Method and system for tracking roadway lane markings

Abstract

To provide a method and system for tracking roadway lane markings.SOLUTION: The method and system for tracking roadway lane markings includes: collecting frames of image data of a roadway; separating first individual lane markings from in a first frame of the image data of the roadway; assigning an identifier to each of individual separated lane markings; and comparing the first individual separated lane markings to the next frame of the image data of the roadway.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a method and system for tracking roadway lane markings. [Background technology]

[0002] A roadway may have lane markings, such as lane lines and dashed lane dividers. Vehicle assistance systems, such as lane keeping assistance systems, and autonomous vehicles may use forward-facing image collection devices to collect images of the lane marks to navigate the vehicle through curves and turns in the roadway. To track the lane lines over a traveled distance, it may be useful for the system to determine that the lane mark detected in a first frame is the same lane line detected in a next frame. Conventional lane mark tracking systems may require a large amount of computing power to identify the lane marks in an image and track the lane marks between frames. Summary of the Invention

[0003] Roadway lane markings may be tracked by an autonomous or semi-autonomous vehicle to determine the location of the vehicle relative to the roadway lane, to maintain the vehicle within the roadway lane, such as with a lane keeping assistance system, to perform lane change maneuvers between multiple lanes, and / or various other functions. Current systems may require a large amount of computational power to determine the location of the roadway lane markings. Furthermore, current systems may look at an entire frame of roadway image data and may not specifically focus on lane markings within the frame of roadway image data. Thus, a need exists for a roadway lane marking detection and tracking system that may use less computational power than conventional systems and methods.

[0004] The method may efficiently track roadway lane markings by using less computing power than conventional roadway lane marking methods and systems.

[0005] The system generally includes a processor, an image collection device, an artificial intelligence device, and a vehicle controller. The processor, the image collection device, the artificial intelligence device, and the vehicle controller may be connected to each other, such as through a wired connection or a wireless network. One or more of the processor, the image collection device, the artificial intelligence device, and / or the vehicle controller may be located in the vehicle. The processor may process frames of forward-facing image data of the roadway to isolate roadway lane markings.

[0006] According to one embodiment, a method for detecting roadway lane marks includes collecting a frame of roadway image data, isolating a first individual lane mark from within the first frame of roadway image data, assigning an identifier to the isolated individual lane mark, and comparing the first isolated individual lane mark with a next frame of roadway image data.

[0007] According to another embodiment, a vehicle navigation system includes a vehicle, an image collection device disposed in the vehicle, a processor, and a vehicle controller, the image collection device, the processor, and the vehicle controller being connected to each other via a network, and the processor receiving input data from the image collection device, isolating lane markings in the input data, and sending an output to the vehicle controller for controlling the vehicle.

[0008] Additional features and advantages of the techniques described in this disclosure will be set forth in the detailed description which follows, and in part will be readily apparent to those skilled in the art from said description, or will be learned by practicing the techniques as described in this disclosure, including the following detailed description, the claims, and the accompanying drawings. [Brief description of the drawings]

[0009] The following detailed description of the disclosure can be better understood when read in conjunction with the following drawings. [Figure 1]FIG. 2 is a schematic depiction of a diagram of a network of devices performing a method according to one or more embodiments shown and described herein. [Diagram 2] FIG. 2 is a schematic depiction of a diagram of roadway marks identified in a frame of image collection device data, according to one or more embodiments shown and described herein. [Diagram 3] FIG. 10 is a diagram that generally depicts a determination angle of a roadway mark identified in a frame of image collection device data, according to one or more embodiments shown and described herein. [Figure 4] FIG. 1 is a schematic diagram illustrating a flow chart of a method according to one or more embodiments shown and described herein. [Diagram 5] FIG. 1 is a schematic diagram illustrating a flow chart of a method according to one or more embodiments shown and described herein.

