Traditional laser localization algorithms such as Monte Carlo localization algorithm have the problems of low accuracy and poor anti-robot kidnapping performance, and traditional two-dimensional code localization algorithms have complex environmental layout and strict limitation to robot's trajectory. In order to solve these problems, a mobile robot localization algorithm based on two-dimensional code vision and laser lidar data was proposed. Firstly, the computer vision technology was used by the robot to detect two-dimensional codes in the test environment, and the poses of detecting two-dimensional codes were transformed to map coordinates respectively, and they were fused to generate the prior pose information. Then the optimized pose was obtained by the point cloud alignment with the generated information as the initial poses. At the same time, the odometry-vision supervising mechanism was introduced to effectively solve the problems brought by the environmental factors such as the information lack of two-dimensional codes and the wrong recognition of the two-dimensional codes as well as ensure the smoothness of the poses. Finally, experimental results based on mobile robot show that, the proposed algorithm has the average error of lidar sampling points reduced by 92%, the average time spent per pose calculation reduced by 88% compared with the classical Adaptive Monto Carlo Localization (AMCL) algorithm, and it solves robot kidnapping problem effectively. This algorithm can be applied to the indoor robots such as storage robot.

Tracking of the person crossing the cameras is a technical challenge for smart city and intelligent security. And person re-identification is the most important technology for cross-camera person tracking. Due to the domain bias, applying person re-identification algorithms for cross-scenario application leads to the dramatic accuracy reduction. To address this challenge, a method based on Generative Adversarial Network (GAN) Uniting with Spatial-Temporal pattern (STUGAN) was proposed. First, training samples of the target scenario generated by the GAN were introduced to enhance the stability of the recognition model. Second, the spatio-temporal features were used to construct the spatio-temporal pattern of the target scenario, so as to screen low-probability matching samples. Finally, the recognition model and the spatio-temporal pattern were combined to realize the person re-identification task. On classic datasets of this field named Market-1501 and DukeMTMC-reID, the proposed method was compared with BoW (Bag-of-Words), PUL (Progressive Unsupervised Learning), UMDL (Unsupervised Multi-task Dictionary Learning) and other advanced unsupervised algorithms. The experimental results show that the proposed method achieves 66.4%, 78.9% and 84.7% recognition accuracy for rank-1, rank-5 and rank-10 indicators on the Market-1501 dataset respectively, which are 5.7, 5.0 and 4.4 percentage points higher than the best results of the comparison algorithm, respectively; and the mean Average Precision (mAP) higher than the comparison algorithms except Similarity Preserving cycle-consistent Generative Adversarial Network (SPGAN).

Aiming at the problems of insufficient generalization ability, poor stability and difficulty in meeting the real-time requirement of facial expression recognition, a real-time facial expression recognition method based on multi-scale kernel feature convolutional neural network was proposed. Firstly, an improved MSSD (MobileNet+Single Shot multiBox Detector) lightweight face detection network was proposed, and the detected face coordinates information was tracked by Kernel Correlation Filter (KCF) model to improve the detection speed and stability. Then, three linear bottlenecks of three different scale convolution kernels were used to form three branches. The multi-scale kernel convolution unit was formed by the feature fusion of channel combination, and the diversity feature was used to improve the accuracy of expression recognition. Finally, in order to improve the generalization ability of the model and prevent over-fitting, different linear transformation methods were used for data enhancement to augment the dataset, and the model trained on the FER-2013 facial expression dataset was migrated to the small sample CK+ dataset for retraining. The experimental results show that the recognition rate of the proposed method on the FER-2013 dataset reaches 73.0%, which is 1.8% higher than that of the Kaggle Expression Recognition Challenge champion, and the recognition rate of the proposed method on the CK+ dataset reaches 99.5%. For 640×480 video, the face detection speed of the proposed method reaches 158 frames per second, which is 6.3 times of that of the mainstream face detection network MTCNN (MultiTask Cascaded Convolutional Neural Network). At the same time, the overall speed of face detection and expression recognition of the proposed method reaches 78 frames per second. It can be seen that the proposed method can achieve fast and accurate facial expression recognition.

