KR101986166B1 - Lane Recognition Apparatus and Method - Google Patents

Abstract

The present invention relates to a lane recognizing apparatus and method for recognizing a lane more accurately on a ramp and a curved road by using a camera of a vehicle's surround view monitoring system and providing an alarm to a driver when the vehicle leaves the lane. The lane recognizing apparatus according to the present invention comprises: an information receiving unit for receiving an image collected by a camera of an ambient view monitoring system of a vehicle; A lane detecting unit detecting a portion determined as a left lane and a right lane of the vehicle using the received image; A point selection unit selecting at least two or more different points in the left lane and selecting a point located at a distance closest to the at least two or more different points selected in the left lane on the right lane; Calculating a distance between the points, determining whether a difference between the calculated at least two distances exceeds a predetermined threshold, and determining whether the calculated at least two distances are within a predetermined threshold range A distance judging unit; And a lane recognition unit for recognizing the lane by using the determination of the distance determination unit.

Description

[0001] Lane Recognition Apparatus and Method [

The present invention relates to a lane recognition apparatus and method. More particularly, the present invention relates to a lane recognizing apparatus and method for recognizing a lane more accurately on a ramp and a curved road by using a camera of a vehicle's surround view monitoring system and providing an alarm to a driver when the vehicle leaves the lane .

Systems that support parking of vehicles such as the AVMS (Around View Monitoring System) or Parking Guide System provide a parking guide line when parking and monitor the surrounding situation of the vehicle to the driver .

However, a system that supports parking of a vehicle does not have a function of recognizing a lane and providing an alarm to a driver when the vehicle leaves the lane.

Lane Departure Warning System (LDWS) provides a function to recognize a lane and provide an alarm to the driver if the vehicle leaves the lane.

Such a lane departure warning system recognizes a lane in which a vehicle is traveling and recognizes a lane in which a vertex is formed rather than a parallel line due to the distortion of the lens and the perspective of the lane.

1 is a view for explaining an example of a method of recognizing a lane in a conventional lane departure warning system.

Referring to FIG. 1, the conventional lane departure warning system recognizes a lane of a triangle shape in which the width of the lane decreases along the distance by the perspective or the like. Therefore, the lane departure warning system has difficulty in recognizing the lane on the ramp and the curved road Respectively.

In order to solve the above-described problems, the present invention provides a lane recognition apparatus for recognizing a lane more accurately on a ramp and a curved road by using a camera of a vehicle's surround view monitoring system and providing an alarm to a driver when the vehicle leaves the lane, And a method thereof.

In order to solve the above problems, a lane recognizing apparatus includes an information receiving unit for receiving an image collected by a camera of an Around View Monitoring System (AVMS) of a vehicle; A lane detecting unit detecting a portion determined as a left lane and a right lane of the vehicle using the received image; A point selection unit selecting at least two or more different points in the left lane and selecting a point located at a distance closest to the at least two or more different points selected in the left lane on the right lane; Calculating a distance between the points, determining whether a difference between the calculated at least two distances exceeds a predetermined threshold, and determining whether the calculated at least two distances are within a predetermined threshold range A distance judging unit; And a lane recognition unit for recognizing the lane by using the determination of the distance determination unit.

 Preferably, the preset threshold value is set using road curvature and at least one of an electric field of the vehicle, an installed position of the camera, or the selected point, And can be set using the width of the road determined by the law.

Preferably, the lane recognizing unit determines that the lane recognizing unit determines that the lane recognizing unit does not determine that the difference in the calculated at least two distances does not exceed the preset threshold value, The lane detecting section recognizes the lane detected by the lane detecting section as a lane forming a space in which the vehicle is traveling, and the determination of the distance determining section determines that the difference in the calculated at least two distances is less than the predetermined threshold Or if at least one of the calculated at least two distances is not within the predetermined threshold range, it may be determined that the lane detected by the lane detecting unit is not a lane.

