Most of the existing target detection algorithms rely on large?scale annotation datasets to ensure the accuracy of detection， however， it is difficult for some scenes to obtain a large number of annotation data and it consums a lot of human and material resources. In order to resolve this problem， a Few?Shot Target Detection method based on Negative Margin loss （NM?FSTD） was proposed. The negative margin loss method belonging to metric learning in Few?Shot Learning （FSL） was introduced into target detection， which could avoid mistakenly mapping the samples of the same novel classes to multiple peaks or clusters and helping to the classification of novel classes in few?shot target detection. Firstly， a large number of training samples and the target detection framework based on negative margin loss were used to train the model with good generalization performance. Then， the model was finetuned through a small number of labeled target category samples. Finally， the finetuned model was used to detect the new sample of target category. To verify the detection effect of NM?FSTD， MS COCO was used for training and evaluation. Experimental results show that the AP₅₀ of NM?FSTD reaches 22.8%； compared with Meta R?CNN （Meta Regions with CNN features） and MPSR （Multi?Scale Positive Sample Refinement）， the accuracies are improved by 3.7 and 4.9 percentage points， respectively. NM?FSTD can effectively improve the detection performance of target categories in the case of few?shot， and solve the problem of insufficient data in the field of target detection.

Concerning the problems of centralized functions of notary nodes and low cross?chain transaction efficiency in notary mechanism， a cross?chain interaction safety model based on notary groups was proposed. Firstly， notary nodes were divided into three kinds of roles， i.e. transaction verifiers， connectors and supervisors， and multiple transactions with consensus were packaged to a big deal by transaction verification group， and the threshold signature technique was used to sign it. Secondly， the confirmed transactions were placed in a cross?chain wait?to?be?transferred pool， some transactions were selected randomly by the connectors， and the technologies such as secure multiparty computation and fully homomorphic encryption were used to judge the authenticity of these transactions. Finally， if the hash values of all eligible transactions were true and reliable as well as verified by the transaction verification group， a batch task of multiple cross?chain transactions was able to be continued by the connector and be interacted with the blockchain in information. Security analysis shows that the proposed cross?chain mechanism is helpful to protect the confidentiality of information and the integrity of data， realizes the collaborative computing of data without leaving the database， and guarantees the stability of the cross?chain system of blockchain. Compared with the traditional cross?chain interaction security model， the complexity of the number of signatures and the number of notary groups that need to be assigned decreases from O ( n ) to O ( \mathrm{1} ) .

Focused on the problem that when traditional Non-negative Matrix Factorization (NMF) is applied to clustering, robustness and sparsity are not considered at the same time, which leads to low clustering performance, a sparse Non-negative Matrix Factorization algorithm based on Kernel technique and HyperGraph regularization (KHGNMF) was proposed. Firstly, on the basis of inheriting good performance of kernel technique, L _2,1 norm was used to improve F-norm of standard NMF, and hyper-graph regularization terms were added to preserve inherent geometric structure information among the original data as much as possible. Secondly, L _2,1/2 pseudo norm and L _1/2 regularization terms were merged into NMF model as sparse constraints. Finally, a new algorithm was proposed and applied to image clustering. The experimental results on six standard datasets show that KHGNMF can improve clustering performance (accuracy and normalized mutual information) by 39% to 54% compared with nonlinear orthogonal graph regularized non-negative matrix factorization, and the sparsity and robustness of the proposed algorithm are increased and the clustering effect is improved.

To effectively improve the denoising effect of the original anisotropic diffusion model that used only the 4 neighborhood pixels information and ignored the diagonal neighborhood pixels information of the pixel to be repaired in the image denoising process, a image denoising algorithm using UK-flag shaped anisotropic diffusion model was proposed. This model not only made full use of the reference information of the 4 neighborhood pixels as in original algorithm, but also used another 4 diagonal neighborhood pixels information in the denoising process. Then the model using the 8 direction pixels information for image denoising was presented, and it was proved to be rational. The proposed algorithm, the original algorithm, and an improved similar algorithm were used to remove the noise from 4 images with noise. The experimental results show that the proposed algorithm has an average increase of 1.90dB and 1.43dB in Peak Signal-to-Noise Ratio (PSNR) value respectively, and an average increase of 0.175 and 0.1 in Mean Structure Similitary Index (MSSIM) value respectively, compared with the original algorithm and the improved similar algorithm, which concludes that the proposed algorithm is more suitable for image denoising. algorithm not only made full use of the reference information of the 4 neighborhood pixels as in original algorithm, but also another 4 diagonal neighborhood pixels information was used in the denoising process, and the algorithm was proved to be rationality. The experimental results showed that the proposed algorithm could increase the PSNR (peak signal-to-noise ratio) value 1.69db, and the MSSIM(mean structure similitary index) value 0.14, compared with the other similar algorithms in image denoising, which conclud that this proposed algorithm is more suitable for image denoising.

