Homography rectification

Abstract

The present disclosure provides a multi-stage image mapping mechanism for mapping a distorted image to a rectified image. For example, the multi-stage image mapping mechanism can remove homography from a distorted image to reconstruct a rectified image in two-stages: (1) a first stage in which distortion is partially removed from a distorted image to generate an intermediate image, and (2) a second stage in which residual distortion is removed from the intermediate image to recover the rectified image.

1 - 20 . (canceled) 
     
     
         21 . A machine vision system comprising:
 a processor configured to run a computer program stored in memory that is configured to cause the processor to:
 receive a distorted image and a homography matrix associated with the distorted image; 
 determine, using a homography decomposition module, a first transform and a second transform that collectively represent the homography matrix, wherein:
 the first transform relates the distorted image to an intermediate image, 
 the second transform relates a transposed intermediate image to a transposed rectified image, 
 the distorted image, the intermediate image, the transposed intermediate image, and the transposed rectified image comprise at least a first dimension and a second dimension, 
 the first transform is constrained to map pixels along the first dimension of the intermediate image to locations along the first dimension of the distorted image, and 
 the locations along the first dimension of the distorted image are separated by a same distance from adjacent locations along the first dimension of the distorted image; 
 
 generate, using a homography removal module, the intermediate image by removing the first transform from the distorted image; 
 transpose, using the homography removal module, the intermediate image prior to removing the second transform from the intermediate image to generate the transposed intermediate image; and 
 generate, using the homography removal module, the transposed rectified image by removing the second transform from the transposed intermediate image. 
   
     
     
         22 . The machine vision system of  claim 21 , wherein the locations along the first dimension of the distorted image are separated by a same distance from adjacent locations along the first dimension of the distorted image by constraining a rate of change of (1) the first dimension of the distorted image with respect to (2) the first dimension of the intermediate image. 
     
     
         23 . The machine vision system of  claim 21 , wherein the second transform is constrained to map pixels along the first dimension of the transposed rectified image to locations along the first dimension of the transposed intermediate image, and wherein the locations along the first dimension of the transposed intermediate image are separated by a same distance from adjacent locations along the first dimension of the transposed intermediate image. 
     
     
         24 . The machine vision system of  claim 23 , wherein the locations along the first dimension of the transposed intermediate image are separated by a same distance from adjacent locations along the first dimension of the transposed intermediate image by constraining a rate of change of (1) the first dimension of the transposed intermediate image with respect to (2) the first dimension of the transposed rectified image. 
     
     
         25 . The machine vision system of  claim 21 , wherein the processor is configured, using the homography removal module, to cause a direct memory access controller to transpose the intermediate image prior to removing the second transform from the intermediate image. 
     
     
         26 . The machine vision system of  claim 21 , wherein the processor is configured, using the homography removal module, to remove the first transform from the distorted image by determining, for a first pixel of the intermediate image, a corresponding first location in the distorted image, and convolving pixels surrounding the corresponding first location in the distorted image to determine an image value for the first pixel. 
     
     
         27 . The machine vision system of  claim 26 , wherein the processor is configured, using the homography removal module, to determine, for a second pixel of the intermediate image having an identical coordinate as the first pixel in a second dimension, a corresponding second location in the distorted image by adding a constant to a coordinate of the corresponding first location in the first dimension. 
     
     
         28 . The machine vision system of  claim 21 , wherein the processor is configured, using the homography removal module, to:
 transpose the transposed rectified image to generate a rectified image; and   provide the rectified image to a pattern detection system so that the pattern detection system can use the rectified image to determine whether the rectified image includes a particular pattern.   
     
     
         29 . The machine vision system of  claim 21 , wherein the processor is configured, using the homography removal module, to select one of a set of kernels based on a sub-pixel coordinate of one of the locations along the first dimension of the distorted image, and apply the selected kernel at the one of the locations. 
     
