TWI451990B - System and method for lane localization and markings - Google Patents

Description

Lane positioning system, lane positioning method and pavement marking

The present invention relates to a lane positioning system and method, and more particularly to a system and method for determining the position of a lane using road markings.

The in-vehicle communication network has been widely discussed in recent years, and its technological development has greatly contributed to traffic safety and traffic management, and many of the proposed in-vehicle communication methods or applications require lane information of the vehicle. However, the feasibility of many studies or applications is limited by the inability of the positioning system to accurately locate the lane in which the vehicle is located. For example, the positioning results provided by the Global Positioning System (GPS-based) can generate from ten meters to several tens of meters due to Atmospheric effects and multiple path effects. The error, so the global positioning system can only roughly locate the road where the vehicle is located, and can not further locate the lane where the vehicle is located. On the other hand, if an image-based positioning system is used, the lane information of the vehicle is known by recognizing the road image. Since it is necessary to compare the images of the front and rear roads, it is susceptible to the misjudgment of the adjacent vehicle obscuring the lane line. The phenomenon. In addition, the image-based positioning system can only determine whether the vehicle is kept in the lane, and cannot determine the lane in which the vehicle is located.

Therefore, the industry is in great need of a technology that can directly use the road markings on the lane line to directly read out the lane in which the vehicle is located, to assist various positioning systems to accurately locate the lane in which the vehicle is located.

An embodiment of the present invention provides a lane positioning system that can determine a position of a lane in which a vehicle is located by using a road marking on a lane line.

An embodiment of the present invention provides a lane positioning system for determining a position of a lane. The lane positioning system includes an image capturing unit, an image recognition unit, and a processing unit. Here, the image capturing unit is configured to capture the lane image of the lane, and the lane image includes at least one of the first lane line and the second lane line on both sides of the lane. The image recognition unit recognizes at least one of the first road marking on the first lane line and the second road marking on the second lane line from the lane image, and generates a lane position signal according to the first road marking or the second road marking. The processing unit determines the position of the lane based on the lane position signal.

An embodiment of the present invention provides a lane positioning method that can determine a position of a lane in which a vehicle is located by using a road marking on a lane line.

Embodiments of the present invention provide a lane positioning method for determining a position of a lane, and the steps are as follows. First, the lane image of the lane is captured, wherein the lane image is used to display at least one of the first lane line and the second lane line on both sides of the lane. Next, at least one of the first road marking on the first lane line and the second road marking on the second lane line is identified by the aforementioned lane image, and a lane position signal is generated accordingly. Finally, the position of the lane is determined based on the generated lane position signal.

An embodiment of the present invention provides a road marking provided on a road surface for assisting the lane positioning system and method to determine a location of the vehicle.

Embodiments of the present invention provide a road marking that is disposed on a road surface having at least one lane and M lane lines, and each lane line corresponds to a road marking. Each of the pavement markings includes an optical identification portion disposed on the corresponding lane line and exposed to the upper surface of the corresponding lane line for indicating the lane line corresponding to the road marking. The i-th lane line and the i+1-th lane line in the M lane lines respectively have different optical identification parts, and M and i are both positive integers, and i+1 is not greater than M.

In summary, the lane positioning system and method proposed by the embodiments of the present invention use the road marking to achieve the lane recognition function, and can be matched with the global positioning system to make the lane position more accurate. Moreover, the road surface marking provided by the embodiment of the present invention can be achieved by slightly changing the existing road surface, and the cost can also be reduced.

The detailed description of the present invention and the accompanying drawings are to be understood by the claims The scope is subject to any restrictions.

