摘要：Keypoint matching is of fundamental importance in computer vision applications. Fish-eye lenses are convenient in such applications that involve a very wide angle of view. However, their use has been limited by the lack of an effective matching algorithm. The Scale Invariant Feature Transform (SIFT) algorithm is an important technique in computer vision to detect and describe local features in images. Thus, we present a Tri-SIFT algorithm, which has a set of modifications to the SIFT algorithm that improve the descriptor accuracy and matching performance for fish-eye images, while preserving its original robustness to scale and rotation. After the keypoint detection of the SIFT algorithm is completed, the points in and around the keypoints are back-projected to a unit sphere following a fish-eye camera model. To simplify the calculation in which the image is on the sphere, the form of descriptor is based on the modification of the Gradient Location and Orientation Histogram (GLOH). In addition, to improve the invariance to the scale and the rotation in fish-eye images, the gradient magnitudes are replaced by the area of the surface, and the orientation is calculated on the sphere. Extensive experiments demonstrate that the performance of our modified algorithms outweigh that of SIFT and other related algorithms for fish-eye images.
