Methods for quantifying lane color changes

By installing image sensors and processing units on vehicles, and using object detection and paint degradation models to evaluate the paint quality of lane markings, the navigation difficulties caused by paint deterioration are solved, improving the accuracy and safety of autonomous driving.

CN123065979APending Publication Date: 2026-11-10GM GLOBAL TECHNOLOGY OPERATIONS LLC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510917377.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2025-05-07
Filing Date
2025-07-03
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Lane marking paint deteriorates due to weather and traffic flow, making it difficult to effectively assess its quality level and affecting navigation and safety of autonomous and semi-autonomous vehicles.

Method used

By installing image sensors and processing units on vehicles, the system can assess in real time whether road surfaces meet qualification requirements, capture images, and determine paint quality levels using object detection models and paint degradation models. It also provides paint quality analysis by combining color processing and filter techniques.

Benefits of technology

It enables accurate assessment of lane marking paint quality, reduces the need for data collection and processing resources, and improves navigation accuracy and safety in autonomous vehicles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123065979A_ABST
    Figure CN123065979A_ABST
Patent Text Reader

Abstract

A method for quantifying lane color changes is provided. A method and system for determining the paint quality level of lane markings on a road surface as a vehicle travels along it are also provided. A sensed data stream indicating the road surface is received, and it is determined whether the road surface meets the eligibility requirements for determining the paint quality level of lane markings associated with it. Based on whether the road surface is eligible for paint quality level determination, an image of the road surface along the road traveled by the vehicle is captured. An object detection model is used to detect the presence of lane markings on the road surface within the captured image. Based on a paint quality degradation model and paint color, the paint quality level for the detected lane markings is determined.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The technical field generally relates to determining the paint quality level for lane markings associated with vehicles, and more specifically to methods and systems for determining the paint quality level of lane markings on a road surface using vehicle systems while a vehicle is traveling along the road surface. Background Technology

[0002] Around the world, cities and states use painted lane markings on roadways to communicate information and guide drivers through traffic flow. In some forms, semi-autonomous and fully autonomous vehicles may also use lane markings as part of their driving systems to navigate roadway terrain. The paint used to create lane markings can deteriorate over time due to weather and / or continuous exposure to various traffic flows, thus requiring repair.

[0003] This disclosure addresses the aforementioned issues and more. Summary of the Invention

[0004] In one embodiment, the technology disclosed herein includes a method for determining a paint quality level for lane markings on a road surface while a vehicle is traveling along the road surface. The lane markings comprise two-dimensional objects formed by paint extending over at least a portion of the road surface, and the paint has a paint color. The method includes: receiving a sensing data stream from an image sensor associated with the vehicle, indicating the presence of an obstacle on the road surface; and, based at least on the sensing data stream, using a processing unit of the vehicle to evaluate whether the road surface meets qualification requirements for determining a paint quality level for the road surface. The qualification requirements indicate whether the road surface is qualified to determine a paint quality level and trigger a period of time for capturing one or more images of the road surface. The method includes: capturing images of the road surface along the road traveled by the vehicle using an image sensor based on whether the road surface meets the qualification requirements; detecting the presence of lane markings on the road surface within the captured images using an object detection model of the vehicle; and determining a paint quality level for the detected lane markings using a paint quality degradation model and paint color using a processing unit of the vehicle.

[0005] In some forms of this technology, the method includes determining whether a driving event is occurring in the vehicle. In some examples, a driving event indicates that the vehicle is traveling along a road. The method also includes determining whether the road surface meets qualification requirements while a driving event is occurring.

[0006] In one aspect of the technology, the step of assessing whether a road surface meets the qualification requirements includes: using an image sensor to detect whether there is an obstacle on the road surface; using a processing unit to determine whether there is a paint quality level for the road surface; based on the determination that there is a paint quality level for the road surface, using the processing unit to determine whether a predetermined time threshold has expired for the paint quality level for lane markings on the road surface; and using the processing unit to determine that the road surface does not meet the qualification requirements when at least one of the following exists: i) there is an obstacle on the road surface, ii) there is a paint quality level for the road surface, iii) a predetermined time frame associated with the paint quality level for lane markings has not expired, or iv) a combination thereof.

[0007] In another form of the technology, the step of assessing whether a road surface meets the eligibility requirements further includes: using an image sensor to detect whether there are obstacles on the road surface; determining whether there is a paint quality level for the road surface; determining whether there is a paint quality level for the road surface; based on the determination of the paint quality level, determining whether a predetermined time threshold has expired for the paint quality level for the road surface; and determining that the road surface meets the eligibility requirements when at least one of the following conditions is met: i) there are no obstacles on the road surface, ii) there is no paint quality level for the road surface, iii) a predetermined time frame associated with the paint quality level for the road surface has expired, or iv) a combination thereof.

[0008] In some aspects of the technology, the method includes: using a processing unit to determine the distance traveled by a vehicle on a road; using the processing unit to determine whether the distance traveled by the vehicle exceeds a predetermined threshold; and when the distance traveled exceeds the predetermined threshold, using the processing unit to determine a subsequent paint quality level for subsequent lane markings on subsequent road surfaces using steps a) to e).

[0009] In at least one form of the technology, the method further includes: receiving location data indicating the position of a vehicle along a road; using a processing unit to determine lane mark positions for lane markings on the road surface in a captured image based on the vehicle's location data; using the processing unit to store paint quality level, timestamp, and lane mark positions associated with the lane marks as lane mark data in a local database within the vehicle; and sending the lane mark data to a remote server outside the vehicle.

[0010] In some aspects of this technology, the method also includes receiving multiple lane marking data. In some forms, each lane marking data is associated with a corresponding road surface, and the lane marking data transmitted from the vehicle is at least one of the multiple lane marking data. The method also includes: generating a lane marking data list as a lane marking priority list based on the lane marking data from the multiple lane marking data, according to their respective paint quality levels; and displaying the lane marking data list via a visual display.

[0011] In some forms of this technology, the step of determining the paint quality level for lane markings in an image includes: processing the blue, green, and red colors of the image into hue, saturation, and lightness colors to form a color-processed image; converting the color-processed image with hue, saturation, and lightness levels into a yellow binary image using a yellow filter and bitwise operations; and counting each non-zero yellow pixel in the yellow binary image. The yellow binary image includes non-zero yellow pixels and zero-value black pixels. The step of determining the paint quality level for lane markings in an image also includes: using a processing unit to determine the total number of pixels in the yellow binary image; and using the processing unit to determine the paint quality level for the lane markings based on the total number of pixels and the number of non-zero yellow pixels.

