期刊文献+
共找到153篇文章
< 1 2 8 >
每页显示 20 50 100
基于Linemod-2D与Otsu的多目标工件快速分拣方法研究 认领 引用 被引量:4
1
作者 杨俊杰 袁清珂 +1 位作者 梁杰超 叶凯冬 《组合机床与自动化加工技术》 北大核心 2022年第10期79-82,87,共4页
针对多目标工件快速分拣的需求,提出一种改进的边缘特征模板匹配算法。首先,采取图像金字塔搜索策略提高实时性;其次,在金字塔顶层用Linemod-2D的快速查表法进行所有旋转模板的全局粗匹配;再次,采用双阈值最大类间方差法获取自适应梯度... 针对多目标工件快速分拣的需求,提出一种改进的边缘特征模板匹配算法。首先,采取图像金字塔搜索策略提高实时性;其次,在金字塔顶层用Linemod-2D的快速查表法进行所有旋转模板的全局粗匹配;再次,采用双阈值最大类间方差法获取自适应梯度幅值阈值,以此来筛选顶层中参与相似性度量的梯度方向;最后,精匹配的过程交由传统边缘特征模板匹配来完成。实验结果表明,改进算法比传统边缘特征模板匹配算法快了5倍,解决了传统算法搜寻多旋转位姿多目标耗时较长的问题,并且保持着传统算法的准确性和稳定性,可有效提高多目标工件分拣效率。 展开更多
关键词 工件分拣 边缘特征 Linemod-2D 模板匹配 最大类间方差法
暂未订购 下载PDF
基于2-D系统理论的D型开闭环迭代学习控制 认领 引用 被引量:2
2
作者 蒋思中 王改云 《电光与控制》 北大核心 2010年第1期37-39,60,共3页
对于具有重复运动性质的系统,迭代学习控制是一种行之有效的控制方法。开闭环迭代学习控制能同时利用系统前次运行和当前运行的信息,因而性能优于单纯的开环迭代学习控制。针对线性连续系统,设计了D(Differential)型开闭环迭代学习控制... 对于具有重复运动性质的系统,迭代学习控制是一种行之有效的控制方法。开闭环迭代学习控制能同时利用系统前次运行和当前运行的信息,因而性能优于单纯的开环迭代学习控制。针对线性连续系统,设计了D(Differential)型开闭环迭代学习控制器,利用2-D(Two-Dimensional)系统理论建立系统的2-D连续—离散Roesser模型,并给出了保证控制器收敛的充分必要条件。最后通过一个仿真实例,证明了该方案的有效性。 展开更多
关键词 线性连续系统 开闭环算法 2-D系统理论 Roesser模型
暂未订购 下载PDF
标准遗传算法引入遗传策略和突变算子对蛋白质2D折叠模拟的影响 认领 引用 被引量:5
3
作者 李绍新 张延娇 《广东医学院学报》 2008年第5期499-502,共4页
目的改进标准遗传算法以提高蛋白质结构的预测效率。方法在标准遗传算法的基础上引入蒙特卡罗局部优化策略、克隆体过滤策略、多胎竞争选择策略等,在均匀变异的基础上,引入一系列结构突变算子。利用改进的遗传算法对标准蛋白质序列进行... 目的改进标准遗传算法以提高蛋白质结构的预测效率。方法在标准遗传算法的基础上引入蒙特卡罗局部优化策略、克隆体过滤策略、多胎竞争选择策略等,在均匀变异的基础上,引入一系列结构突变算子。利用改进的遗传算法对标准蛋白质序列进行二维折叠模拟。结果与其他算法相比,利用改进的遗传算法搜索到了HP60和HP64序列能量更低的构型。结论引入的遗传策略和突变算子增强了遗传算法的寻优能力。改进的遗传算法是个极具潜力的蛋白质结构预测方法。 展开更多
关键词 遗传算法 2D折叠模拟 HP模型
暂未订购 下载PDF
人脸图像识别中非贪婪L1范数的2DPCA最大化鲁棒算法 认领 引用
4
作者 刘辉 马文 王志锋 《南京邮电大学学报(自然科学版)》 北大核心 2016年第2期90-95,共6页
基于L1范数的二维主成分分析是近年来提出的一种在图像域降维和特征提取的方法。通常,直接求解L1范数最大化问题很困难,因此,一种贪婪的策略被提出来了。然而,这种策略的初始化投影是随意选取的,为了获得更好的投影向量,得到一个最优的... 基于L1范数的二维主成分分析是近年来提出的一种在图像域降维和特征提取的方法。通常,直接求解L1范数最大化问题很困难,因此,一种贪婪的策略被提出来了。然而,这种策略的初始化投影是随意选取的,为了获得更好的投影向量,得到一个最优的局部解,提出了一个非贪婪的L1范数最大化算法,该非贪婪算法具有三大优势:使用L1范数和非贪婪策略对于异常值很稳健;与PCA-L1相比较,更多的空间结构信息得到了保留;相比2DPCA-L1,所有的投影方向可以被优化并且可以获得更好的解决方案。人脸和其他数据集上的实验结果验证了所提出的方法更加有效。 展开更多
关键词 二维主成分分析 L1范数 非贪婪算法 异常值 主成分分析法
暂未订购 下载PDF
Identification of Convective and Stratiform Clouds Based on the Improved DBSCAN Clustering Algorithm 认领 引用 被引量:9
5
作者 Yuanyuan ZUO Zhiqun HU +3 位作者 Shujie YUAN Jiafeng ZHENG Xiaoyan YIN Boyong LI 《Advances in Atmospheric Sciences》 SCIE CAS CSCD 2022年第12期2203-2212,共10页
A convective and stratiform cloud classification method for weather radar is proposed based on the density-based spatial clustering of applications with noise(DBSCAN)algorithm.To identify convective and stratiform clo... A convective and stratiform cloud classification method for weather radar is proposed based on the density-based spatial clustering of applications with noise(DBSCAN)algorithm.To identify convective and stratiform clouds in different developmental phases,two-dimensional(2D)and three-dimensional(3D)models are proposed by applying reflectivity factors at 0.5°and at 0.5°,1.5°,and 2.4°elevation angles,respectively.According to the thresholds of the algorithm,which include echo intensity,the echo top height of 35 dBZ(ET),density threshold,andεneighborhood,cloud clusters can be marked into four types:deep-convective cloud(DCC),shallow-convective cloud(SCC),hybrid convective-stratiform