Adversarial examples can evaluate the robustness and safety of deep neural networks effectively. Aiming at the problem of low success rate of adversarial attacks in black-box scenarios and to improve the transferability of adversarial examples， a Multi-space Probability Enhancement Adversarial example generation Method （MPEAM） was proposed. The transferability of the adversarial examples was improved by the proposed method through introduction of two pieces of random data enhancement branches in the adversarial example generation method. In this process， random image Cropping and Padding （CP） based on the pixel space， as well as random Color Changing （CC） based on HSV color space， were implemented， respectively， by each branch. At the same time， the returned image examples were controlled by constructing a probability model， which increased the diversity of the original examples while decreasing the dependence of the adversarial examples on the original dataset， thereby enhancing the transferability of adversarial examples. On this basis， the proposed method was introduced into the integration model to further improve the success rate of the adversarial example attack in black-box scenarios. After extensive experiments on ImageNet dataset， the experimental results show that the proposed method improves the black-box attack success rate by 28.72 and 8.44 percentage points， averagely and respectively， compared to the benchmark methods Iterative Fast Gradient Sign Method （IFGSM） and Momentum Iterative Fast Gradient Sign Method （MIFGSM）， and improves the black-box attack success rate by up to 6.81 percentage points compared to the attack methods based on single-space probability enhancement. The above indicates that the proposed method can improve the transferability of adversarial examples at a small cost of complexity and achieve effective attacks in black-box scenarios.

In response to the resource allocation problem in multi-beam scenarios of Low Earth Orbit （LEO） satellite， as the factors such as interference and noise between wave beams in actual satellite communication environments are complex and variable， conventional subcarrier dynamic allocation algorithms cannot adjust parameters dynamically to adapt to changes in the communication environment. By combining traditional communication scheduling algorithms with reinforcement learning techniques， with the goal of minimizing user packet loss rate， user’s scheduling situations were adjusted dynamically and resources of the entire satellite communication system were allocated dynamically to adapt to environmental changes. The dynamic characteristic model of LEO satellite was discretized by time slot division， and a Deep Reinforcement Learning （DRL）-based resource allocation strategy was proposed on the basis of the modeling of LEO satellite resource allocation scenarios. In this strategy， the scheduling opportunities for users with high latency were increased by adjusting the satellite scheduling queue situation， that is， adjusting the resource blocks in each beam of a single LEO satellite to correspond to qualifications of users， thereby ensuring a certain level of fairness and reducing the user packet loss rate at the same time. Simulation results show that under the condition meeting total power constraints， the user transmission fairness and system throughput are stable in the proposed Deep Reinforcement Learning based Resource Allocation algorithm （DRL-RA）， and users with large latency obtain more scheduling opportunities in DRL-RA due to priority improvement. Compared with Proportional Fairness （PF） algorithm and Maximum Carrier/Interference （Max C/I） algorithm， DRL-RA has the data packet loss rate reduced by 13.9% and 15.6% respectively. It can be seen that the proposed algorithm solves the problem of packet loss effectively during data transmission.

Aiming at the problems of lack of satellite positioning signal， limited communication and weak ambient light of Unmanned Surface Vehicle （USV） in subterranean closed water body， a cooperative visual positioning method of multiple USVs in subterranean closed water body was proposed. Firstly， a vehicle-borne light source cooperative marker was designed， and the marker structure was optimized according to the vehicle structure and application scene. Secondly， monocular vision was used to collect the marker images， and the image coordinates of the feature points were solved. Thirdly， on the basis of camera imaging model， by using the relationship between the spatial coordinates of feature points of the markers and the corresponding image coordinates， the relative positions between adjacent vehicles were calculated through improving direct linear transformation method. Fourthly， the cameras of the front and rear vehicles were used to make look face to face between the vehicles. Through the minimum variance algorithm， the relative positions calculated on the basis of the camera images of the front and rear vehicles were fused to improve the relative positioning accuracy. Finally， the absolute location of each USV was obtained by using the known absolute coordinates in the scene. The factors influencing positioning error were analyzed through simulation， and the proposed method was compared with the traditional direct linear transformation method. The results show that as the distance increases， the effect of this method becomes more obvious. At a distance of 15 m， the position variance solved by the proposed method is stable within 0.2 m²， verifying the accuracy of this method. Static experimental results show that the proposed method can stabilize the relative error within 10.0%； dynamic experimental results in underground river courses show that the absolute positioning navigation trajectory solved by the proposed method achieves accuracy similar to satellite positioning， which verifies the feasibility of this method.

