KR101979422B1 - Camera system and camera system included calibration adjusting method - Google Patents

Abstract

According to the present invention, there is provided an information processing apparatus including an image information sensing unit for sensing distance information on a lane, curvature information of a lane and an intersection of a lane on the basis of the generated front image information, a vehicle information sensing unit for sensing heading angle information of the vehicle, If the change amount of the curvature running information of the vehicle is equal to or less than the predetermined threshold curvature running information and the variation amount of the distance information with respect to the lane is equal to or less than the predetermined threshold distance information, the lane curvature information, A calculation unit for calculating an estimated intersection point of the lane in the forward image information using the distance information between the lane and the lane, and a notification that the preset existing calibration information is an error if the difference between the intersection of the lane and the estimated intersection of the lane exceeds the preset allowable value And a camera system including the camera.

Description

[0001] CAMERA SYSTEM AND CAMERA SYSTEM INCLUDED CALIBRATION ADJUSTING METHOD [0002]

The present invention relates to a camera system included in a vehicle.

Recently, as interest in autonomous vehicles increases, researches on sensors mounted on autonomous vehicles are actively under way.

There are cameras, infrared sensors, radar, GPS, lidar, and gyroscope that are mounted on the autonomous vehicle. Among them, the camera occupies an important position as a sensor to replace the human eye.

Generally, the object information detected by the camera is characterized in that the information on the lateral direction (meaning vertical direction to the monitoring direction) is correct and the information on the longitudinal direction (meaning the direction of the monitoring) is not accurate.

For this reason, in general, an autonomous vehicle uses lateral information of a sensing object based on information sensed by a camera, and uses longitudinal information of the sensing object or the position of the sensing object using information sensed by a sensor other than the camera .

On the other hand, when a plurality of sensors are used in the autonomous vehicle, the price may increase depending on a number of sensors.

In order to overcome such a problem, recently, a camera system including a camera sets calibration information in advance based on a geometric operation of a camera, etc., and calculates longitudinal information (e.g., lane information, Vehicle information and pedestrian information) can be accurately detected.

The calibration information is information set according to the position of the camera installed in the vehicle, the monitoring angle of the camera, and the like when the vehicle is shipped.

Therefore, if the wind of the vehicle tire is lost or the setting of the suspension is changed, a camera system using calibration information tailored to the vehicle before the change may cause a problem that the longitudinal direction information of the sensing object is incorrectly detected.

In view of the foregoing, it is an object of the present invention to provide, in one aspect, a technique relating to a camera system that notifies the camera system of an error in preset calibration information.

According to an aspect of the present invention, there is provided an information processing apparatus including an image information sensing unit for sensing distance information on a lane, curvature information of a lane, and an intersection of a lane on the basis of the generated front image information and a vehicle information sensing unit for sensing heading angle information of the vehicle, When the amount of change in the curvature running information of the vehicle is less than or equal to the preset threshold curvature running information and the amount of change in the distance information between the lane and the lane is equal to or less than the predetermined threshold distance information, When the difference between the calculating section for calculating the estimated intersection point of the lane in the forward image information and the estimated intersection point of the lane and the estimated intersection point of the lane exceeds the preset allowable value using the heading angle information and the distance information between the lane information and the lane, And a notification unit for notifying the user of the error.

According to another aspect of the present invention, there is provided a method for controlling a vehicle, comprising the steps of sensing distance information on a lane, curvature information of a lane, and an intersection of a lane on the basis of the generated front image information, And an estimating step of estimating curvature running information of the vehicle, and when the amount of change in the curvature running information of the vehicle is equal to or less than preset critical curvature running information and the amount of change in the distance information with respect to the lane is less than preset threshold distance information, Calculating the estimated intersection point of the lane in the forward image information by using the heading angle information and the distance information between the lane information and the lane information of the lane and the estimated intersection point of the lane when the difference between the intersection point of the lane and the estimated intersection point of the lane exceeds a preset allowable value, The difference between the intersection point of the lane and the estimated intersection point of the lane exceeds the allowable value, Generating new calibration information based on a new first angle and a new second angle such that a difference between an intersection point and an estimated intersection point of a lane is within the allowable value and correcting the existing calibration information into the new calibration information Provides a method for calibrating calibration information of a camera system.

