosed in this document can more accurately and easily determine whether the driver and passengers of the vehicle are wearing seat belts by controlling the angle of lighting according to the vehicle type. there is.

In addition, the information analysis method using an image according to an embodiment disclosed in this document determines an error based on the position of the sun and the type of coating film of a vehicle, thereby securing reliability when analyzing an image related to a violation of wearing a seat belt. .

In the above, even if all components constituting the embodiments disclosed in this document have been described as being combined or operated as one, the embodiments disclosed in this document are not necessarily limited to these embodiments. That is, within the scope of the objectives of the embodiments disclosed in this document, all of the components may be selectively combined with one or more to operate.

In addition, terms such as "comprise", "comprise" or "having" described above mean that the corresponding component may be present unless otherwise stated, and thus exclude other components. It should be construed as being able to further include other components. All terms, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document belong, unless defined otherwise. Commonly used terms, such as terms defined in a dictionary, should be interpreted as consistent with the contextual meaning of the related art, and unless explicitly defined in this document, they are not interpreted in an ideal or excessively formal meaning.

The above description is only an illustrative example of the technical idea disclosed in this document, and those skilled in the art to which the embodiments disclosed in this document belong will be within the scope of the essential characteristics of the embodiments disclosed in this document. Many modifications and variations will be possible. Therefore, the embodiments disclosed in this document are not intended to limit the technical spirit of the embodiments disclosed in this document, but to explain, and the scope of the technical spirit disclosed in this document is not limited by these embodiments. The scope of protection of technical ideas disclosed in this document should be interpreted according to the scope of claims below, and all technical ideas within an equivalent scope should be construed as being included in the scope of rights of this document.

Claims (15)

Acquiring identification information of a vehicle entering a reference area;
Adjusting an irradiation angle of light by controlling a lighting unit based on the identification information of the vehicle,
A data processing unit configured to determine whether the vehicle violates traffic laws by analyzing an image captured together with the light of the lighting unit when the vehicle passes the reference area. The method according to claim 1, wherein the data processing unit,
Information analysis system using an image, set to select one of a plurality of light sources having different light irradiation angles included in the lighting unit based on the identification information of the vehicle. The method according to claim 1, wherein the data processing unit,
Obtaining specification information of the vehicle that matches identification information of the vehicle;
Selecting one of a plurality of light sources included in the lighting unit and having different light irradiation angles based on the identification information of the vehicle;
An information analysis system using an image for adjusting an angle of the selected light source to correspond to the specification information of the vehicle. According to claim 2 or 3,
The identification information of the vehicle is an information analysis system using an image including at least one of a vehicle model and a vehicle number of the vehicle. The method of claim 4,
The information analysis system using an image, wherein the vehicle specification information includes information about an angle of a windshield provided in the vehicle. The method of claim 4,
The information analysis system using an image, wherein the vehicle specification information includes at least one of information about a height of a windshield provided in the vehicle and information about a size of the vehicle. The method according to claim 1, wherein the data processing unit,
An information analysis system using an image for determining a cause of an error occurring when determining whether the vehicle violates traffic laws based on the position of the sun while the vehicle passes the reference area and the shadow generated by the vehicle. The method of claim 7,
An information analysis system using an image further comprising a sensor unit for detecting a change in position of the sun over time. The method according to claim 1, wherein the data processing unit,
An information analysis system using an image for determining the type of film provided in the vehicle using the image of the vehicle and determining the cause of the error based on the type of the film. The method of claim 1,
An information analysis system using an image further comprising an object detection unit for detecting a vehicle entering the reference area. The method of claim 1,
Information analysis system using an image further comprising a; photographing unit for capturing the image. The method according to claim 11, wherein the photographing unit,
An information analysis system using an image that controls the lighting unit so that the lighting unit, the angle of which is adjusted by the data processing unit, emits light. The method according to claim 11, wherein the data processing unit,
An information analysis system using an image set to obtain at least one of traffic information, behavior information, or crime prevention information through the photographing unit. The method of claim 13,
An operating device configured to control road conditions through information obtained through the photographing unit and the data processing unit; information analysis system using an image further comprising. In the method of operating an information analysis system using an image,
obtaining vehicle identification information of a vehicle entering a reference area;
adjusting an irradiation angle of light by controlling a lighting unit based on the identification information of the vehicle; and
A method of operating an information analysis system comprising: determining whether the vehicle violates traffic laws by analyzing an image captured together with the light of the lighting unit when the vehicle passes the reference area.

Images