An image fusion algorithm based on Lifting Stationary Wavelet Transform(LSWT) and joint structural group sparse representation was proposed to restrain pseudo-Gibbs phenomenon created by conventional wavelet transform in multi-focus image fusion, overcome the defect that the fusion method with conventional sparse representation was likely to lead textures, edges, and other detail features of fused images to the tendency of smoothness, and improve the efficiency and quality of multi-focus image fusion. Firstly, lifting stationary wavelet transform was conducted on the experimental images, different fusion modes were adopted according to the respective physical characteristics of low frequency coefficients and high frequency coefficients after decomposition. When selecting coefficients of low frequency, the scheme of coefficient selection based on joint structural group sparse representation was adopted; When selecting coefficients of high frequency, the scheme of coefficient selection based on Directional Region Sum Modified-Laplacian (DRSML) and matched-degree was adopted. Finally, ultimate fusion image was obtained by inverse transform. According to the experiment results, the improved algorithm can effectively improve such image indicators as mutual information and average gradient, keep textures, edges, and other detail features of images intact, and produce better image fusion effects.

Plant recognition includes two kinds of tasks:specimen recognition and real-environment recognition. Due to the existence of background noise, real-environment plant image recognition is more difficult. To reduce the weight of Convolutional Neural Networks (CNN), to improve over-fitting, to improve the recognition rate and generalization ability, a method of plant identification with Family Priority (FP) was proposed. Combined with the lightweight CNN MobileNet model, a plant recognition model Family Priority MobileNet (FP-MobileNet) was established by means of migration learning. On the single background plant dataset flavia, the MobileNet model achieved 99.8% of accuracy. For the more challenging real-environment flower dataset flower102, when the number of samples in the training set was greater than that in the test set FP-MobileNet achieved 99.56% of accuracy. When the number of samples in the training set was smaller than that in the test set, FP-MobileNet still obtained 95.56% of accuracy. The experimental results show that the accuracies of FP-MobileNet under two different data set partitioning schemes are both higher than those of the pure MobileNet model. In addition, FP-MobileNet weighs only occupy 13.7 MB with high recognition rate. It takes into account both accuracy and delay, and is suitable for promotion to mobile devices that require a lightweight model.

The traditional intrusion prevention system is the serially connected in the network environment, its ability to deal with the intrusion is limited and may cause network congestion easily. In order to solve the problems, an intrusion prevention scheme for cloud computing applications was designed based on Software Defined Network (SDN). Firstly, the SDN controller was integrated in the OpenStack platform. Then, by using the programmable characteristics of the controller, the linkage mechanism of intrusion detection and controller was designed to realize the intrusion prevention. The principle of the linkage mechanism is that the intrusion information is passed to the controller when the intrusion detection system detects the intrusion, then the security policy was issued to the virtual switch by the controller for filtering the intrusion traffic and dynamically preventing the intrusion. Finally, the proposed scheme was compared with the traditional intrusion prevention scheme in experiment. The comparison and analysis results show that, the proposed scheme can detect more than 90% of the instructions when they come at 40000 packets per second, while the traditional scheme only detect 85% of the instructions when they come at 12000 packets per second. The proposed scheme can be used to improve the detection efficiency of intrusion prevention in the cloud environment.

A new denoising algorithm, Adaptive Total Generalized Variation (ATGV), was proposed for removing streak artifacts within the reconstructed image of low-dose Computed Tomography (CT). Considering the shortage that the traditional Total Generalized Variation (TGV) would blur the edge details, the intuitionistic fuzzy entropy which can distinguish the smooth and detail regions was introduced into the TGV algorithm. Different areas of the image were processed with different denoising intensities. As a result, the image details could be well preserved. Firstly, the Filtered Back Projection (FBP) algorithm was used to obtain a reconstructed image. Secondly, the edge indicator function based on intuitive fuzzy entropy was applied to improve the TGV algorithm. Finally, the new algorithm was employed to reduce the noise in the reconstructed image. The simulations of the low-dose CT image reconstruction for the Shepp-Logan model and the thorax phantom were used to test the effectiveness of the proposed algorithm. The experimental results show that the proposed algorithm has the smaller values of the Normalized Mean Square Distance (NMSD) and Normalized Average Absolute Distance (NAAD) in the two experiment images, compared with the Total Variation (TV) algorithm and TGV algorithm. Meanwhile, the two experiment images processed with the new method can obtain high Peak Signal-to-Noise Ratios (PSNR) of 26.90 dB and 44.58 dB, respectively. So the proposed algorithm can effectively preserve image details and edges, while reducing streak artifacts.

