A panorama-based method of personal positioning and orientation and its real-time applications for wearable computers

In this paper, we describe an improved method of personal positioning and orientation using image registration between input video frames and panoramic images captured beforehand. In our previous work, we proposed the method of image registration with an affine transform. However, the affine transform is generally not capable of image registration between a frame and a panorama. We improved the previous method so that it can estimate projective transform parameters without severely increasing computational cost. We also improved the method to be robust with respect to lighting changes by using the weighted sum of absolute difference of both brightness and its gradient between images. We confirmed that this improved method could estimate image registration parameters under conditions that hindered the previous method. Its computational cost increased by only 10-20% and its software implementation was capable of real-time processing.