Considering the defects of conventional optimization methods, a novel optimization algorithm is introduced in this paper. Target space partitioning method is used in this algorithm to solve multi-objective optimizatio...Considering the defects of conventional optimization methods, a novel optimization algorithm is introduced in this paper. Target space partitioning method is used in this algorithm to solve multi-objective optimization problem, thus achieve the coherent solution which can meet the requirements of all target functions, and improve the population's overall evolution level. The algorithm which guarantees diversity preservation and fast convergence to the Pareto set is applied to structural optimization problems. The empirical analysis supports the algorithm and gives an example with program.展开更多
From subject,object and target subsystems,we analyze the rural human resource development system.The subject system includes government,education and training organizations,society,and rural human resource itself.Diff...From subject,object and target subsystems,we analyze the rural human resource development system.The subject system includes government,education and training organizations,society,and rural human resource itself.Different development subject bears different responsibility.Object system includes farmers engaged in farming,farmer workers,rural unemployed people,rural students,rural left-behind people,and other people in rural areas.Different development object has different features.Development target system includes raising quality of rural human resource,keeping reasonable population size,optimizing structure of rural human resource,and improving vitality of rural human resource,etc.展开更多
Conducting reasonable weapon-target assignment( WTA) with near real time can bring the maximum awards with minimum costs which are especially significant in the modern war. A framework of dynamic WTA( DWTA) model base...Conducting reasonable weapon-target assignment( WTA) with near real time can bring the maximum awards with minimum costs which are especially significant in the modern war. A framework of dynamic WTA( DWTA) model based on a series of staged static WTA( SWTA) models is established where dynamic factors including time window of target and time window of weapon are considered in the staged SWTA model. Then,a hybrid algorithm for the staged SWTA named Decomposition-Based Dynamic Weapon-target Assignment( DDWTA) is proposed which is based on the framework of multi-objective evolutionary algorithm based on decomposition( MOEA / D) with two major improvements: one is the coding based on constraint of resource to generate the feasible solutions, and the other is the tabu search strategy to speed up the convergence.Comparative experiments prove that the proposed algorithm is capable of obtaining a well-converged and well diversified set of solutions on a problem instance and meets the time demand in the battlefield environment.展开更多
Focusing on the failure under the condition of target blocking, the similarity between target color and background color for the Camshift algorithm, an improved algorithm based on Camshift algorithm is proposed. Gauss...Focusing on the failure under the condition of target blocking, the similarity between target color and background color for the Camshift algorithm, an improved algorithm based on Camshift algorithm is proposed. Gaussian mixture model is used to determine the tracking area fast and accurately because it is not sensitive to the external conditions such as light and shadow. Kalman predictor is used to predict the blocked target effectively. The video is processed in the MATLAB environment. The moving target can be tracked and its position can be predicted accurately with the proposed improved algorithm. The results verify the feasibility and effectiveness of the algorithm.展开更多
In this paper, the problem of bearings-only maneuvering target tracking in sensors network is investigated. Two objectives are proposed and optimized by the ant colony optimization （ACO）, then two kinds of node sear...In this paper, the problem of bearings-only maneuvering target tracking in sensors network is investigated. Two objectives are proposed and optimized by the ant colony optimization （ACO）, then two kinds of node searching strategies of the ACO algorithm are presented. On the basis of the nodes determined by the ACO algorithm, the interacting multiple models extended Kalman filter （IMMEKF） for the multi-sensor bearings-only maneuvering target tracking is introduced. Simulation results indicate that the proposed ACO algorithm performs better than the Closest Nodes method. Furthermore, the Strategy 2 of the two given strategies is preferred in terms of the requirement of real time.展开更多