Outdoor images captured in bad weather often have poor qualities in terms of visibility and contrast. A simple and effective algorithm was designed to remove haze. Firstly, the spatial high-pass filtering was used to suppress the low-frequency component and enhance the edge detail, and then the contrast-stretching transformation was used to acquire an image with high dynamic range. Finally, the exposure fusion method based on Laplacian pyramid was utilized to fuse the two results above and get the defogged image. The experimental results show that the proposed method has a good performance on enhancing images that are degraded by fog, dust or underwater and it is appropriate for real-time applications.

For the traditional player skill estimation algorithms based on probabilistic graphical model neglect the first-move advantage (or home play advantage) which affects estimation accuracy, a new method to model the first-move advantage was proposed. Based on the graphical model, the nodes of first-move advantage were introduced and added into player's skills. Then, according to the game results, true skills and first-move advantage of palyers were caculated by Bayesian learning method. Finally, predictions for the upcoming matches were made using those estimated results. Two real world datasets were used to compare the proposed method with the traditional model that neglect the first-move advantage. The result shows that the proposed method can improve average estimation accuracy noticeably.

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.

As the radio frequency communication technology gets more mature and the hardware manufacturing cost decreases, Radio Frequency IDentification (RFID) technology has been applied in the domains of real-time object monitoring, tracing and tracking. In supply chain applications, there are usually a great number of RFID objects to be monitored and traced, and objects' locations are changed essentially, so how to query the locations and the histories of location change of the RFID objects, from the huge volume of RFID data, is an urgent problem to be addressed. Concerning the characteristics of mobile RFID objects and the tracing query requirements in supply chain applications, an effective spatio-temporal index, called as CR-L, was put forward, and its structure and maintenance algorithms, including insertion, deletion, bi-splitting, and lazy splitting, were discussed in detail. In order to support object queries effectively, a new calculation principle of Minimum Bounding Rectangle (MBR), considering the three dimensional information including readers, time and objects, was presented to cluster the trajectories by the same reader at close time into the same node or the neighboring nodes. As to trajectory queries, a linked list was designed to link all trajectories belonging to the same object. The experimental results verify that CR-L has better query efficiency and lower space utilization rate than the existing method.

Currently, various image inpainting algorithms based on Curvature-Driven Diffusion (CDD) model only make use of the reference information of four neighborhood pixels. Therefore, they cannot keep shape edges and their inpainting precisions high enough. To conquer these difficulties, the image inpainting algorithm based on double-cross CDD was presented, in which the reference information for damaged pixel was extended from four into eight neighborhood pixels. Firstly, one inpainting value for damaged pixel could obtain from the reference information of four neighborhood pixels using the original CDD algorithm. Secondly, another new inpainting value was computed with the newly introduced four neighborhood pixels. Finally, the final inpainting value was a weighted mean of the above-mentioned two inpainting computational value. The proposed method, original CDD algorithm and its improved editions were implemented and compared in the experiments. The experimental results show that the proposed algorithm can effectively improve the inpainting precision and keep shape edges without increasing time complexity.

Currently, template size of texture-based image inpainting algorithm is fixed. Therefore, when the template size is small, the inpainting accuracy improves, but time complexity increases substantially; on the contrary, when the size is large, the time complexity declines, but inpainting error rate increases significantly. Adaptive template size algorithm proposed in this paper can enlarge template size according to the change of expect and variance of grayscale value between current template and its expanded one. Meanwhile, this approach can reduce template size according to the match degree between template and exemplar. After adaptively determining the template size, texture-based image inpainting algorithm was improved and used in experiments. The experimental results show this approach can highly improve the inpainting accuracy with high efficiency.

Concerning the problem that some results are easily leaked while the component testing ontology is retrieved using the existed calculation method of ontology semantic similarity, a similarity calculation method based on concept and attribute was proposed to improve the retrieval efficiency of component testing information. Firstly, the structure, hierarchy, the number of offspring nodes and ancestor nodes of concept were used to calculate the concept similarity. Then, the attribute similarity was calculated based on the concept similarity of the attributes and its data type similarity. Finally, the concept similarity and attribute similarity were combined to calculate the comprehensive ontology semantic similarity. The experimental results indicate that the similarity calculation method can be applied in component testing and other domains effectively.