[Example of lane positioning system]

Referring to FIG. 1 and FIG. 2A together, FIG. 1 is a functional block diagram of a lane positioning system according to an exemplary embodiment of the present invention. 2A is a schematic diagram showing the operation of a lane positioning system according to an exemplary embodiment of the present invention. As shown in the figure, the lane positioning system 1 has an image capturing unit 10, an image recognition unit 12, a processing unit 14, and an image processing unit 16. The image processing unit 16 is coupled between the image capturing unit 10 and the image recognition unit 12, and the processing unit 14 is coupled to the image recognition unit 12. In general, the lane positioning system 1 can be mounted on a vehicle (such as a car or a locomotive), and when the vehicle travels on one of the plurality of lanes 20, 22, 24, the lane positioning system 1 can accurately locate the lane The lane in which the vehicle travels. The components of the lane positioning system 1 will be described in detail below.

When the vehicle travels in the lane 24, the image capturing unit 10 is used to capture the lane image A of the lane 24, and the lane image A can display not only the image in the lane 24 but also the first lane line 266 on both sides of the lane 24. An image with the second lane line 268. In practice, the image capture unit 10 can be a camera and mounted at the front of the vehicle for monitoring the road conditions of the lane 24 in which the vehicle is located. Here, the present invention does not limit the type of the image capturing unit 10. For example, the image capturing unit 10 may be a driving recorder, a mobile phone, a handheld video recorder, or other suitable photographic device. In other words, the image capturing unit 10 can actually continuously capture the road condition of the lane 24 in which the vehicle is located, and record a corresponding video stream, and at least one of the video streams can include a lane image. A.

In addition, although the image capturing unit 10 is used to capture the lane image A in front of the vehicle, the present invention is not limited thereto, and the image capturing unit 10 can be used to capture the image. Road conditions behind or on the side of the vehicle. Therefore, as long as the lane image A captured by any photographic apparatus can include images of the first lane line 266 and the second lane line 268, it can conform to the scope of the image capturing unit 10 of the present invention.

1 and FIG. 2A, after the image recognition unit 12 receives the lane image A captured by the image capturing unit 10, the first road marking 266a and the second lane on the first lane line 266 can be identified from the lane image A. A second pavement marking 268a on lane line 268 and a lane position signal is generated in accordance with first pavement marking 266a and second pavement marking 268a. In general, the vehicle should travel in the center of the lane 24, with the first lane line 266 on the left side of the vehicle and the second lane line 268 on the right side of the vehicle. When the image recognition unit 12 determines that the lane image A captured by the image capturing unit 10 has the first road marking 266a on the left side of the screen, and the lane image A has the second road marking 268a on the right side of the screen, the image recognition unit 12 may According to the output of the corresponding lane position signal. In other words, the lane position signal is the lane 24 for indicating the first road marking 266a and the second road marking 268a.

Please note that the present invention does not limit the lane image A captured by the image capturing unit 10 to include both the first road marking 266a on the first lane line 266 and the second road marking 268a on the second lane line 268. A may display only one of the first pavement marking 266a and the second pavement marking 268a. Here, when the image recognition unit 12 determines that the first road marking 266a is located on the right side of the lane image A, the image recognition unit 12 may directly determine that the vehicle is located in the lane 24 regardless of whether the second road marking 268a is photographed on the left side of the lane image A. Inside. Similarly, when the image recognition unit 12 determines that the second road marking 268a is located on the left side of the lane image A, the image recognition unit 12 can directly determine that the vehicle is located in the lane 24 regardless of whether the first road marking 266a is captured on the right side of the lane image A. Inside.

On the other hand, if the image recognition unit 12 determines that the first road marking 266a and the second road marking 268a are not present in the lane image A, in addition to waiting for the image capturing unit 10 to retrieve a new lane image, actually It can also be judged that the vehicle is in a single lane. Here, although the present embodiment uses two road markings to determine the lane in which it is located, it is to be understood that the present invention is not limited thereto, but merely for the purpose of facilitating a clear understanding of the present invention by those skilled in the art.