[0010] Reference will now be made in more detail to various embodiments of the present disclosure, some embodiments of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Embodiments of the present disclosure are directed to a method and system for tracking roadway lane markings. The method may include capturing a frame of roadway image data with an image collection device, such as a camera. The system may automatically isolate the lane markings in the frame of roadway image data. The system may then isolate individual pixels in the frame of roadway image data that form roadway markings, such as lane lines. The system may then assign a unique identifier to the isolated pixels. The system may then compare the identified isolated pixels to a next frame of roadway image data. In other embodiments, the system may be used to navigate a vehicle. The image collection device, the processor, and the vehicle controller are all connected to each other via a network. The image collection device may provide input to the processor. The processor may send output to a vehicle controller that controls the vehicle.

[0012] Conventional roadway marking detection methods and systems may require a large amount of computational power to detect and track roadway marks between frames of roadway data. For example, conventional methods and systems may process an entire frame of roadway image data rather than isolating only a portion of the frame of roadway image data that contains the roadway marking. Embodiments may improve roadway marking detection methods and systems by isolating pixels in the frame of roadway image data that contain the roadway marking and processing only that small portion of the frame of roadway image data.

[0013] Referring now to FIG. 1, an example of a system 100 for tracking roadway lane markings is shown consistent with an embodiment of the present disclosure. As shown in FIG. 1, a vehicle 102, a processor 110, an image collection device 120, an artificial intelligence device 130, a user interface 142, and a map device 144 are communicatively connected to each other via a network 150. Although a particular number of processors 110, image collection devices 120, artificial intelligence devices 130, vehicle controllers 140, user interfaces 142, and map devices 144 are depicted in FIG. 1, any number of such devices may be provided. Furthermore, functionality provided by one or more devices of the system 100 may be combined, and functionality of any one or more components of the system 100 may be implemented by any suitable computing environment.

[0014] Network 150 facilitates communication between various devices in system 100, such as vehicle 102, processor 110, image collection device 120, artificial intelligence device 130, user interface 142, and map device 144. Network 150 may be a shared, public, or private network, may encompass a wide area or a local area, and may be implemented through any suitable combination of wired and / or wireless communication networks. Furthermore, network 150 may include a local area network (LAN), a wide area network (WAN), an intranet, or the Internet. Network 150 may enable near real-time communication between devices connected through the network.

[0015] In an embodiment, the vehicle 102 may be an autonomous vehicle or a semi-autonomous vehicle. In other embodiments, the vehicle 102 may have a lane keeping assistance system that may assist a user of the vehicle 102 in keeping the vehicle 102 within a lane of a roadway.

[0016] The vehicle 102 may be an autonomous vehicle or a semi-autonomous vehicle. In other embodiments, the vehicle 102 may have a lane keeping assistance system that may assist a user of the vehicle 102 in keeping the vehicle 102 within a lane of a roadway. The vehicle 102 may have a vehicle controller 140. The vehicle controller 140 may be a computing device that controls the vehicle 102. In embodiments in which the vehicle 102 is an autonomous vehicle, the vehicle controller 140 may control all aspects of the movement of the vehicle 102, including but not limited to acceleration, braking, and steering, such that the system 100 may autonomously control the vehicle based on detected lane markings. In embodiments in which the vehicle 102 is not an autonomous vehicle, the vehicle controller 140 may supplement the operator's acceleration, braking, and steering inputs.

[0017] The processor 110 may include a non-transitory processor-readable storage medium that stores program modules that, when executed by the processor, perform one or more processes described herein. The non-transitory processor-readable storage medium may be one or more memory devices that store data and software, and may also comprise, for example, one or more of RAM, ROM, magnetic storage, or optical storage. The embodiments of the present disclosure may be implemented using a HTTPS (Hypertext Transfer Protocol Secure) environment, so that data transfers over a network such as the Internet may be performed in a secure manner.

[0018] Image collection device 120 may be a camera or other suitable device for capturing images. Image collection device 120 may be oriented to collect forward-looking image data from roadway 158. In one embodiment, image collection device 120 may collect a first frame of roadway data 160 and a next frame of roadway data.