cloud(HCS),and stratiform cloud(SFC)types.Each cloud cluster type is further identified as a core area and boundary area,which can provide more abundant cloud structure information.The algorithm is verified using the volume scan data observed with new-generation S-band weather radars in Nanjing,Xuzhou,and Qingdao.The results show that cloud clusters can be intuitively identified as core and boundary points,which change in area continuously during the process of convective evolution,by the improved DBSCAN algorithm.Therefore,the occurrence and disappearance of convective weather can be estimated in advance by observing the changes of the classification.Because density thresholds are different and multiple elevations are utilized in the 3D model,the identified echo types and areas are dissimilar between the 2D and 3D models.The 3D model identifies larger convective and stratiform clouds than the 2D model.However,the developing convective clouds of small areas at lower heights cannot be identified with the 3D model because they are covered by thick stratiform clouds.In addition,the 3D model can avoid the influence of the melting layer and better suggest convective clouds in the developmental stage. 展开更多
关键词 improved DBSCAN clustering algorithm cloud identification and classification 2D model 3D model weather radar
暂未订购 下载PDF
基于改进Linemod⁃2D的快速形状匹配算法 认领 引用 被引量:5
6
作者 陈全义 陈三风 +1 位作者 胡涛 刘祚时 《现代电子技术》 2021年第6期159-164,共6页
Linemod⁃2D是一种基于特征匹配的快速目标识别算法,其像素级的定位精度,使其不能直接用于亚像素级高精度要求的工业检测场景。针对上述问题进行改进,提出一种基于改进Linemod⁃2D的快速形状匹配算法。采用网格化方式提取模板特征,并用Zer... Linemod⁃2D是一种基于特征匹配的快速目标识别算法,其像素级的定位精度,使其不能直接用于亚像素级高精度要求的工业检测场景。针对上述问题进行改进,提出一种基于改进Linemod⁃2D的快速形状匹配算法。采用网格化方式提取模板特征,并用Zernike矩对边缘点进行亚像素校正,以获取精确的位置和角度作为匹配特征。在图像金字塔的上层采用改进的Linemod⁃2D进行快速的粗匹配,其角度量化方向扩展为16个。在图像金字塔底层,采用角度量化扩展为360个方向的匹配策略进行精匹配,得到像素级的匹配位置和小于0.5°的角度误差,然后采用最小二乘平差法得到亚像素级的匹配位置和精确的角度。实验研究结果表明,该算法的匹配位置误差小于±0.04像素,角度误差小于±0.015°,其匹配精度和速度优于CkVisionBuilder的形状匹配算法,接近Halcon的形状匹配算法。 展开更多
关键词 形状匹配算法 Linemod⁃2D 特征匹配 亚像素校正 像素级定位 实验分析
暂未订购 下载PDF
Genetic Based Approach for Optimal Power and Channel Allocation to Enhance D2D Underlaied Cellular Network Capacity in 5G 认领 引用 被引量:1
7
作者 Ahmed.A.Rosas Mona Shokair M.I.Dessouky 《Computers, Materials & Continua》 SCIE EI 2022年第8期3751-3762,共12页
With the obvious throughput shortage in traditional cellular radio networks,Device-to-Device(D2D)communications has gained a lot of attention to improve the utilization,capacity and channel performance of nextgenerati... With the obvious throughput shortage in traditional cellular radio networks,Device-to-Device(D2D)communications has gained a lot of attention to improve the utilization,capacity and channel performance of nextgeneration networks.In this paper,we study a joint consideration of power and channel allocation based on genetic algorithm as a promising direction to expand the overall network capacity for D2D underlaied cellular networks.The genetic based algorithm targets allocating more suitable channels to D2D users and finding the optimal transmit powers for all D2D links and cellular users efficiently,aiming to maximize the overall system throughput of D2D underlaied cellular network with minimum interference level,while satisfying the required quality of service QoS of each user.The simulation results show that our proposed approach has an advantage in terms of maximizing the overall system utilization than fixed,random,BAT algorithm(BA)and Particle Swarm Optimization(PSO)based power allocation schemes. 展开更多