On the other hand, the image recognition unit 12 recognizes the first road marking 266a and the second road marking 268a by computer graphics, and the image recognition unit 12 can be a programmable chip, which can be set by the user. The type of road marking to be recognized by the image recognition unit 12. For example, if the road marking of a certain road segment is a specific pattern, as long as the user provides the specific pattern to the image recognition unit 12 in advance, the image recognition unit 12 can also be easily recognized when the vehicle travels through the road segment. The pavement marking on the road segment. In other words, the image recognition unit 12 can have a storage component (not shown) built in, and the storage unit has a database of expandable road markings. Therefore, regardless of whether the road marking is a pattern, a color or a mark, the user can expand the database of the road markings by himself, so that the image recognition unit 12 can recognize various road markings.

It is worth mentioning that, in addition to the bar code shape illustrated in FIG. 1 and FIG. 2A, the first road marking 266a and the second road marking 268a may be configured with different colors for each lane line as pavement markings. This makes the pavement markings easier to identify. For example, FIG. 2B is a schematic diagram showing the operation of a lane positioning system according to another exemplary embodiment of the present invention. Here, each lane line 262', 264', 266', 268' may be a different color, such that the image recognition unit 12 determines that the lane image A has a lane line 266' having a first color on the left side of the screen, and the lane image When the lane line 268' having the second color appears on the right side of the screen, the image recognition unit 12 can output the lane position signal corresponding to the lane 24.

From a practical point of view, the first road marking 266a can be used not only to indicate the lane position signal of the corresponding lane, but also to indicate road condition information, geographic location (latitude and longitude information), rest station information or other auxiliary use of the corresponding lane. The invention is not limited herein. In other words, the first road marking 266a may of course have more information to be recorded if the first road marking 266a has a more complicated pattern than the bar code used to indicate the lane position. Here, the complex pattern may be a text, a two-dimensional barcode or other suitable pattern, which can be changed by a person having ordinary knowledge in the technical field.

In addition, the first pavement marking 266a can be directly recognized by the naked eye of the pedestrian of the undriving vehicle, in addition to being recognized by the image recognition unit 12 by computer graphics. For example, when the first pavement marking 266a is a character, the pedestrian can directly observe the first pavement marking 266a on the lane line to determine the geographic location (latitude and longitude information) where he is located or obtain various usage information. On the other hand, when the first pavement mark 266a is a two-dimensional barcode or other complicated pattern, the pedestrian can use the smart phone to capture the image of the first pavement mark 266a, and analyze the first pavement mark 266a through the smart phone. To accurately locate your location. Further, the user can use the application in the smart phone to obtain information about restaurants, attractions, shops, hospitals and the like around the current location. Please note that the present invention is exemplified by a smart phone here, but it is not limited thereto, and those having ordinary knowledge in the art can select a tablet computer or other electronic calculator with a photographic lens to achieve the same function.

After receiving the lane position signal, the processing unit 14 determines the position of the lane 24 based on the lane position signal. In practice, the processing unit 14 can further integrate the navigation system of the vehicle, so that the processing unit 14 can provide information of the vehicle in the lane, thereby expanding the function of the navigation system. In general, since the conventional navigation system can only roughly locate the road section where the vehicle is located, and cannot accurately locate the lane in which the vehicle is located, it is not possible to give the most appropriate advice based on the lane in which the vehicle is located.

In other words, the lane positioning system 1 of the present invention can greatly enhance the positioning capability of the commercially available navigation system, and can accurately locate the lane in which the vehicle is located when positioning the vehicle. For example, when the destination of the user needs to turn to the right and the vehicle driven by the user is still in the innermost lane, after the processing unit 14 of the present invention determines the lane in which the vehicle is located, the commercially available navigation system can The user is notified in advance by the voice to lean to the outer lane to prepare for a right turn. Or before the left turn is needed, the commercially available navigation system uses the voice to inform the user to lean toward the inner lane to make the route for assisting the vehicle smoother. Of course, the lane positioning system 1 can be further matched with the route planning, path calculation or other functions for navigation that the commercially available navigation system originally has, and the present invention is not limited thereto.