 Preferably, the lane recognizing device informs the driver of the vehicle of an audible output, a screen output, a seatbelt vibration, a seat vibration, or the like during a lane recognition of the lane, And may further include a lane departure warning unit for informing the user of the access using at least one of the methods.

Preferably, the predetermined threshold range may be set by receiving information on a road on which the vehicle is traveling from navigation installed in the vehicle and using the road information on the road.

In order to solve the above problem, a lane recognition method includes an information receiving step of receiving an image collected by a camera of an Around View Monitoring System (AVMS) of a vehicle; A lane detecting step of detecting a portion determined as a left lane and a right lane of the vehicle using the received image; A point selecting step of selecting at least two or more different points in the left lane and a point located at a distance closest to the at least two or more different points selected in the left lane on the right lane; Calculating a distance between the points, determining whether a difference between the calculated at least two distances exceeds a predetermined threshold, and determining whether the calculated at least two distances are within a predetermined threshold range Determining a distance; And a lane recognition step in which the vehicle recognizes the lane using the determination of the distance determination step.

 Preferably, the preset threshold value is set using road curvature and at least one of an electric field of the vehicle, an installed position of the camera, or the selected point, And can be set using the width of the road determined by the law.

Preferably, the lane recognizing step includes a step of judging whether or not the lane recognition step determines that the size of the difference between the calculated at least two distances does not exceed the preset threshold value, The lane detecting means detects the lane detected in the lane detecting step as a lane forming the space in which the vehicle is traveling, and when the determination of the distance determining step determines that the difference between the calculated distances of at least two or more distances The lane detecting unit may determine that the lane detected in the lane detecting step is not a lane when the predetermined threshold is exceeded or at least one of the calculated at least two distances is not within the predetermined threshold range.

 Preferably, the lane recognition method further includes a step of, when the vehicle approaches the predetermined distance or less at a position recognized as a lane in the lane recognition step, instructing the driver of the vehicle to perform voice output, screen output, And a lane departure warning step of informing the user of the access using at least one of the methods.

Preferably, the predetermined threshold range may be set by receiving information on a road on which the vehicle is traveling from navigation installed in the vehicle and using the road information on the road.

The present invention can improve lane recognition on curved roads or ramps.

In addition, the present invention can be applied to an around-view monitoring system in mass production to improve the system function.

In addition, the present invention enables the lane departure warning function to be performed in a system that assists the parking of the vehicle, thereby reducing the number of modules according to the function integration.

1 is a view for explaining an example of a method of recognizing a lane in a conventional lane departure warning system.
2 is a block diagram of a lane recognition apparatus according to a preferred embodiment of the present invention.
FIG. 3 is a diagram illustrating an example of selecting a point in the point selection unit of the lane recognition apparatus according to the present invention.
4 is a flowchart of a lane recognition method according to a preferred embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. In the following description and the accompanying drawings, substantially the same components are denoted by the same reference numerals, respectively, and redundant description will be omitted. 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 rather unclear.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

In this specification, a singular form may include plural forms unless specifically stated in the phrase. It is noted that the terms "comprises" and / or "comprising" used in the specification are intended to be inclusive in a manner similar to the components, steps, operations, and / Or additions.

The lane recognizing device according to the present invention is a device that implements the functions of the parking assist device and the driving lane recognizing device, which are constituted by separate modules, as a single module. In particular, the present invention recognizes a lane using information collected from a camera of a vehicle's surround view monitoring system (AVMS), which is one of the parking assist devices, and recognizes the lane And may be provided with an alarm function.

That is, the present invention may be used as an apparatus for an ambient view monitoring system using an image installed in a vehicle.

2 is a block diagram of a lane recognition apparatus according to a preferred embodiment of the present invention.

2, the lane recognizing apparatus 200 includes an information receiving unit 210, a lane detecting unit 220, a point selecting unit 230, a distance determining unit 240, a lane recognizing unit 250, and / Or a lane departure warning unit 260. [

The information receiving unit 210 receives information collected by a camera installed in the vehicle.