[0012] In one aspect of this technology, the step of determining the paint quality level for lane markings in an image further includes: converting the blue, green, and red colors of the processed image to grayscale colors to form a grayscale image; and converting the grayscale image to a white binary image using a white filter and bitwise operations. The white binary image includes non-zero white pixels and zero-value black pixels. The step of determining the paint quality level for lane markings in an image further includes: counting the non-zero white pixels in the white binary image; counting the total number of pixels from the binary image; and determining the paint quality level for the lane markings based on the total number of pixels and the number of non-zero white pixels.

[0013] In another form of this technology, the step of determining the paint quality level for lane markings in an image further includes: cropping the image to modify at least a portion of the image, thereby adjusting the size, shape, or combination thereof of the lane markings detected in the image to form a first cropped image and a second cropped image; processing the blue, green, and red color scales of the first cropped image using hue, saturation, and lightness to produce contrasting pixel colors within the first cropped image, thereby forming a color-processed image; and converting the color-processed image into a yellow binary image using a yellow filter and bitwise operations. The yellow binary image includes non-zero yellow pixels and zero-value black pixels. The step of determining the paint quality level for lane markings in an image further includes: counting each non-zero yellow pixel in the yellow binary image; determining the total number of pixels in the yellow binary image; determining the yellow paint quality level for the lane markings based on the total number of pixels and the number of non-zero yellow pixels; converting the blue, green, and red colors of the second cropped image into grayscale colors to form a grayscale image; and converting the grayscale image into a white binary image based on a white filter and bitwise operations. The white binary image includes non-zero white pixels and zero-value black pixels. The step of determining the paint quality level for lane markings in an image further includes: counting non-zero white pixels in a white binary image; counting the total number of pixels from the white binary image; determining the white paint quality level for lane markings based on the total number of pixels and the number of non-zero white pixels in the white binary image; and selecting either the yellow paint quality level or the white paint quality level based on the fact that at least one of the yellow paint quality level or the white paint quality level is below a predetermined threshold.

[0014] In some aspects of this technology, the method includes: receiving latitude and longitude coordinates for each data point of a lane marker; determining the location of the lane marker based on the latitude and longitude coordinates; and determining multiple property details associated with the location of the lane marker. In some forms, the multiple property details include at least one of road name, city name, state name, and road type to form property data. The method also includes: aggregating the property data with lane marker data to form lane property data; and displaying the lane property data as mapping data on a digital map to be displayed to a user.

[0015] In another embodiment, the technology includes a vehicle system for determining a paint quality level for lane markings on a road surface as the vehicle travels along the road surface. Lane markings comprise two-dimensional objects formed by paint extending over at least a portion of the road surface, and the paint has a paint color. The vehicle system includes a paint quality determination module with a processing unit configured to: a) receive a sensing data stream indicating the presence of obstacles on the road surface using an image sensor associated with the vehicle; and b) use the vehicle's processing unit to determine whether the road surface meets qualification requirements for determining a paint quality level for the road surface. In some forms, qualification requirements indicate whether the road surface is qualified to determine a paint quality level and trigger a period of time for capturing one or more images of the road surface. The processing unit is also configured to: c) capture images of the road surface along the road the vehicle is traveling along using an image sensor based on whether the road surface is qualified to determine a paint quality level; d) detect the presence of lane markings on the road surface within the captured images using an object detection model of the vehicle; and e) determine a paint quality level for the detected lane markings using the vehicle's processing unit based on a paint quality degradation model and paint color.

[0016] In one form of this technology, the processing unit is further configured to determine whether a driving event is occurring in the vehicle. In some forms, the driving event indicates that the vehicle is traveling along a road. The processing unit is also configured to, when a driving event is occurring, determine, based on image data, whether the road surface meets the qualification requirements for determining the coating quality level.

[0017] In some aspects of this technology, the processing unit is configured to determine whether the road surface meets the qualification requirements for determining the paint quality level, and is further configured to: use an image sensor to detect whether there is an obstacle on the road surface; determine whether there is a previously determined paint quality level for lane markings in a captured image; based on the determination that there is a previously determined paint quality level for lane markings associated with the road surface, determine whether a predetermined time threshold has expired for the previously determined paint quality level for lane markings associated with the road surface; and determine that the road surface does not meet the qualification requirements for determining the paint quality level for lane markings associated with the road surface when at least one of the following exists: i) there is an obstacle on the road surface, ii) there is a paint quality level for the road surface; iii) the predetermined time threshold has not expired for the previously determined paint quality level associated with the road surface, or iv) a combination thereof.

[0018] In some forms of this technology, the processing unit is configured to determine whether to capture an image of the road surface, including: detecting whether there are obstacles on the road surface; determining whether there is a paint quality level for the road surface; based on the determination that there is a paint quality level for the road surface, determining whether a predetermined time threshold has expired for the paint quality level for the road surface; and determining that the road surface meets the eligibility requirements when at least one of the following conditions is met: i) there are no obstacles on the road surface in the image data, ii) there is no paint quality level for the road surface, iii) a predetermined time frame associated with the paint quality level for the road surface has expired, or iv) a combination thereof.

[0019] In some aspects of this technology, the processing unit is also configured to: determine the distance the vehicle has traveled on the road; determine whether the distance traveled by the vehicle exceeds a predetermined threshold; and when the distance traveled exceeds the predetermined threshold, use steps a) to e) to determine the quality level of subsequent paint for subsequent lane markings on subsequent road surfaces.

[0020] In one form of the technique, the processor is configured to determine the paint quality level for lane markings in a captured image, and further includes: cropping the image to modify at least a portion of the image to adjust the size, shape, or combination thereof of the lane markings detected in the image to form a cropped image; adjusting the color scale of the cropped image to form contrasting pixel colors within the cropped image to form a color-scaled image; converting the color-scaled image into a binary image based on bitwise operations and a color filter; and determining the paint quality of the lane markings based on the binary image and the color filter.

[0021] In at least one aspect of the technology, the processing unit is configured to determine the paint quality level for lane markings in an image, and further includes: cropping the captured image to adjust the size, shape, or combination thereof of the lane markings detected in the image to form a cropped image; processing the blue, green, and red colors of the cropped image into hue, saturation, and lightness colors to form a color-processed image; converting the color-processed image into a yellow binary image using a yellow filter and bitwise operations; counting each non-zero yellow pixel in the yellow binary image; determining the total number of pixels in the yellow binary image; and determining the paint quality of the lane markings based on the total number of pixels and the number of non-zero yellow pixels.

