Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Simulation (135)
- Path planning (76)
- Genetic algorithm (48)
- Deep learning (44)
- Numerical simulation (44)
-
- Digital twin (42)
- Virtual reality (42)
- Modeling and simulation (39)
- Multi-objective optimization (39)
- Particle swarm optimization (35)
- Reinforcement learning (34)
- Modeling (33)
- Fault diagnosis (29)
- Attention mechanism (28)
- Deep reinforcement learning (28)
- UAV (26)
- Neural network (25)
- Simulation model (25)
- Complex network (22)
- System simulation (22)
- System dynamics (21)
- Visualization (21)
- Virtual simulation (20)
- DRL (19)
- Optimization (19)
- Multi-agent (18)
- Trajectory planning (18)
- Traffic simulation (17)
- Unity3D (17)
- A* algorithm (16)
- Publication Year
Articles 3331 - 3360 of 3880
Full-Text Articles in Engineering
Optimization Of Frictionless Cylinder-Structure Based On Pso, Liu Yu, Gouxin Zhao
Optimization Of Frictionless Cylinder-Structure Based On Pso, Liu Yu, Gouxin Zhao
Journal of System Simulation
Abstract: Aerostatic frictionless cylinder is the critical component of pneumatic gravity compensation device, the key of its design is to take all related factors into consideration for optimum performance. To optimize the structure of aerostatic frictionless cylinder, the optimal parameters in the cylinder are proposed, which maximizes the bearing capacity in radial direction and keeps the leakage at a relatively low level. Through analyzing the structure of the aerostatic frictionless cylinder, a mathematic model of the aerostatic frictionless cylinder is deduced. Based on simulations, the relationship during the structural parameters, the bearing capacity and the leakage is acquired. It is …
Design Of Imu/Gps-Based Seamless Location System For Android, Sun Wei, Wang Ye, Ruibao Li, Yang Dan
Design Of Imu/Gps-Based Seamless Location System For Android, Sun Wei, Wang Ye, Ruibao Li, Yang Dan
Journal of System Simulation
Abstract: The method of seamless combination of IMU and GPS module based on Android mobile terminal is researched and implemented, and the design scheme and experimental results are given. When the GPS signal is missing, the gait detection, heading calculation and track estimation can be carried out by using the IMU inertial sensor which is inherent in the mobile terminal to complete the seamless positioning. Based on the Android system and the open platform of Baidu map, the algorithm implementation and human-computer interaction can be completed in the mobile terminal. The test results show that the relative error of the …
Event-Triggered Scheme And Co-Design Of $H_{\Infty}$ Control In Networked Control System, Jingqi Fu, Wu Jie, Weili Shen
Event-Triggered Scheme And Co-Design Of $H_{\Infty}$ Control In Networked Control System, Jingqi Fu, Wu Jie, Weili Shen
Journal of System Simulation
Abstract: Since the wireless network time-varying delay and communication channel bandwidth have great effects on networked control systems(NCSs), this paper studies an event-triggered scheme and a $H_{\infty}$control co-design method. Initially, a delay mathematic model of NCSs is constructed. In consideration of wireless network time-varying delay between event generator and zero order holder, this paper designs an improved event-triggered communication scheme. Furthermore, by applying a new Lyapunov-Krasovskii functional and linear matrix inequality method, a criterion for the delay-independent $H_{\infty}$ stabilization is derived, and the co-design method for gaining the trigger parameters and state feedback $H_{\infty}$ control is …
An Improved Algorithm Of Vire Based On Bp Neural Network, Hongshan Kong, Bin Yu
An Improved Algorithm Of Vire Based On Bp Neural Network, Hongshan Kong, Bin Yu
Journal of System Simulation
Abstract: Aimed at the problem that the proper threshold affects the accuracy of positioning in VIRE algorithm, a RFID positioning method combining BP neural networks with VIRE algorithm is presented and is named BP-VIRE. BP-VIRE utilizes the same reader’s configuration and deployment as that of VIRE, and regards referenced tag RSSI and coordinate values as training samples, and constructs the positioning model based on neural networks with the help of BP algorithm which uses the method of error back propagation. According to the simulation results, compared with VIRE, BP-VIRE performance is better in the capability of positioning, esp. in the …
Simulation Of Automated Terminal With Dual-Rail Transport Trolley And Hollow Track Layout, Pengfei Zhou, Xiaowei Xing
Simulation Of Automated Terminal With Dual-Rail Transport Trolley And Hollow Track Layout, Pengfei Zhou, Xiaowei Xing
Journal of System Simulation
Abstract: Container terminals with dual-rail transport trolley and hollow track layout (CTTH) are novel concept, for which a simulation model is developed with stochastic Petri nets. The simulation realization is discussed using Plant Simulation platform. A CTTH simulation system is developed to analyze its operational efficiency and parameter effects. Experiments show that CTTHs are more efficient than container terminals with automated RMGs. The study findings are helpful reference for the simulation models of automated container terminal and CTTH developments.