[0019] The artificial intelligence device 130 may be a device that houses an artificial intelligence model 132. The artificial intelligence model 132 may be a feature recognition algorithm.

[0020] User interface 142 may be a device through which a user selects options or otherwise interacts with system 100. In embodiments, user interface 142 may be a mobile computing device, a tablet, a computer, or any other suitable type of user interface. In other embodiments, user interface 142 may be incorporated within an infotainment system of vehicle 102, such as an infotainment touchscreen or control knob.

[0021] Map device 144 may be a device that stores maps of roadways. Map device 144 may download maps onto a memory associated with map device 144, may access maps from a map database, or may have access to maps from any other suitable source.

[0022] In an embodiment, processor 110 receives input data from image collection device 120, processes the input data, and sends output to vehicle controller 140. In a further embodiment, processor 110 may receive input from a user interface 142. In yet a further embodiment, processor 110 may be supplemented by artificial intelligence models 132 stored on artificial intelligence device 130.

[0023] In an embodiment, one or more of the processor 110 , the image collection device 120 , the artificial intelligence device 130 , the user interface 142 , and / or the map device 144 may be physically located in the vehicle 102 .

[0024] 2, a diagram of the operation of the system 100 is shown consistent with an embodiment of the present disclosure. The system 100 may capture a first frame 160 of roadway data. The first frame of roadway data may be a photograph of the roadway at a first location. The roadway 158 may be a highway, a roadway, or other surface that the vehicle 102 may traverse. The roadway 158 may include one or more lane markings that indicate the divisions between lanes of the roadway 158, the outer boundaries of the roadway 158, or other possible roadway features.

[0025] The first frame of roadway data 160 may include, for example, a first lane marking 162, a second lane marking 164, and a third lane marking 166. In other embodiments, the first frame of roadway data 160 may include any suitable number of lane marks, such as one lane marking, two lane marks, five lane marks, ten lane marks, or any other suitable number of lane marks. Although the first lane marking 162 and the third lane marking 166 are shown as solid lines and the second lane marking 164, it should be understood that the roadway 158 may include any variation on solid or dashed roadway markings.

[0026] The first frame 160 of roadway data may be constructed of a plurality of pixels. Each of the plurality of pixels may represent a unique data point of the first frame 160 of roadway data. The system 100 may isolate pixels from the first frame 160 of roadway data that represent a first lane marking 162, a second lane marking 164, and / or a third lane marking 166. The system 100 may define a first lane 163 of the roadway between the first lane marking 162 and the second lane marking 164, and a second lane 165 of the roadway between the second lane marking 164 and the third lane marking 166. The system 100 may isolate the pixels using any suitable process, such as by an artificial intelligence model 132 trained as an image recognition model. In other embodiments, a user may manually isolate pixels through the user interface 142, for example, by manually selecting the pixels or drawing a shape around a group of pixels to isolate the pixels.

[0027] The system 100 may place a first bounding box 168 around the first lane marking 162. The first bounding box 168 may identify the first lane marking 162 within the first frame 160 of roadway data. Although the first bounding box 168 is referred to as a "box," it should be understood that any suitable shape may be placed around the first lane marking 162, including, but not limited to, a circle, an oval, or a rectangle. A first identifier 174 may be associated with the first bounding box 168. The first identifier 174 may be a unique string to identify the first lane marking 162 from various other lane marks. Although the first identifier 174 is shown as an alphanumeric string, it should be understood that any unique identifier may be used, including, but not limited to, a shape, a color, or any other suitable identifier.

[0028] Similarly, system 100 may place a second bounding box 170 around second lane marking 164, and a second identifier 176 may be associated with second bounding box 170. System 100 may also place a third bounding box 172 around third lane marking 166, and a third identifier 178 may be associated with third bounding box 172.