In addition, the lane positioning system 1 further includes an image processing unit 16 for performing image processing on the lane image A captured by the image capturing unit 10, wherein the image processing program may include grayscale calculation of the lane image and reduce noise. The operation or image binarization operation is used to assist the image recognition unit 12 to analyze the image processed lane image A to identify the image of the first road marking 266a and the second road marking 268a. In practice, the grayscale operation, the noise reduction operation, or the image binarization operation are processed by the open source function library ARToolKit. The present invention does not limit the image processing program to grayscale processing, noise reduction, or image binarization. In the technical field to which the present invention pertains, the general knowledge person can decide how to express the lane more clearly. Image A. Of course, if the lane image A captured by the image capturing unit 10 is clear enough, the present invention can also directly use the image capturing unit 10 without using the image processing unit 16.

The foregoing lane positioning system of the present invention will be further described in conjunction with the lane positioning method of the present invention. Please refer to FIG. 1, FIG. 2A and FIG. 3 together. FIG. 3 is a flow chart showing a lane positioning method according to an exemplary embodiment of the present invention. It is to be noted that FIG. 3 illustrates the manner in which the various components of the lane positioning system 1 operate when the lane positioning system 1 of the present invention does not require the image processing unit 16. As shown in the figure, in step S301, the image capturing unit 10 captures the lane image A of the lane 24 and transmits the lane image A to the image recognition unit 12. In step S303, the image recognition unit 12 first determines whether there is an identifiable lane line in the lane image A. If the result of the determination in step S303 is NO, it indicates that the lane image A captured by the image capturing unit 10 does not include the first lane line 266 and the second lane line 268, and then the process returns to step S301 to cause the image capturing unit 10 to Retake a new lane image A'.

If the result of the determination in step S303 is YES, it indicates that the lane image A captured by the image capturing unit 10 has the identifiable first lane line 266 and the second lane line 268, then the process proceeds to step S305, and the image recognition unit 12 further It is identified whether there is a second pavement marking 268a on the first lane marking 266 and the second lane marking 268a on the first lane line 266. If the result of the determination in step S305 is NO, it indicates that the lane image A captured by the image capturing unit 10 has the first lane line 266 and the second lane line 268, but the first lane line 266 is not captured. The road marking 266a and the second road marking 268a on the second lane line 268 need to return to step S301, so that the image capturing unit 10 retrieves a new lane image A'.

If the result of the determination in step S305 is YES, it indicates that the lane image A captured by the image capturing unit 10 has the identifiable first road marking 266a and the second road marking 268a, and then proceeds to step S307. In step S307, the image recognition unit 12 generates a lane position signal according to the first road marking 266a and the second road marking 268a. In step S309, the processing unit 14 receives the lane position signal from the image recognition unit 12, and determines the position of the lane 24 based on the lane position signal.

On the other hand, when the lane positioning system 1 of the present invention has the image processing unit 16, the operation of each component in the lane positioning system 1 can be as shown in FIG. Please refer to FIG. 1, FIG. 2A and FIG. 4 together. FIG. 4 is a flow chart showing a lane positioning method according to another exemplary embodiment of the present invention. As shown in the figure, in step S401, the image capturing unit 10 is configured to capture the lane image A. Next, in step S403, the image processing unit 16 first grayscales the lane image to simplify the information contained in the lane image A to assist subsequent image processing. In step S405, the image processing unit 16 further performs a noise reduction operation on the lane image A to try to separate the image of the first lane line 266 from the second lane line 268.

In step S409, the image recognition unit 12 receives the lane image A after the noise reduction operation, and determines whether there is an identifiable lane line in the lane image A after the noise reduction operation. If the result of the determination in step S409 is YES, it indicates that the lane image A after the image processing has the identifiable first lane line 266 and the second lane line 268, and then step S411 is continued. In step S411, the image recognition unit 12 further instructs the image processing unit 16 to perform image binarization calculation, and continues to convert the lane image A after the noise reduction in step S405 into an image displayed in black and white. Next, in step S413, the image recognition unit 12 further separates the first road surface mark 266a and the second road surface mark 268a from the lane image A after the image binarization operation.