[0022] In some forms of this technology, the processing unit is configured to determine the paint quality level for lane markings in an image, which further includes: cropping the captured image to adjust the size, shape, or combination thereof of the lane markings detected in the image to form a cropped image; converting the blue, green, and red colors of the cropped image to grayscale colors to form a grayscale image; converting the grayscale image to a white binary image using a white filter and bitwise operations; counting each non-zero white pixel in the white binary image; counting the total number of pixels from the white binary image; and determining the paint quality of the lane markings based on the total number of pixels and the number of non-zero pixels.

[0023] In another embodiment, the technology includes a method for determining a paint quality level for lane markings on a road surface while a vehicle is traveling along the road surface. The lane markings comprise a two-dimensional object formed by paint extending over at least a portion of the road surface, and the paint has a paint color. The method includes: a) determining whether a driving event is occurring in the vehicle, wherein the driving event indicates that the vehicle is traveling along the road; b) when the driving event is occurring, receiving a sensing data stream indicating the presence of an obstacle on the road surface using an image sensor associated with the vehicle; c) based at least on the sensing data stream, using a processing unit to evaluate whether the road surface meets qualification requirements for determining a paint quality level for the road surface. The qualification requirements indicate whether the road surface is qualified to determine a paint quality level and trigger a period of time for capturing one or more images of the road surface. The step of assessing whether the road surface meets the eligibility requirements for determining the paint quality level is further configured to: use an image sensor to detect whether there are obstacles on the road surface; determine whether there is a paint quality level for the road surface; based on the determination that there is a paint quality level for the road surface, determine whether a predetermined time threshold has expired for the paint quality level for the road surface; determine that the road surface meets the eligibility requirements when each of the following conditions is met: i) there are no obstacles on the road surface in the image data, ii) there is no paint quality level for the road surface, and iii) the predetermined time frame associated with the paint quality level for the lane markings has expired; and determine that the road surface does not meet the eligibility requirements when each of the following conditions is met: i) there are obstacles on the road surface, ii) there is a paint quality level for the road surface, and iii) the predetermined time frame associated with the paint quality level for the road surface has not yet expired. The method further includes: d) capturing an image of the road surface along the road where the vehicle is traveling, based on whether the road surface meets eligibility requirements; e) detecting the presence of lane markings on the road surface within the captured image using an object detection model, wherein lane markings include paint colors that are white, yellow, or combinations thereof; and f) determining a paint quality level for the detected lane markings using a processing unit based on a paint quality degradation model and paint color, wherein the captured image includes a first image and a second image as a copy of the first image. The step of determining the paint quality includes: cropping the first image to adjust the size, shape, or combination thereof of the lane markings detected in the image to form a first cropped image; processing the blue, green, and red colors of the first cropped image into hue, saturation, and lightness colors to form a first color-processed image; and converting the color-processed image into a yellow binary image using a yellow filter and bitwise operations. The yellow binary image includes non-zero yellow pixels and zero-value black pixels.The steps for determining paint quality further include: counting each non-zero pixel in the yellow binary image; determining the total number of pixels in the yellow binary image; determining a yellow paint quality level for the lane markings based on the total number of pixels and the number of non-zero yellow pixels; converting the blue, green, and red colors of the second cropped image to grayscale colors to form a grayscale image; and processing the grayscale image into a white binary image using a white filter and bitwise operations. The white binary image includes non-zero white pixels and zero-value black pixels. The steps for determining paint quality further include: counting each non-zero white pixel in the white binary image; counting the total number of pixels from the white binary image; determining a white paint quality level for the lane markings based on the total number of pixels and the number of non-zero white pixels; and selecting either a yellow paint quality level or a white paint quality level based on at least one of the yellow paint quality level or the white paint quality level being below a predetermined threshold. Attached Figure Description

[0024] Exemplary embodiments will now be described in conjunction with the following figures, wherein similar numerals denote similar elements, and wherein:

[0025] Figure 1 This is a schematic diagram of an exemplary user environment for performing a method to determine the paint quality level of lane markings on a road surface in a vehicle traveling along a road.

[0026] Figure 2 This is an overview reference. Figure 1 Flowchart of the publicly disclosed method;

[0027] Figure 3 yes Figure 2 The flowchart of the routine used in the method to determine whether the road surface is eligible to determine the paint quality level for lane markings;

[0028] Figure 4 This is a flowchart of a routine used to determine the paint quality level for detected lane markings based on a paint degradation model;

[0029] Figure 5 This is an operation reference. Figure 1 and Figure 2 A system block diagram of the disclosed method; and

[0030] Figure 6 yes Figure 5 The diagram shows the block diagram of the coating quality determination module of the system. Detailed Implementation

[0031] The following detailed description is merely exemplary in nature and is not intended to limit application and use. Furthermore, it is not intended to be bound by any express or implied theory presented in the foregoing technical field, background art, summary of the invention, or the following detailed description. As used herein, the term "module" means application-specific integrated circuit (ASIC), electronic circuitry, processor (shared, dedicated, or grouped) and memory executing one or more software or firmware programs, combinational logic circuitry, and / or other suitable components providing the described functionality.

[0032] In one form, the technology described in this disclosure includes methods and systems for determining the paint quality level of lane markings applied to a road surface for vehicles to travel along. Benefits of the described technology include scaling capabilities and the ability to prioritize roads that may require repainting. Another benefit of the technology includes eligibility requirements for determining when to begin collecting image-related data in a vehicle to determine the paint quality level for lane markings. These eligibility requirements allow the vehicle to collect data only if its requirements are met. Therefore, this limits the amount of data collected by the vehicle and restricts the vehicle's processing resource requirements. Another benefit includes onboard analysis of paint quality levels, which limits the bandwidth and data processing resources and costs associated with offboarding data (such as image data). Furthermore, the transmission of image data is not limited to small-packet data transmission. Yet another benefit of the technology includes processes for quantifying and qualitatively characterizing roads in semi-autonomous and fully autonomous vehicles for mapping and driving. Another benefit of the technology includes using multiple cameras at various locations and angles around the vehicle to capture image data. Another benefit includes using a single frame image at any desired time to determine the paint quality level of lane markings. Another benefit of this technology includes the use of image processing filters to provide greater accuracy when detecting and assessing the paint quality level of lane markings.

