Optical flow estimation in omnidirectional images using wavelet approach

The motion estimation computation in the image sequences is a significant problem in image processing. Many researches were carried out on this subject in the image sequences with a traditional camera. These techniques were applied in omnidirectional image sequences. But the majority of these methods are not adapted to this kind of sequences. Indeed they suppose the flow is locally constant but the omnidirectional sensor generates distortions which contradict this assumption. In this paper, we propose a fast method to compute the optical flow in omnidirectional image sequences. This method is based on a Brightness Change Constraint Equation decomposition on a wavelet basis. To take account of the distortions created by the sensor, we replace the assumption of flow locally constant used in traditional images by a hypothesis more appropriate.