针对云端单一集中数据处理时效性低、架空线路上鸟巢检测精度不高、模型对边缘计算设备算力高消耗以及目标定位不准确的问题,提出了一种基于云边端协作的架空线路鸟巢检测与定位算法。该算法通过云、终、边缘3端的协作,解决了云端集中...针对云端单一集中数据处理时效性低、架空线路上鸟巢检测精度不高、模型对边缘计算设备算力高消耗以及目标定位不准确的问题,提出了一种基于云边端协作的架空线路鸟巢检测与定位算法。该算法通过云、终、边缘3端的协作,解决了云端集中处理效率低的问题,并通过云边数据可视化协作解决由于角度及光线引起的图像不清晰问题。为了提高架空线路鸟巢检测的精度,该算法在YOLOv5x模型基础上进行了优化。首先,通过将主干特征提取网络中的C3模块替换为C2f模块,并在最后一层加入SE(squeeze and excitation)注意力模块,以提升模型对小目标的检测能力。其次,将激活函数替换为Mish函数,解决训练梯度饱和导致神经元停止学习的问题。为了降低模型对边缘计算设备算力的消耗,对改进后的模型进行剪枝微调以降低模型参数规模。基于此优化模型,提出了三维目标定位算法,结合GIS(geographic information system)系统对定位结果进行修正,实现了对检测目标的精准定位。实验数据显示,改进后的模型平均精度均值达到93.25%,比原YOLOv5x模型提升了3.44%,优化后的模型剪枝率达到45%。检测目标经过三维空间建模计算并通过位置修正能够定位到相应的杆塔,有效指导工作人员快速准确排除隐患。展开更多
Infrared scene simulation has extensive applications in military and civil fields. Based on a certain experimental environment,object-oriented graphics rendering engine（ OGRE） is utilized to simulate a real three-di...Infrared scene simulation has extensive applications in military and civil fields. Based on a certain experimental environment,object-oriented graphics rendering engine（ OGRE） is utilized to simulate a real three-dimensional infrared complex scene. First,the target radiation of each part is calculated based on our experimental data. Then through the analysis of the radiation characteristics of targets and related material,an infrared texture library is established and the 3ds Max software is applied to establish an infrared radiation model.Finally,a real complex infrared scene is created by using the OGRE engine image rendering technology and graphic processing unit（ GPU） programmable pipeline technology. The results show that the simulation images are very similar to real images and are good supplements to real data.展开更多
针对高速公路隧道内光线昏暗、图像受灯光影响及远距离小目标检测困难等问题,提出了一种改进的YOLOv5高速公路隧道车辆和人员检测算法。首先,使用高斯混合聚类来获得更加匹配数据集目标的一组锚框,提高了模型的检测精度;其次,在特征融...针对高速公路隧道内光线昏暗、图像受灯光影响及远距离小目标检测困难等问题,提出了一种改进的YOLOv5高速公路隧道车辆和人员检测算法。首先,使用高斯混合聚类来获得更加匹配数据集目标的一组锚框,提高了模型的检测精度;其次,在特征融合部分引入内容感知重组特征(content-aware ReAssembly of FEatures, CARAFE)上采样算子,扩大感受野,降低上采样过程特征细节损失;最后,通过向网络中插入坐标注意力(coordinate attention, CA),进一步增强模型对图像各位置特征的提取能力。为验证算法的有效性,在浙江温丽高速公路隧道数据集上进行实验,结果表明:所提算法的平均检测精度(mean average precision, mAP)达到了95.7%,较原模型提升3.8%,对于远距离小目标和受严重灯光影响的目标能够实现更加精准检测,为复杂环境下高速公路隧道内车辆和人员检测提供了一种有效的解决方案。展开更多
基金National Natural Science Foundations of China (No. 60970004, No. 60743010)Natural Science Foundation of ShandongProvince, China (No. Z2008G02)
文摘Considering the defects of conventional optimization methods, a novel optimization algorithm is introduced in this paper. Target space partitioning method is used in this algorithm to solve multi-objective optimization problem, thus achieve the coherent solution which can meet the requirements of all target functions, and improve the population's overall evolution level. The algorithm which guarantees diversity preservation and fast convergence to the Pareto set is applied to structural optimization problems. The empirical analysis supports the algorithm and gives an example with program.
基金Supported by Project of National Social Science Foundation(09XMZ055)General Program of Scientific Research Project of Guangxi Provincial Department of Education (200911MS104)
文摘From subject,object and target subsystems,we analyze the rural human resource development system.The subject system includes government,education and training organizations,society,and rural human resource itself.Different development subject bears different responsibility.Object system includes farmers engaged in farming,farmer workers,rural unemployed people,rural students,rural left-behind people,and other people in rural areas.Different development object has different features.Development target system includes raising quality of rural human resource,keeping reasonable population size,optimizing structure of rural human resource,and improving vitality of rural human resource,etc.
文摘Conducting reasonable weapon-target assignment( WTA) with near real time can bring the maximum awards with minimum costs which are especially significant in the modern war. A framework of dynamic WTA( DWTA) model based on a series of staged static WTA( SWTA) models is established where dynamic factors including time window of target and time window of weapon are considered in the staged SWTA model. Then,a hybrid algorithm for the staged SWTA named Decomposition-Based Dynamic Weapon-target Assignment( DDWTA) is proposed which is based on the framework of multi-objective evolutionary algorithm based on decomposition( MOEA / D) with two major improvements: one is the coding based on constraint of resource to generate the feasible solutions, and the other is the tabu search strategy to speed up the convergence.Comparative experiments prove that the proposed algorithm is capable of obtaining a well-converged and well diversified set of solutions on a problem instance and meets the time demand in the battlefield environment.
