In order to solve the problem of low accuracy of video-based person re-identification caused by factors such as occlusion, background interference, and person appearance and posture similarity in video surveillance, a video-based person re-identification method of Evenly Sampling-random Erasing (ESE) and global temporal feature pooling was proposed. Firstly, aiming at the situation where the object person is disturbed or partially occluded, a data enhancement method of evenly sampling-random erasing was adopted to effectively alleviate the occlusion problem, improving the generalization ability of the model, so as to more accurately match the person. Secondly, to further improve the accuracy of video-based person re-identification, and learn more discriminative feature representations, a 3D Convolutional Neural Network (3DCNN) was used to extract temporal and spatial features. And a Global Temporal Feature Pooling (GTFP) layer was added to the network before the output of person feature representations, so as to ensure the obtaining of spatial information of the context, and refine the intra-frame temporal information. Lots of experiments conducted on three public video datasets, MARS, DukeMTMC-VideoReID and PRID-201l, prove that the method of jointing evenly sampling-random erasing and global temporal feature pooling is competitive compared with some state-of-the-art video-based person re-identification methods.

Focusing on the problems in video semantic detection that the insufficience of labeled samples would seriously affect the performance of the detection and the performances of the base classifiers in ensemble learning would be improved deficiently due to noise in the pseudo-label samples, a semi-supervised ensemble learning algorithm based on pseudo-label confidence selection was proposed. Firstly, three base classifiers were trained in three different feature spaces to get the label vectors of the base classifiers. Secondly, the error between the maximum and submaximal probability of a certain class of weighted fusion samples and the error between the maximum probability of a certain class of samples and the average probability of the other classes of samples were introduced as the label confidences of the base classifiers, and the pseudo-label and integrated confidence of samples were obtained through fusing label vectors and label confidences. Thirdly, samples with high degree of integrated confidence were added to the labeled sample set, and base classifiers were trained iteratively. Finally, the trained base classifiers were integrated to detect the video semantic concept collaboratively. The average accuracy of the algorithm on the experimental data set UCF11 reaches 83.48%. Compared with Co-KNN-SVM algorithm, the average accuracy is increased by 3.48 percentage points. The selected pseudo-label by the algorithm can reflect the overall variation among the class of samples and other classes, as well as the uniqueness of the class of samples, which can reduce the risk of using pseudo-label samples, and effectively improve the accuracy of video semantic concept detection.

In data mining, mining maximum frequent itemsets instead of mining frequent itemsets can greatly improve the operating efficiency of system. The running time consumption of existing maximum frequent itemset mining algorithms is still very large. In order to solve the problem, a new DiffNodeset Maxmal Frequent Itemset Mining (DNMFIM) algorithm was proposed. Firstly, a new data structure DiffNodeset was adopted to realize the fast calculation of intersection and support degree. Secondly, the connection method with linear time complexity was adopted to reduce the complexity of connecting two DiffNodesets and avoid multiple invalid calculations. Then, the set-enumeration tree was adopted as the search space, and a variety of optimal pruning strategies were used to reduce the search space. Finally, the superset detection technology used in the MAximal Frequent Itemset Algorithm (MAFIA) algorithm was adopted to improve the accuracy of algorithm effectively. The experimental results show that, DNMFIM algorithm outperforms MAFIA and N-list based MAFIA (NB-MAFIA) in terms of time efficiency. The proposed algorithm has a good performance when mining the maximal frequent itemsets in different types of datasets.

Starting from the enhanced ability of fractional differential to image details, the authors analyzed the mechanism of fractional differential. By averaging the nonzero weights of operator template to the image pixels which have the same distance to constant coefficient “1” as well as utilizing self-dependency of surrounding pixels, an improved fractional order differential operator template was achieved. The experimental results show: in response to those images that have rich textural detail information, fractional differential outperforms integral differential operation to extract the textural detail information in smooth region witout too much gray scale change.