关键词 5G D2D communication spectrum allocation power allocation genetic algorithm optimization BAT-optimization particle swarm optimization
暂未订购 下载PDF
基于2D-MUSIC算法的DOA估计 认领 引用 被引量:5
8
作者 康亚芳 王静 +1 位作者 张清泉 行小帅 《海南师范大学学报(自然科学版)》 CAS 2014年第3期266-270,共5页
利用经典的2D-MUSIC算法对二维阵列的DOA估计进行了研究,在平面阵列数学模型以及2D-MUSIC算法的DOA估计模型基础上,以均匀平面阵列为例,对3种不同参数的DOA估计进行了计算机仿真,分析了仿真结果.得出了在不同参数变化趋势下DOA估计的相... 利用经典的2D-MUSIC算法对二维阵列的DOA估计进行了研究,在平面阵列数学模型以及2D-MUSIC算法的DOA估计模型基础上,以均匀平面阵列为例,对3种不同参数的DOA估计进行了计算机仿真,分析了仿真结果.得出了在不同参数变化趋势下DOA估计的相应变化情况. 展开更多
关键词 2D-MUSIC算法 均匀平面阵 二维DOA估计
暂未订购 下载PDF
Fuzzy-2D-HMMS算法及其收敛性 认领 引用 被引量:1
9
作者 杨于镭 李兵 吴佳燕 《模糊系统与数学》 北大核心 2009年第4期161-167,共7页
通过对Dat Tran和Michael Wagner等提出的FCM-FE-HMMS算法研究,并把它与2维隐马氏模型联系起来,提出了Fuzzy-2D-HMMS算法,得出在给定初值的情况下该算法将收敛到一个局部最优解。
关键词 2维隐马氏模型 FCM算法 目标函数 收敛性
暂未订购 下载PDF
一种高速2-D滑动FFT的设计实现 认领 引用
10
作者 许丁鸿 张多利 +2 位作者 陶相颖 韩帅鹏 宋宇鲲 《合肥工业大学学报(自然科学版)》 CAS 北大核心 2023年第7期912-918,共7页
文章介绍了采用2-D快速傅里叶变换(fast Fourier transform,FFT)算法的滑动窗FFT的基本特性原理和硬件实现过程,完成了窗长256点、步长16点的2-D滑动窗FFT的专用集成电路(application specific integrated circuit,ASIC)设计。传统FFT... 文章介绍了采用2-D快速傅里叶变换(fast Fourier transform,FFT)算法的滑动窗FFT的基本特性原理和硬件实现过程,完成了窗长256点、步长16点的2-D滑动窗FFT的专用集成电路(application specific integrated circuit,ASIC)设计。传统FFT算法受序列完整性的制约,时滞较大,无法满足某些高实时性信号分析领域的处理速度要求。该文采用滑动FFT算法,克服了传统FFT对序列完整性的依赖,设计的滑动FFT处理器使用2-D FFT压缩新序列计算时间,以基16蝶形运算器为核心,采用系数复用和高基Booth方法优化系数编码技术压缩乘法器的数量,减少电路面积。所设计的2-D滑动FFT完成单次滑动窗长的计算时间比传统算法节约了16.1%,变换结果与MATLAB的运算结果相比,信噪比(signal-to-noise ratio,SNR)大于130 dB。在TSMC 28 nm的工艺下,工作主频为600 MHz,面积为1980μm×2060μm。 展开更多
关键词 快速傅里叶变换(FFT) 滑动FFT 2-D FFT算法 高基Booth编码
暂未订购 下载PDF
Simulation of Flux Distribution in Central Metabolism of Saccharo-myces cerevisiae by Hybridized Genetic Algorithm 认领 引用
11
作者 张慧敏 姚善泾 《Chinese Journal of Chemical Engineering》 SCIE EI CAS 2007年第2期150-156,共7页
A scheme of investigating the intracellular metabolic fluxes in central metabolism of Saccharomyces cerevisiae based on isotope model and tracer experiment was developed. The metabolic model applied in this study incl... A scheme of investigating the intracellular metabolic fluxes in central metabolism of Saccharomyces cerevisiae based on isotope model and tracer experiment was developed. The metabolic model applied in this study includes the Embden-Meyerhof-Parnas pathway,the pentose phosphate pathway,the tricarboxylic acid cycle,CO2 anaplerotic reactions,ethanol and acetate formation,and pathways involved in amino acid synthesis. The approach of hybridized genetic algorithm combined with the sequential simplex technique was used to optimize a quadratic error function without the requirement of the information on the partial derivatives. The impact of some key pa-rameters on the algorithm was studied. This approach was proved to be rapid and numerically stable in the analysis of the central metabolism of S.cerevisiae. 展开更多
关键词 Saccharomyces cerevisiae metabolic flux hybridized genetic algorithm 2D NMR central metabolism
