Fast tracking of feature points in full-view image

This paper proposes a method of fast tracking feature points in a full-view image. The full-view image consists of a pair of fisheye sub-images. Each sub-image of the sensor has wider field of view than a hemisphere. The local region of feature points of scenes changes abruptly when the feature points move from one of the pair of fisheye sub-image to the other due to the heavy distortion of fisheye images. In this paper, the tracking of feature points is performed via a spherical model. The similarity of local region of feature points is measured by the normalized image patch of the local region on the spherical model. The computation process is carried out speedily using a look-up table. Furthermore, a good performance on matching correctness via tracking is achieved.