Finite Element Numerical Simulation Of Pre-Damaged Reinforced Concrete Beam, Jiaquan Wu, Hongyan Li, Ye Fei, Xinyu Zhang, Kun Ma
Finite Element Numerical Simulation Of Pre-Damaged Reinforced Concrete Beam, Jiaquan Wu, Hongyan Li, Ye Fei, Xinyu Zhang, Kun Ma
Journal of System Simulation
Abstract: Based on the theory of model analysis, the general variation of model parameters, such as the structure natural frequency, displacement mode, curvature mode and strain mode etc.model of reinforced concrete beams with different damage locations and different damage states are reversely studied by finite element numerical simulation with the pre-damaged reinforced concrete beam structure as the research object, model and the aptability, sensitivity in the reinforced concrete structure damage identification are discussed. The results show that the frequency and displacement mode can not effectively reflect the existence of structural damage, but curvature mode and strain mode can reflect the …
Modeling And Simulation Of Initial Loading Balls And Replenishing Balls Of The Duplex Inlet & Outlet Coal Mill, Junjie Gu, Yukun Wang, Zhizhong Bai
Modeling And Simulation Of Initial Loading Balls And Replenishing Balls Of The Duplex Inlet & Outlet Coal Mill, Junjie Gu, Yukun Wang, Zhizhong Bai
Journal of System Simulation
Abstract: To solve the problems of excess of abrasion of steel balls and high power consumption used for grinding of the duplex inlet & outlet coal mill, a method that can calculate the initial balls loading, the period and quantity of adding balls for the mill is presented on the basis of building up the models of steal balls’ abrasion and motion. Setting #E coal mill as example, period and quantity of adding balls are confirmed accurately in consideration of variation of power, the maximum capacity and fineness of coal powder, compensatory quantity of each grade of balls are also …
Blind Equalization Algorithm Of Variable Segment Error Function Based On Catfish Effect Particle Swarm Optimization, Yecai Guo, Jiping Wu
Blind Equalization Algorithm Of Variable Segment Error Function Based On Catfish Effect Particle Swarm Optimization, Yecai Guo, Jiping Wu
Journal of System Simulation
Abstract: In order to overcome the disadvantage of the slow convergence rate and big steady state error of constant modulus algorithm (CMA), a variable segment error constant modulus blind equalization algorithm based on the catfish effect particle swarm optimization algorithm (CEPSO-VSCMA) is proposed. The algorithm introduces catfish effect particle swarm optimization on the base of VSCMA, finding the globally optimal solution with the global searching of particle swarm. Meanwhile, vibrant and competitive catfish individual are employed to reactivate particle swarm and accelerate convergence. The simulation results show that the proposed algorithm performs better in improving convergence rate, decreasing inter-symbol …
Modeling And Simulation On Entities’ Belief In Cyberspace, Jiuyang Tao, Wu Lin, Xiaoyuan He, Rong Ming
Modeling And Simulation On Entities’ Belief In Cyberspace, Jiuyang Tao, Wu Lin, Xiaoyuan He, Rong Ming
Journal of System Simulation
Abstract: Of all cyber-attacks, 'fabrication' which is aimed at impacting one’s awareness is becoming the common means, so it is of great importance to explore ways so as to defend such attacks. An attack can success or not always rely on the entities’ belief of certain events. In this paper, two different ways of 'fabrication' attack are put forward, and three essential conditions for 'fabrication' attack are analyzed. Second, a cyberspace belief model in terms of the Dempster-Shafer framework based on situation awareness theory is built to study the evolution of the cyber entities’ belief under the 'fabrication' attack. In …
Design Of Remote Medical Care Service Robot System, Yulin Xu, Chen Ling, Li Xin, Aolei Yang, Yanran Long, Chunli Zhu, Yanbo Liu, Yuzhang Jin
Design Of Remote Medical Care Service Robot System, Yulin Xu, Chen Ling, Li Xin, Aolei Yang, Yanran Long, Chunli Zhu, Yanbo Liu, Yuzhang Jin
Journal of System Simulation
Abstract: This paper introduces a service robot system for remote medical inspection. The robot is developed with the following functions: it is able to navigate in working area autonomously and be controlled remotely by doctors through a handheld terminal device; it is able to follow a fixed target such as nurses and doctors to reach any area; it has a touch-control interactive interface which can realize remote audio and video interaction between doctors and patients; it is embedded with portable type-B ultrasonic device, sphygmomanometer and thermometer for doctors to obtain physiological data of patients. With the above-mentioned functions, the robot …