Specifically, the information receiving unit 210 receives information collected from cameras installed in the left and right portions of the camera or the vehicle of the surrounding view monitoring system.

The information receiving unit 210 is installed in one side of the vehicle, but may receive the collected image information of the left and right parts of the vehicle due to the performance of the camera or the angle of view range of the camera.

The information received by the information receiving unit 210 preferably includes image information of the left side of the vehicle and the bottom of the right side of the vehicle or the road portion.

The lane detecting unit 220 detects the lane portion of the road using the information received by the information receiving unit 210. [

Specifically, the lane detecting unit 220 detects a portion of the information received by the information receiving unit 210, which is determined as a lane in the left side image of the vehicle and the right side image information of the vehicle.

The boundary detecting method using the depth value, the color information, and the like can be used as a method of detecting the portion of the lane detecting portion 220 determined as the lane. That is, the lane detecting unit 220 can detect the lane portion using the fact that there is a clear difference between the color of the road and the color of the lane.

The lane detecting unit 220 can remove the noise of the information received from the camera, correct the distortion, and detect the portion determined as the lane.

The lane detected by the lane detecting unit 220 determines whether the lane is erroneously detected by an obstacle, noise, or the like through the point selecting unit 230, the distance determining unit and the lane recognizing unit 250, and recognizes the correct lane.

The point selecting unit 230 selects points in the portion determined as the lane detected by the lane detecting unit 220.

Specifically, the point selecting unit 230 selects at least two or more different points in the lane-detected portion S1 in the left image information of the vehicle.

In addition, the point selecting section 230 selects at least two or more different points in the lane-detected portion S2 in the right side image information of the vehicle, and each of the points selects each different point and the shortest distance As shown in FIG.

If it is determined that the lane is the lane and the detected lane width exists, the point selecting unit 230 preferably selects the center portion of the lane as a point.

FIG. 3 is a diagram illustrating an example of selecting a point in the point selection unit of the lane recognition apparatus according to the present invention.

Referring to FIG. 3, it is preferable that the number of points selected in S1 and the number of points selected in S2 are the same, and each point is preferably matched one to one so that the shortest distance is selected.

In FIG. 3, it can be seen that PL1 is matched with PR1, PL2 is matched with PR2, and PL3 is matched with PR3.

The point selected by the point selecting unit 230 may be a method of selecting a point and selecting a matching point in the other side image according to a preset direction in the one-side image information, and all the points on both sides may be selected It is possible.

The preset bar may be changed according to the length of the vehicle, the width of the vehicle, the position of the camera, the speed of the vehicle, the performance of the camera, and the like.

The point selecting unit 230 selects a point on the lane detected by the lane detecting unit 220 to measure the distance between the selected points and determine whether the detected lane is misrecognized using the measured distance .

 That is, the lanes that form the range to which the vehicle belongs generally form a certain distance and exist in parallel. This is irrespective of whether the road is curved or inclined.

Accordingly, the present invention detects a lane portion in a left side image and a right side image of a vehicle collected by a camera used in an environment monitoring system or the like, judges whether or not the detected lane maintains a certain distance, .

The distance determining unit 230 calculates the distance between the points selected by the point selecting unit 230 and determines whether the difference in the calculated distances exceeds a predetermined threshold value.

Also, the distance determination unit determines whether the calculated distance between the points selected by the point selection unit 230 is within a predetermined threshold range.

Specifically, calculating the distance between the points selected by the distance determination unit is to calculate the distance between the points that are matched with each other at the closest distance.

For example, the distance determination unit may calculate the distance between PL1 and PR1 in Fig. 2, calculate the distance between PL2 and PR2, The distance between PL3 and PR3 is calculated.

