Systems and methods for monitoring lane mark quality

1 . A host vehicle-based feature harvester, comprising:

at least one processor comprising circuitry and a memory, wherein the memory includes instructions that when executed by the circuitry cause the at least one processor to:

receive a plurality of images captured by a camera onboard the host vehicle as the host vehicle travels a road segment, wherein the plurality of images are representative of an environment of the host vehicle;

analyze at least one image from the plurality of images to identify a representation of a lane mark;

select at least one lane mark sample area of the representation of the lane mark, wherein the at least one lane mark sample area is associated with an image location of at least a portion of the representation of lane mark;

determine a location identifier of the at least one lane mark sample area;

determine a lane mark surface quality indicator associated with the at least one lane mark sample area, wherein determining the surface quality indicator is based at least on:

analyzing a color of the lane mark sample area or a uniformity level of the lane mark sample area, and

a degree of confidence that the lane mark sample area includes a representation of the lane mark; and

cause transmission of the location identifier of the at least one lane mark sample area and the respective lane mark surface quality indicator to an entity remotely-located relative to the host vehicle, wherein the entity remotely-located relative to the host vehicle is configured to:

generate a map based on the location identifier of the at least one lane mark sample area and the respective lane mark surface quality indicator; and

transmit at least a portion of the map to one or more vehicles for use in navigating the one or more vehicles along the road segment, the one or more vehicles being configured to determine at least one navigational response for navigating along the road segment based on the at least a portion of the map.

2 . The host vehicle-based feature harvester of claim 1 , wherein the at least one sample area includes at least one edge of the representation of the lane mark.

3 . The host vehicle-based feature harvester of claim 1 , wherein the image location is selected along a width of the representation of the lane mark in the at least one image, a length of a longitudinal segment of the representation of the lane mark in the at least one image, or both the width and the length.

4 . The host vehicle-based feature harvester of claim 1 , wherein the image location is randomly selected from the representation of the lane mark in the at least one image.

5 . The host vehicle-based feature harvester of claim 1 , wherein the lane mark is a dashed lane mark.

6 . The host vehicle-based feature harvester of claim 1 , wherein the location identifier includes an X-Y-Z location relative to a real-world origin.

7 . The host vehicle-based feature harvester of claim 1 , wherein determining the location identifier includes determining a three-dimensional position of the at least one sample area in the environment of the host vehicle.

8 . The host vehicle-based feature harvester of claim 7 , wherein the three-dimensional position is determined using at least one of: map information, an output of a GPS receiver associated with the host vehicle, or an output of a LIDAR system associated with the host vehicle.

9 . The host vehicle-based feature harvester of claim 1 , wherein determining the location identifier includes determining a two-dimensional position of a representation of the at least one sample area in the at least one image.

10 . The host vehicle-based feature harvester of claim 1 , wherein the location identifier is determined based on an analysis of representations of the lane mark across two or more of the plurality of images and based on an output of at least one ego motion sensor associated with the host vehicle.

11 . The host vehicle-based feature harvester of claim 10 , wherein the ego motion sensor includes at least one of a speedometer, an accelerometer, or a GPS receiver.

12 . The host vehicle-based feature harvester of claim 1 , wherein the surface quality indicator includes at least one of a paint quality score or a lane mark confidence score.

13 . The host vehicle-based feature harvester of claim 1 , wherein the at least one sample area includes at least two adjoining pixels.

14 . The host vehicle-based feature harvester of claim 1 , wherein the at least one sample area includes at least 10 pixels and less than 20 pixels.

15 . The host vehicle-based feature harvester of claim 1 , wherein the at least one sample area is less than 5 centimeters along a dimension of the at least one sample area.

16 . The host vehicle-based feature harvester of claim 1 , wherein selecting the at least one sample area includes selecting two or more sample areas of the representation of the lane mark.

17 . The host vehicle-based feature harvester of claim 1 , wherein the entity remotely-located relative to the host vehicle includes a server.