As described above, according to the present invention, it is possible to provide a technique related to a camera system that notifies the camera system of whether or not error of preset calibration information is detected.

1 is a diagram showing a configuration of a camera system according to a first embodiment.
2 is a diagram illustrating an example of operation of the camera system according to the first embodiment.
3 is a diagram showing a configuration of a camera system according to the second embodiment.
FIG. 4 is a diagram illustrating an example of operation of the camera system according to the second embodiment.
5 is a diagram showing a configuration of a camera system according to the third embodiment.
6 is a diagram illustrating an example of operation of the camera system according to the third embodiment.
7 is a flowchart showing a calibration information adjustment method of the camera system according to the first embodiment.

Hereinafter, some embodiments will be described in detail with reference to exemplary drawings. In the drawings, like reference numerals are used to denote like elements throughout the drawings, even if they are shown on different drawings. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention unclear.

In describing the constituent elements of the present embodiment, terms such as first, second, A, B, (a), and (b) may be used. These terms are intended to distinguish the components from other components, and the terms do not limit the nature, order, order, or number of the components. When a component is described as being "connected", "coupled", or "connected" to another component, the component may be directly connected or connected to the other component, Quot; intervening " or that each component may be " connected, " " coupled, " or " connected " through other components.

FIG. 1 is a diagram illustrating a configuration of a camera system according to a first embodiment. FIG. 2 is a diagram illustrating an example of operation of the camera system according to the first embodiment.

Referring to FIGS. 1 and 2, the camera system 100 according to the first embodiment of the present invention detects the intersection of lane information, lane curvature information, and lane on the basis of the generated front image information (S200) The information sensing unit 110 senses the heading angle information of the vehicle (S210), the vehicle information sensing unit 120 senses the curvature driving information of the vehicle (S220), estimates the curvature driving information of the vehicle (S220) (YES in S230) and the variation amount of the distance information with the lane is less than the predetermined threshold distance information (YES in S240), the curvature information of the lane, the heading angle information of the vehicle, and the distance The estimated intersection point of the lane in the forward image information is calculated (S250). If the difference between the intersection of the lane and the estimated intersection of the lane exceeds the preset allowable value (YES in S260) Calibration information is error (Step S270).

The image information sensing unit 110 of the camera system 100 according to the first exemplary embodiment can recognize a predetermined lane from the forward image information generated from the image sensing device (for example, a camera sensor or the like) (For example, color information of a lane, width information of a lane, length information of a lane, and the like), and based on the sensed lane, distance information to the lane, curvature information of the lane, The intersection can be detected.

The intersection of the above lanes may mean that a parallel lane intersects by perspective.

The vehicle information sensing unit 120 of the camera system 100 according to the first embodiment can sense the heading angle information of the vehicle based on the sensing value of the sensor capable of sensing the turning motion of the vehicle.

The estimating unit 130 of the camera system 100 according to the first embodiment can sense the curvature driving information of the vehicle based on the sensing value of the sensor capable of sensing the turning motion of the vehicle.

For example, the sensor capable of detecting the turning motion of the vehicle may include a steering angle sensor, a lateral acceleration sensor, and the like. The sensor may detect the heading angle information of the vehicle and the curvature driving information of the vehicle based on the turning motion of the vehicle. All methods of calculation can be applied.

The calculation unit 140 of the camera system 100 according to the first embodiment determines whether the variation of the curvature travel information of the estimated vehicle is equal to or less than the predetermined threshold curvature travel information and the amount of change in the distance information with respect to the sensed lane, If the information is less than or equal to the information, the estimated intersection point of the lane can be calculated from the front image information generated from the image sensing apparatus that monitors the front of the vehicle using the curvature information of the sensed lane, the heading angle information of the vehicle, .

In more detail, the calculating unit 140 calculates the lane estimation (estimated) from the front image information generated from the image sensing apparatus that monitors the front of the vehicle using the curvature information of the sensed lane, the heading angle information of the vehicle, It may take a calculation time to calculate the intersection point.

