Many techniques have been developed for computer vision in the past years. Features extraction and matching are the basis of many high-level applications. In this paper, we propose a multi-level features extraction for discontinuous target tracking in remote sensing image monitoring. The features of the reference image are pre-extracted at different levels. The first-level features are used to roughly check the candidate targets and other levels are used for refined matching. With Gaussian weight function introduced, the support of matching features is accumulated to make a final decision. Adaptive neighborhood and principal component analysis are used to improve the description of the feature. Experimental results verify the efficiency and accuracy of the proposed method.
Image matching is an important problem in computer vision and many technologies based on local descriptors have been developed. In this paper, we propose a novel local features descriptor based on an adaptive neighborhood and embedding Zernike moments. Instead of a fixed-size neighborhood, a size changeable neighborhood is introduced to detect the key-points and describe the features in the frame of Gaussian scale space. The radius is determined by the scale parameter of the key-point and the dominant direction is computed based on skew distribution fitting instead of the traditional eight-direction statistics. Then a 72-dimensional features vector based on a 3×3 grid is presented. A 19-dimensional vector consists of Zernike moments are applied to achieve better rotation invariance and finally contributes to a 91-dimensional descriptor. The accuracy and efficiency of proposed descriptor for image matching are verified by several numerical experiments.
Computer vision has been developed greatly in the past several years, and many useful and interesting technologies have been presented and widely applied. Image matching is an important technology based on similarity measurement. In this paper, we propose a novel feature describing model based on scale space and local principle component analysis for heterogeneous image matching. The traditional uniform eight-direction statistics is updated by a task-related k-direction statistics based on prior information of the keypoints. In addition, the k directions are determined by an approximately solution of a Min-Max problem. The principle component analysis is introduced to compute the main directions of local patches based on the gradient field. In addition, the describing vector is formed by then implementing PCA on each sub-patch of a mesh. Experimental results show the accuracy and efficiency of proposed method.