Precise Wide Baseline Stereo Image Matching for Compact Digital Cameras

Martinus Edwin Tjahjadi, Fourry Handoko


Numerous  image  matching  methods  for  wide range  of  applications  have  been  invented  in  the  last  decade. When high precision  and reliability  of the  object space  point coordinates  is  highly  demanding,  a  stereo  image  matching method which can produce conjugate point of images and a standard deviation of  the  matched point  is  examined. In  this approach, image gradients are used locally to seek a conjugate patch.  The  normalized  cross  correlation  is  first  utilized  to estimate an approximate location of the conjugate patch between two normalized images. Then the location of conjugate patch is further refined by using Gaussian-Newton least squares image matching. Both radiometric and geometric parameters of least squares models are used selectively in seeking the best possible accuracy.  Iterative  computation is  conducted to  incrementally refine the geometric location of the conjugate point. After a matched patch has been found, a variant-covariant matrix of the parameter is analyzed to inform the precision of the conjugate points  both  on  images  and  object  space.  This  method  can compute high precision object space points and some examples demonstrate the insight of the approach.

Full Text: PDF


  • There are currently no refbacks.