[0029] 3, an illustration of the operation of the system 100 is shown consistent with an embodiment of the present disclosure. A first frame 160 of roadway data may include a second lane marking 164, a second bounding box 170, and a second identifier 176. The system 100 may determine a first angle Θ of the second lane marking 164 relative to a horizontal axis X. The first angle Θ may be stored by the system 100. It should be understood that in an embodiment, the first angle Θ may be determined relative to any other suitable axis, such as a vertical axis Y.

[0030] The system 100 may repeat identifying one or more roadway marks for a subsequent second frame of roadway data. The second frame of roadway data may be captured by the image collection device 120 at a later time (e.g., one second later) than the first frame of roadway data 160. Thus, the vehicle 102 may have moved between the capture of the first frame of roadway data 160 and the capture of the second frame of roadway data, which may change the orientation of the second frame of roadway data relative to the image collection device.

[0031] In an embodiment, the system 100 may isolate pixels forming various roadway marks in the second frame of roadway data, place a bounding box around the isolated roadway marks in the second frame of roadway data, and determine a second angle of the roadway mark relative to the axis in the second frame of roadway data. The system 100 may compare the second angle from the second frame of roadway data to the determined first angle Θ of the first frame of roadway data 160. If the first angle Θ and the second angle are within a predetermined range of each other, the system 100 may determine that the second lane mark 164 in the first frame of roadway data 160 is the same lane mark that was isolated in the second frame of roadway image data. That is, system 100 may determine that a separated second lane marking 164 in first frame of roadway data 160 is the same lane marking along roadway 158 in the second frame of roadway data because first angle Θ is equal to or approximately equal to the second angle. In an embodiment, the predetermined range may be that first angle Θ and second angle are within 5 degrees of each other, within 1 degree of each other, within 0.1 degrees of each other, within 0.01 degrees of each other, or any other suitable range.

[0032] The trajectory of the vehicle 102 may be tracked, such as by an accelerometer associated with the vehicle 102. In some embodiments, the system 100 may take into account the trajectory of the vehicle 102 and the change in orientation of the vehicle 102 relative to the lane markings between the first frame of roadway data 160 and the second frame of roadway data. As a non-limiting example, if the accelerometer indicates that the vehicle 102 is making a left turn between the capture of the first frame of roadway data 160 and the capture of the second frame of roadway data, the system 100 may expect the second angle of the detached lane marking relative to the horizontal x-axis to be less than the first angle Θ.

[0033] The location of the vehicle 102 may be tracked, such as by a GPS device associated with the vehicle 102. In some embodiments, the system 100 may compare the location of the vehicle 102, the identified lane marks, and the map in the map device 144. The system 100 may add the location of the identified lane marks to the map in the map device 144.

[0034] 4, a method 400 is shown consistent with an embodiment of the present disclosure. The method 400 is directed to tracking roadway marks. At step 410, the method 400 includes capturing a first frame 160 of roadway data. That is, the image collection device 120 may capture a frame of the roadway 158.

[0035] At step 420, the method 400 includes isolating individual lane markings from within the first frame of roadway image data. That is, the artificial intelligence device 130, a user utilizing the user interface 142, or any other suitable device capable of isolating individual lane markings may isolate the lane markings from the first frame of roadway data 160.

[0036] At step 430, the method 400 includes placing a bounding box around the pixels forming the lane markings, i.e., the system 100 may place a shape around the lane markings to identify the lane markings within the first frame 160 of roadway data.

[0037] At step 440, method 400 includes assigning a unique identifier to the bounding box. That is, system 100 may assign a unique identifier, such as an alphanumeric string, a shape, or a color, to the bounding box to distinguish the bounding box and isolated lane markings from other bounding boxes and isolated lane markings.

[0038] At step 450, the method 400 includes determining the angle of the lane marking relative to an axis, i.e., the system 100 may measure the angle of the lane marking relative to a horizontal axis, a vertical axis, or any other suitable axis.

[0039] At step 460, the method 400 includes capturing a second frame of roadway data, i.e., the image collection device 120 may capture a frame of the roadway 158 at a time after the first frame of roadway data was captured.