[0033] refer to Figure 1This provides an environmental view of method 100 and system 200, as well as a method for determining the paint quality level for lane markings (also known as road markings or paving markings). As shown, a vehicle 106 travels along a road 108 having a pavement 104 with multiple lane markings 102. In one form, lane markings 102 are applied to pavement 104 to indicate traffic lanes and inform drivers and pedestrians of such marked traffic lanes. In some forms, lane markings 102 are also used to divide lanes, provide instructions to navigate vehicles from one lane to another, and guide vehicles to stop. Typically, lane markings 102 comprise two-dimensional objects coated on pavement 104 that cover at least a portion of pavement 104 of road 108. Lane markings 102 are typically white, yellow, or a combination thereof. In some forms, lane markings 102 may include paint of any color. For example, lane marking 102 may resemble at least one of the following: a single solid yellow line, double solid yellow lines, dashed yellow lines, a single solid white line, double solid white lines, dashed white lines, lane end markings, right-turn arrows, left-turn arrows, multi-color road markings for guiding vehicles to highway lanes, etc. In one form, system 200 includes vehicle 106 and a remote server 110 communicating with vehicle 106.

[0034] like Figure 1 As shown, when vehicle 106 travels along road 108, system 200 captures an image of lane markings 102 on road surface 104 of road 108 and determines the paint quality level associated with the lane markings 102 captured in the image. The paint quality level indicates paint characteristics that visibly demonstrate the integrity of the lane markings 102. For example, the paint quality level indicates the area of ​​paint on road surface 104. In other examples, the paint quality level indicates paint quantity, paint density, paint strength, color contrast, or a combination thereof. In one form, the integrity of lane markings 102 indicates a predetermined minimum threshold of the amount of lane marking paint area required for a driver to visually identify the corresponding lane marking. For example, lane marking integrity can be defined as requiring a minimum acceptable paint coverage of 40% for the corresponding lane marking to be identified by the driver.

[0035] refer to Figure 2The method 100 for determining the paint quality level of lane markings 102 for road surface 104 will now be discussed in more detail. As described above, method 100 is utilized and executed by system 200. System 200 initiates at a start and proceeds to routine 300. At routine 300, system 200 determines whether a driving event is occurring in vehicle 106. A driving event indicates that vehicle 106 is traveling along road 108. In one form, routine 300 receives sensed motion data from at least one of a plurality of sensors 112, such as a vehicle motion detection sensor 114 located in vehicle 106. In one example, vehicle motion detection sensor 114 may include at least one of the following sensor types: accelerometer, gyroscope, global positioning system (GPS) sensor, combinations thereof, etc. The accelerometer senses the acceleration of vehicle 106 and outputs sensed motion data in response. The gyroscope senses the rotational motion of vehicle 106 and outputs sensed motion data in response. The GPS sensor detects the position of vehicle 106 in longitude and latitude coordinates, processes the longitude and latitude coordinates, and outputs sensed motion data. System 200 determines whether a driving event is occurring based on the sensed motion data. If a driving event is occurring, system 200 determines "yes" and proceeds from routine 300 to routine 400. If a driving event is not occurring, system 200 determines "no" and proceeds to the end to return to the beginning.

[0036] At routine 400, system 200 assesses whether the road surface meets predetermined qualification requirements for determining the paint quality level for lane marking 102. Qualification requirements indicate whether road surface 104 is qualified to determine the paint quality level and trigger a period for capturing an image of road surface 104. For example, qualification requirements include determining that the road surface and / or the image of the road surface is free of obstructions. Obstructions include objects that obscure at least a portion of road surface 104. For example, obstacles include debris or environmental elements covering at least a portion of the road surface, preventing it from being processed by system 200. In one form of this technique, image sensor 116 scans road surface 104 adjacent to vehicle 106, detects the presence of obstructions on road surface 104, and outputs a sensing data stream in response. Based on the sensing data stream, system 200 determines whether road surface 104 meets the predetermined qualification requirements. If yes, system 200 proceeds from routine 400 to routine 500. If no, system 200 proceeds from routine 400 to the end to return to the beginning.

[0037] At routine 500, system 200 uses image sensor 116 to capture an image of road surface 104 along road 108 as vehicle 106 travels. For example, image sensor 116 captures an image of road surface 104 and outputs the image of the road surface, forming the captured image. In one form, the captured image includes single-frame still image data. In another example, the captured image includes moving image data. After capturing the image of road surface 104, system 200 proceeds from routine 500 to routine 600.

[0038] Using routine 600, system 200 uses object detection model 118 (see example 600). Figure 6 The system determines whether lane marking 102 exists within the captured image. The object detection model 118 locates and identifies lane marking 102 within the captured image. The object detection model 118 detects lane marking 102 in the captured image, classifies lane marking 102, and identifies and marks the location of lane marking 102 in the captured image using bounding boxes to delineate its location. If lane marking 102 is detected in the captured image, the system 200 determines "yes" and proceeds from routine 600 to routine 700. If lane marking 102 is not detected in the captured image, the system 200 determines "no" and proceeds from routine 500 to the end.

[0039] At routine 700, system 200 determines the paint quality level for the detected lane marking 102 based on paint degradation model 120. As previously mentioned, lane marking 102 has a paint color. Paint colors include white and / or yellow. In some forms, system 200 determines the paint quality level for the detected lane marking 102 based on paint degradation model 120 and the paint color associated with the detected lane marking 102. After determining the paint quality, in one form, system 200 proceeds from routine 700 to routine 800.

[0040] At routine 800, system 200 has lane color changing application 146 (see example 146). Figure 1The system 200 sends a paint quality level to the remote server 110 for further processing of the paint quality level for lane marking 102. In one embodiment, when vehicle 106 is traveling on road surface 104, system 200 receives location data indicating the vehicle's position. After receiving the vehicle position, system 200 determines the lane marking position based on the vehicle position. System 200 stores the corresponding paint quality level, timestamp, and lane marking position as a lane marking data record in paint quality database 126 within vehicle 106 and sends the lane marking data record to the remote server 110 outside vehicle 106. In some embodiments, system 200 may clear the lane marking data record from paint quality database 126 after confirming that the lane marking data record has been successfully sent to remote server 110. After sending the lane marking data record, system 200 proceeds from routine 800 to routine 900.

[0041] At routine 900, system 200 assesses whether a subsequent paint quality level has been determined for another or subsequent pavement 104. In one form, system 200 assesses the distance traveled by vehicle 106 since the paint quality level for lane marking 102 was determined. After assessing the distance traveled by vehicle 106, system 200 determines whether the distance traveled by vehicle 106 exceeds a predetermined distance threshold. For example, the predetermined distance threshold indicates how frequently subsequent images of pavement 104 are captured to determine the subsequent paint quality level. For example, the predetermined distance threshold is equal to five decimal places of latitude and five decimal places of longitude (e.g., 1 meter). If "yes," the system proceeds from routine 900 to routine 300 to determine the subsequent paint quality level for subsequent pavement 104. If "no," system 200 proceeds from routine 900 to the end.

