Method and apparatus for processing an image of a road having a road marker to identify a region of the image which represents the road marker

1 . A method of processing an image of a road having a road marker, which has been acquired by a vehicle-mounted camera, to generate boundary data indicative of a boundary of a road marker region of the image that represents the road marker, the method comprising:

generating an LL sub-band image of an M th level of an (M+1)-level discrete wavelet transform, DWT, decomposition of the image by performing an iterative process of iteratively low-pass filtering and down-sampling the image M times, where Mis an integer equal to or greater than one;

setting M to a value that is based on an image resolution of the image, by using a predetermined mapping between values of the image resolution and values of M;

generating an LH sub-band image of an (M+1) th level of the (M+1) level DWT decomposition of the image by high-pass filtering the LL sub-band image of the M th level, and down-sampling a result of the high-pass filtering; and

generating the boundary data by determining a boundary of a region of pixels of the LH sub-band image of the (M+1) th level, the region of pixels being surrounded by pixels having pixel values that are different from the pixel values of the pixels in the region, the boundary of the region being indicative of the boundary of the road marker region in the image, wherein generating the boundary data includes determining the boundary around the region of pixels of the LH sub-band image by at least one of:

a first process including:

determining a pixel location of a pixel of the LH sub-band image of the (M+1) th level whose pixel value exceeds a predetermined threshold, and

executing a contour tracing algorithm using the determined pixel location to identify the boundary of the region, wherein the boundary separates pixels of the region that are adjacent to the boundary and have pixel values above the predetermined threshold from pixels outside the region that are adjacent to the boundary and have pixel values below the predetermined threshold, or

a second process including:

determining, for each of a plurality of columns of pixels in the LH sub-band image of the (M+1) th level, a pixel location of a pixel in the column at which a difference between a pixel value of the pixel and a pixel value of an adjacent pixel in the column exceeds a predetermined threshold, and

defining line segments in the LH sub-band image of the (M+1) th level using the determined pixel locations, wherein the line segments define the boundary around the region, wherein each of the line segments is defined to connect a pixel at the determined pixel location in a respective column of the plurality of columns of pixels to a pixel at the determined pixel location in an adjacent column of the plurality of columns of pixels.

2 . The method according to claim 1 , wherein a first low-pass filter having a first sequence of filter coefficients that are symmetrical is used in at least one iteration of the iterative process.

3 . The method according to claim 2 , wherein the filter coefficients in the first sequence of filter coefficients are set to values in a row of Pascal's triangle having the same number of values as an order of the first low-pass filter.

4 . The method according to claim 2 , wherein the low-pass filter used to generate the LH sub-band image of the (M+1) th level of the (M+1)-level DWT decomposition of the image has a sequence of filter coefficients that are symmetrical.

5 . The method according to claim 1 , wherein the high-pass filtering used to generate the sub-band image of the (M+1) th level includes applying a high-pass filter having a second sequence of filter coefficients that are symmetrical.

6 . The method according to claim 5 , wherein:

alternate filter coefficients in the second sequence of filter coefficients are set to correspondingly located values in a row of Pascal's triangle having the same number of values as an order of the high-pass filter, and

each remaining filter coefficient in the second sequence of filter coefficients is set to a value obtained by multiplying a correspondingly located value in the row of Pascal's triangle by −1.

7 . The method according to claim 1 , wherein the LH sub-band image of the (M+1) th level of the (M+1)-level DWT decomposition of the image is generated by at least one of:

a third process including:

generating a low-pass filtered LL sub-band image by applying a row kernel which defines a low-pass filter across rows of the LL sub-band image of the M th level;

down-sampling the columns of the low-pass filtered LL sub-band image by a factor of two to generate a down-sampled sub-band image;

generating a high-pass filtered LL sub-band image by applying a column kernel which defines a high-pass filter across columns of the down-sampled sub-band image; and

down-sampling the rows of the high-pass filtered LL sub-band image by a factor of two to generate the LH sub-band image of the (M+1) th level;

a fourth process including:

generating a high-pass filtered LL sub-band image by applying a column kernel which defines a high-pass filter across the columns of the LL sub-band image of the M th level;

down-sampling the rows of the high-pass filtered LL sub-band image by a factor of two to generate a down-sampled sub-band image;

generating a low-pass filtered sub-band image by applying a row kernel which defines a low-pass filter across the rows of the down-sampled sub-band image of the M th level; and

down-sampling the columns of the low-pass filtered sub-band image by a factor of two to generate the LH sub-band image of the (M+1) th level; or

a fifth process including:

generating a filtered sub-band image by applying a two-dimensional kernel across the LL sub-band image of the M th level, the two-dimensional kernel being separable into a product of a row kernel and a column kernel, the row kernel defining a low-pass filter and the column kernel defining a high-pass filter; and

down-sampling rows and columns of the filtered sub-band image by a factor of two.

8 . The method according to claim 7 , wherein the low-pass filter and the high-pass filter used to generate the LH sub-band image of the (M+1) th level of the (M+1)-level DWT decomposition of the image define a quadrature mirror filter pair.