Intelligent Diagnosis Of Aircraft Electrical Faults Based On Rmbp Neural Network, Lishan Jia, Zhe Liu, Sun Yi
Intelligent Diagnosis Of Aircraft Electrical Faults Based On Rmbp Neural Network, Lishan Jia, Zhe Liu, Sun Yi
Journal of System Simulation
Abstract: To the characteristics of multiple properties, hard to remove and high cost of time and manpower of aircraft electrical faults maintenance in aircraft maintenance of civil aviation, construction of intelligent aircraft electrical faults diagnosis system using RMBP neural network is proposed. RMBP algorithm is used to study sample data in the intelligent faults diagnosis system as it can overcome the faults of long time of convergence and easy to go into local minima of common BP algorithm, and is suitable for training large-scale neural network,. Experience data are collected, samples are made, samples training and experiment are carried out. …
Complex Network Modeling And Visualization Analysis For Ocean Observation Data, Sun Xin, Zhenhua Li, Junyu Dong, Xinyan Luo, Yuting Yang
Complex Network Modeling And Visualization Analysis For Ocean Observation Data, Sun Xin, Zhenhua Li, Junyu Dong, Xinyan Luo, Yuting Yang
Journal of System Simulation
Abstract: Ocean data analysis is one of the important foundations in marine science research. Analysis on the sea surface temperature based on complex network theory helps explore the marine dynamics in a new perspective. The ocean is divided into grids, and the annual average of the sea surface temperature is calculated to reflect the properties of the corresponding grid area. The mutual information and the Pearson correlation coefficient are used to measure the similarity between different areas. The nonlinear and linear complex network models which reflect the station of the global marine climate can be built. Finally some popular measures …
Virtual-Reality Video Fusion System Based On Video Model, Zhou Yi, Meng Ming, Wu Wei, Zhou Zhong
Virtual-Reality Video Fusion System Based On Video Model, Zhou Yi, Meng Ming, Wu Wei, Zhou Zhong
Journal of System Simulation
Abstract: The aim of virtual reality integration is to reduce the visual difference of virtual object and real video image. However, it still has several problems, including heavy imagery distortion when the user deviates from the source viewport, and huge modeling cost of virtual scene. For these issues, this paper proposes a novel virtual-reality video fusion system based on video model. We firstly introduce how we register and build video model with interactive operations, then present the fusion method of video and virtual scenes. On the design and implementation stage, we introduce the architecture of our system. Finally, we …
A 3d Tree Visualization Of Network Data Based On Webvr, Lin Ding, Guoxin Huang, Xu Ying
A 3d Tree Visualization Of Network Data Based On Webvr, Lin Ding, Guoxin Huang, Xu Ying
Journal of System Simulation
Abstract: A new method of three dimensional tree-style visualization of network data is proposed in this paper based on cluster computing, which maps the network structure of clustered data to hierarchical tree structure. The number of nodes of a community is treated as the weight to improve the PhylloTrees' phyllotactic layout algorithm and the 3D visualization of network data is implemented based on WebVR. Friendly interactive manipulations are achieved in the immersive VR scene such as rotation, zooming, pan, picking, and transparent fade / highlight enhancement of different displaying. The experimental results show that our method can show not only …
3d Wireframe Model Encryption Based On Chaos, Zhao Geng, Shuyun Zhu, Jin Xin, Xiaodong Li, Hongbo Sun, Zhili Xu, Yin Sui, Zhaohui Tian, Sun Nan
3d Wireframe Model Encryption Based On Chaos, Zhao Geng, Shuyun Zhu, Jin Xin, Xiaodong Li, Hongbo Sun, Zhili Xu, Yin Sui, Zhaohui Tian, Sun Nan
Journal of System Simulation
Abstract: With the rapid growth of graphics data in the network environment, the security of graphics data has become a new challenge of network security that needs to be solved urgently. Encryption of 3D models is also urgent. In this paper, an encryption scheme for 3D wireframe model is proposed by using chaos mapping. The method is divided into two parts: confusion and diffuse. A random invertible matrix is generated by using logical mapping to spread the points. The side is scrambled by Arnold's cat map, then the encrypted vertices and polygons are combined to form the final encrypted 3D …
Design Of Aircraft Engine Adaptive Model Based On Improved Strong Tracking Filter, Xizhong Yang, Jianliang Ai
Design Of Aircraft Engine Adaptive Model Based On Improved Strong Tracking Filter, Xizhong Yang, Jianliang Ai
Journal of System Simulation