暂未订购 下载PDF
A study on Parallel Computation Based on Finite Element Forward Modeling of 2D Magnetotelluric 认领 引用 被引量:1
12
作者 Mao Wang Handong Tan +2 位作者 Changhong Lin Xiao Liu Zhiyong Zhang 《International Journal of Geosciences》 CAS 2015年第8期863-868,共6页
Magnetotelluric sounding method based on the difference of the rock’s resistivity is an exploration method about doing research in earth’s resistivity and phase using the native electromagnetic field. The paper adop... Magnetotelluric sounding method based on the difference of the rock’s resistivity is an exploration method about doing research in earth’s resistivity and phase using the native electromagnetic field. The paper adopts 2D finite element method as the magnetotelluric forward method and calculates the total field by primary field (also named background field) plus secondary field. We can?get more accurate forward result through the finite element method and we can get the result effected by the dense degree of grid slightly by the total field. But the method is not effective?enough when the model is divided into relative big grid. When the frequency changes, program solves relevant equation separately. According to the feature of the algorithm, we apply MPI parallel method in the algorithm. Every process solves relevant equation. The account of frequency?that a process needs to solve in parallel computation is less than the account that the process?needs to solve in serial algorithm. We can see that the forward result is the same with the serial algorithm and proves the correctness of algorithm. We do statistics about the efficiency of the parallel algorithm. When the account of processes is from 2 to 8, the speedup is from 1.63 to 2.64. It proves the effectiveness of the parallel algorithm. 展开更多
关键词 Magnetotelluric 2D Forward Modeling Finite Element Parallel Algorithm Total Field
暂未订购 下载PDF
Identification of Noisy Utterance Speech Signal using GA-Based Optimized 2D-MFCC Method and a Bispectrum Analysis 认领 引用
13
作者 Benyamin Kusumoputro Agus Buono Li Na 《Journal of Software Engineering and Applications》 2012年第12期193-199,共7页
One-dimensional Mel-Frequency Cepstrum Coefficients (1D-MFCC) in conjunction with a power spectrum analysis method is usually used as a feature extraction in a speaker identification system. However, as this one dimen... One-dimensional Mel-Frequency Cepstrum Coefficients (1D-MFCC) in conjunction with a power spectrum analysis method is usually used as a feature extraction in a speaker identification system. However, as this one dimensional feature extraction subsystem shows low recognition rate for identifying an utterance speech signal under harsh noise conditions, we have developed a speaker identification system based on two-dimensional Bispectrum data that was theoretically more robust to the addition of Gaussian noise. As the processing sequence of ID-MFCC method could not be directly used for processing the two-dimensional Bispectrum data, in this paper we proposed a 2D-MFCC method as an extension of the 1D-MFCC method and the optimization of the 2D filter design using Genetic Algorithms. By using the 2D-MFCC