System and method for calibrating an autonomous vehicle camera
Systems and methods for implementing one or more autonomous features for autonomous and semi-autonomous control of one or more vehicles are provided. More specifically, image data may be obtained from an image acquisition device and processed utilizing one or more machine learning models to identify, track, and extract one or more features of the image utilized in decision making processes for providing steering angle and/or acceleration/deceleration input to one or more vehicle controllers. In some instances, techniques may be employed such that the autonomous and semi-autonomous control of a vehicle may change between vehicle follow and lane follow modes. In some instances, at least a portion of the machine learning model may be updated based on one or more conditions.
1. A method comprising: determining if one or more calibration parameters are available for an image acquisition device; if the one or more calibration parameters are not available for the image acquisition device: obtaining an image from the image acquisition device; determining a vanishing point for the image; comparing the vanishing point to a center point of the image; modifying at least one of the one or more calibration parameters based on the determined vanishing point being different than the center point for the image; and modifying processing of a subsequent image, with the one or more calibration parameters that compensate for the vanishing point being different than the center point for the image, to change a steering output; wherein the one or more calibration parameters include pitch and yaw of the image acquisition device; wherein the pitch is a first number of pixels, in a vertical direction, the center point of an image is from the vanishing point; and wherein the yaw is a second number of pixels, in a horizontal direction, the center point of an image is from the vanishing point.
2. The method of claim 1 , wherein the vanishing point is determined from an object in the image.
3. The method of claim 2 , wherein a noncontinuous edge, which does not extend to the vanishing point, of the object helps determine the vanishing point.
4. The method of claim 3 , wherein an angle of the edge indicates a location for the vanishing point.
5. The method of claim 4 , wherein the object is a lane marker.
6. The method of claim 5 , wherein the object is an exterior of a building.
7. The method of claim 6 , wherein the calibration parameters are stored and applied to subsequent images.
8. A system comprising: a memory; a processor in communication with the memory, wherein the processor executes instructions stored in the memory, which cause the processor to execute a method, the method comprising: determining if one or more calibration parameters are available for an image acquisition device; if the one or more calibration parameters are not available for the image acquisition device: obtaining an image from the image acquisition device; determining a vanishing point for the image; comparing the vanishing point to a center point of the image; modifying at least one of the one or more calibration parameters based on the determined vanishing point being different than the center point for the image; modifying processing of a subsequent image, with the one or more calibration parameters that compensate for the vanishing point being different than the center point for the image, to change a steering output; and wherein the one or more calibration parameters include pitch and yaw of the image acquisition device, wherein the pitch is a first number of pixels, in a vertical direction, the center point of an image is from the vanishing point, and wherein the yaw is a second number of pixels, in a horizontal direction, the center point of an image is from the vanishing point.
9. The system of claim 8 , wherein the vanishing point is determined from an object in the image, wherein a non-continuous edge of the object is projected to a horizon to determine the vanishing point and an angle of the edge, which both indicate a location for the vanishing point.
10. The system of claim 9 , wherein the object is one of a lane marker or a building.
11. The system of claim 8 , wherein the calibration parameters are stored and applied to subsequent images.
12. A non-transitory computer readable medium having stored thereon instructions, which when executed by a processor cause the processor to execute a method, the method comprising: determining if one or more calibration parameters are available for an image acquisition device; if the one or more calibration parameters are not available for the image acquisition device: obtaining an image from the image acquisition device; determining a vanishing point for the image; comparing the vanishing point to a center point of the image; modifying at least one of the one or more calibration parameters based on the determined vanishing point being different than the center point for the image; and modifying processing of a subsequent image, with the one or more calibration parameters that compensate for the vanishing point being different than the center point for the image, to change a steering output; and wherein the one or more calibration parameters include pitch and yaw of the image acquisition device, wherein the pitch is a first number of pixels, in a vertical direction, the center point of an image is from the vanishing point, and wherein the yaw is a second number of pixels, in a horizontal direction, the center point of an image is from the vanishing point.
13. The non-transitory computer readable medium of claim 12 , wherein the vanishing point is determined from an object in the image, wherein an angle of a non-continuous edge of the object, compared to a horizon indicates a location for the vanishing point.
14. The non-transitory computer readable medium of claim 13 , wherein the object is one of a lane marker or a building.
15. The non-transitory computer readable medium of claim 12 , wherein the calibration parameters are stored and applied to subsequent images.