Method of Processing Images and Apparatus
1 Assignment
0 Petitions
Accused Products
Abstract
A method of processing an image includes a region of a highway in front of the vehicle captured using an imager having a two dimensional array of image capturing pixels. The array includes a first set of pixels substantially independent of hue and a second set of pixels dependent of a limited range of hues. The method further includes the steps of producing a first image where each pixel is assigned a value derived from the first set of pixels and producing a second image where each pixel is assigned a value derived from the first set of pixels and the second set of pixels. The method includes identifying-for at least one pixel in the first image a first intensity change value indicative of the difference between that pixel and at least one adjacent pixel identifying for a corresponding pixel in the second image a second intensity change value indicative of the difference between that pixel and at least one adjacent pixel. A combined image is formed using a defined set of combination rules to assign a value to the corresponding pixel in the combined image which depends on the first and second identified intensity change values for that corresponding pixel.
19 Citations
47 Claims
-
1-25. -25. (canceled)
-
26. A method of processing an image for use in a lane detection apparatus suitable for being fitted to a vehicle, the method comprising:
-
capturing an initial image of a region of a highway in front of the vehicle using an imager having a two dimensional array of image capturing pixels, the array comprising a first set of pixels located at spaced coordinates (XY) which each produce an output signal whose value is substantially independent of the hue of the corresponding portion of the scene captured in the image and a second set of pixels located at spaced locations which each produce an output signal having a value dependent on a limited range of hues of the corresponding portion of the scene captured in the image and partially dependent on the lightness of the corresponding portion of the scene captured in the image, producing from the initial captured image a first image where each pixel in the first image is assigned a value derived using values from at least one pixel in the first set of pixels, producing from the initial image a second image where each pixel in the second image is assigned a value that is derived using values from at least one pixel in the first set of pixels and at least one pixel in the second set of pixels, identifying for at least one pixel in the first image a first intensity change value indicative of the difference between the value assigned to that pixel and the value assigned to at least one adjacent pixel, identifying for a corresponding pixel in the second image a second intensity change value indicative of the difference between the value assigned to that pixel and the value assigned to at least one adjacent pixel, and forming a combined image by using a defined set of combination rules to assign a value to the corresponding pixel in the combined image which depends on the magnitude and/or sign of each of the first and second identified intensity change values for that corresponding pixel in the first and second images, the combined image being suitable for use in the lane detection apparatus. - View Dependent Claims (27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 45, 46, 47)
-
-
40. An image processing apparatus for a vehicle comprising:
-
an imager arranged to capture an initial image of a region of a highway in front of the vehicle, the imager comprising a two dimensional array of image capturing pixels, the array comprising a first set of pixels located at spaced coordinates (XY) which each produce an output signal whose value is substantially independent of the hue of the corresponding portion of the scene captured in the image interspersed with a second set of pixels which each produce an output signal having a value dependent on a limited range of hues of the corresponding portion of the scene captured in the image and partially dependent on the lightness of the corresponding portion of the scene captured in the image, and a processing means which comprises; first processing means adapted to produce from the initial captured image a first image which is substantially independent of hue in the scene where each pixel in the first image is assigned a value derived using values from at least one pixel in the first set of pixels, second processing means which is adapted to produce from the initial image a second image where each pixel in the second image is assigned a value that is derived using values from at least one pixel in both of the first and second sets of pixels, first identifying means for identifying for at least one pixel in the first image a first intensity change value indicative of the difference between the value assigned to that pixel and the value assigned to at least one adjacent pixel, second identifying means for identifying a corresponding pixel in the second image a second intensity change value indicative of the difference between the value assigned to that pixel and the value assigned to at least one adjacent pixel, and a combining means for forming a combined image by using a defined set of combination rules to assign a value to the corresponding pixel in the combined image which depends on the magnitude and/or sign of each of the first and second identified intensity change values for that corresponding pixel in the first and second images, the combined image being suitable for use in the lane detection apparatus. - View Dependent Claims (41, 42, 43, 44)
-
Specification