Accordingly, in order for the calculating unit 140 to accurately calculate the estimated intersection of the lane, the curvature information of the lane, the heading angle information of the lane, and the distance information between the lane and the lane must be maintained during the calculation time.

That is, in order to calculate the estimated intersection point of the correct lane, the calculation unit 140 calculates the estimated intersection point of the lane of the lane by comparing the estimated amount of curvature travel information of the vehicle with the predetermined threshold curvature travel information, The estimated intersection point of the lane can be calculated.

This estimated intersection point means a point in which parallel lanes intersect by perspective, and may be estimated by reflecting the calibration information or the like to be described in detail below.

The notification unit 150 of the camera system 100 according to the first embodiment can notify that the previously set calibration information is an error when the difference between the intersection of the sensed lane and the estimated intersection of the calculated lane exceeds a preset allowable value have.

The calibration information may be information used for calculating detailed information on an object included in the generated image information, and may be information related to the operation of the image sensing sensor from a geometrical point of view. The detailed information is information on a vertical direction (meaning a direction monitored by a camera outputting image information), and may include recognition of an object, distance to an object, length of an object, and the like.

The calibration information may be represented by a matrix as shown in the following Equation (1).

[Equation 1]

은 카메라 시스템에 설정되는 고유한(Intrinsic) 성분으로서, 다음 수학식 2와 같은 관계식으로 표현될 수 있으며,

은 카메라 시스템에 설정되는 외적인(Extrinsic) 성분으로서, 다음 수학식 3과 같은 회전변환에 따른 관계식을 포함할 수 있다.here,

Is an intrinsic component set in the camera system and can be expressed by the following equation (2)

Is an extrinsic component set in the camera system and may include a relational expression according to the rotation transformation as shown in Equation (3).

&Quot; (2) "

는 x축(또는, u축으로 명명하기도 함)에 대한 픽셀 수를 의미하고,

는 y축(또는, v축으로 명명하기도 함)에 대한 픽셀 수를 의미하고,

는 x축에 대한 픽셀의 중앙 위치를 의미하고,

는 y축에 대한 픽셀의 중앙 위치를 의미하고,

는 왜곡성분(skew factor)을 의미하며, f 는 광축(Optical axis)에 대한 초점거리를 의미한다.here,

Quot; means the number of pixels for the x-axis (or the u-axis)

Means the number of pixels for the y-axis (or the v-axis)

Denotes the center position of the pixel with respect to the x-axis,

Denotes the center position of the pixel with respect to the y-axis,

Denotes a skew factor, and f denotes a focal length of the optical axis.

&Quot; (3) "

는 요우레이트(Yaw rate)에 대한 각도로서, 본 명세서의 제1각을 의미하고,

는 피치(Pitch)에 대한 각도로서, 본 명세서의 제2각을 의미하며,

는 요우레이트 및 피치 각각과 직교하는 성분에 대한 각도로서, 차량의 움직임에 있어 무시할 수 있다.here,

Is the angle with respect to the yaw rate, which means the first angle herein,

Is an angle with respect to the pitch, which means the second angle of the present specification,

Is an angle with respect to a component orthogonal to each of the yaw rate and pitch, and can be neglected in the movement of the vehicle.

The above-described equations (1) to (3) are relational expressions based on the geometric viewpoint, the viewpoint between the image frame and the pixel frame and the viewpoint according to the calibration information, and the detailed description will be omitted.

If the existing calibration information preset in the camera system 100 is normal, the difference between the intersection of the lane detected by the sensing unit 110 and the estimated intersection of the lane calculated by the calculation unit 140 based on the existing calibration information is The detailed information of the forward object calculated using the existing calibration information that is normal can be accurate information.

On the other hand, if the existing calibration information is abnormal, the difference between the intersection of the lane detected by the sensing unit 110 and the estimated intersection of the lane calculated by the calculating unit 140 based on the existing calibration information may exceed the predetermined tolerance , The detailed information of the forward object calculated using the abnormal calibration information may be inaccurate information.

The camera system according to the first embodiment described above with reference to FIGS. 1 and 2 has an effect of determining that the set calibration information is error, and notifying the driver of the error. This can prevent the camera system from incorrectly recognizing the object in response to an error in the calibration information.