In step S415, the image recognition unit 12 further determines whether or not there is an identifiable road surface marker in the lane image A after the image binarization operation. If the result of the determination in step S415 is NO, the lane image A after the image binarization operation has the first lane line 266 and the second lane line 268, but the first road marking 266a on the first lane line 266 is not captured. With the second road marking 268a on the second lane line 268, it is necessary to return to step S401, so that the image capturing unit 10 retrieves a new lane image A'.

If the result of the determination in step S415 is YES, the lane image A after the image binarization operation has the identifiable first road marking 266a and the second road marking 268a, and the process proceeds to step S417. In step S417, the image recognition unit 12 generates a lane position signal according to the first road marking 266a and the second road marking 268a. In step S419, the processing unit 14 receives the lane position signal from the image recognition unit 12, and determines the position of the lane 24 based on the lane position signal.

[Example of pavement marking]

In detail, each of the pavement markings of the present invention may have features that can be directly recognized by the naked eye or the camera. Please refer to FIG. 1 , FIG. 2A , FIG. 5A and FIG. 5B together, and FIG. 5A illustrates an exemplary embodiment of the present invention. A schematic representation of a pavement marking of an embodiment. FIG. 5B is a schematic diagram showing a pavement marking according to another exemplary embodiment of the present invention. As shown, the pavement markings 266a in Figure 1 are disposed on a roadway lane 266, and each pavement marking has an optical identification portion that is directly recognizable to the naked eye or camera. For example, the optical identification portion of the pavement marking 266a in FIG. 1 can be a code that is formed at one end of the lane line 266.

In practice, in addition to directly attaching different colors to the upper surface of the lane line 266 to form the bar code, a portion of the lane line at the end of the lane line 266 can be scraped off. Since the lane line and the road surface are different in color, as shown in FIG. 5A, after scraping off part of the lane line at the end of the lane line 266, a discontinuous pattern is formed at the end of the lane line 266 to form a bar code, so that the road marking 266a The optical recognition portion can be regarded as the barcode.

On the other hand, the optical recognition portion may be a bump having a color in addition to a single code. For example, the optical identification portion of the pavement marking 266b may be an opal or mirror that reveals the first color, while the pavement markings on adjacent lane lines may each have a different color. Here, the first color can be realized by using LED lamps 266c of different chromaticity in the road markings 266b. In addition, the pavement markings of the present invention can be disposed on the lane line in a plurality of manners, for example, the pavement markings are marked at one end of the lane line, at both ends, or at any position on the lane line, and the present invention is not limited thereto.

In summary, the lane positioning system and method proposed by the embodiments of the present invention use the road marking to achieve the lane recognition function, and can be matched with the global positioning system to make the lane position more accurate. Moreover, the road surface marking provided by the embodiment of the present invention can be achieved by slightly changing the existing road surface, and the cost can also be reduced.

For a better understanding of the features and technical aspects of the present invention, reference should be made to the accompanying drawings The scope is subject to any restrictions.

1. . . Lane positioning system

10. . . Image capture unit

12. . . Image recognition unit

14. . . Processing unit

16. . . Image processing unit

20, 22, 24. . . Lane

262, 264, 266, 268. . . Lane line

262', 264', 266', 268'. . . Lane line

266a, 266b, 268a. . . Pavement marking

266c. . . LED light

S301~S309, S401~S419. . . Process step

1 is a functional block diagram of a lane positioning system in accordance with an exemplary embodiment of the present invention.

2A is a schematic diagram showing the operation of a lane positioning system according to an exemplary embodiment of the present invention.

2B is a schematic diagram showing the operation of a lane positioning system according to another exemplary embodiment of the present invention.

3 is a flow chart showing a lane positioning method according to an exemplary embodiment of the present invention.

4 is a flow chart showing a lane positioning method according to another exemplary embodiment of the present invention.

5A is a schematic view of a pavement marking in accordance with an exemplary embodiment of the present invention.