Abstract: Due to deterioration under real working condition, the aircraft engine performance parameters of benchmark model don’t match the real engine. This problem was studied based on in-flight engine nonlinear real-time performance model considering the practical engineering application. Immeasurable health parameters were estimated from measurable sensor parameters by UKF (Unscented Kalman Filter) and STUKF (Strong Tracking UKF). The engine adaptive model was established through modifying the benchmark model’s performance parameters in Simulink. A method of improved STUKF was proposed. Simulation results showed that the precision of engine adaptive model was greatly increased which satisfied real-time and robustness requirements in dynamic …
Area And Centerline Distribution On Stealth Design Of S-Shaped Inlet, Le Zhang, Zhou Zhou, Xiaoping Xu
Area And Centerline Distribution On Stealth Design Of S-Shaped Inlet, Le Zhang, Zhou Zhou, Xiaoping Xu
Journal of System Simulation
Abstract: Based on the conformal inlet’s size requirement of flying wing unmanned aerial vehicle (UAV), s-shaped inlets are designed with super-ellipse equation, and they are also designed in three typical centerline and area distributions of “beginning fast and end slow”, “beginning and end the same”, and “beginning slow and end fast”. The numerical simulation is verified on electromagnetic scattering characteristics of the inlet with straight cavity based on multilevel fast multipole method (MLFMM), and the stealth analysis is also carried out. And then the mechanism is analyzed combining with electric current distribution. Results indicate that with the inlet terminator open, …
Real-Time Collision Detection Of Coastline In Navigation Simulator, Qianfeng Jing, Helong Shen, Yin Yong, Xiuwen Liu
Real-Time Collision Detection Of Coastline In Navigation Simulator, Qianfeng Jing, Helong Shen, Yin Yong, Xiuwen Liu
Journal of System Simulation
Abstract: In order to develop real-time collision detection module of coastline in navigation simulator, a mesh preprocessing method for coastline data is applied. The principle of meshing is established and the coastline data is meshed based on the clipping algorithm. The mesh data is stored into an appropriate data structure. The collision detection algorithm and test program are developed based on Microsoft Foundation Classes (MFC). The ship contour points and the mesh expansion method are applied to avoid error in special cases which could also improve the accuracy of collision detection. The results show that the method reduces much time …
Cell-Devs Social Interaction Modeling And Simulation For Emergency Evacuation Systems, Yanhong Wang, Wang Xia, Shaowei Wang
Cell-Devs Social Interaction Modeling And Simulation For Emergency Evacuation Systems, Yanhong Wang, Wang Xia, Shaowei Wang
Journal of System Simulation
Abstract: This paper aims to present a Cell-DEVS model for emergency evacuation systems, which behave uncertainty and are intricately driven by the social factors. The model introduces social interaction factors such as familiarity degrees, individual vision, communication and conduction, and velocity zones as the state variables, describing the relationship between the evacuees and environment, as well as the interactions with each other. The algorithm optimization enhances reality of simulation. The RESTful CD++ is applied as middleware to execute remote simulation. The results confirm the existence of social interaction. This work benefits to the architecture design, evacuation planning and …
Mesh Morphing Process For Facial Plastic Surgery Simulation, Jinfang Li, Rifu Li, Hanwu He, Junlong Xu, Jiayuan Liu, Li Hang
Mesh Morphing Process For Facial Plastic Surgery Simulation, Jinfang Li, Rifu Li, Hanwu He, Junlong Xu, Jiayuan Liu, Li Hang
Journal of System Simulation
Abstract: In order to present the result of facial plastic surgery accurately, we propose a mesh morphing process method based on the grayscale texture in this paper. A grayscale texture is created by selecting the region of interest (ROI), and a set of texture coordinate is computed for the vertices in real time to establish the mapping relationship between the vertices and the grayscale texture. In order to make the morphing smooth, we blur the grayscale texture with the mean blurred processing algorithm and control the blur effect by the number of iterations. The advantages of this algorithm are as …
Research On Open Cell Effect Based On Vacation Queueing Model, Wenwen Pan, Bingyu An, Zangbo Chi, Mingmin Zhang, Zhuxin Hu
Research On Open Cell Effect Based On Vacation Queueing Model, Wenwen Pan, Bingyu An, Zangbo Chi, Mingmin Zhang, Zhuxin Hu
Journal of System Simulation