Meanwhile, the camera system according to the second embodiment not only determines that the previously set calibration information is an error like the camera system according to the first embodiment, but also corrects the existing calibration information determined as an error to the normal new calibration information And the like.

This will be described in detail with reference to FIGS. 3 and 4. FIG.

FIG. 3 is a diagram illustrating a configuration of a camera system according to a second embodiment. FIG. 4 is a diagram illustrating an exemplary operation of the camera system according to the second embodiment.

3 and 4, the camera system 101 according to the second embodiment detects the intersection of lane information, lane curvature information, and lane based on the generated front image information (S200) The information sensing unit 110 senses the heading angle information of the vehicle (S210), the vehicle information sensing unit 120 senses the curvature driving information of the vehicle (S220), estimates the curvature driving information of the vehicle (S220) (YES in S230) and the variation amount of the distance information with the lane is less than the predetermined threshold distance information (YES in S240), the curvature information of the lane, the heading angle information of the vehicle, and the distance If the difference between the intersection of the lane and the estimated intersection of the lane exceeds the predetermined allowable value (YES in S260), the estimated intersection point of the lane is calculated (S250) Calibration information is error (S260), and when the difference between the intersection of the lane and the estimated intersection of the lane exceeds the allowable value (YES in S260), the difference between the intersection of the lane and the estimated intersection of the lane (S400), and correcting the existing calibration information to the new calibration information (S410) based on the new second angle and the new second angle.

For example, the corrector 160 generates a new first angle and a new second angle that make the difference between the intersection of the lane and the estimated intersection of the lane within the tolerance, New calibration information can be generated based on Equations (1) to (3).

Alternatively, the corrector 160 may extract the existing first angle and the existing second angle by decomposing the existing calibration information, and generate a new first angle and a new first angle by correcting each of the extracted first angle and the existing second angle, New calibration information can be generated based on the second angle.

The sizes of the respective correction angles corrected for the new first angle and the new second angle in the existing first angle and the existing second angle are determined based on the intersection of the lane detected by the image information sensing unit 110 and the distance 140). ≪ / RTI >

The directions of the respective correction angles corrected by the new first angle and the new second angle in the existing first angle and the existing second angle are determined by the intersection of the lane detected by the image information sensing unit 110 and the angle And the direction of the difference of the estimated intersection points calculated in the step of FIG.

In this way, the calibration unit 160 can generate the new calibration information more quickly and accurately based on the extracted first angle and the existing second angle extracted from the existing calibration information.

The camera system according to the second embodiment described above with reference to FIG. 3 and FIG. 4 can correct the new calibration information to be normal if the existing calibration information is determined to be an error.

Meanwhile, the camera system according to the third embodiment not only determines that the previously set calibration information is an error like the camera system according to the first embodiment, but also uses the existing calibration information determined to be normal, And a distance sensing unit for sensing a distance to an object.

This will be described in detail with reference to FIG. 5 and FIG.

FIG. 5 is a diagram illustrating a configuration of a camera system according to a third embodiment. FIG. 6 is a diagram illustrating an exemplary operation of the camera system according to the third embodiment.

5 and 6, the camera system 102 according to the third embodiment detects the intersection of lane information, lane curvature information, and lane information based on the generated front image information (S200) The information sensing unit 110 senses the heading angle information of the vehicle (S210), the vehicle information sensing unit 120 senses the curvature driving information of the vehicle (S220), estimates the curvature driving information of the vehicle (S220) (YES in S230) and the variation amount of the distance information with the lane is less than the predetermined threshold distance information (YES in S240), the curvature information of the lane, the heading angle information of the vehicle, and the distance If the difference between the intersection of the lane and the estimated intersection of the lane exceeds the predetermined allowable value (YES in S260), the estimated intersection point of the lane is calculated (S250) Calibration information is error (S260). If the difference between the notification unit 150 and the estimated intersection of the lane and the estimated intersection of the lane does not exceed the allowable value (NO in S260), the distance to the object included in the forward image information is calculated using the existing calibration information And a distance sensing unit 170 for sensing the distance (S600).

