No abstract

No abstract

No abstract

Target tracking is an important task in computer vision. Now many tracking algorithms have achieved great results. However, several challenges still hinder the development of tracking algorithms, such as abrupt motion, occlusion and so on. In order to use the feature information of the target more effectively and improve the accuracy and robustness of target tracking, a novel model is designed which is different from the previous discriminative component and generative component, and a novel discriminative-generative collaborative appearance model is presented to combine the two components in this paper. First, for the discriminative component, Locality-Constrained Sparse Coding Algorithm is proposed. In this algorithm, the objective function of the local feature of the target spatial information is determined by fusing the pyramid maximum pool and local feature histogram method. The objective function has three important parameters, which are solved by different optimization strategies. Second, for the generative component, the Histogram of Locality-Constrained Feature Algorithm is proposed. In this algorithm, the locality constraint is served to describe the spatial information of the target as a generative appearance model. Each image patch can be approximated by a linear combination of a local coordinate system formed by a dictionary whose elements are cluster centers that contain the most representative model of the target. Third, this paper designs a collaborative target tracking framework based on semi-supervised learning algorithm with locality constraint coding. The framework can quickly and robustly determine the feature information of the tracking region. The proposed algorithm is evaluated on the comprehensive test platform. The experimental results show that our method is more robust and efficient, and the precision and success rate of our algorithm are improved by 5.4% and 4.7%, respectively. INDEX TERMS Locality-constrained, collaborative model, visual tracking, Bayesian framework.

An intelligent rolling bearing fault diagnosis method is proposed using empirical mode decomposition (EMD)–Teager energy operator (TEO) and Mahalanobis distance. EMD can adaptively decompose vibration signals into a series of intrinsic mode functions (IMFs), which are zero mean monocomponent AM–FM signals. TEO can estimate the total mechanical energy required to generate signals. Thus, TEO exhibits good time resolution and self-adaptive ability with regard to the transient components of the signal, which is an advantage in detecting signal impact characteristics. With regard to the impulse feature of the bearing fault vibration signals, TEO can be used to detect the cyclical impulse characteristic caused by bearing failure, gain an instantaneous amplitude spectrum for each IMF component, and then identify the characteristic frequency of a single, interesting IMF component in the bearing fault by means of the Teager energy spectrum. The amplitude of the Teager energy spectrum in the inner race and outer race fault frequencies, as well as the ratio of the energy of the resonance frequency band to the total energy, were extracted as feature vectors, which were then separately used as training samples and test samples for fault diagnosis. Thereafter, the Mahalanobis distances between the real measure and the different overall types of fault samples were calculated to classify the real condition of the rolling bearing. Finally, the Mahalanobis distances were converted into CV values, which assessed the current health state of the rolling bearing. Experimental results prove that this method can accurately identify and diagnose different fault types of rolling bearings.