To address the problems of blurred texture details and color distortion in low-light image enhancement， an end-to-end lightweight dual-branch network by combining spatial and frequency information， named SAFNet， was proposed. Transformer-based spatial block and frequency block were adopted by SAFNet to process spatial information and Fourier transformed frequency information of input image in spatial and frequency branchs， respectively. Attention mechanism was also applied in SAFNet to fuse features captured from spatial and frequency branchs adaptively to obtain final enhanced image. Furthermore， a frequency-domain loss function for frequency information was added into joint loss function， in order to constrain SAFNet on both spatial and frequency domains. Experiments on public datasets LOL and LSRW were conducted to evaluate the performance of SAFNet. Experimed results show that SAFNet achieved 0.823， 0.114 in metrics of Structural SIMilarity （SSIM） and Learned Perceptual Image Patch Similarity （LPIPS） on LOL， respectively， and 17.234 dB， 0.550 in Peak Signal-to-Noise Ratio （PSNR） and SSIM on LSRW. SAFNet achieve supreme performance than evaluated mainstream methods， such as LLFormer （Low-Light Transformer）， IAT （Illumination Adaptive Transformer）， and KinD （Kindling the Darkness） ++ with only 0.07×10⁶ parameters. On DarkFace dataset， the average precision of human face detection is increased from 52.6% to 72.5% by applying SAFNet as preprocessing step. Above experimental results illustrate that SAFNet can effectively enhance low-light images quality and improve performance of low-light face detection for downstream tasks significantly.

Orthogonal Time Sequency Multiplexing （OTSM） achieves transmission performance similar to Orthogonal Time Frequency Space （OTFS） modulation with lower complexity， providing a promising solution for future high-speed mobile communication systems that require low complexity transceivers. To address the issue of insufficient efficiency in existing time-domain based Gauss-Seidel （GS） iterative equalization， a secondary signal detection algorithm was proposed. First， Linear Minimum Mean Square Error （LMMSE） detection with low complexity was performed in the time domain， and then Successive Over Relaxation （SOR） iterative algorithm was used to further eliminate residual symbol interference. To further optimize convergence efficiency and detection performance， the SOR algorithm was linearly optimized to obtain an Improved SOR （ISOR） algorithm. The simulation experimental results show that compared with SOR algorithm， ISOR algorithm improves detection performance and accelerates convergence while increasing lower complexity. Compared with GS iterative algorithm， ISOR algorithm has a gain of 1.61 dB when using 16 QAM modulation with a bit error rate of {\mathrm{10}}^{-\mathrm{4}} .

Real-time semantic segmentation methods often use dual-branch structures to store shallow spatial information and deep semantic information of images respectively. However， current real-time semantic segmentation methods based on dual-branch structure focus on mining semantic features and ignore the maintenance of spatial features， which make the network unable to accurately capture detailed features such as boundaries and textures of objects in the image， and the final segmentation effect not good. To solve the above problems， a Dual-Branch real-time semantic segmentation Network based on Detail Enhancement （DEDBNet） was proposed to enhance spatial detail information in multiple stages. First， a Detail-Enhanced Bidirectional Interaction Module （DEBIM） was proposed. In the interaction stage between branches， a lightweight spatial attention mechanism was used to enhance the ability of high-resolution feature maps to express detailed information， and promote the flow of spatial detail features on the high and low branches， improving the network’s ability to learn detailed information. Second， a Local Detail Attention Feature Fusion （LDAFF） module was designed to model the global semantic information and local spatial information at the same time in the process of feature fusion at the ends of the two branches， so as to solve the problem of discontinuity of details between feature maps at different levels. In addition， boundary loss was introduced to guide the learning of object boundary information by the network shallow layers without affecting the speed of the model. The proposed network achieved a mean Intersection over Union （mIoU） of 78.2% on the Cityscapes validation set at a speed of 92.3 frame/s， and an mIoU of 79.2% on the CamVid test set at a speed of 202.8 frame/s； compared with Deep Dual Resolution Network （DDRNet-23-slim）， the mIoU of the proposed network increased by 1.1 and 4.5 percentage points respectively. The experimental results show that DEDBNet can accurately segment scene images and meet real-time requirements.