The camera system according to the third embodiment described above with reference to FIG. 5 and FIG. 6 can detect the distance to the object included in the forward image information when the existing calibration information set is determined to be normal. Thus, the camera system according to the third embodiment can prevent the distance to the object included in the forward image information from being detected incorrectly.

Meanwhile, the estimating unit included in the camera system according to the first embodiment to the camera system according to the third embodiment can estimate the curvature running information of the vehicle based on the yaw rate information and the vehicle speed information of the vehicle.

More specifically, the estimating unit reflects the yaw rate information of the vehicle and the velocity information of the vehicle on the preset traveling model of the vehicle (or the yaw rate information of the vehicle and the data map based on the velocity information of the vehicle) Can be estimated. The running model of the vehicle can be set in advance based on the length of the vehicle, the width of the vehicle, and the like.

To this end, the vehicle information sensing unit may further detect the yaw rate information of the vehicle and the speed information of the vehicle.

The estimating unit included in the camera system according to the first embodiment or the camera system according to the third embodiment can estimate the curvature running information of the vehicle based on each piece of information on the tire.

More specifically, the estimating unit can estimate the curvature running information of the vehicle by reflecting each information of the tire on a running model of the vehicle (or a data map based on each information of the tire) set in advance. The running model of the vehicle can be set in advance based on the length of the vehicle, the width of the vehicle, and the like.

To this end, the vehicle information sensing unit can further detect each piece of information of the tire. For example, the vehicle information sensing unit can sense each information of the tire based on the wheel information on both sides of the tire of the vehicle.

Hereinafter, a method of adjusting calibration information of a camera system, which is an operation performed by the camera system described with reference to FIGS. 3 and 4, will be briefly described.

7 is a flowchart showing a calibration information adjustment method of the camera system according to the first embodiment.

Referring to FIG. 7, the calibration information adjustment method of the camera system according to the first exemplary embodiment includes an image information sensing step of sensing distance information on a lane, curvature information of a lane, and an intersection of a lane on the basis of the generated front image information A step S710 of sensing the heading angle information of the vehicle, an estimation step S720 of estimating curvature driving information of the vehicle, a step S710 of sensing the curvature driving information of the vehicle, (S730) for calculating an estimated intersection point of the lane in the forward image information using the curvature information of the lane, the heading angle information of the vehicle, and the distance information between the lane and the lane if the amount of change in the distance information is less than the predetermined threshold distance information, And a notification step (S740) of notifying that the previously set calibration information is an error if the difference between the intersection of the lane and the estimated intersection of the lane exceeds the preset allowable value ) And a new second angle and a new second angle based on the difference between the estimated intersection of the lane and the estimated intersection of the lane exceeds the allowable value (YES in S260) And a correction step (S750) of generating calibration information and correcting the existing calibration information into new calibration information.

The image information sensing step S700 of the calibration information adjustment method of the camera system according to the first embodiment may include a step S700 of sensing the front image information generated from the image sensing device (for example, a camera sensor) The lane information is detected based on the lane information (for example, color information of the lane, width information of the lane, length information of the lane, etc.), and based on the sensed lane, information on the distance to the lane, The intersection point of the intersection point.

The intersection of the above lanes may mean that a parallel lane intersects by perspective.

The vehicle information sensing step S710 of the calibration information adjustment method of the camera system according to the first embodiment may sense the heading angle information of the vehicle based on the sensing value of the sensor capable of sensing the turning motion of the vehicle.

The estimating step S720 of the calibration information adjusting method of the camera system according to the first embodiment may detect the curvature running information of the vehicle based on the detection value of the sensor capable of detecting the turning motion of the vehicle.

For example, the sensor capable of detecting the turning motion of the vehicle may include a steering angle sensor, a lateral acceleration sensor, and the like. The sensor may detect the heading angle information of the vehicle and the curvature driving information of the vehicle based on the turning motion of the vehicle. All of the existing methods can be applied in detail.