[0040] At step 470, method 400 includes isolating individual lane markings from within the second frame of image data of the roadway, i.e., artificial intelligence device 130, a user utilizing user interface 142, or any other suitable device capable of isolating individual lane markings may isolate the lane markings from the second frame of roadway data.

[0041] That is, the artificial intelligence device 130, a user utilizing the user interface 142, or any other device capable of isolating pixels may isolate the pixels that make up the lane markings from the second frame of roadway data.

[0042] At step 480, the method 400 includes placing a bounding box around the pixels forming the lane markings from the second frame of roadway data, i.e., the system 100 may place a shape around the lane markings to identify the lane markings in the second frame of roadway data.

[0043] At step 490, the method 400 includes determining an angle of the lane marking relative to an axis in the second frame of roadway data. That is, the system 100 may measure the angle of the lane marking in the second frame of roadway data relative to a horizontal axis, a vertical axis, or any other suitable axis. The axis used to measure the angle of the lane marking from the first frame of roadway data 160 should be the same axis used to measure the angle of the roadway marking from the second frame of roadway data.

[0044] At step 4100, the method 400 includes determining whether an angle of the lane mark from the first frame 160 of roadway data matches an angle of the lane mark from the second frame of roadway data. That is, the system 100 may compare the angle of the lane mark from the first frame 160 of roadway data with the angle of the lane mark from the second frame of roadway data. If the angle of the lane mark from the first frame 160 of roadway data is within a predetermined threshold range of the angle of the lane mark from the second frame of roadway data, the method proceeds to step 4110. If the angle of the lane mark from the first frame 160 of roadway data is not within a predetermined threshold range of the angle of the lane mark from the second frame of roadway data, the method proceeds to step 4120.

[0045] At step 4110, method 400 includes associating the unique identifier associated with the lane mark in the first frame 160 of roadway data to the lane mark in the second frame of roadway data. That is, system 100 may determine that the lane mark in the first frame 160 of roadway data is the same lane mark as the lane mark in the second frame of roadway data, and thus maintain the same unique identifier across multiple frames of roadway data.

[0046] At step 4120, method 400 includes associating a new unique identifier with the lane marking in the second frame of roadway data. That is, system 100 may determine that the roadway marking in the second frame of roadway data is a different lane marking than the lane marking in the first frame of roadway data 160, and thus a new unique identifier should be associated with the roadway marking in the second frame of roadway data.

[0047] 5, a method 500 is shown consistent with an embodiment of the present disclosure. The method 500 is directed to tracking roadway marks. At step 510, the method 500 includes capturing a first frame 160 of roadway data. That is, the image collection device 120 may capture a frame of the roadway 158.

[0048] At step 520, the method 500 includes isolating individual lane markings from within the first frame of roadway image data. That is, the artificial intelligence device 130, a user utilizing the user interface 142, or any other suitable device capable of isolating individual lane markings may isolate the lane markings from the first frame 160 of roadway data.

[0049] At step 530, the method 500 includes placing a bounding box around the pixels forming the lane markings, i.e., the system 100 may place a shape around the lane markings to identify the lane markings within the first frame 160 of roadway data.

[0050] At step 540, method 500 includes assigning a unique identifier to the bounding box. That is, system 100 may assign a unique identifier, such as an alphanumeric string, a shape, or a color, to the bounding box to distinguish the bounding box and isolated lane markings from other bounding boxes and isolated lane markings.

[0051] At step 550, method 500 includes determining a location of image collection device 120 and mapping the lane marks identified in the first frame of roadway data 160 onto a map contained within map device 144. In an embodiment, image collection device 120 may be associated with vehicle 102, which may have a GPS device associated therewith.

[0052] In step 560, the method 500 includes determining the angle of the lane marking relative to an axis, i.e., the system 100 may measure the angle of the lane marking relative to a horizontal axis, a vertical axis, or any other suitable axis.

[0053] At step 570, the method 500 includes capturing a second frame of roadway data. That is, the image collection device 120 may capture a frame of the roadway 158 at a time after the image collection device 120 captured the first frame of roadway data 160.