9 . The method according to claim 1 , wherein:

no more than two sub-band images are generated in each level of the (M+1)-level DWT decomposition of the image up to the M th level, and

only the sub-band image is generated at the (M+1) th level of the (M+1)-level DWT decomposition of the image.

10 . The method according to claim 1 , further comprising applying a scaling factor to the pixel value of each pixel of the sub-band image and saturating scaled pixel values that are above a pixel saturation threshold, before generating the boundary data.

11 . The method according to claim 1 , further comprising:

defining a boundary of the road marker region in the image by:

up-scaling the boundary of the region of pixels by a factor of 2 M+1 to generate an up-scaled boundary; and

mapping the second up-scaled boundary to the image.

12 . The method of claim 1 , wherein the camera is configured to acquire, as the image, an image of a scene including the road and a portion of the sky, and the method excludes from the processing a portion of the image representing the portion of the sky.

13 . An apparatus for processing an image of a road having a road marker, which has been acquired by a vehicle-mounted camera, to generate boundary data indicative of a boundary of a road marker region of the image which represents the road marker, the apparatus comprising:

a discrete wavelet transform, DWT, decomposition module arranged to:

generate an LL sub-band image of an M th level of an (M+1)-level DWT decomposition of the image by iteratively low-pass filtering and down-sampling the image M times, where Mis an integer equal to or greater than one;

set M to a value that is based on an image resolution of the image, by using a predetermined mapping between values of the image resolution and values of M; and

generate an LH sub-band image of an (M+1) th level of the (M+1)-level DWT decomposition of the image by high-pass filtering the LL sub-band image of the M th level, and down-sampling a result of the high-pass filtering; and

a boundary data generator module arranged to generate the boundary data by determining a boundary of a region of pixels of the LH sub-band image of the (M+1) th level, the region of pixels being surrounded by pixels having pixel values that are different from the pixel values of the pixels in the region, and wherein the boundary of the region is indicative of the boundary of the road marker region in the image of the road, wherein the boundary data generator module is arranged to generate the boundary data by determining the boundary around the region of pixels of the LH sub-band image by one of:

a first process including:

determining a pixel location of a pixel of the LH sub-band image of the (M+1) th level whose pixel value exceeds a predetermined threshold, and

executing a contour tracing algorithm using the determined pixel location to identify the boundary of the region, wherein the boundary separates pixels of the region that are adjacent to the boundary and have pixel values above the predetermined threshold from pixels outside the region that are adjacent to the boundary and have pixel values below the predetermined threshold, or

a second process including:

determining, for each of a plurality of columns of pixels in the LH sub-band image of the (M+1) th level, a pixel location of a pixel in the column at which a difference between a pixel value of the pixel and a pixel value of an adjacent pixel in the column exceeds a predetermined threshold, and

defining line segments in the LH sub-band image of the (M+1) th level using the determined pixel locations, wherein the line segments define the boundary around the region, wherein each of the line segments is defined to connect a pixel at the determined pixel location in a respective column of the plurality of columns of pixels to a pixel at the determined pixel location in an adjacent column of the plurality of columns of pixels.

14 . A non-transitory computer-readable medium comprising processor-executable instructions, the instructions including:

generating an LL sub-band image of an M th level of an (M+1)-level discrete wavelet transform, DWT, decomposition of the image by performing an iterative process of iteratively low-pass filtering and down-sampling the image M times, where Mis an integer equal to or greater than one;

setting M to a value that is based on an image resolution of the image, by using a predetermined mapping between values of the image resolution and values of M;

generating an LH sub-band image of an (M+1) th level of the (M+1) level DWT decomposition of the image by high-pass filtering the LL sub-band image of the M th level, and down-sampling a result of the high-pass filtering; and

generating the boundary data by determining a boundary of a region of pixels of the LH sub-band image of the (M+1) th level, the region of pixels being surrounded by pixels having pixel values that are different from the pixel values of the pixels in the region, the boundary of the region being indicative of the boundary of the road marker region in the image, wherein generating the boundary data includes determining the boundary around the region of pixels of the LH sub-band image by at least one of:

a first process including:

determining a pixel location of a pixel of the LH sub-band image of the (M+1) th level whose pixel value exceeds a predetermined threshold, and

executing a contour tracing algorithm using the determined pixel location to identify the boundary of the region, wherein the boundary separates pixels of the region that are adjacent to the boundary and have pixel values above the predetermined threshold from pixels outside the region that are adjacent to the boundary and have pixel values below the predetermined threshold, or

a second process including:

determining, for each of a plurality of columns of pixels in the LH sub-band image of the (M+1) th level, a pixel location of a pixel in the column at which a difference between a pixel value of the pixel and a pixel value of an adjacent pixel in the column exceeds a predetermined threshold, and

defining line segments in the LH sub-band image of the (M+1) th level using the determined pixel locations, wherein the line segments define the boundary around the region, wherein each of the line segments is defined to connect a pixel at the determined pixel location in a respective column of the plurality of columns of pixels to a pixel at the determined pixel location in an adjacent column of the plurality of columns of pixels.