[0042] Now go to Figure 3 Example 400 uses the paint quality determination module 122 (see...) Figures 5-6 The routine 400 assesses whether the road surface meets the qualification requirements for determining the paint quality level for lane marking 102. The routine begins at the start and proceeds to step 402. At step 402, the routine 400 receives a sensing data stream from image sensor 116 indicating the presence of an obstacle on the road surface. In one form, the obstacle includes image degradation, such as an occluded image, a blurred image, an underexposed image, etc. In another form, the obstacle includes a non-lane marking object (e.g., debris) covering the road surface 104 of road 108. In one form, image sensor 116 detects the presence of an obstacle on road surface 104 based on the detection of a driving event and outputs a sensing data stream in response. After receiving the sensing data stream, the routine 400 proceeds from step 402 to step 404.

[0043] At step 404, routine 300 uses paint quality determination module 122 to determine, in real-time or near real-time, the presence of an obstacle on road surface 104 based on the sensed data stream. Real-time or “near real-time” includes any time frame short enough to provide a reasonable response time for on-demand information processing, such as approximately one (1) second or within 1-2 seconds after scanning the road surface. Paint quality determination module 122 may employ image processing techniques such as edge detection, color segmentation, and machine learning to determine whether an obstacle obscures at least a portion of road surface 104. In one form, paint quality determination module 122 detects image degradation in the sensed data stream and outputs obstacle data indicating the presence of an obstacle. In another form, paint quality determination module 122 detects quality changes in the sensed data stream and outputs obstacle data indicating the presence of an obstacle. In one form, changes in the sensed data stream include changes in light intensity, at least a portion of the image being a blurred area, etc. In another embodiment, the paint quality determination module 122 detects when an object that is not a lane marking 102 or road surface 104 exists in the sensing data stream, and in response, outputs obstacle data indicating the presence of an obstacle. Based on the obstacle data, routine 400 determines whether an obstacle exists on the road surface. If an obstacle exists, routine 400 determines "yes" and proceeds from step 404 to step 412. On the other hand, if an obstacle does not exist, routine 400 determines "no" and proceeds from step 404 to step 406.

[0044] Routine 400 determines at step 406 whether a previously determined paint quality level exists for the location associated with the lane markings on the pavement 104 of road 108. In one form, routine 400 searches the paint quality database 126 (see [link to database]). Figure 5 This determines whether a previously determined paint quality level exists for the location associated with lane marking 102. In one form, a paint quality database 126 is located in vehicle 106. In another example, the paint quality database 126 may be located on a remote server 110. If "yes", routine 400 proceeds from step 406 to step 408. If "no", the routine proceeds from step 406 to step 410.

[0045] At step 408, routine 400 determines whether a predetermined time threshold has expired since the previously determined paint quality level was determined. In one form, the predetermined time threshold is defined by the time period that has elapsed since the paint quality level for lane marking 102 was determined. The predetermined time threshold may be determined based on the rate of decay of lane marking quality (such as paint type, paint brand, road age, pavement type, season, weather factors (temperature, precipitation, UV exposure), etc.). In this example, the predetermined time threshold is set to a 2-week time period. If "yes," routine 400 proceeds from step 408 to step 410. If "no," routine 400 proceeds from step 408 to step 412.

[0046] At step 410, routine 400 determines that road surface 104 meets the qualification requirements for determining a paint quality level for road surface 104. For example, the qualification requirements are met when at least one or more of the following conditions are met: i) there are no obstacles on road surface 104 in the image data; ii) a previously determined paint quality level for lane markings 102 on road surface 104 does not exist; and iii) a predetermined time frame associated with an existing predetermined paint quality level for lane markings 102 has expired. Routine 400 proceeds from step 410 to routine 500.

[0047] At step 412, routine 400 determines that pavement 104 does not meet the qualification requirements for determining a paint quality level for pavement 104. For example, the qualification requirements are not met when at least one or more of the following are present: i) there is an obstacle on pavement 104; ii) a paint quality level for pavement is present; iii) a predetermined time threshold has not yet expired for a previously determined paint quality level associated with pavement 104; or iv) a combination thereof. Routine 400 proceeds from step 412 to the end.

[0048] Go to Figure 4 Example 700 is based on paint degradation model 120 (see Figure 6The paint quality determination module 122 is used to determine the paint quality level for the detected lane marking 102. In one form, routine 700 begins at the start and proceeds to step 702. At step 702, routine 700 uses paint degradation model 120 to crop the captured image, thereby modifying the size, shape, or combination thereof of the lane marking 102 detected in the captured image to produce a cropped image with lane marking 102. In one example, routine 700 uses dimensions associated with a bounding box to crop the captured image to form a cropped image. The cropped image is then copied to form a first cropped image and a second cropped image. In one form, the first cropped image and the second cropped image are identical in size and shape and include the detected lane marking 102. After forming the first cropped image and the second cropped image, routine 700 proceeds from step 702 to step 704.

[0049] In step 704, routine 700 uses paint degradation model 120 to adjust the color scale of the cropped image to produce contrasting pixel colors within the cropped image, thereby forming a color-processed image. Lane markings 102 typically include paint colors that are white, yellow, or combinations thereof. In one form, routine 700 processes lane markings 102 in a first cropped image to have a yellow paint color. Routine 700 also processes lane markings 102 in a second cropped image to have a white paint color. In one form, routine 700 processes each of the first and second cropped images simultaneously. In other forms, routine 700 processes the first and second cropped images sequentially. In another aspect, routine 700 processes the red-green-blue (RGB) color scale of the first cropped image to produce a first plurality of contrasting pixels having hue, saturation, and value colors, thereby forming a first color-processed image. In a similar manner, routine 700 processes the RGB color scale of the second cropped image to produce a second plurality of contrasting pixels with a grayscale color scale, thereby forming a second color-processed image. After processing each of the first and second color-processed images, routine 700 proceeds from step 704 to step 706.

