Control algorithm to precisely evaluate edge quality from imagery
A method for evaluating edge quality in an image includes receiving an image from a camera of a vehicle, detecting an edge in the image captured by the camera, fitting a polynomial curve to the edge in the image captured by the camera, executing a numerical optimizer to determine a minimum distance from each pixel in the image of the edge to the polynomial curve, determining a modulation transfer function (MTF) value using the minimum distance, determining whether the MTF value is greater than predetermined threshold, and providing an alert in response to determining that the MTF value is not greater than the predetermined threshold.
1. A method for evaluating edge quality in an image, comprising:
receiving an image from a camera of a vehicle, wherein the image includes image data;
detecting an edge in the image captured by the camera;
fitting a polynomial curve to the edge in the image captured by the camera;
executing a numerical optimizer to determine a minimum distance from each pixel in the image of the edge to the polynomial curve;
determining a modulation transfer function (MTF) value using the minimum distance;
determining whether the MTF value is greater than predetermined threshold;
providing an alert in response to determining that the MTF value is not greater than the predetermined threshold;
pixel binning a plurality of pixels of the edge in the image to generate a plurality of super pixels;
determining an average luminance value for each of the plurality of super pixels;
executing an adjusted pixel binning using the average luminance value for each of the plurality of super pixels;
storing the image data in response to determining that the MTF value is greater than predetermined threshold; and
determining an edge spread function of the edge using the plurality of super pixels.
2. The method of claim 1 , further comprising determining a line spread function of the edge using the edge spread function, wherein the line spread function is a first derivative of the edge spread function.
3. The method of claim 2 , wherein determining the MTF value using the minimum distance includes determining the MTF value using the line spread function, wherein the MTF is a Fast Fourier transform of the line spread function.
4. The method of claim 1 , wherein detecting the edge in the image captured by the camera includes using a Canny edge detector to detect the edge in the image.
5. The method of claim 1 , wherein detecting the edge in the image captured by the camera includes using a Sobel edge detector to detect the edge in the image.
6. The method of claim 1 , further comprising cropping the image such that the edge is centered in the image, wherein the cropping is performed before fitting the polynomial curve to the edge of the image.
7. A tangible, non-transitory, machine-readable medium, comprising machine-readable instructions, that when executed by a processor, cause the processor to:
receive an image from a camera of a vehicle, wherein the image includes image data;
detect an edge in the image captured by the camera;
fit a polynomial curve to the edge in the image captured by the camera;
execute a numerical optimizer to determine a minimum distance from each pixel in the image of the edge to the polynomial curve;
determine a modulation transfer function (MTF) value using the minimum distance;
determine whether the MTF value is greater than predetermined threshold;
provide an alert in response to determining that the MTF value is not greater than the predetermined threshold;
pixel bin a plurality of pixels of the edge in the image to generate a plurality of super pixels;
determine an average luminance value for each of the plurality of super pixels;
execute an adjusted pixel binning using the average luminance value for each of the plurality of super pixels;
store the image data in response to determining that the MTF value is greater than predetermined threshold; and
determine an edge spread function using the plurality of super pixels.
8. The tangible, non-transitory, machine-readable medium of claim 7 , further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
determine a line spread function using the edge spread function, wherein the line spread function is a first derivative of the edge spread function.
9. The tangible, non-transitory, machine-readable medium of claim 8 , further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
determine the MTF value using the line spread function.
10. The tangible, non-transitory, machine-readable medium of claim 9 , wherein the MTF is a Fast Fourier transform of the line spread function.
11. The tangible, non-transitory, machine-readable medium of claim 7 , further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
use a Canny edge detector to detect the edge in the image.
12. The tangible, non-transitory, machine-readable medium of claim 7 , further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
use a Sobel edge detector to detect the edge in the image.
13. The tangible, non-transitory, machine-readable medium of claim 7 , further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
crop the image such that the edge is centered in the image, wherein the cropping is performed before fitting the polynomial curve to the edge of the image.
14. A method for evaluating edge quality in an image, comprising:
receiving an image from a camera of a vehicle, wherein the image includes image data;
detecting an edge in the image captured by the camera;
fitting a polynomial curve to the edge in the image captured by the camera;
cropping the image such that the edge is centered in the image, wherein the cropping is performed before fitting the polynomial curve to the edge of the image;
executing a numerical optimizer to determine a minimum distance from each pixel in the image of the edge to the polynomial curve;
determining a modulation transfer function (MTF) value using the minimum distance;
determining whether the MTF value is greater than predetermined threshold;
providing an alert in response to determining that the MTF value is not greater than the predetermined threshold;
pixel binning a plurality of pixels of the edge in the image to generate a plurality of super pixels;
determining an average luminance value for each of the plurality of super pixels;
executing an adjusted pixel binning using the average luminance value for each of the plurality of super pixels;
storing the image data in response to determining that the MTF value is greater than predetermined threshold;
determining an edge spread function of the edge using the plurality of super pixels; and
determining a line spread function of the edge using the edge spread function, wherein the line spread function is a first derivative of the edge spread function.
15. The method of claim 14 , wherein determining the MTF value using the minimum distance includes determining the MTF value using the line spread function, wherein the MTF is a Fast Fourier transform of the line spread function.
16. The method of claim 14 , wherein detecting the edge in the image captured by the camera includes using a Canny edge detector to detect the edge in the image.
17. The method of claim 14 , wherein detecting the edge in the image captured by the camera includes using a Sobel edge detector to detect the edge in the image.