A least squares approach for the joint domain and range registration of images

An approach for jointly registering images in domain and range using a least squares formalism is presented. This joint approach is in contrast to almost all current registration methods that only register images with respect to their domains and neglect accounting for exposure differences between images. The inclusion of range into the registration process is accomplished by approximating the camera's nonlinear comparametric function with a piecewise linear one. This results in a computationally attractive least squares approach to an otherwise inherently nonlinear optimization problem. The effectiveness of this approach is illustrated.