Abstract: The paper analyzes the related influence factors when closed residential area is open to its surrounding roads. Using the traffic flow theory, the evaluation system of AHP and vacation queuing model based on Markov chain are established. After describing and quantifying the road traffic impact about the open community, we put forward some suggestions about the open of closed residential community. At the same time, the evaluation and improvement rate are proposed under different conditions such as changing the structure of the community, changing the surrounding road structure and changing the traffic flow off. In consideration of traffic lights, …
Key Techniques Of Remote Visualization Of 3d Seismic Volume Supporting Multi-User, Lianen Ji, Zhao Ni, Shiyi Liang, Huang Bo
Key Techniques Of Remote Visualization Of 3d Seismic Volume Supporting Multi-User, Lianen Ji, Zhao Ni, Shiyi Liang, Huang Bo
Journal of System Simulation
Abstract: During the remote visualization of large-scale seismic volume for multi-user concurrent interaction, traditional task scheduling approaches could lead to large amount of I/O operation and repetitive calculation of volume texture blocks. So, a more efficient multi-task scheduling strategy was proposed, which rearranged the schedule order of volume rendering tasks through computing their viewpoint correlation. Furthermore, an optimized design of LRU based on parallel protection lock was made. In order to improve the network transmission efficiency and quality of seismic visualization image simultaneously, and to meet the requirement of users to observe the region of interest (ROI) preferentially, the …
Rgbd Image Co-Segmentation Via Saliency Detection And Graph Cut, Xiaoyang Li, Lili Wan, Henan Li, Shenghui Wang
Rgbd Image Co-Segmentation Via Saliency Detection And Graph Cut, Xiaoyang Li, Lili Wan, Henan Li, Shenghui Wang
Journal of System Simulation
Abstract: In order to solve the problem that it is difficult to accurately segment images with similar colors in the foreground, we propose a RGBD image co-segmentation algorithm that utilizes saliency detection and graph cut. Our algorithm not only achieves the co-segmentation of multiple images, but also uses depth data to solve the foreground and background confusion problem caused by color similarity. Depth is incorporated into a superpixel segmentation algorithm to change each RGBD image into a set of superpixel blocks. A graph model of superpixels is constructed and saliency detection is used to extend the seed nodes area. The …
Research On Parametric Modeling Of Radar Electronic Warfare Visual Simulation, Jinliang Guo, Zhang Yang, Xiaoyan Li, Xue Yuan
Research On Parametric Modeling Of Radar Electronic Warfare Visual Simulation, Jinliang Guo, Zhang Yang, Xiaoyan Li, Xue Yuan
Journal of System Simulation
Abstract: In order to improve the versatility of electronic warfare scene simulation and reduce the repeated development, a parametric modeling approach was proposed. Based on the visual simulation development model of Vega Prime, the modular simulation architecture was designed to provide a unified design structure for parametric modeling. The method of parameter extraction and description was researched to standardize the design of simulation model parameters. Parameter constraint rules were researched to associate model parameters, avoid the conflict between parameters, and simplify parameter instantiation. A parametric visual simulation system of electronic warfare was designed and implemented. The parametric modeling process …
Physically-Based Interactive Virtual Clothing Animation Simulation, Shi Min, Junzheng Wang, Tianlu Mao, Yaning Liu
Physically-Based Interactive Virtual Clothing Animation Simulation, Shi Min, Junzheng Wang, Tianlu Mao, Yaning Liu
Journal of System Simulation
Abstract: Realistic effective clothing animation simulation involves many factors, including the lifelike animation rendering, stable animation modeling, interaction control of the adjustable parameter and so on. An interactive clothing animation method based on physics is studied. According to the content feature of model and animation resources, we design an effective way of storage and provide the interface to adjust the parameters interactively. We build implicit constraint dynamics system, accelerated collision detection and the constrained optimization calculation model, and calculate clothing animation. The simulation based on Unity 3D engine is rendered to present garment animation simulation effect under different virtual light. …
Analysis Of Fuzzy Control Constant Current Charging Characteristic For Breaking And Making Capacitor Of Permanent Magnet Circuit Breaker, Peng Jin, Xianbing Wang, Xiangao Wang, Xichen Ye, Wang Huan