[0054] At step 580, the method 500 includes isolating the individual lane markings from within the second frame of image data of the roadway, i.e., the artificial intelligence device 130, a user utilizing the user interface 142, or any other suitable device capable of isolating individual lane markings may isolate the lane markings from the second frame of roadway data.

[0055] The method 500 includes isolating pixels of the second frame of roadway data that form the lane markings, i.e., the artificial intelligence device 130, a user utilizing the user interface 142, or any other device capable of isolating pixels may isolate the pixels that make up the lane markings from the second frame of roadway data.

[0056] At step 590, the method 500 includes placing a bounding box around the pixels forming the lane marking from the second frame of roadway data, i.e., the system 100 may place a shape around the lane marking to identify the lane marking in the second frame of roadway data.

[0057] In step 5100, the method 500 includes determining the angle of the lane mark relative to an axis. That is, the system 100 may measure the angle of the lane mark relative to a horizontal axis, a vertical axis, or any other suitable axis. The axis used to measure the angle of the roadway mark from the first frame 160 of roadway data should be the same axis used to measure the angle of the roadway mark from the second frame of roadway data.

[0058] In step 5110, the method 500 includes determining a trajectory acquired by the image collection device 120 between the first frame of roadway data 160 and the second frame of roadway data, and adjusting the axis lines based on the trajectory acquired by the image collection device 120. That is, if the trajectory acquired by the image collection device 120 veers left between the first frame of roadway data 160 and the second frame of roadway data, the system 100 may adjust the axis lines to compensate for the change in orientation of the image collection device 120 between the first frame of roadway data 160 and the second frame of roadway data.

[0059] At step 5120, the method 500 includes determining whether the angle of the lane mark from the first frame 160 of roadway data matches the angle of the lane mark from the second frame of roadway data. That is, the system 100 may compare the angle of the lane mark from the first frame 160 of roadway data with the angle of the lane mark from the second frame of roadway data. If the angle of the lane mark from the first frame 160 of roadway data matches the angle of the lane mark from the second frame of roadway data, the method proceeds to step 5130. If the angle of the lane mark from the first frame 160 of roadway data does not match the angle of the lane mark from the second frame of roadway data, the method proceeds to step 5140.

[0060] At step 5130, method 500 includes associating the unique identifier associated with the lane mark in the first frame 160 of roadway data to the lane mark in the second frame of roadway data. That is, system 100 may determine that the lane mark in the first frame 160 of roadway data is the same lane mark as the lane mark in the second frame of roadway data, and thus maintain the same unique identifier across multiple frames of roadway data.

[0061] At step 5140, method 500 includes associating a new unique identifier with the lane mark in the second frame of roadway data. That is, system 100 may determine that the roadway mark in the second frame of roadway data is a different lane mark than the lane mark in the first frame of roadway data 160, and therefore a new unique identifier should be associated with the roadway mark in the second frame of roadway data.

[0062] Thus, embodiments of the present disclosure provide methods and systems for more effectively and efficiently tracking roadway lane marks and navigating a vehicle using the tracked roadway lane marks. In particular, the methods and systems may isolate pixels comprising roadway lane marks from frames of roadway image data to limit the amount of computational power required to track lane marks between frames of roadway image data. In embodiments, the systems may be used to navigate a vehicle such that the vehicle tracks identified roadway marks along the roadway in order to follow the curvature of the roadway, perform lane change maneuvers, or be otherwise navigated.

[0063] It may be noted that one or more of the following claims utilize the terms "where," "wherein," or "in which" as transitional phrases. For purposes of defining the present technology, it may be noted that these terms are introduced in the claims as open-ended transitional phrases used to introduce a description of a series of features of a structure, and are to be interpreted in a similar manner to the more commonly used open-ended preamble term "comprising."

[0064] It is understood that any two quantitative values ​​assigned to a property may constitute a range for that property, and all combinations of ranges formed from all recited quantitative values ​​for a given property are contemplated in this disclosure.