In FIG. 3, the magnitude of the difference between the distances calculated between PL1 and PR1 and the distances calculated between PL2 and PR2 is K1, the distance between PL2 and PR2, and the distance between PL3 and PR3 is K2 , And the magnitude of the difference between the distances calculated between PL3 and PR3 and the distances calculated between PL1 and PR1 is K3, the distance judging unit judges whether each of K1, K2 and K3 exceeds a predetermined threshold value. When at least one of K1, K2, and K3 exceeds a preset threshold value, the lane recognition unit 250 recognizes that the lane detected by the lane detecting unit 220 is not a lane with a mistakenly recognized lane.

It is because it is proper to judge that the lane is not a lane if the shortest distance between the left lane of the vehicle and the right lane of the vehicle is not constant on the basis of the vehicle, which is formed at a constant distance. However, it is reasonable to consider some errors in light of the fact that it is difficult to generate a lane while maintaining a perfectly constant distance in the lane generating process.

That is, the predetermined threshold may be a value that takes a predetermined error into consideration. If the lane is perfectly parallel, the predetermined threshold value should be 0 for K1, K2, and K3. However, as described above, it is difficult to generate a perfectly parallel lane, and the width of the lane itself is not constant It is preferable that the value is in consideration of the error. For example, the predetermined threshold value may be set to a value of about 10 cm in consideration of an error at zero. The predetermined threshold value may be changed for various reasons such as the position of the camera, the road state of the country, the performance of the camera, and the like.

The distance determining unit determines whether the calculated distance between the points selected by the point selecting unit 230 is within a predetermined threshold range by determining that the lane detected by the lane detecting unit 220 is a lane recognized by the obstacle or noise In order to judge whether or not it is.

That is, the distance calculated between PL1 and PR1 is LR1, the distance calculated between PL2 and PR2 is LR2, and the distance calculated between PL3 and PR3 is LR3, the distance determining unit determines LR1, LR2 and LR3 It is determined whether or not all of them are within a predetermined threshold range.

The predetermined threshold range is set according to the lane width present in the country in which the device is used. For example, in the case of the Republic of Korea, the road width is about 3.0 to 3.6 meters wide. Specifically, the width of the lane can be different depending on whether it is a road in a local area or a road in an urban area, and may be different depending on whether it is a highway, a main road, an integrated road, or a local road. The width of the Korean road is specified in Article 10 of the Regulation on the Structural and Facility Standard of Roads. That is, the predetermined threshold range may be changed according to the regulations related to the road width of the country, and it is preferable that the predetermined threshold range is set in consideration of an error when generating the lane. For example, the predetermined threshold range may be set to 2.8 m to 3.8 m.

In addition, the predetermined threshold range may be changed according to the information of the road on which the vehicle travels after receiving the navigation information.

That is, for example, when the information that the road on which the vehicle travels from the navigation system is the local road in the urban area is received from the navigation system, the width of the vehicle is designed to be 3.0 m in the legally prescribed range, and the predetermined threshold range is set to 2.8 m to 3.2 m Or the setting may be changed during running of the vehicle. The change of the setting can be performed by the distance determination unit.

The lane recognition unit 250 determines whether the lane detected by the lane detecting unit 220 is a noise or an obstacle based on the determination of the distance determining unit 220, and recognizes the lane if it is not a noise or an obstacle.

More specifically, the lane recognition unit 250 determines that the lane recognition unit 250 determines that the difference between the distances between the points selected by the point selecting unit 230 does not exceed the preset threshold value, The lane detected by the detecting unit is recognized as a lane on the road rather than a noise or an obstacle.

On the other hand, the lane recognition unit 250 determines that the lane recognition unit 250 determines that the difference between the distances between the points selected by the point selecting unit 230 exceeds a preset threshold value, The lane recognition unit 250 determines that the lane detected by the lane detecting unit 220 is an obstacle or noise other than a lane.

