Change Detection on Comparametrically Related Images

In this paper we present a change detection approach for exposure-different images. This approach is based on a significance test on the joint comparametric probability distribution, that is, the joint noise and intensity image pair distribution. The approach involves determining a binary comparametric change detection mask for which homologous pixel pairs in our images are compared. In addition, joint spatial and tonal image registration is performed prior to carrying out the change detection. Two examples of real imagery are presented and receiver operating characteristic curves from three other change detection approaches are provided as comparison. The results demonstrate the increasing importance of properly accounting for exposure in change detection approaches as the exposure difference between images increases.