[0050] At step 706, routine 700 uses paint degradation model 120 to convert the color-processed image into a binary image based on a predetermined color filter and bitwise operations. Typically, bitwise operators perform operations to manipulate individual data bits (such as zeros and ones). Specifically, routine 700 uses a yellow filter mask and bitwise operations to convert the first color-processed image into a yellow binary image. The yellow binary image comprises non-zero yellow pixels and zero-value black pixels. For example, routine 700 applies a yellow filter with a lower limit of [15, 80, 80] and an upper limit of [35, 255, 255] to create a yellow filter mask. For each pixel in the first color-processed image, routine 700 applies bitwise operations and the yellow filter mask, thereby producing a yellow binary image. In a similar manner, routine 700 converts the second color-processed image into a white binary image based on a white filter mask and bitwise operations. The second color-processed image is a grayscale image processed to have black and white pixels. For example, if a pixel in the second color-processed image has an intensity between 0 and 200, then routine 700 processes the pixel as a black pixel and sets it to a default value of zero (0) intensity. On the other hand, if a pixel has an intensity between 201 and 255, then routine 700 processes the pixel as a white pixel and sets it to a default value of 255 intensity. In one form, the white filter mask includes an intensity filtering threshold between 200 and 255. For each pixel in the second color-processed image, routine 700 applies bitwise operations and the white filter mask and thereby produces a white binary image. The white binary image includes non-zero white pixels and zero-value black pixels. In one example, each pixel is defined by a numerical value to either be equivalent to black or equivalent to white based on its corresponding intensity value. After producing the yellow binary image and the white binary image, routine 700 proceeds from step 706 to step 708.

[0051] In step 708, routine 700 uses paint degradation model 120 to determine the paint quality level for lane marking 102 associated with a binary image. In one form, routine 700 counts each non-zero yellow pixel in the yellow binary image, determines the total number of pixels in the binary image, and calculates the yellow paint quality level based on the total number of pixels and the number of non-zero yellow pixels. The yellow paint quality level includes the value, percentage, or ratio of the number of non-zero yellow pixels in the yellow binary image to the total number of pixels. In another form, routine 700 counts non-zero pixels in the white binary image, counts the total number of pixels from the white binary image, and generates a white paint quality level based on the total number of pixels in the white binary image and the number of non-zero white pixels. Similar to the yellow paint quality level, the white paint quality level is a value between 0 and 1, equal to the percentage or ratio of the number of non-zero pixels to the total number of pixels in the white binary image. In one form, for lane marking 102, the higher the value, percentage, or ratio, the higher the amount of yellow or white paint color present. In contrast, for lane marking 102, the lower the value, percentage, or ratio, the lower the amount of yellow or white paint color present. In one form, routine 700 selects at least one of the yellow paint quality level and the white paint quality level for the detected lane marking. For example, if the yellow paint quality level is above a predetermined threshold and the white paint quality level is within a predetermined white threshold range, then routine 700 selects the yellow paint quality level. In one example, the predetermined threshold is essentially equal to zero (0). When the white paint quality level is above the predetermined threshold and the yellow paint quality level is within a predetermined threshold range, routine 700 selects the white paint quality level. When each paint quality level is within a predetermined threshold range, routine 700 may discard both the yellow and white paint quality levels. After determining the paint quality level, routine 700 proceeds from step 708 to routine 800.

[0052] Now for reference Figure 5 The diagram further illustrates a system 200 for implementing the method 100 having routines 300-900. In one form, system 200 includes multiple sensors 112, a paint quality determination module 122, a communication module 124, and a paint quality database 126. Sensors 112 include a vehicle motion detection (VMD) sensor 114 and an image sensor 116. The VMD sensor 114 detects the movement and position of vehicle 106 along road surface 104 and outputs motion data in response. In one example, the VMD sensor 114 includes onboard sensors such as an accelerometer, a gyroscope, a GPS sensor, or combinations thereof. The accelerometer senses the acceleration of vehicle 106 and outputs sensed motion data in response. The gyroscope senses the rotational motion of the vehicle and outputs a sensed motion data stream in response. The GPS sensor detects the position of the vehicle in longitude and latitude coordinates.

[0053] In one example, image sensor 116 is located around vehicle 106. For example, image sensor 116 includes at least one of the following: a digital camera, a camera module, a thermal imaging device, radar, sonar, combinations thereof, etc. For illustrative purposes, image sensor 116 is a camera module that scans road surface 104, detects the presence of obstacles on the road surface, and outputs a sensing data stream in response. In one form, the sensing data stream includes moving image data.

[0054] In another example, image sensor 116 captures a single-frame image of road surface 104 and outputs the captured image of road surface 104. In one form, the single-frame image includes a still image. In some examples, image sensor 116 includes multiple image sensors arranged at various locations around vehicle 106 to provide multiple angles for viewing road surface 104 to determine the paint quality level for a single lane marking 102 or multiple lane markings 102. For example, the multiple image sensors include a front image sensor, a rear image sensor, an undercarriage image sensor, a left image sensor, and a right image sensor relative to the vehicle. The front image sensor is located around the front of vehicle 106. The front image sensor captures an image of road surface 104 at the front position of vehicle 106 and outputs front image data in response. The rear image sensor is located around the rear of vehicle 106. The rear camera sensor captures an image of road surface 104 at the rear position of vehicle 106 and outputs rear image data in response. The undercarriage camera sensor is located on or near the underside of vehicle 106. A vehicle-mounted camera sensor captures images of the road surface 104 located beneath the vehicle 106 and outputs under-vehicle image data accordingly. A left-side camera sensor is located on or near the upper left side of the vehicle 106. The left-side camera sensor captures images of the road surface 104 located on the left side of the vehicle 106 and outputs left-side image data accordingly. A right-side camera sensor is located on the upper right side of the vehicle. The right-side camera sensor captures images of the road surface 104 located on the right side of the vehicle 106 and outputs right-side image data accordingly. Although each of the multiple image sensors can individually capture images of one or more road surfaces 104 and output one or more images accordingly, each of the front image sensor, rear image sensor, under-vehicle image sensor, right-side image sensor, and left-side image sensor has similar characteristics and functions and should be individually and collectively referred to as "image sensor 116".

[0055] Now for reference Figure 5 and Figure 6The paint quality determination module 122 communicates with multiple sensors 112 and receives motion data, sensing data streams, captured images of the road surface 104, or combinations thereof. The paint quality determination module 122 includes a driving event detector 130, a qualification determiner 132, an object detection model 118, a paint degradation model 120, and a distance detector 140.

[0056] The driving event detector 130 executes routine 300 and determines whether a driving event is occurring. A driving event indicates that vehicle 106 is traveling along road 108. The driving event detector 130 communicates with sensor 112. The driving event detector 130 receives motion data from VMD sensor 114 and determines whether a driving event is occurring based on the motion data.