[0065] Although the subject matter of the present disclosure has been described in detail by referring to certain embodiments, it may be noted that various details described in the present disclosure should not be considered as implying that the details relate to elements that are essential components of the various embodiments described in the present disclosure, even if a particular element may be shown in each of the drawings accompanying this specification. Rather, the claims attached hereto should be considered as the only representation of the breadth of the present disclosure and the corresponding scope of the various embodiments described in the present disclosure. Moreover, it will be apparent that modifications and variations are possible without departing from the scope of the appended claims.

Claims

1. 1. A method for detecting roadway lane markings, the method comprising: collecting a frame of image data of a roadway; isolating a first individual lane marking from within the frame of image data of the roadway; assigning an identifier to the first separated individual lane marking; comparing the first isolated individual lane markings to a next frame of image data of the roadway; A method comprising:

2. determining an angle of the first separated individual lane marking relative to an axis; comparing the angle of the first separated individual lane marking relative to the axis with an angle of the first separated individual lane marking from a next frame of the image data of the roadway relative to the axis; The method of claim 1 further comprising:

3. The method of claim 1 , wherein isolating the first individual lane markings from the frame of image data of the roadway is performed by an artificial intelligence model.

4. The method of claim 1 , wherein isolating the first individual lane markings from the frame of image data of the roadway occurs on a user interface.

5. The method of claim 1 , further comprising navigating a vehicle using the first separated individual lane markings.

6. The method of claim 1 , further comprising mapping the first separated individual lane marks onto a map.

7. isolating a second individual lane marking from within the frame of image data of the roadway; and defining a first lane of the roadway between the first separated individual lane marking and the second separated individual lane marking; The method of claim 1 further comprising:

8. isolating a third individual lane marking from within the frame of image data of the roadway; and defining a second lane of the roadway between the second separated individual lane marking and the third separated individual lane marking; The method of claim 7 further comprising:

9. The method of claim 1 , wherein collecting the frames of image data of the roadway is performed by a forward-facing camera on a vehicle.

10. The method of claim 9 , further comprising: a difference between the frame of image data of the roadway and a subsequent frame of image data of the roadway being corrected for vehicle trajectory.

11. The method of claim 1 , wherein isolating isolated individual lane markings from the frame of roadway image data further comprises placing a bounding box around the isolated lane markings.

12. 12. The method of claim 11, wherein the step of isolating a lane marking from the frame of roadway image data and placing the bounding box around the isolated lane marking further comprises associating a unique identifier with the bounding box.

13. 1. A vehicle navigation system, comprising: Vehicles and an image acquisition device disposed in the vehicle; A processor; A vehicle controller; Equipped with A vehicle navigation system, wherein the image collection device, the processor, and the vehicle controller are connected to each other via a network, and the processor can receive input data from the image collection device, isolate lane markings in the input data, and send an output to the vehicle controller for controlling the vehicle.

14. The vehicle navigation system of claim 13 , further comprising an artificial intelligence device, said artificial intelligence device connected to said image collection device, said processor, and said vehicle controller through said network.

15. 15. The vehicle navigation system of claim 14, wherein the artificial intelligence device stores an artificial intelligence model, the artificial intelligence model configured to isolate individual lane markings of roadway data.

16. The vehicle navigation system of claim 13 , wherein the output sent from the processor causes the vehicle controller to control the vehicle to follow a curvature in a roadway.

17. 17. The vehicle navigation system of claim 16, wherein the output transmitted from the processor tracks one or more isolated roadway lane markings.

18. The vehicle navigation system of claim 13 , wherein the output transmitted from the processor causes the vehicle controller to control the vehicle to perform a lane change maneuver.

19. The vehicle navigation system of claim 13 , further comprising a user interface communicatively connected to the vehicle navigation system.

20. 20. The vehicle navigation system of claim 19, wherein the user interface is configured to allow a user to isolate pixels of roadway data that comprise lane markings.

Images