Search

Object tracking has been one of the most important and active research areas in the field of computer vision. In this paper, we address the problem of object tracking under complex conditions in a video, which propose a object tracking method based on particle filter of adaptive patches combined color histograms with Histogram of Oriented Gradient(HOG). The adaptive patch is performed by horizontal and vertical projection based on object gray levels, which can improve the patch adaptability to the object appearance diversity and the accuracy of object tracking under occlusion conditions. The fusion of color histograms and HOG features is adopted to describe each sub-patch, which not only solves the tracking divergence problem of similar objects, but also reduces the effect of local deformation. In addition, the weighted Bhattacharyya coefficient is introduced to calculate the sub-patch matching degree of the particle, and the particle sub-patch weight will be adjusted by integrating the particle space information, and the feature model is also updated in time to achieve robust object tracking. Many simulation experiments show that our proposed algorithm achieves more favorable performance than these existing state-of-the-art algorithms in handing various challenging videos, especially occlusion and shape deformation.

Assessment model for the potential of clean energy development should be proposed because which is important for more efficient clean energy development. Introduce the mutation theory into the assessment of the development potential of clean energy and establish a model for the evaluation of the development potential of clean energy. Through the example analysis, the validity of the established evaluation index of the potential of clean energy development is verified, and the validity of the model of mutation evaluation of the potential of clean energy development is verified.

In the existing multiple choice methods of decision tree' test attributes, can't see such report as” Let missing data processing integrated in the selection process of test attributes”, however, the existing process methods of missing attribute value data can draw into bias in different degrees, base on this, propose an information gain rate base on combination entropy as the decision tree's testing attributes selection criteria, which can eliminate missing value arrtibutes' infulence on testing attributes selection, and be implemented on WEKA. The computational complexity of the MultiInfo Tree is better than that of C4.5.

Network traffic prediction is an important research aspect of network behavior. Conventionally, ARMA time sequence model is usually adopted in network traffic prediction. However, the parameters used in normal time sequence models are difficult to be estimated and the nonstationary time sequence problem can not be processed using ARMA time sequence model. The neural network techniques may memory large quantity of characteristics of data set by learning previous data, and is suitable for solving these problems with large complexity. IP6 network traffic prediction is just the problem with nonlinear feature and can be solved using appropriate neural network model. In this paper, according to the daily cycle characteristic of IPv6 network traffic, a novel transfer function is designed, which has lots of advantages such as fast convergence and high precision. Based on the new transfer function, an improved BP neural network model is produced, and a IPv6 network traffic prediction system is implemented. Using this new BP neural network model to process the actual data, the results present that our model has a faster learning ability and has a higher precision compared with previous BP neural network model. Therefore, this BP neural network model can be used for normal traffic prediction in current IPv6 network.