     
         30 . A computerized method comprising:
 receiving, at a homography decomposition module, a distorted image and a homography matrix associated with the distorted image;   determining, using the homography decomposition module, a first transform and a second transform that collectively represent the homography matrix, wherein:
 the first transform relates the distorted image to an intermediate image, 
 the second transform relates a transposed intermediate image to a transposed rectified image, 
 the distorted image, the intermediate image, the transposed intermediate image, and the transposed rectified image comprise at least a first dimension and a second dimension, 
 the first transform is constrained to map pixels along the first dimension of the intermediate image to locations along the first dimension of the distorted image, and 
 the locations along the first dimension of the distorted image are separated by a same distance from adjacent locations along the first dimension of the distorted image; 
   generating, using a homography removal module, the intermediate image by removing the first transform from the distorted image;   transposing, using the homography removal module, the intermediate image prior to removing the second transform from the intermediate image to generate the transposed intermediate image; and   generating, using the homography removal module, the transposed rectified image by removing the second transform from the transposed intermediate image.   
     
     
         31 . The method of  claim 30 , wherein the locations along the first dimension of the distorted image are separated by a same distance from adjacent locations along the first dimension of the distorted image by constraining a rate of change of (1) the first dimension of the distorted image with respect to (2) the first dimension of the intermediate image. 
     
     
         32 . The method of  claim 30 , wherein the second transform is constrained to map pixels along the first dimension of the transposed rectified image to locations along the first dimension of the transposed intermediate image, and wherein the locations along the first dimension of the transposed intermediate image are separated by a same distance from adjacent locations along the first dimension of the transposed intermediate image. 
     
     
         33 . The method of  claim 32 , wherein the locations along the first dimension of the transposed intermediate image are separated by a same distance from adjacent locations along the first dimension of the transposed intermediate image by constraining a rate of change of (1) the first dimension of the transposed intermediate image with respect to (2) the first dimension of the transposed rectified image. 
     
     
         34 . The method of  claim 30 , further comprising causing, using the homography removal module, a direct memory access controller to transpose the intermediate image prior to removing the second transform from the intermediate image. 
     
     
         35 . The method of  claim 30 , wherein removing the first transform from the distorted image comprises determining, for a first pixel of the intermediate image, a corresponding first location in the distorted image, and convolving pixels surrounding the corresponding location in the distorted image to determine an image value for the first pixel. 
     
     
         36 . The method of  claim 35 , further comprising determining, for a second pixel of the intermediate image having an identical coordinate as the first pixel in a second dimension, a corresponding second location in the distorted image by adding a constant to a coordinate of the corresponding first location in the first dimension. 
     
     
         37 . The method of  claim 30 , further comprising:
 transposing the transposed rectified image to generate a rectified image; and   providing the rectified image to a pattern detection system so that the pattern detection system can use the rectified image to determine whether the rectified image includes a particular pattern.   
     
     
         38 . The method of  claim 30 , further comprising selecting one of a set of kernels based on a sub-pixel coordinate of one of the locations along the first dimension of the distorted image, and applying the selected kernel at the one of the locations. 
     
     
         39 . A non-transitory computer readable medium having executable instructions associated with a homography decomposition module and a homography removal module, operable to cause a machine vision system to:
 receive a distorted image and a homography matrix associated with the distorted image;   determine a first transform and a second transform that collectively represent the homography matrix, wherein:
 the first transform relates the distorted image to an intermediate image, 
 the second transform relates a transposed intermediate image to a transposed rectified image, 
 the distorted image, the intermediate image, the transposed intermediate image, and the transposed rectified image comprise at least a first dimension and a second dimension, 
 the first transform is constrained to map pixels along the first dimension of the intermediate image to locations along the first dimension of the distorted image, and 
 the locations along the first dimension of the distorted image are separated by a same distance from adjacent locations along the first dimension of the distorted image; 
   generate the intermediate image by removing the first transform from the distorted image;   transpose the intermediate image prior to removing the second transform from the intermediate image to generate the transposed intermediate image; and   generate the transposed rectified image by removing the second transform from the transposed intermediate image.