[0057] The qualification determiner 132 communicates with the driving event detector 130 and the image sensor 116. The qualification determiner 132 executes routine 400 and, based at least on the sensed data stream, evaluates whether the road surface 104 meets the qualification requirements for determining the paint quality level for lane markings 102 associated with the road surface 104. The qualification requirements indicate whether the road surface 104 is qualified to determine the paint quality level and trigger a period of time for capturing one or more images of the road surface 104.

[0058] Object detection model 118 communicates with qualification determiner 132 and image sensor 116. Object detection model 118 executes routine 600 and determines whether lane marking 102 exists within the captured images. Object detection model 118 receives images captured from image sensor 116. Additionally, object detection model 118 locates and identifies lane marking 102 within each captured image, detects lane marking 102 in the captured images, classifies lane marking 102, and identifies and marks the location of lane marking 102 in the images. For illustrative purposes, object detection model 118 includes a machine learning model to classify lane marking 102 in the captured images and determine its location and orientation. In one example, the machine learning model includes at least one of several model architectures such as: one or more supervised learning models, one or more unsupervised learning models, and one or more neural network models (e.g., deep neural networks (DNNs), convolutional neural networks (CNNs), spiking neural networks (SNNs)).

[0059] Paint degradation model 120 communicates with object detection model 118. Paint degradation model 120 executes routine 700 and determines the paint quality level for lane marking 102 detected in the captured image. In one form, paint degradation model 120 employs one or more image processing techniques, such as an image editing process. For illustrative purposes, the image editing process includes at least one of a raster graphics editor or a vector graphics editor. As previously mentioned, lane marking 102 has a white and / or yellow paint color. Paint degradation model 120 determines the paint quality level for the detected lane marking 102 based on the paint color associated with the detected lane marking 102.

[0060] In one embodiment, as the vehicle travels on road surface 104, paint degradation model 120 receives location data indicating the vehicle's position. Upon receiving the vehicle position, paint degradation model 120 determines the lane marker position based on the vehicle position. Paint degradation model 120 stores the paint quality level, timestamp, and lane marker position associated with the detected lane marker 102 as lane marker data in a paint quality database within vehicle 106.

[0061] Paint degradation model 120 receives GPS coordinates for each data point of lane marking 102. Paint degradation model 120 aligns the GPS coordinates with each data point of lane marking 102 in the lane marking data. Paint degradation model 120 determines multiple property details associated with the location of lane marking 102. These multiple property details include at least one of road name, city name, state name, and road type to form property data. Paint degradation model 120 aggregates the property data with the lane marking data to form lane property data and stores the lane property data in paint quality database 126.

[0062] Distance detector 140 communicates with paint degradation model 120. Distance detector 140 executes routine 900 and determines whether a subsequent paint quality level for subsequent lane markings 102 associated with subsequent road surface 104 has been determined. Distance detector 140 determines the distance traveled by vehicle 106 since the paint quality level for lane markings 102 was determined. After determining the distance traveled by vehicle 106, distance detector 140 determines whether the distance traveled by vehicle 106 exceeds a predetermined distance threshold. In one example, the predetermined distance threshold identifies the frequency at which images of road surface 104 are captured to determine the paint quality level of lane markings 102. For example, the predetermined distance threshold is equal to five (5) decimal places of latitude and five (5) decimal places of longitude (e.g., 1 meter).

[0063] Communication module 124 communicates with paint degradation model 120 and remote server 110. Communication module 124 receives lane marking data and related data from paint quality database 126 and sends paint quality levels and lane marking data to remote server 110. In one embodiment, the remote server includes a cloud-based application 146, such as a lane color-changing application 146, to further process the paint quality level for lane marking 102. In some embodiments, lane color-changing application 146 generates a list of lane markings based on one or more priority factors and displays the list to a user for viewing. In one embodiment, communication module 124 clears the lane marking data from the paint quality database after sending the lane marking data.

[0064] Refer again Figure 1 Remote server 110 hosts cloud-based applications 146 for displaying a list of lane markings, such as lane color-changing applications 146 (see [link to application]). Figure 1 In one embodiment, cloud-based application 146 receives lane marking data associated with a corresponding road surface 104 and lane marking data transmitted from a vehicle. Cloud-based application 146 generates a priority list of lane markings based on multiple lane marking data sets. Cloud-based application 146 includes a visual display for displaying the lane marking priority list. Cloud-based application 146 can provide a graphical image of the lane marking list and its corresponding paint quality level in real time. Cloud-based application 146 can also display the lane marking priority list based on the paint quality level with the lowest value. Cloud-based application 146 can also display the lane marking priority list based on the corresponding attenuation value of the lane markings.

[0065] Cloud-based application 146 can also plot lane marking data on a digital map to display historical trend data. Cloud-based application 146 estimates the decay time length for lane marking 102 associated with the lane marking data by comparing the paint quality level of lane marking 102 with other historical data trends. Cloud-based application 146 determines whether supplementary data exists for further estimating when the paint quality level for lane marking 102 will reach a lower threshold with an unacceptable value. Supplementary data includes traffic volume, road decay data, road health data, road paint specifications, and road paint application date. Cloud-based application 146 receives at least one of traffic volume, road decay data, road health data, road paint specifications, and road paint application date, and calculates the estimated time when the paint quality level will reach the lower threshold for lane marking 102. Subsequently, cloud-based application 146 can display the estimated time to a user via a visual display.

[0066] While at least one exemplary embodiment has been presented in the foregoing detailed description, it should be understood that numerous variations exist. It should also be understood that the exemplary embodiments or multiple exemplary embodiments are merely examples and are not intended to limit the scope, applicability, or configuration of this disclosure in any way. Rather, the foregoing detailed description will provide those skilled in the art with a convenient roadmap for implementing the exemplary embodiments or multiple exemplary embodiments. It should be understood that various changes can be made to the function and arrangement of the elements without departing from the scope of this disclosure as set forth in the appended claims and their legal equivalents.

Claims

1. A method for determining the paint quality level of lane markings on a road surface using vehicles traveling along a road, wherein the lane markings comprise a coating object disposed on at least a portion of the road surface, the method comprising: a) Receive a sensing data stream from an image sensor associated with the vehicle, indicating whether an obstacle exists on the road surface; b) At least based on the sensed data stream, the vehicle's processing unit is used to evaluate whether the road surface meets the qualification requirements for determining the paint quality level for the road surface, wherein the qualification requirements indicate whether the road surface is qualified to determine the paint quality level, and triggers a period of time for capturing one or more images of the road surface; c) Based on whether the road surface meets the eligibility requirements, use the image sensor to capture an image of the road surface along the road the vehicle is traveling on; d) Use the vehicle's object detection model to detect whether the lane markings exist on the road surface within the captured image; as well as e) Based on the paint quality degradation model and the paint color of the lane markings, the processing unit of the vehicle determines the paint quality level for the detected lane markings.

