System and method for online camera to ground alignment
A vehicle, a system and a method of navigating the vehicle. The system includes a camera conveyed by the vehicle and a processor. The camera is configured to obtain an original image data file of an environment. The processor is configured to reduce the original image data file to obtain a reduced image data file and determine an alignment between a camera-centered coordinate system and a ground coordinate system using the reduced image data file.
1. A method of navigating a vehicle, comprising:
obtaining an original image data file of an environment at a camera conveyed by the vehicle;
reducing the original image data file to obtain a reduced image data file;
determining an alignment between a camera-centered coordinate system and a ground coordinate system using the reduced image data file; and
determining a weighted average value of the alignment using a confidence level of a moving average of the alignment for a plurality of frames of the reduced image data file.
2. The method of claim 1 , wherein the original image data file includes a plurality or temporally spaced frames.
3. The method of claim 2 , wherein obtaining the reduced image data file further comprises at least one of: (i) selecting a first frame and a second frame from a plurality of temporally spaced frames of the original image data file, wherein a temporal spacing between the first frame and the second frame is based on a velocity of the vehicle; (ii) removing a pixel from a frame of the original image data file using on a reduction algorithm; and (iii) cropping the frame to remove a section of the frame.
4. The method of claim 3 , further comprising forming a feature pair between a first feature of the first frame and a second feature of the second frame and removing the feature pair when a metric of the first feature and the second feature is less than a criterion.
5. The method of claim 4 , further comprising assigning a quality score to the feature pair and removing the feature pair when the quality score is less than a quality threshold.
6. The method of claim 1 , further comprising generating a road mask in an image plane of the camera from the alignment.
7. The method of claim 1 , further comprising controlling the vehicle to navigate the vehicle with respect to an object in a road using an image obtained from the camera after alignment.
8. A system for navigating a vehicle, comprising:
a camera conveyed by the vehicle, the camera configured to obtain an original image data file of an environment; and
a processor configured to:
reduce the original image data file to obtain a reduced image data file;
determine an alignment between a camera-centered coordinate system and a ground coordinate system using the reduced image data file; and
determine a weighted average value of the alignment using a confidence level of a moving average of the alignment for a plurality of frames of the reduced image data file.
9. The system of claim 8 , wherein the original image data file includes a plurality or temporally spaced frames.
10. The system of claim 9 , wherein the processor is further configured to obtain the reduced image data file by performing at least one of: (i) selecting a first frame and a second frame from a plurality of temporally spaced frames of the original image data file, wherein a temporal spacing between the first frame and the second frame is based on a velocity of the vehicle; (ii) removing a pixel from a frame of the original image data file using on a reduction algorithm; and (iii) cropping the frame to remove a section of the frame.
11. The system of claim 10 , wherein the processor is further configured to form a feature pair between a first feature of the first frame and a second feature of the second frame and remove the feature pair when a metric of the first feature and the second feature is less than a criterion.
12. The system of claim 11 , wherein the processor is further configured to assign a quality score to the feature pair and remove the feature pair when the quality score is less than a quality threshold.
13. The system of claim 8 , wherein the processor is further configured to generate a road mask in an image plane of the camera from the alignment.
14. The system of claim 8 , wherein the processor is further configured to control the vehicle to navigate the vehicle with respect to an object in a road using an image obtained from the camera after alignment.
15. A vehicle, comprising:
a camera configured to obtain an original image data file of an environment; and
a processor configured to:
reduce the original image data file to obtain a reduced image data file;
determine an alignment between a camera-centered coordinate system and a ground coordinate system using the reduced image data file; and
determine a weighted average value of the alignment using a confidence level of a moving average of the alignment for a plurality of frames of the reduced image data file.
16. The vehicle of claim 15 , wherein the original image data file includes a plurality or temporally spaced frames.
17. The vehicle of claim 16 , wherein the processor is configured to obtain the reduced image data file by performing at least one of: (i) selecting a first frame and a second frame from a plurality of temporally spaced frames of the original image data file, wherein a temporal spacing between the first frame and the second frame is based on a velocity of the vehicle; (ii) removing a pixel from a frame of the original image data file using on a reduction algorithm; and (iii) cropping the frame to remove a section of the frame.
18. The vehicle of claim 17 , wherein the processor is further configured to form a feature pair between a first feature of the first frame and a second feature of the second frame and remove the feature pair when a metric of the first feature and the second feature is less than a criterion.
19. The vehicle of claim 18 , wherein the processor is further configured to assign a quality score to the feature pair and remove the feature pair when the quality score is less than a quality threshold.
20. The vehicle of claim 15 , wherein the processor is further configured to generate a road mask in an image plane of the camera from the alignment.