Method for tracking point feature based on fractional-order differentiation

Abstract

The invention relates to a method for tracking a point feature based on fractional-order differentiation, comprising detecting a point feature by adopting a method based on the fractional-order differentiation; forecasting the location of the next frame point by using a Kalman method or an extension method; searching in a given area, carrying out a similarity measurement, and acquiring a corresponding tracking point if requirements are satisfied; otherwise, considering the corresponding tracking point to be absent, and for such a point, considering the tracking is lost if a corresponding matched tracking point is still absent in a range of following k frames, wherein the value of k is larger than 2; and updating the point feature if the tracking is normal. The fractional-order differentiation has advantages over integral-order differentiation in presenting areas which have abundant texture details and inconspicuous texture information. Different differential gradient images are formed for fractional-order differentiation with different directions and different orders, and convolution directional diagrams with different scales are formed by combining the different differential gradient images with Gaussian kernel convolution in different sizes respectively, so that significant changes presented by the point feature are ensured when the direction is changed, having properties of rotation invariance, translation and scale invariance.

Description

technical field [0001] The invention relates to a point feature tracking method based on fractional differentiation. Background technique [0002] In the point feature tracking method, the detection and accurate matching of points is a difficult point, mainly due to the change of camera angle, low image quality and occlusion. The key of point detection and matching is point feature representation and similarity measure. At present, the latest point feature extraction methods include SIFT, SURF, and DAISY. Lowe proposed the scale-invariant feature point extraction algorithm SIFT in 1999, by calculating the gradient histogram of the feature point neighborhood as the descriptor of the feature point, and then matching according to the descriptor of the feature point. However, the calculation of SIFT feature points is complex, the dimension is high, and the real-time performance is poor. [0003] Herbert Bay proposed a fast and robust feature point detection algorithm (Speed ​...

AI Technical Summary

Problems solved by technology

However, these methods are all based on the eigenvectors obtained by integer order differentiation, which are not accurate for the slight blur caused by the shaking in the mobile vehicle camera shooting and the speed of the vehicle, or the information description of the point features in the area where the texture information is not obvious.

Images