2. The method according to claim 1, further comprising: Determine whether a driving event is occurring in the vehicle, wherein the driving event indicates that the vehicle is traveling along the road; as well as When the driving event is occurring, determine whether the road surface of the road meets the eligibility requirements.

3. The method of claim 1, wherein the step of evaluating whether the sensed data stream meets the qualification requirements for determining the coating quality level further comprises: An image sensor is used to detect whether there are obstacles on the road surface. The processing unit is used to determine whether there is a coating quality level above a threshold for the road surface; Based on the determination that there is a coating quality level for the road surface, the processing unit is used to determine whether a predetermined time threshold has expired for the coating quality level for the road surface. as well as The processing unit determines that the road surface is not qualified to determine the paint quality level for the lane markings associated with the road surface when at least one of the following exists: i) the obstacle exists on the road surface, ii) the paint quality level for the lane markings associated with the road surface exists, iii) a predetermined time frame associated with the paint quality level for the road surface has not yet expired, or iv) a combination thereof.

4. The method of claim 1, wherein the step of evaluating whether the sensed data stream meets the qualification requirements for determining the coating quality level further comprises: An image sensor is used to detect whether there are obstacles on the road surface; Determine whether the paint quality level applies to the road surface; Based on the determination that there is a coating quality level for the road surface, it is determined whether a predetermined time threshold has expired for the coating quality level for the road surface. as well as The road surface is determined to meet the eligibility requirements when at least one of the following conditions is met: i) the road surface is free of any obstacles in the image data; ii) the paint quality level for the road surface is not present; iii) a predetermined time frame associated with the paint quality level for the road surface has expired; or iv) a combination thereof.

5. The method according to claim 1, further comprising: Receive location data indicating the position of the vehicle along the road; Based on the vehicle's location data, the processing unit is used to determine the lane mark position of the lane mark on the road surface in the captured image; The processing unit uses the paint quality level, timestamp, and lane mark location associated with the lane mark as lane mark data stored in the vehicle's local database. as well as The lane marking data is sent to a remote server outside the vehicle.

6. The method of claim 1, wherein the step of determining the paint quality level for the lane markings in the image further comprises: The blue, green, and red colors of the image are processed into hue, saturation, and brightness colors to form a color-processed image; The color-processed image, having hue, saturation, and brightness levels, is converted into a yellow binary image using a yellow filter and bitwise operations, wherein the yellow binary image includes non-zero yellow pixels and zero-value black pixels; Count each non-zero yellow pixel in the yellow binary image; The processing unit is used to determine the total number of pixels in the yellow binary image; as well as Based on the total number of pixels and the number of non-zero yellow pixels, the processing unit is used to determine the paint quality level for the lane markings.

7. The method of claim 1, wherein the step of determining the paint quality level for the lane markings in the image further comprises: The blue, green, and red colors of the processed image are converted into grayscale colors to form a grayscale image; The grayscale image is converted into a white binary image using a white filter and bitwise operations, wherein the white binary image includes non-zero white pixels and zero-value black pixels; Count the non-zero white pixels in the white binary image; The total number of pixels from the white binary image is counted; as well as The paint quality level for the lane markings is determined based on the total number of pixels and the number of non-zero white pixels.

8. The method of claim 1, wherein the step of determining the paint quality level for the lane markings in the image further comprises: The image is cropped to modify at least a portion of the image, thereby adjusting the size, shape, or combination thereof of the lane markings detected in the image to form a first cropped image and a second cropped image; The blue, green, and red color scales of the first cropped image are processed using hue, saturation, and lightness to produce contrasting pixel colors within the first cropped image, thereby forming a color-processed image with yellow and black pixels. The color-processed image is converted into a yellow binary image using a yellow filter and bitwise operations, wherein the yellow binary image includes non-zero yellow pixels and zero-value black pixels; Count each non-zero yellow pixel in the yellow binary image; Determine the total number of pixels in the yellow binary image; The yellow paint color change indicator is determined based on the total number of pixels and the number of non-zero yellow pixels; The blue, green, and red colors of the second cropped image are converted to grayscale colors to form a white image; The white image is converted into a white binary image based on a white filter and bitwise operations, wherein the white binary image includes non-zero white pixels and zero-value black pixels; Count the non-zero pixels of the white binary image; The total number of pixels from the white binary image is counted; A white paint color-changing indicator for the lane markings is generated based on the total number of pixels and the number of non-zero pixels in the white binary image; and If at least one of the white paint quality level or the yellow paint quality level is below a predetermined threshold, the paint quality level will be selected as either the white paint quality level or the yellow paint quality level.

9. The method according to claim 1, further comprising: Receive the latitude and longitude coordinates of each data point for the lane marking; The location of the lane marking is determined based on the latitude and longitude coordinates of the lane marking; Determine multiple property details associated with the location of the lane marking, wherein the multiple property details include at least one of road name, city name, state name and road type, to form property data; The property data is aggregated with the lane marking data to form lane property data; as well as The lane property data is displayed as mapping data on the digital map to be shown to the user.

10. A vehicle system for determining a paint quality level of lane markings for a road surface as a vehicle travels along a road, wherein the lane markings comprise a coated object disposed on at least a portion of the road surface, the vehicle system comprising: A coating quality determination module, wherein the coating quality determination module has a processing unit, the processing unit being configured to: a) Receive a sensing data stream from an image sensor associated with the vehicle, indicating whether an obstacle exists on the road surface; b) Based on the sensed data stream, the vehicle's processing unit determines whether the road surface meets the qualification requirements for determining the paint quality level of the road surface, wherein the qualification requirements indicate whether the road surface is qualified to determine the paint quality level, and triggers a time period for capturing one or more images of the road surface; c) Based on whether the road surface meets the eligibility requirements, use the image sensor to capture an image of the road surface along the road the vehicle is traveling on; d) Use the vehicle's object detection model to detect whether the lane markings exist on the road surface within the captured image; as well as e) Based on the paint quality degradation model and the paint color of the lane markings, the processing unit of the vehicle determines the paint quality level for the detected lane markings.