The calibration information calculation step (S730) of the camera system according to the first embodiment determines whether the amount of change in the curvature travel information of the estimated vehicle is equal to or less than the preset threshold curvature travel information and the amount of change in the distance information with respect to the sensed lane, The estimated intersection point of the lane can be calculated from the forward image information generated from the image sensing apparatus that monitors the front of the vehicle using the curvature information of the detected lane, the heading angle information of the vehicle, and the distance information with respect to the lane.

More specifically, in the calculation step S730, the lane estimation is performed in the front image information generated from the image sensing apparatus for monitoring the front of the vehicle using the curvature information of the detected lane, the heading angle information of the vehicle, It may take a calculation time to calculate the intersection point.

Therefore, in order to correctly calculate the estimated intersection of the lane, the calculating step S730 should maintain the curvature information of the lane, the heading angle information of the lane, and the distance information to the lane during the calculation time.

That is, in the calculating step S730, in order to calculate the estimated intersection point of the correct lane, the estimated amount of change in the curvature running information of the vehicle is equal to or less than the preset threshold curvature running information, and the amount of change in the distance information with respect to the sensed lane The estimated intersection point of the lane can be calculated.

This estimated intersection point means a point in which parallel lanes intersect by perspective, and may be estimated by reflecting the calibration information or the like to be described in detail below.

In the notification step S740 of the calibration information adjustment method of the camera system according to the first embodiment, if the difference between the intersection of the sensed lane and the estimated intersection of the calculated lane exceeds a preset allowable value, Can be informed.

The calibration information may be information used for calculating detailed information on an object included in the generated image information, and may be information related to the operation of the image sensing sensor from a geometrical point of view. The detailed information may include a distance to an object, a length of the object, and the like.

The correction step S750 of the calibration information adjustment method of the camera system according to the first embodiment generates a new first angle and a new second angle that make the difference between the intersection of the lane and the estimated intersection of the lane within the permissible value, New calibration information can be generated based on the above-described equations (1) to (3) for the angle and the new second angle.

Alternatively, in the correction step S750, the existing first angle and the existing second angle are extracted by decomposing the existing calibration information, and the new first angle and the new first angle, which are generated by correcting the extracted first angle and the existing second angle, New calibration information can be generated based on the second angle.

In other words, the magnitude of each correction angle corrected for the new first angle and the new second angle in the existing first angle and the existing second angle is determined by the intersection of the lane detected in the image information sensing step S700 and the calculation step S730). ≪ / RTI >

In addition, the directions of the respective correction angles corrected to the new first angle and the new second angle in the existing first angle and the existing second angle are determined by the intersection of the lane detected in the image information sensing step S700 and the calculation step S730, And the direction of the difference of the estimated intersection points calculated in the step of FIG.

In this manner, the calibration step S750 can generate the new calibration information more quickly and accurately based on the existing first angle and the existing second angle extracted by disassembling the existing calibration information.

The calibration information adjustment method of the camera system according to the first embodiment described with reference to FIG. 7 can correct the existing calibration information to be normal when the existing calibration information is determined to be an error.

Thus, the camera system reflecting the new calibration information has the effect of accurately detecting the detailed information of the object included in the forward image information. The detailed information may include a distance to an object, a length of the object, and the like.

In addition, the calibration information adjustment method of the camera system can perform all the operations performed by the camera system described with reference to Figs. 1 to 6.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the present invention. Therefore, it is intended that the present invention cover the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents. , Separation, substitution, and alteration of the invention will be apparent to those skilled in the art. Therefore, the disclosed embodiments are intended to illustrate and not limit the technical idea, and the scope of the technical idea is not limited by these embodiments. The scope of protection of the embodiments should be interpreted according to the following claims, and all technical ideas within the scope of equivalents should be interpreted as being included in the scope of the present invention.