In addition, the lane detecting unit 220 may detect one or more lanes that are determined as lanes in any one of the left and right image information of the image information received by the information receiving unit 210. In this case, The selecting unit 230 selects a point for each detected lane. Then, the distance determination unit calculates the distance and determines the calculated distance as a predetermined threshold value and a predetermined threshold range.

The lane recognizing unit 250 can discriminate between lane-based noise, obstacle, and lane based on the determination by the distance determining unit, or can determine whether the lane is a noise or an obstacle.

The lane departure warning unit 260 receives the lane recognition information from the lane recognition unit 250 and can alert the driver to the lane departure when the vehicle being driven approaches the lane using the received information.

Specifically, the lane departure warning unit 260 may inform the driver that the lane departure warning unit 260 detects that the lane departing from the lane recognition unit 250 is audible, visual, or tactile . That is, the lane departure warning unit 260 can inform the driver of the risk of audible, visual, or tactile by using a crane, a voice output device, a navigation display device, a seat belt, a seat or a head up display.

The lane departure warning unit 260 may receive the operation information from the turn signal lamp or the vehicle flashing device of the vehicle so that the lane departure warning unit 260 may not perform the alarm even if the vehicle deviates from the lane in the case of the lane change, left turn, right turn or U- .

In general, a known technique for recognizing a lane recognizes a lane in which a vertex, rather than a parallel line, is formed due to the perspective of the lane, as described in conjunction with Fig. Accordingly, in the known technology, there is an error in the lane recognition or difficulty in recognizing the lane when the road is curved or inclined, but the lane recognizing device 200 according to the present invention can not recognize the lane recognition even when the road is curved or inclined The lane can be recognized.

Further, the present invention is applied to a system having a camera device such as an ambient view monitoring system, so that it can recognize a lane and perform a lane departure warning function in addition to a function of supporting a parking assist.

4 is a flowchart of a lane recognition method according to a preferred embodiment of the present invention.

Referring to FIG. 4, the lane recognition method receives information collected by a camera installed in a vehicle by the information receiving unit 210 (step S705).

The lane detecting unit 220 detects the left lane and the right lane in the information received by the information receiving unit 210 (step S710).

The point selecting unit 230 selects at least two or more points on the left lane detected by the lane detecting unit 220 and selects a point that is closest to the selected point on the right lane detected by the lane detecting unit 220 (Step S715).

The distance determining unit calculates the distance between the point selected on the left lane and the point located closest to the right lane in step S720 and determines whether the calculated difference in the distance exceeds the predetermined threshold value S725).

Also, the distance determination unit determines whether all of the calculated distances between the points are within a predetermined threshold range (S730).

The lane recognizing section 250 determines that the lane detecting section 220 determines that the lane detecting section 220 determines that the calculated distance does not exceed the preset threshold value and all of the calculated distances are within the predetermined threshold range The detected lane can be recognized as a lane forming a space in which the vehicle is traveling (step S735). Otherwise, the lane recognition unit 250 may determine that the lane detected by the lane detecting unit 220 is not a lane (step S740).

If the lane departure warning unit 260 approaches the lane of less than a predetermined distance in step S745, the lane departure warning unit 260 may inform the driver of the lane departure information in step S750.

It should be understood that the block diagram of the lane recognition apparatus 200 according to the preferred embodiment of the present invention represents exemplary conceptual aspects embodying the principles of the invention. Similarly, all of the flowcharts should be understood to represent various processes that may be substantially represented on a computer-readable medium and executed by a computer or processor, whether the computer or processor is explicitly shown.

The functions of the various elements shown in the drawings, including the functional blocks shown in a processor or similar concept, may be provided by use of dedicated hardware as well as hardware capable of executing software in connection with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, a single shared processor, or a plurality of individual processors, some of which may be shared.

Also, the explicit use of terms such as processor, control, or similar concepts should not be interpreted exclusively as hardware capable of running software, and may be used without limitation as a digital signal processor (DSP) (ROM), random access memory (RAM), and non-volatile memory. Other hardware may also be included.