FIG. 5B is a schematic diagram showing a pavement marking according to another exemplary embodiment of the present invention.

1. . . Lane positioning system

10. . . Image capture unit

12. . . Image recognition unit

14. . . Processing unit

16. . . Image processing unit

266a, 268a. . . Pavement marking

Claims (12)

A lane positioning system for determining a position of a lane, comprising: an image capturing unit, capturing a lane image of the lane, the lane image being used to display at least one of the first lane line and the second lane on both sides of the lane One of the lane lines; an image recognition unit coupled to the image capturing unit, the image recognition unit identifying at least a first road marking on the first lane line and a first lane line on the second lane line by the lane image After the one of the two pavement markings, the first pavement marking or the second pavement marking is used to generate a lane position signal corresponding to the lane; and a processing unit coupled to the image recognizing unit to determine the lane position signal according to the lane marking signal The location of the driveway. The lane positioning system of claim 1, further comprising: an image processing unit coupled between the image capturing unit and the image recognition unit for performing an image processing program on the lane image; The image recognition unit receives the image of the lane after the image processing, and identifies at least one of the first road marking and the second road marking from the image of the lane after the image processing. For example, in the lane positioning system of claim 2, the image processing program performs a grayscale operation, a noise reduction operation or an image binarization operation on the lane image to assist the image recognition unit. In the image of the lane after the image processing, at least one of the images of the first road marking and the second road marking is recognized. For example, the lane positioning system of claim 1 of the patent scope, wherein the processing unit is further Receiving a global positioning system signal and determining the position of the lane based on the global positioning system signal and the lane position signal. The lane positioning system of claim 1, wherein the lane positioning system is a handheld mobile device, and the handheld mobile device further captures latitude and longitude information included in the first pavement marking or the second pavement marking, corresponding to Provide geographic information about the user's current location. A lane positioning method for determining a position of a lane includes the following steps: capturing a lane image of the lane, the lane image being used to display at least one of the first lane line and the second lane line on both sides of the lane After the at least one first road marking on the first lane line and one second road marking on the second lane line are identified by the lane image, the first road marking or the second road marking is generated according to the lane image a lane position signal corresponding to the lane; and determining the position of the lane based on the lane position signal. For example, in the lane positioning method of claim 6, wherein after capturing the lane image of the lane, the method further comprises the steps of: performing grayscale calculation on the lane image; performing a noise reduction operation to eliminate gray scale The noise in the lane image after the calculation; performing an image binarization operation, converting the lane image after the noise reduction operation into an image displayed in black and white; and the image binarization operation At least one of the first pavement marking and the second pavement marking is separated from the lane image. For example, the lane positioning method of claim 6 is based on the lane In the step of determining the position of the lane by the position signal, the position of the lane is determined based on a global positioning system signal and the lane position signal. The lane positioning method of claim 8 , wherein the lane positioning method further comprises: capturing the latitude and longitude information included in the first pavement marking or the second pavement marking, and correspondingly providing geographic information about the current location of the user. A road marking, disposed on a road surface, is suitable for a lane positioning system to determine a position of a lane, the road surface having at least one lane and M lane lines, each lane line corresponding to the road marking, the road marking comprises: An optical identification portion disposed on the corresponding lane line and exposed to the corresponding upper surface of the lane line for identifying the lane positioning system to generate a lane position signal indicating the lane line corresponding to the road marking; The i-th lane line and the i+1th lane line of the M lane lines respectively have different optical identification parts, and M and i are positive integers, and i+1 is not greater than M. The road marking according to claim 10, wherein the optical identification unit indicates the lane line corresponding to the road marking by a bar code, and the optical identification of the ith lane line and the (i+1) lane line The portions respectively have a first barcode and a second barcode, and the optical identification portion is disposed at at least one end of the corresponding lane line. The road marking according to claim 10, wherein the optical identification unit indicates the lane line corresponding to the road marking by color, and the optical identification of the ith lane line and the (i+1) lane line The portions have a first color and a second color, respectively.