Claims (8)

An image information sensing unit for sensing distance information on the lane, curvature information of the lane, and an intersection of the lane on the basis of the forward image information;
A vehicle information sensing unit for sensing heading angle information of the vehicle and each information of the tire;
An estimating unit that estimates curvature running information of the vehicle based on each piece of information of the tire;
Judges that the running condition of the vehicle is kept constant if the amount of change in the curvature running information of the vehicle is equal to or less than the predetermined threshold curvature running information and the amount of change in the distance information with respect to the lane is equal to or less than preset threshold distance information, An estimated intersection point of the lane in the forward image information by using the curvature information of the vehicle, the heading angle information of the vehicle, and the distance information of the lane;
An informing unit informing that an existing preset calibration information is an error if a difference between an intersection of the lane and an estimated intersection of the lane exceeds a predetermined allowable value; And
Wherein when a difference between an intersection of the lane and an estimated intersection of the lane exceeds the tolerance, a difference between the intersection of the lane and the estimated intersection of the lane is set within the allowable range, And correcting the existing calibration information to the new calibration information,
The intersection of the lanes is a point where two parallel lanes in the driving lane on which the vehicle travels intersect at a point intersecting with the perspective,
The estimated intersection point of the lane is a point at which two parallel lanes in the driving lane on which the vehicle travels are estimated to cross by a perspective method,
The calibration information is information used to calculate detailed information on an object included in the forward image information,
Wherein the detailed information is information on which the object is recognized in a direction monitored by an image sensing apparatus that outputs the forward image information,
Wherein,
Extracting the existing first angle and the existing second angle by decomposing the existing calibration information, correcting each of the existing first angle and the existing second angle to the new first angle and the new second angle,
The magnitudes of the respective correction angles corrected to the new first angle and the new second angle in the existing first angle and the existing second angle are proportional to the magnitude of the difference between the intersection of the lane and the estimated intersection,
Wherein the direction of each of the correction angles is a direction from the estimated intersection point to an intersection of the lane based on the estimated intersection point. delete delete The method according to claim 1,
A distance sensing unit for sensing a distance to an object included in the forward image information using the existing calibration information if a difference between an intersection of the lane and an estimated intersection of the lane is within the tolerance;
The camera system further comprising: The method according to claim 1,
Wherein the vehicle information sensing unit further senses yaw rate information and vehicle speed information of the vehicle,
Wherein the estimating unit comprises:
Estimating curvature running information of the vehicle based on yaw rate information of the vehicle and velocity information of the vehicle. delete An image information sensing step of sensing the distance information to the lane, the curvature information of the lane, and the intersection of the lane based on the forward image information;
A vehicle information sensing step of sensing heading angle information of the vehicle and each information of the tire;
An estimating step of estimating curvature running information of the vehicle based on each piece of information of the tire;
Judges that the running condition of the vehicle is kept constant if the amount of change in the curvature running information of the vehicle is equal to or less than the predetermined threshold curvature running information and the amount of change in the distance information with respect to the lane is equal to or less than preset threshold distance information, Calculating an estimated intersection point of the lane in the forward image information using curvature information of the vehicle, heading angle information of the vehicle, and distance information between the lane and the lane;
An informing step of informing that an existing preset calibration information is an error if a difference between an intersection of the lane and an estimated intersection of the lane exceeds a predetermined allowable value; And
Based on the new first angle and the new second angle such that the difference between the intersection of the lane and the estimated intersection of the lane is within the tolerance when the difference between the intersection of the lane and the estimated intersection of the lane exceeds the allowable value And a calibration step of generating new calibration information and correcting the existing calibration information into the new calibration information,
The intersection of the lanes is a point where two parallel lanes in the driving lane on which the vehicle travels intersect at a point intersecting with the perspective,
The estimated intersection point of the lane is a point at which two parallel lanes in the driving lane on which the vehicle travels are estimated to cross by a perspective method,
The calibration information is information used to calculate detailed information on an object included in the forward image information,
Wherein the detailed information is information on which the object is recognized in a direction monitored by an image sensing apparatus that outputs the forward image information,
Wherein the correcting step comprises:
Extracting the existing first angle and the existing second angle by decomposing the existing calibration information, correcting each of the existing first angle and the existing second angle to the new first angle and the new second angle,
The magnitudes of the respective correction angles corrected to the new first angle and the new second angle in the existing first angle and the existing second angle are proportional to the magnitude of the difference between the intersection of the lane and the estimated intersection,
Wherein the direction of each of the correction angles is a direction from the estimated intersection point to an intersection of the lane on the basis of the estimated intersection point. delete

Images