Focused on the issue that the category relationship between samples is not considered in the unsupervised Locally Invariant Robust Principal Component Analysis （LIRPCA） algorithm， a feature extraction model based on Neighbor Supervised LIRPCA （NSLIRPCA） was proposed. The category information between samples was considered by the proposed model， and a relationship matrix was constructed based on this information. The formulas of the model were solved and the convergences of the formulas were proved. At the same time， the proposed model was applied to various occlusion datasets. Experimental results show that compared with Principal Component Analysis （PCA）， PCA based on L₁-norm （PCA-L₁）， Non-negative Matrix Factorization （NMF）， Locality Preserving Projection （LPP） and LIRPCA algorithms on ORL， Yale， COIL-Processed and PolyU datasets， the proposed model has the recognition rate improved by 8.80%， 7.76%， 20.37%， 4.72% and 4.61% at most respectively on the original image datasets， and the recognition rate improved by 30.79%， 30.73%， 36.02%， 19.65% and 17.31% at most respectively on the occluded image datasets. It can be seen that with the proposed model， the recognition performance of the algorithm is improved， and the complexity of the model is reduced， verifying that the model is obviously better than the comparison algorithms.

To effectively extract the temporal information between consecutive video frames， a prediction network IndRNN-VAE （Independently Recurrent Neural Network-Variational AutoEncoder） that fuses Independently Recurrent Neural Network （IndRNN） and Variational AutoEncoder （VAE） network was proposed. Firstly， the spatial information of video frames was extracted through VAE network， and the latent features of video frames were obtained by a linear transformation. Secondly， the latent features were used as the input of IndRNN to obtain the temporal information of the sequence of video frames. Finally， the obtained latent features and temporal information were fused through residual block and input to the decoding network to generate the prediction frame. By testing on UCSD Ped1， UCSD Ped2 and Avenue public datasets， experimental results show that compared with the existing anomaly detection methods， the method based on IndRNN-VAE has the performance significantly improved， and has the Area Under Curve （AUC） values reached 84.3%， 96.2%， and 86.6% respectively， the Equal Error Rate （EER） values reached 22.7%， 8.8%， and 19.0% respectively， the difference values in the mean anomaly scores reached 0.263， 0.497， and 0.293 respectively. Besides， the running speed of this method reaches 28 FPS （Frames Per Socond）.

Concerning the shortcoming that the current feature-weighted Fuzzy Support Vector Machines （FSVM） only consider the influence of feature weights on the membership functions but ignore the application of feature weights to the kernel functions calculation during sample training， a new FSVM algorithm that considers the influence of feature weights on the membership function and the kernel function calculation simultaneously was proposed， namely Doubly Feature-Weighted FSVM （DFW-FSVM）. Firstly， relative weight of each feature was calculated by using Information Gain （IG）. Secondly， the weighted Euclidean distance between the sample and the class center was calculated in the original space based on the feature weights， and then the membership function was constructed by applying the weighted Euclidean distance； at the same time， the feature weights were applied to the calculation of the kernel function in the sample training process. Finally， DFW-FSVM algorithm was constructed according to the weighted membership functions and kernel functions. In this way， DFW-FSVM is able to avoid being dominated by trivial relevant or irrelevant features. The comparative experiments were carried out on eight UCI datasets， and the results show that compared with the best results of SVM， FSVM， Feature-Weighted SVM （FWSVM）， Feature-Weighted FSVM （FWFSVM） and FSVM based on Centered Kernel Alignment （CKA-FSVM） ， the accuracy and F1 value of the DFW-FSVM algorithm increase by 2.33 and 5.07 percentage points， respectively， indicating that the proposed DFW-FSVM has good classification performance.

