Improving the Point Correspondence Accuracy of Kanade-Lucas Method

J.B. Shim, Y. Takeuchi, T. Mukai, and N. Chnishi (Japan)


Kanade-Lucas(KL) method, affine transformation, point correspondence, correlation.


The Kanade-Lucas(KL) feature tracker is one of the good matching methods. However it fails to find corresponded points of two images when image motion is quite large. We propose the feature point matching method by the use of affine transformation and correlation so that KL method works well for large image motion. First, KL method is used for matching points. Some points are matched well, other points are mismatched or failed to be matched. Sec ond, correlation of two matched points between the first and the second image obtained by KL method is used to discriminate well matched point and badly matched point. If correlation coefficient is lower than a specified thresh old, it is regarded as an outlier. Third, all the points to be matched in the first image are transformed on the sec ond image by affine transformation obtained by the use of well matched points alone. However, all the transformed points from the first image to the second image are not matched well due to the movement of image. The role of affine transformation is to reduce the computation time and the number of mismatching points by designating only the small searching area around the transformed point. Finally, correlation is used to find the best matching point around the transformed point. Real image data has been used to test the proposed method, and excellent results have been obtained with the error of 0.811 pixels in average.

Important Links:

Go Back