It will be apparent to those skilled in the art that various modifications, substitutions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims. will be. Therefore, the embodiments disclosed in the present invention and the accompanying drawings are intended to illustrate and not to limit the technical spirit of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments and the accompanying drawings . The scope of protection of the present invention should be construed according to the following claims, and all technical ideas falling within the scope of the same shall be construed as falling within the scope of the present invention.

Claims (10)

An information receiving unit for receiving an image collected by a camera of an Around View Monitoring System (AVMS) of a vehicle;
A lane detecting unit detecting a portion determined as a left lane and a right lane of the vehicle using the received image;
A point selection unit selecting at least two or more different points in the left lane and selecting a point located at a distance closest to the at least two or more different points selected in the left lane on the right lane;
Calculating a distance between the points, determining whether a difference between the calculated at least two distances exceeds a predetermined threshold, and determining whether the calculated at least two distances are within a predetermined threshold range A distance judging unit; And
And a lane recognition unit for recognizing the lane by using the determination of the distance determination unit,
Wherein the preset threshold value is set using at least one of the full length of the vehicle, the installed position of the camera, or the selected point and the road curvature,
Wherein the predetermined threshold range is set using a width of a road determined by a law and is set using navigation information while receiving information of a road on which the vehicle is traveling from navigation installed in the vehicle,
The lane recognizing unit,
The lane departure determination unit determines that the calculated difference of at least two distances does not exceed the predetermined threshold value and the calculated at least two distances are within the predetermined threshold range, Recognizes the detected lane as a lane forming the space in which the vehicle is traveling,
When the determination by the distance determination unit determines that a difference between the calculated at least two distances exceeds the predetermined threshold or at least one of the calculated distances is not within the predetermined threshold range, And the lane detecting unit determines that the lane detected by the lane detecting unit is not a lane.
delete delete The method according to claim 1,
The lane recognizing device includes:
When the vehicle approaches the predetermined distance or less at a position recognized as a lane in the lane recognizing section, the driver of the vehicle is notified of the approach by using at least one of voice output, screen output, seat belt vibration, And a lane departure warning section for informing whether or not the lane departure warning section is present.
delete An information receiving step of receiving an image collected by a camera of an Around View Monitoring System (AVMS) of the vehicle;
A lane detecting step of detecting a portion determined as a left lane and a right lane of the vehicle using the received image;
A point selecting step of selecting at least two or more different points in the left lane and a point located at a distance closest to the at least two or more different points selected in the left lane on the right lane;
Calculating a distance between the points, determining whether a difference between the calculated at least two distances exceeds a predetermined threshold, and determining whether the calculated at least two distances are within a predetermined threshold range Determining a distance; And
And a lane recognition step in which the vehicle recognizes the lane using the determination of the distance determination step,
Wherein the preset threshold value is set using at least one of the full length of the vehicle, the installed position of the camera, or the selected point and the road curvature,
Wherein the predetermined threshold range is set using a width of a road determined by a law and is set using navigation information while receiving information of a road on which the vehicle is traveling from navigation installed in the vehicle,
The lane recognition step includes:
Wherein when the determination of the distance determining step is that the calculated difference in at least two distances does not exceed the predetermined threshold value and the calculated at least two distances are within the predetermined threshold range, The lane detected in the detecting step is recognized as a lane forming the space in which the vehicle is traveling,
If the determination of the distance determination step determines that the difference between the calculated distances of at least two or more distances exceeds the preset threshold value or at least one of the calculated at least two distances does not exist within the preset threshold range , The lane detection step determines that the lane detected in the lane detecting step is not a lane.
delete delete The method according to claim 6,
In the lane recognition method,
When the vehicle approaches the predetermined distance or less at a position recognized as a lane in the lane recognizing step, the driver of the vehicle is notified of the approach by using at least one of voice output, screen output, seat belt vibration, And a lane departure warning step of informing the driver of the lane departure warning.
delete

Images