Classifying similar， counterfeit and deteriorated slices in Chinese herbal slices plays a vital role in clinical application of Chinese medicine. Traditional manual identification methods are subjective and fallible. And the classification of traditional Chinese herbal slices based on computer vision is superior in speed and accuracy， which makes Chinese herbal slice screening intelligent. Firstly， general steps of Chinese medicine recognition algorithm based on computer vision were introduced， and technical development status of preprocessing， feature extraction and recognition model of Chinese medicine images were reviewed separately. Then， 12 classes of similar and easily confused Chinese herbal slices were selected as a case to study. By constructing a dataset with 9 156 pictures of Chinese herbal slices， the recognition performance differences of traditional recognition algorithms and various deep learning models were analyzed and compared. Finally， the difficulties and future development trends of computer vision in Chinese herbal slices were summarized and prospected.

During the operation of the Unmanned Surface Vehicles （USVs）， the propellers are easily gotten entangled by waterweeds， which is a problem encountered by the whole industry. Concerning the global distribution， dispersivity， and complexity of the edge and texture of waterweeds in the water surface images， the U-Net was improved and used to classify all pixels in the image， in order to reduce the feature loss of the network， and enhance the extraction of both global and local features， thereby improving the overall segmentation performance. Firstly， the image data of waterweeds in multiple locations and multiple periods were collected， and a comprehensive dataset of waterweeds for semantic segmentation was built. Secondly， three scales of input images were introduced into the network to enable full extraction of the features via the network， and three loss functions for the upsampled images were introduced to balance the overall loss brought by the three different scales of input images. In addition， a hybrid attention module， including the dilated convolution branch and the channel attention enhancement branch， was proposed and introduced to the network. Finally， the proposed network was verified on the newly built waterweed dataset. Experimental results show that the accuracy， mean Intersection over Union （mIoU） and mean Pixel Accuracy （mPA） values of the proposed method can reach 96.8%， 91.22% and 95.29%， respectively， which are improved by 4.62 percentage points， 3.87 percentage points and 3.12 percentage points compared with those of U-Net （VGG16） segmentation method. The proposed method can be applied to unmanned surface vehicles for detection of waterweeds， and perform the corresponding path planning to realize waterweed avoidance.

To solve the problem of the regulation of badminton dynamic stable equilibrium, the particle influence coefficient method of feather piece was put forward. The method combined badminton quality models and quality feather piece, bending camber degree, angle of attack, and other related factors. The feather piece of particle influence coefficient was obtained by adjusting the height centroid which satisfied badminton dynamic stability requirements got by striking tilt minimum square. Compared with the traditional badminton dynamic stabilization which must depend on the experience accumulated for a long time, the badminton particle influence coefficient method of feather piece that was put forward by this paper formed a theoretical system. And it had less time consumption, high efficiency, etc. The numerical results show that the proposed method is correct and effective.

Most of the variants of Graph Cut algorithm do not impose any shape constraints on the segmentations, rendering it difficult to obtain semantic valid segmentation results. As for pedestrian segmentation, this difficulty leads to the non-human shape of the segmented object. An improved Graph Cut algorithm combining shape priors and discriminatively learned appearance model was proposed in this paper to segment pedestrians in static images. In this approach, a large number of real pedestrian silhouettes were used to encode the a'priori shape of pedestrians, and a hierarchical model of pedestrian template was built to reduce the matching time, which would hopefully bias the segmentation results to be humanlike. A discriminative appearance model of the pedestrian was also proposed in this paper to better distinguish persons from the background. The experimental results verify the improved performance of this approach.

Concerning the premature convergence problem in Particle Swarm Optimization (PSO) algorithm, a Diversity Feedback and Control PSO (DFCPSO) algorithm was proposed. In the process of search, the algorithm dynamically adjusted the algorithm parameters according to the feedback information of diversity; as a result, the distribution of iterations in the diversity curve was improved. When the population diversity or the variance of the population's fitness dropped to the given thresholds, the proposed algorithm would let the particle swarm initialize based on the repulsion of the global best position and fly away from the gathering area efficiently to search again, hence the diversity was controlled in a reasonable range, which avoided premature convergence. The experimental results on several well-known benchmark functions show that DFCPSO has stronger global optimization ability in the complicated problems and multi-modal optimization when being compared with the existing Diversity-Controlled PSO (DCPSO).