Analysis Of Fuzzy Control Constant Current Charging Characteristic For Breaking And Making Capacitor Of Permanent Magnet Circuit Breaker, Peng Jin, Xianbing Wang, Xiangao Wang, Xichen Ye, Wang Huan
Journal of System Simulation
Abstract: In order to realize the precise control of breaking and making capacitors constant current charging for the permanent magnet (PM) circuit breaker, a fuzzy constant current charging technology of breaking and making capacitors is put forward. On the basis of analyzing the working characteristics for breaking and making capacitors constant current charging, the membership functions of current deviation e, deviation changing rate ec and output variable u for breaking and making capacitors constant current and fuzzy control rules are set up. The establishment of a two-dimensional lookup table replacing the complex fuzzy control algorithm can effectively improve the …
Design And Realization Of Behavior Tree In Weapon Equipment Virtual Maintenance Training System, Wensheng Xu, Wu Bo, Jianhong Jiang
Design And Realization Of Behavior Tree In Weapon Equipment Virtual Maintenance Training System, Wensheng Xu, Wu Bo, Jianhong Jiang
Journal of System Simulation
Abstract: To solve the problem of long development period of virtual maintenance training system for complicated weapon equipment, the 3D modeling, the behavior modeling and the decision modeling of virtual maintenance were studied. The behavior trees design model was applied to analyze, design and develop the system which was tested in the maintenance case of marching tensioning device of a certain weapon equipment. The scripting unit and the running efficiency of the behavior trees model in the case were tested. The test results showed that this design method with behavior tree model has better scalability and model description clarity, and …
Airframe Damage Region Division Evaluation Method Based On Boundary Grid Gradient, Shuyu Cai, Lizhong Shi
Airframe Damage Region Division Evaluation Method Based On Boundary Grid Gradient, Shuyu Cai, Lizhong Shi
Journal of System Simulation
Abstract: In order to provide decision support for efficiently choosing and evaluating airframe damage region division methods, the characteristic of airframe damage region was analyzed, evaluating indicator of damage image division-boundary grid gradient was established. By introducing entropy method, combining with indicator of boundary grid gradient, the optimization of TOPSIS was presented, and the evaluation system of airframe damage region division was completely established. Airframe damage region division evaluation experiments were performed by different gray level entropy threshold of damage division image. Experimental results showed that, the proposed method efficiently represented division status of damage adjacency region, and avoided the …
Deep Learning Method For Hyperspectral Remote Sensing Images With Small Samples, Xiangbin Shi, Zhong Jian, Cuiwei Liu, Liu Fang, Deyuan Zhang
Deep Learning Method For Hyperspectral Remote Sensing Images With Small Samples, Xiangbin Shi, Zhong Jian, Cuiwei Liu, Liu Fang, Deyuan Zhang
Journal of System Simulation
Abstract: In order to solve the problem of large information dimension and fewer labeled training samples of hyperspectral remote sensing images, this paper proposes a hyperspectral remote sensing image classification framework HSI-CNN, which reduces the number of model parameters while maintaining the depth of neural network. Image pattern invariance and spectral channel contribution rate are analyzed, and the spectral redundancy information is reduced by principal component analysis. A full convolution neural network structure suitable for small sample hyperspectral remote sensing images is designed and the amount of network parameters is effectively reduced. Three kinds of HSI-CNN structures are proposed …
Saliency Feature Extraction Method Based On Multi-Scale Region Covariance, Shimin Wang, Jihua Ye, Mingwen Wang, Jiali Zuo, Changhong Liu
Saliency Feature Extraction Method Based On Multi-Scale Region Covariance, Shimin Wang, Jihua Ye, Mingwen Wang, Jiali Zuo, Changhong Liu
Journal of System Simulation
Abstract: In order to solve the problem that the saliency detection target boundary is vague, the paper proposes a saliency feature extraction method based on multi-scale region covariance. This method firstly extracts the multi-scale features of an image, then combines region covariance to extract the image bottom features, calculates the image’s multi-scale uncertainty weights, and the weights are optimized for the final saliency features, which are obtained by fusion. In the paper, our proposed model compares the experimental results with the commonly used feature extraction algorithms. The experimental results show that the proposed algorithm is closer to the actual …