18 . The host vehicle-based feature harvester of claim 1 , wherein the entity remotely-located relative to the host vehicle includes one or more processors programmed to receive, in addition to the location identifier and the surface quality indicator transmitted by the host vehicle, drive information from each of a plurality of other vehicles, wherein the drive information includes location information and surface quality information collected by each of the plurality of other vehicles.

19 . The host vehicle-based feature harvester of claim 1 , wherein determining the lane mark surface quality indicator is based on both analyzing the color of the lane mark sample area and analyzing the uniformity level of the lane mark sample area.

20 . The host vehicle-based feature harvester of claim 1 , wherein the uniformity level of the lane mark sample area includes color uniformity, a brightness uniformity, or a coverage uniformity.

21 . A method for harvesting features by a host vehicle, the method comprising:

receiving a plurality of images captured by a camera onboard the host vehicle as the host vehicle travels a road segment, wherein the plurality of images are representative of an environment of the host vehicle;

analyzing at least one image from the plurality of images to identify a representation of a lane mark;

selecting at least one lane mark sample area of the representation of the lane mark, wherein the at least one lane mark sample area is associated with an image location of at least a portion of the representation of lane mark;

determining a location identifier of the at least one lane mark sample area;

determining a lane mark surface quality indicator associated with the at least one lane mark sample area, wherein determining the surface quality indicator is based at least on:

analyzing a color of the lane mark sample area or a uniformity level of the lane mark sample area, and

a degree of confidence that the lane mark sample area includes a representation of the lane mark; and

causing transmission of the location identifier of the at least one lane mark sample area and the respective lane mark surface quality indicator to an entity remotely-located relative to the host vehicle, wherein the entity remotely-located relative to the host vehicle is configured to:

generate a map based on the location identifier of the at least one lane mark sample area and the respective lane mark surface quality indicator; and

transmit at least a portion of the map to one or more vehicles for use in navigating the one or more vehicles along the road segment, the one or more vehicles being configured to determine at least one navigational response for navigating along the road segment based on the at least a portion of the map.

22 . The method of claim 21 , wherein determining the lane mark surface quality indicator is based on both analyzing the color of the lane mark sample area and analyzing the uniformity level of the lane mark sample area.

23 . The method of claim 21 , wherein the uniformity level of the lane mark sample area includes color uniformity, a brightness uniformity, or a coverage uniformity.

24 . A non-transitory computer readable medium containing instructions that when executed by at least one processor, cause the at least one processor to perform a method for harvesting features by a host vehicle, the method comprising:

receiving a plurality of images captured by a camera onboard the host vehicle as the host vehicle travels a road segment, wherein the plurality of images are representative of an environment of the host vehicle;

analyzing at least one image from the plurality of images to identify a representation of a lane mark;

selecting at least one lane mark sample area of the representation of the lane mark, wherein the at least one lane mark sample area is associated with an image location of at least a portion of the representation of lane mark;

determining a location identifier of the at least one lane mark sample area;

determining a lane mark surface quality indicator associated with the at least one lane mark sample area, wherein determining the surface quality indicator is based at least on:

analyzing a color of the lane mark sample area or a uniformity level of the lane mark sample area, and

a degree of confidence that the lane mark sample area includes a representation of the lane mark; and

causing transmission of the location identifier of the at least one lane mark sample area and the respective lane mark surface quality indicator to an entity remotely-located relative to the host vehicle, wherein the entity remotely-located relative to the host vehicle is configured to:

generate a map based on the location identifier of the at least one lane mark sample area and the respective lane mark surface quality indicator; and

transmit at least a portion of the map to one or more vehicles for use in navigating the one or more vehicles along the road segment, the one or more vehicles being configured to determine at least one navigational response for navigating along the road segment based on the at least a portion of the map.

25 . The non-transitory computer readable medium of claim 24 , wherein determining the lane mark surface quality indicator is based on both analyzing the color of the lane mark sample area and analyzing the uniformity level of the lane mark sample area.

26 . The non-transitory computer readable medium of claim 24 , wherein the uniformity level of the lane mark sample area includes color uniformity, a brightness uniformity, or a coverage uniformity.