Considering the complexity and inaccuracy of traditional theoretical modeling for rigid-flexible couple system, the frequency domain subspace method was used to identify the motor's model and piezoelectric ceramic piece's model in the experimental system. Due to the problem of chattering and long reaching time of traditional reaching law, a novel sliding mode control with power reaching law was proposed. Theoretical analysis shows that the reaching time can be shortened and the range of traditional power reaching law's parameter α can be expanded, which will not affect the chattering. Considering the effect of vibration characteristics of flexible beam on system performance, the method of sub-sliding surface was used to design the sliding mode controller. Lastly, experimental results show that the designed controller can track the angle of the center of the rigid body rapidly and suppress the vibration of the flexible beam quickly.

The log-based index update mechanism in flash-based database system has following shortage: low query efficiency, expensive update cost, unreasonable space allocation and merge for the log. In order to solve these problems, a new adaptive index structure named LM-B+TREE was proposed. LM-B+TREE can map the page for index update buffer into corresponding node of traditional B+ TREE. Furthermore, according to the read/write workload and read/write overhead, LM-B+TREE can dynamically maintain the update buffer and adjust the index frame adaptively. The experimental results show that LM-B+ TREE can dynamically adjust the index structure to adapt to the read-write workload, significantly reduce the overhead of index update and improve the query performance.

Applying the adversarial optimization approach to remove the error matches in image matching usually causes the removal of correct matches，especially when multiple iterations are run．Concerning this drawback，a limit was put on the number of iterations，and a subsequent processing was added，which reestimated the homography matrix using a Random Sample Consensus （RANSAC）like method．The experiments show that the improved method can preserve almost all the correct matches with smaller root mean square error．And in the aspect of computing speed，the time the improved method needs is less than half the time the original method needs．

This paper proposed an algorithm for 3D reconstruction based on uncalibrated images. First, this algorithm detected the feature points by using Harris corners, and presented an improved bidirectional matching to match these feature points. Under the condition of the known camera parameters, the authors carried out 3D reconstruction of two images. Then the quaternion algorithm was adopted to transform coordinate. The results coming from different subsets were brought into a common coordinate frame, achieving 3D reconstruction of multiple images. Finally, bundle adjustment was used to optimize the results. The experimental results show that object structure can be well reconstructed by using this algorithm.

Image processing technology depends on the quality of the visual saliency map to obtain better results. The existing visual saliency detection method usually can only detect and get rough visual saliency attribute graph, seriously affecting the image processing results. This paper put forward a method of using Bayes theorem and statistical learning of visual saliency detection to detect the visual saliency property of image. The method was based on Bayes theorem of static image top-down significant and overall significance, and combined the top-down knowledge and the down-top significance. For the synthetic integration of characteristics, all the factors related to the weight parameter were studied by using linear model with the linear weighting combination method and regularized neural network combined with nonlinear weighting method. The ROC curves of the bottom-up visual saliency model in two fixed data set for quantitative evaluation, show that the effect of non-linear combination is better than that of linear combination.

Dynamic trusted measurement is a hot and difficult research topic in trusted computing. Concerning the measurement difficulty invoked by the dynamic nature of operating system kernel, a Dynamic Trusted Kernel Measurement (DTKM) model was proposed. Dynamic Measurement Variable (DMV) was presented to describe and construct dynamic data objects and their relations, and the method of semantic constraint was proposed to measure the dynamic integrity of kernel components. In DTKM, the collection of memory data was implemented in real-time, and the dynamic integrity was verified by checking whether the constructed DMV was consistent with semantic constraints which were defined based on the security semantics. The nature analysis and application examples show that DTKM can effectively implement dynamic measurement of the kernel and detect the illegal modification of the kernel dynamic data.