文摘Focusing on the failure under the condition of target blocking, the similarity between target color and background color for the Camshift algorithm, an improved algorithm based on Camshift algorithm is proposed. Gaussian mixture model is used to determine the tracking area fast and accurately because it is not sensitive to the external conditions such as light and shadow. Kalman predictor is used to predict the blocked target effectively. The video is processed in the MATLAB environment. The moving target can be tracked and its position can be predicted accurately with the proposed improved algorithm. The results verify the feasibility and effectiveness of the algorithm.
基金This paper was supported by the Natural Science Foundation of Jiangsu province of China (BK2004132)
文摘In this paper, the problem of bearings-only maneuvering target tracking in sensors network is investigated. Two objectives are proposed and optimized by the ant colony optimization （ACO）, then two kinds of node searching strategies of the ACO algorithm are presented. On the basis of the nodes determined by the ACO algorithm, the interacting multiple models extended Kalman filter （IMMEKF） for the multi-sensor bearings-only maneuvering target tracking is introduced. Simulation results indicate that the proposed ACO algorithm performs better than the Closest Nodes method. Furthermore, the Strategy 2 of the two given strategies is preferred in terms of the requirement of real time.
文摘针对云端单一集中数据处理时效性低、架空线路上鸟巢检测精度不高、模型对边缘计算设备算力高消耗以及目标定位不准确的问题,提出了一种基于云边端协作的架空线路鸟巢检测与定位算法。该算法通过云、终、边缘3端的协作,解决了云端集中处理效率低的问题,并通过云边数据可视化协作解决由于角度及光线引起的图像不清晰问题。为了提高架空线路鸟巢检测的精度,该算法在YOLOv5x模型基础上进行了优化。首先,通过将主干特征提取网络中的C3模块替换为C2f模块,并在最后一层加入SE(squeeze and excitation)注意力模块,以提升模型对小目标的检测能力。其次,将激活函数替换为Mish函数,解决训练梯度饱和导致神经元停止学习的问题。为了降低模型对边缘计算设备算力的消耗,对改进后的模型进行剪枝微调以降低模型参数规模。基于此优化模型,提出了三维目标定位算法,结合GIS(geographic information system)系统对定位结果进行修正,实现了对检测目标的精准定位。实验数据显示,改进后的模型平均精度均值达到93.25%,比原YOLOv5x模型提升了3.44%,优化后的模型剪枝率达到45%。检测目标经过三维空间建模计算并通过位置修正能够定位到相应的杆塔,有效指导工作人员快速准确排除隐患。
基金Supported by the National Twelfth Five-Year Project(40405050303)
文摘Infrared scene simulation has extensive applications in military and civil fields. Based on a certain experimental environment,object-oriented graphics rendering engine（ OGRE） is utilized to simulate a real three-dimensional infrared complex scene. First,the target radiation of each part is calculated based on our experimental data. Then through the analysis of the radiation characteristics of targets and related material,an infrared texture library is established and the 3ds Max software is applied to establish an infrared radiation model.Finally,a real complex infrared scene is created by using the OGRE engine image rendering technology and graphic processing unit（ GPU） programmable pipeline technology. The results show that the simulation images are very similar to real images and are good supplements to real data.
文摘针对高速公路隧道内光线昏暗、图像受灯光影响及远距离小目标检测困难等问题,提出了一种改进的YOLOv5高速公路隧道车辆和人员检测算法。首先,使用高斯混合聚类来获得更加匹配数据集目标的一组锚框,提高了模型的检测精度;其次,在特征融合部分引入内容感知重组特征(content-aware ReAssembly of FEatures, CARAFE)上采样算子,扩大感受野,降低上采样过程特征细节损失;最后,通过向网络中插入坐标注意力(coordinate attention, CA),进一步增强模型对图像各位置特征的提取能力。为验证算法的有效性,在浙江温丽高速公路隧道数据集上进行实验,结果表明:所提算法的平均检测精度(mean average precision, mAP)达到了95.7%,较原模型提升3.8%,对于远距离小目标和受严重灯光影响的目标能够实现更加精准检测,为复杂环境下高速公路隧道内车辆和人员检测提供了一种有效的解决方案。