For the common key space shortage problem found in existing Arnold digital image encryption algorithm, a new digital image encryption algorithm-SMA (Sparse Matrix Arnold) based on sparse matrix and Arnold transformation was proposed and in order to further improve the security of the algorithm, an improved algorithm-3SMA (3 round SMA) using the ideas of multi-layered decomposition and three-tier structure encryption was proposed. The SMA algorithm adopted Arnold transform to spread the plaintext picture into a large sparse matrix, and then removed invalid sparse matrix elements to get the cipher text. While, the decryption of SMA needed to enter the cipher text picture, and moved pixels in cipher text picture back to their original positions in accordance with the previously computed swapping table. The 3SMA algorithm comprised three different round keys. Each round, the improved algorithm needed to process two color components of the plaintext picture to achieve the purpose of encryption. The experimental results show that the proposed encryption algorithm and its improvement obtain higher security compared to Arnold encryption algorithms analyzed.

To solve the problem that high dimension of descriptor decreases the matching speed of Scale Invariant Feature Transform (SIFT) algorithm, an improved SIFT algorithm was proposed. The feature point was acted as the center, the circular rotation invariance structure was used to construct feature descriptor in the approximate size circular feature points' neighborhood, which was divided into several sub-rings. In each sub-ring, the pixel information was to maintain a relatively constant and positions changed only. The accumulated value of the gradient within each ring element was sorted to generate the feature vector descriptor when the image was rotated. The dimensions and complexity of the algorithm was reduced and the dimensions of feature descriptor were reduced from 128 to 48. The experimental results show that, the improved algorithm can improve rotating registration repetition rate to more than 85%. Compared with the SIFT algorithm, the average matching registration rate increases by 5%, the average time of image registration reduces by about 30% in the image rotation, zoom and illumination change cases. The improved SIFT algorithm is effective.

A robust distributed output tracking controller was proposed for a class of linear multi-Agent system subject to external disturbances. This controller was applied to the case where the communication topology among the Agents was direct and possibly time-varying (i.e. switching). This controller is composed of two parts: the first part could ensure the tracking error uniformly exponentially converges to zero in the ideal case (without external disturbances), while the other part was used to compensate for the effect of the present disturbances. It is shown that the effect of constant disturbances can be completely attenuated by the proposed controller, that is, the tracking error converges asymptotically to zero even in the presence of constant disturbances; while for other type of disturbances with bounded derivatives, the ultimate bound of tracking error can be made arbitrarily small by choosing appropriate design parameters. Finally, the two-fold theoretical results were verified by a simulation example.

Concerning the serious recession problems of the low-dose Computed Tomography (CT) reconstruction images, a low-dose CT reconstruction method of MLEM based on non-locality and variable exponent was presented. Considering the traditional anisotropic diffusion noise reduction is insufficient, variable exponent which could effectively compromise between heat conduction and anisotropic diffusion P-M models, and the similarity function which could detect the edge and details instead of gradient were applied to the traditional anisotropic diffusion, so as to achieve the desired effect. In each iteration, firstly, the basic MLEM algorithm was used to reconstruct the low-dose projection data. And then the diffusion function was improved by the non-local similarity measure, variable index and fuzzy mathematics theory, and the improved anisotropic diffusion was used to denoise the reconstructed image. Finally median filter was used to eliminate impulse noise points in the image. The experimental results show the proposed algorithm has a smaller numerical value than OS-PLS (Ordered Subsets-Penalized Least Squares), OS-PML-OSL (Ordered Subsets-Penalized Maximum Likelihood-One Step Late), and the algorithm based on the traditional PM, in the variance of Mean Absolute Error (MAE), and Normalized Mean Square Distance (NMSD), especially its Signal-to-Noise Ratio (SNR) is up to 10.52. This algorithm can effectively eliminate the bar of artifacts, and can keep image edges and details information better.

In order to decrease the influence caused by low bandwidth and high latency on Media Access Control (MAC) layer in Underwater Acoustic Sensor Network (UWASN), an Evolutionary Game Theory based MAC (EGT-MAC) protocol was proposed. In EGT-MAC, each sensor node adopted two strategies including spatial multiplexing and temporal multiplexing. With the replication kinetics equation, each strategy got an evolutionary stable strategy and reached stable equilibrium of evolution. In this way, it improved channel utilization rate and data transmission efficiency to achieve performance optimization for MAC protocol. The simulation results show that EGT-MAC can improve the network throughput as well as the transmission rate of data packet.