Through analyzing the application status of Vehicle Ad Hoc NETwork (VANET) in road transportation field, according to the characteristics of VANET and challenges in news transmission process, concerning the problems of previous algorithms being difficult to establish spatial model accurately and hardly considering the regularity characteristics of social behavior, a routing scheme named HBSR was proposed based on the historical behavior statistics of vehicles, including nodes connected algorithm calculating the connectivity between vehicles, topological overlap algorithm calculating the number of periods between the source node and destination node, paths selected algorithm selecting messages forwarding paths and loss strategy. Compared with several typical routing algorithms on ONE simulation platform, the simulation results prove that HBSR can find news forwarding paths more effectively, and reduces message delivery delay obviously while delivery rate increases significantly, and performance is relatively stable in VANET.

Gabor uncertainty features fusion can solve the problem that multiscale Gabor features are unsuitable for ARM because of huge data and dimensions in the embedded face recognition system. Multiscale Gabor features were first extracted, and then the uncertain weight was calculated, at last multiscale Gabor features were integrated into one. The embedded face recognition system detected face by using Haar-like features of face, and reduced dimensions by using 2-Dimensional Principal Component Analysis (2DPCA) algorithm. Based on EELiod 270 development board, the performance of face recognition was tested on ORL and Yale. Comparative results with other face recognition algorithms show that a significant decline is got in the amount of arithmetic operations, and a good real-time recognition is obtained while ensuring the recognition rate.

For the dynamic characteristic of vehicle Ad-Hoc network's topology, the file is difficult to completely downloaded within the communication of a single vehicle road Access Point (AP) using the existing schemes of information dissemination, having the long time delay limitation of waiting for the next AP to document communication. A method that downloaded and spread the file fragmentation using multiple vehicles within the range of some free APs was proposed, the message delivery delay was divided into direct and indirect encounter delays, and discussion was made on them respectively, and a specific option was given to choose message carried vehicles. The experimental results of the message loss rate and delay show that the environment joined with the proposed scheme can effectively improve the reliability of message downloading, shorten the delay of downloading message to the purpose vehicle, without significant additional load to the network.

Human objects Segmentation is one of the key problems of Visual Analysis. In this paper, a novel touched human objects segmentation based on Mean-shift algorithm was proposed. At first, Video Images was preprocessed and motion regions were obtained, and model of human object was built according to statistical characteristics of body surface. Then, a few of points of motion region picked equably were taken as seeds, and local mode centroids were calculated by Mean-shift iterative process. At last, the number of categories was automatically acqured based on the clustering algorithm, and human objects were segmented according to the result of clustering. The experiment based on PETS 2006 Database proves this method is feasible.

The software design of Global Positioning System (GPS) vehicle terminal was discussed, which was based on General Packet Radio Service (GPRS) wireless communication, including the definition of communication protocol between vehicle terminal and monitor center, the design of efficient strategy of GPS information receiving and unpacking, and GPRS communication flow design. The work provides a useful reference for developing GPRS communication equipment and GPS location equipment.

A new algorithm was developed through replacing the crossover operation in NSGA-Ⅱ with the mode of position updating in multiobjective particle swarm optimizer (MOPSO). In order to seamlessly combine NSGAⅡand the greatly different MOPSO, the special concepts (particle and its velocity, Pbest and leader) for MOPSO were dealt with within the scope of NSGA-Ⅱ: 1) particle in MOPSO was considered to be equivalent to offspring individual in NSGA-Ⅱ; 2) the concept of velocity fell into disuse; 3) the concept of Pbest also came into disuse. Instead of that, for each dimension of a particle, the nearest one among its nondominated individuals in parent population was used; 4) the leader of a particle was the individual with largest sparse degree among parent population or selected from parent population by binary tournament selection method, which of them taking effect lies on the predefined probability. In addition, a new concept, i.e., sparse degree, was introduced to evaluate the distribution of particles in objective function space. Experiments on six benchmark problems indicate that the new algorithm is an effective and stable one when compared with NSGA-Ⅱ and two of the latest MOPSOs (CLMOPSO and EM-MOPSO).