To solve the issue of low precision and poor real-time performance in image registration, this paper presents an algorithm for extracting and matching of image feature points based on an invariant feature algorithm of the complementation between Harris operator corner detection and SIFT algorithm. First, with Harris operator ‘s quick calculating, the algorithm extracts much corner points in the image as original feature points. Then, description goes to the feature vector of pre-selected feature points on the strike of scale-space invariant features transform (SIFT), thus obtaining descriptors of feature points. By calculating the minimum Euclidean distance of two points in vectors of different feature points described by the SIFT algorithm in the two to-be-spliced images, the accurate image matching is then achieved. Experiments demonstrate that the algorithm combines the rapid achieve performance of Harris operator and the scale-space invariance of the SIFT algorithm, which boasts good robustness for translation, whirling and scaling transformation. In the experiments of 100 images, when there occurs the translation, whirling or scaling transformation to the image, the fully consistent ratio between the coordinates of matching points and the actual coordinates with using this algorithm is over 95%. This algorithm can quickly extract with high precision feature points for matching to achieve the seamless images.
For the mean shift tracking algorithm, we use the histogram feature which contains little information, but the moving direction and velocity information are not been considered, which leads to the target will be missed easily, what is more, the limitation of traditional algorithm which can not change the size of the window to adapt to the size of target, etc. To overcome those weaknesses, we introduce both the target feature representation idea having the features of adapting to window size adjustment and spatial characteristics and the nature of the kernel function, then, there is no need to estimate the probability for all regions. The results of experiment show that compared with using kalman filtering and mean shift algorithm alone, the weighted mean improved filtering algorithm has greatly improved the instability of target tracking and the robustness of the moving target tracking.