Concerning the contradiction between edge-preserving and noise-suppressing in the process of image denoising, a patch similarity anisotropic diffusion algorithm based on variable exponent for image denoising was proposed. The algorithm combined adaptive Perona-Malik (PM) model based on variable exponent for image denoising and the idea of patch similarity, constructed a new edge indicator and a new diffusion coefficient function. The traditional anisotropic diffusion algorithms for image denoising based on the intensity similarity of each single pixel (or gradient information) to detect edge cannot effectively preserve weak edges and details such as texture. However, the proposed algorithm can preserve more detail information while removing the noise, since the algorithm utilizes the intensity similarity of neighbor pixels. The simulation results show that, compared with the traditional image denoising algorithms based on Partial Differential Equation (PDE), the proposed algorithm improves Signal-to-Noise ratio (SNR) and Peak-Signal-to-Noise Ratio (PSNR) to 16.602480dB and 31.284672dB respectively, and enhances anti-noise capability. At the same time, the filtered image preserves more detail features such as weak edges and textures and has good visual effects. Therefore, the algorithm achieves a good balance between noise reduction and edge maintenance.

When dealing with keywords detection without training samples, template matching-based keyword spotting can still be able to spot compared with the traditional method. However, template matching-based method is time-consuming, because it uses frame-by-frame move method to calculate the local minimum distance. The extreme points of the local minimum distance are usually near phoneme segmentation points. A fast template matching method can come out by combining their positions with interpolation idea. By using interpolation to generate the local minimum distance between phoneme segmentation points, this method can greatly reduce the calculation time. When running on the TIMIT and CASIA corpus, the improved method approximately is 2.8 times faster than the conventional template matching-based keyword spotting.

In order to ensure system security and reflect availability in authorization management, a method for querying authorization was proposed based on solvers for partial maximal satisfiability problem. Static authorization descriptions and dynamic mutually exclusive constraints were translated into hard clauses. The algorithm was adopted to update hard clauses and translate requested permissions into soft clauses. Soft clauses were effectively encoded, and the recursive algorithm was utilized to satisfy all hard clauses and as many soft clauses as possible. The experimental results show that the method can ensure system security, it follows the least privilege principle, and the query efficiency outperforms solvers for maximal satisfiability problem.

Concerning the problem of the decline of 3GPP Long Term Evolution (LTE) system throughput caused by the frequent handover, a location prediction model based on user movement mechanism and changing probability of direction was proposed. The proposed model was combined with the standard handover algorithm of LTE. The model calculated the weight of each possible location using the changing probability of direction, then got the predicted received signal strength through summing. The simulation results show that the number of handover does not change obviously, but the system throughput is improved after using the combined algorithm. In addition, the proposed model is better than the traditional data mining prediction model.

To acquire landmark's information and calculate unmanned helicopter's attitude information, a landmark recognition method based on image's contour fitting was proposed in this paper. The method judged the landmark's situation through imposing geometric constraint. If the image contained full landmark, real-time calculation of corners could obtain the helicopter's attitude information; if the image contained part of the landmark, the method could estimate the direction and size of the helicopter's movement which would make the landmark presented in the view completely. The simulations under the condition of laboratory show that the proposed method is stable and feasible.

For describing the distribution of samples with high-dimensions and discrete classification data, the method of scoring-ratio based on Gain was presented. It computed scoring-ratio for every sample according to the importance of attributes and attribute-value, and the distribution of samples in a class was described from the point of view of membership degree of sample to each class. The probability density curve and histogram showed the distribution of typical and noise samples in each class distinctly.

In order to deal with the problem that current digital rights expression models have less ability to describe dynamic semantics, a new model, DDRM(Dynamic Digical Rights Model), which can describe action state was presented. Based on first-order dynamic logic, a new symbol system of first-order dynamic logic, DrFDL(Digital rights Fist-order Dynamic Logic), was defined to describe digital rights conception DrFDL semantic structure which can reflect dynamic property of action was presented based on DDRM. In addition, a license syntax based on DDRM was provided for rights expression. Then DrFDL logic was used to express the formal semantics of the licenses produced from this syntax and the determinacy with validity of these licenses was explored at last.