Since the intrusion detection method based on One-Class Support Vector Machine (OCSVM) can not detect internal abnormal points and outliers, which leads to the deviation of decision function from training samples. A new OCSVM anomaly detection function combining DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and K-means was proposed. Firstly, the outliers in the training data were removed by DBSCAN algorithm to eliminate the influence of outliers. Then, K-means clustering method was used to classify normal data clusters, so that the internal abnormal points could be selected. Finally, a one-class classifier for each data cluster was created to detect exception data by OCSVM algorithm. The experimental results on industrial control networks show that the combined classifier can detect the intrusion attacks of the industrial control network by using normal data, and it can improve the detection effect of OCSVM algorithm. In intrusion detection experiment of gas pipeline, the overall detection rate of the proposed method is 91.81%, while the overall detection rate of OCSVM algorithm is 80.77%.

In traditional Non-Local Means (NLM) algorithm, the weighted Euclidean norm can not truly reflect the similarity between two neighborhoods under large noise standard deviation. To address this problem, a new NLM denoising algorithm combined with similarity weight was proposed. Firstly, the noise image was decomposed by using the advantages of stationary wavelet transform, and the filtering function was used to predenoise each detailed subband data. Secondly, according to the refined image, the similarity reference factor between the patches was calculated, and it was used to replace Gauss kernel function of the traditional NLM algorithm. Finally, to make the similarity weights more in line with the characteristics of Human Visual System (HVS), the block Singular Value Decomposition (SVD) method based on image structure perception was used to define neighborhood similarity measure, which can more accurately reflect the similarity between neighborhoods compared with the traditional NLM. The experimental results demonstrate that the hybrid similarity weighted NLM algorithm performs better than the traditional NLM in retaining the texture details and edge information, and the Structural SIMilarity (SSIM) index measurement values is also improved in comparison with the traditional NLM algorithm. When the noise standard deviation is large enough, the proposed approach is of effectiveness and robustness.

The recognition accuracy rate of traditional Sparse Representation Classification (SRC) algorithm is relatively low under the interference of complex non-face ingredient, large training sample set and high similarity between the training samples. To solve these problems, a novel face recognition algorithm based on Cluster-Sparse of Active Appearance Model (CS-AAM) was proposed. Firstly, Active Appearance Model (AAM) rapidly and accurately locate facial feature points and to get the main information of the face. Secondly, K-means clustering was run on the training sample set, the images with high similarity degree were assigned to a category and the clustering center was calculated. Then, the center was used as atomic to structure over-complete dictionary and do sparse decomposition. Finally, face images were classified and recognized by computing sparse coefficients and reconstruction residuals. The face images with different samples and different dimensions from ORL face database and Extended Yale B face database were tested for comparing CS-AAM with Nearest Neighbor (NN), Support Vector Machine (SVM), Sparse Representation Classification (SRC), and Collaborative Representation Classification (CRC). The recognition rate of CS-AAM algorithm is higher than other algorithms with the same samples or the same dimensions. Under the same dimensions, the recognition rate of CS-AAM is 95.2% when the selected number of samples is 210 on ORL face database; the recognition rate of CS-AAM is 96.8% when the selected number of samples is 600 on Extended Yale B face database. The experimental results demonstrate that the proposed method has higher recognition accuracy rate.

When using Linear Deconvolution (LD) algorithm in the selection process, endmembers subset has similar endmembers and similar endmembers have an impact on the accuracy of spectral unmixing,a hyperspectral unmixing optimization algorithm based on per-pixel optimal endmember selection named Spectral Information Divergence (SID) and Spectral Angle Mapping (SAM) was proposed. At the end of the second choice, the method adopted Spectral Information Divergence mixed with Spectral Angle (SID-SA) rule as the most similar endmember selection criteria, removed the similar endmembers and reduced the effect of the accuracy by spectral unmixing. The experiment results show that hyperspectral unmixing optimization algorithm based on SID and SAM makes Root Mean Square Error (RMSE) of reconstruction images be reduced to 0.0104. This method improves the accuracy of endmember selection in comparison with traditional method, reduces abundance estimation error and error distributes more evenly.

There is a long time detection problem caused by too large surveyed area in the classical Tracking-Learning-Detection (TLD) target tracking algorithm. Moreover, the TLD algorithm could not do the similar targets processing well. So in this paper, an efficient approach called TLD-DO was proposed for tracking targets in which the surveyed areas could be automatically adjusted according to the target's velocity of movement. In order to accelerate the process speed of TLD algorithm without reducing tracking precision, a novel algorithm named Double Kalman Filter (DKF) with optimal surveyed area which could reduce the detection range of TLD detector was constructed based on twice Kalman filtering operation for acceleration correction. Meanwhile, the improved method could also increase the accuracy of target tracking through eliminating the interference of the similar targets in complex background. The experimental results show that tracking effect of improved method is better than that of the original TLD algorithm under the circumstance of similar target disturbance. Furthermore, the detection speed has been improved 1.31-3.19 times for different videos and scenes. In addition, the improved method is robust to target vibration or distortion.

For the traditional Gaussian mixture model cannot detect complete moving object and is prone to detect the background as the foreground region, an improved algorithm was proposed for moving object detection based on Gauss mixture model. The Gaussian background model mixed with improved frame difference method for integration, distinguished the uncovered background area and moving object region, which could extract the complete moving object. To give a larger background updating rate of uncovered background area, the background exposure of regional influences was eliminated. In complex scene, it used the method of replacement by background model to improve the stability of the algorithm. The experiments prove that the improved algorithm has been greatly improved in the aspects of adaptability, accuracy, real-time, practicality and so on, and can correctly and effectively detect moving object in the situation with various complicated factors.

A block resource scheduling strategy for remote sensing images in multi-line server environment was proposed with the problems of huge amount of remote sensing data, heavy server load caused by multi-user concurrent requests which decreased the transmission efficiency of remote sensing images. To improve the transmission efficiency, an Improved Ant Colony Optimization (IACO) algorithm was used, which introduced a line waiting factor γ to dynamically select the optimal transmission lines. Intercomparison experiments among IACO, Ant Colony Optimization (ACO), Max-min, Min-min, and Random algorithm were conducted and IACO algorithm finished the tasks in the client and executed in the server with the shortest time, and the larger the amount of tasks, the more obvious the effect. Besides, the line resource utilization of IACO was the highest. The simulation results show that: combining multi-line server block scheduling strategy with IACO algorithm can raise the speed of remote sensing image transmission and the utilization of line resource to some degree.