System for automated lane marking
View Patent ↗Systems and processes can automatically identify lane markings within images through the use of a machine learning model. The machine learning model may use a reduced set of data and output an improved estimate of lane markings by applying normalized data or images to the machine learning model. Each image applied to the model can be normalized by, for example, rotating each of the images such that the depicted roads are horizontal or otherwise share the same angle. By aligning disparate images of roads, it is possible to reduce the amount of data applied to the model or to model generation, and to increase the accuracy of the machine learning model. Further, the use of normalized images by the machine learning model enables a reduction in computing resources used to apply data to the machine learning model to, for example, identify lane markings within images.
1. A computer-implemented method of performing an automated lane marking process on an image of a road network using a machine learning model, the computer-implemented method comprising:
as implemented by a lane detection system comprising one or more hardware processors and configured with specific computer-executable instructions,
accessing a rotated image segment depicting a road segment, wherein the rotated image segment comprises a rotated portion of an image of a road network obtained by performance of a first rotation, and wherein the rotated image segment is rotated by a degree of rotation with respect to a target axis to align the road segment with the target axis;
applying the rotated image segment to a machine learning model to obtain a lane marked rotated image segment, wherein the machine learning model outputs a likelihood that a group of pixels within the rotated image segment includes a first portion of a lane marking, and wherein the likelihood is based at least in part on whether a probability that a neighboring group of pixels includes a second portion of the lane marking satisfies a threshold;
determining the degree of rotation with respect to the target axis of the rotated image segment;
performing a second rotation by counter rotating the lane marked rotated image segment by an amount corresponding to the degree of rotation to obtain a lane-marked image segment; and updating the image of the road network based at least in part on the lane-marked image segment to obtain an updated image.
2. The computer-implemented method of claim 1 , wherein lane markings on the lane-marked rotated image segment or on the lane-marked image segment are included as part of an overlay layer that provides lane marking data for one or more of: a vehicle routing system, a driver-assist system, or an autonomous vehicle system.
3. The computer-implemented method of claim 1 , wherein the degree of rotation comprises an amount that a portion of the image of the road network was rotated to obtain the rotated image segment.
4. The computer-implemented method of claim 1 , wherein the degree of rotation is determined from metadata associated with the rotated image segment.
5. The computer-implemented method of claim 1 , wherein the image of the road network comprises a map of the road network.
6. The computer-implemented method of claim 1 , wherein updating the image of the road network comprises replacing a corresponding portion of the image with the lane-marked image segment.
7. The computer-implemented method of claim 1 , wherein updating the image of the road network comprises applying lane markings from the lane-marked image segment to a corresponding portion of the image.
8. The computer-implemented method of claim 1 , further comprising storing the updated map at a map repository configured to store mapping data for one or more of: a vehicle routing system, a driver-assist system, or an autonomous vehicle system.
9. The computer-implemented method of claim 1 , wherein the target axis comprises a horizontal axis.
10. A system for performing an automated lane marking process on an image of a road network using a machine learning model, the system comprising:
a storage configured to store rotated image segments depicting portions of roads rotated to align with a target axis;
and a lane detection system comprising one or more hardware processors configured to:
access from the storage a rotated image segment depicting a road segment, wherein the rotated image segment is a rotated portion of an image of a road network obtained by performance of a first rotation, and wherein the rotated image segment is rotated to align the road segment with the target axis;
input the rotated image segment to a machine learning model to obtain a lane-marked rotated image segment, wherein the machine learning model outputs a likelihood that a group of pixels within the rotated image segment includes a first portion of a lane marking, and wherein the likelihood is based at least in part on whether a probability that a neighboring group of pixels includes a second portion of the lane marking satisfies a threshold;
determine a degree of rotation with respect to the target axis of the rotated image segment;
perform a second rotation by counter rotating the lane-marked rotated image segment by the degree of rotation to obtain a lane-marked image segment; and
modify the image of the road network based at least in part on the lane-marked image segment to obtain a modified image.
11. The system of claim 10 , wherein the lane detection system is further configured to generate an overlay layer that includes lane markings from the lane-marked rotated image segment or the lane-marked image segment, and wherein the overlay layer is provided to one or more of: a vehicle routing system, a driver-assist system, or an autonomous vehicle system.
12. The system of claim 10 , wherein the degree of rotation comprises an amount that a portion of the image of the road network was rotated to obtain the rotated image segment.
13. The system of claim 10 , wherein the lane detection system is further configured to modify the image of the road network by replacing a corresponding portion of the image with the lane-marked image segment.
14. The system of claim 10 , wherein the lane detection system is further configured to modify the image of the road network by applying lane markings from the lane-marked image segment to a corresponding portion of the image.
15. The system of claim 10 , wherein the lane detection system is further configured to store the modified map at a map repository configured to store mapping data for one or more of: a vehicle routing system, a driver-assist system, or an autonomous vehicle system.
16. The system of claim 15 , wherein the storage comprises the map repository.
17. A non-transitory computer-readable storage medium storing computer executable instructions that, when executed by one or more computing devices, configure the one or more computing devices to perform operations comprising:
obtaining a rotated image segment depicting a road segment, wherein the rotated image segment is a rotated portion of an image of a road network, and wherein the rotated image segment is rotated to align the road segment with a target axis;
applying the rotated image segment as input to a machine learning model to obtain a lane-marked rotated image segment, wherein the machine learning model outputs a likelihood that a group of pixels within the rotated image segment includes a first portion of a lane marking, and wherein the likelihood is based at least in part on whether a probability that a neighboring group of pixels includes a second portion of the lane marking satisfies a threshold;
determining a degree of rotation with respect to the target axis of the rotated image segment;
counter rotating the lane-marked rotated image segment by the degree of rotation to obtain a lane-marked image segment;
and annotating the image of the road network based at least in part on the lane-marked image segment to obtain an annotated image.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the operations further comprise: generating an overlay layer that includes lane markings from the lane-marked rotated image segment or the lane-marked image segment; and providing the overlay layer to one or more of: a vehicle routing system, a driver-assist system, or an autonomous vehicle system.
19. The non-transitory computer-readable storage medium of claim 17 , wherein annotating the image of the road network comprises replacing a corresponding portion of the image with the lane-marked image segment.
20. The non-transitory computer-readable storage medium of claim 17 , wherein annotating the image of the road network comprises applying lane markings from the lane-marked image segment to a corresponding portion of the image.