method with the Bispectrum analysis method as the feature extraction technique, we then used Hidden Markov Model as the pattern classifier. In this paper, we have experimentally shows our developed methods for identifying an utterance speech signal buried with various levels of noise. Experimental result shows that the 2D-MFCC method without GA optimization has a comparable high recognition rate with that of 1D-MFCC method for utterance signal without noise addition. However, when the utterance signal is buried with Gaussian noises, the developed 2D-MFCC shows higher recognition capability, especially, when the 2D-MFCC optimized by Genetics Algorithms is utilized. 展开更多
关键词 2D Mel-Frequency Cepstrum Coefficients Bispectrum Hidden Markov Model Genetics Algorithms
暂未订购 下载PDF
基于机器视觉的工件识别、定位与抓取研究 认领 引用 被引量:4
14
作者 赵岩 程家浩 +2 位作者 王震 闫仕程 康军 《天津理工大学学报》 2026年第1期41-48,共8页
针对传统的机器人工件抓取过程中识别精度低的问题,提出一种最大类间方差法(Nobuyuki Otsu,NO)与改进的Linemod-2D算法相结合的方法对工件进行识别定位与抓取研究。通过Otsu对图像双边阈值计算,采用Canny算子对图像边缘提取,对图像的边... 针对传统的机器人工件抓取过程中识别精度低的问题,提出一种最大类间方差法(Nobuyuki Otsu,NO)与改进的Linemod-2D算法相结合的方法对工件进行识别定位与抓取研究。通过Otsu对图像双边阈值计算,采用Canny算子对图像边缘提取,对图像的边缘离散化,提高了工件识别的实时性和准确性,增加了工件识别的鲁棒性。同时将Linemod-2D的梯度量化增加到16个方向,金字塔的层数可根据目标图像大小自适应加快匹配速度。DH参数法对机器人仿真分析,控制Dobot CR5机器人的运动,实现了对工件的抓取和放置。试验结果与预期相符,满足智能制造中的实际需求。 展开更多
关键词 机器视觉 目标定位 模板匹配 改进Linemod-2D 机器人抓取
暂未订购 下载PDF
A Robust Resource Allocation Scheme for Device-to-Device Communications Based on Q-Learning 认领 引用 被引量:8
15
作者 Azka Amin Xihua Liu +3 位作者 Imran Khan Peerapong Uthansakul Masoud Forsat Seyed Sajad Mirjavadi 《Computers, Materials & Continua》 SCIE EI 2020年第11期1487-1505,共19页
One of the most effective technology for the 5G mobile communications is Device-to-device(D2D)communication which is also called terminal pass-through technology.It can directly communicate between devices under the c... One of the most effective technology for the 5G mobile communications is Device-to-device(D2D)communication which is also called terminal pass-through technology.It can directly communicate between devices under the control of a base station and does not require a base station to forward it.The advantages of applying D2D communication technology to cellular networks are:It can increase the communication system capacity,improve the system spectrum efficiency,increase the data transmission rate,and reduce the base station load.Aiming at the problem of co-channel interference between the D2D and cellular users,this paper proposes an efficient algorithm for resource allocation based on the idea of Q-learning,which creates multi-agent learners from multiple D2D users,and the system throughput is determined from the corresponding state-learning of the Q value list and the maximum Q action is obtained through dynamic power for control for D2D users.The mutual interference between the D2D users and base stations and exact channel state information is not required during the Q-learning process and symmetric data transmission mechanism is adopted.The proposed algorithm maximizes the system throughput by controlling the power of D2D users while guaranteeing the quality-of-service of the cellular users.Simulation results show that the proposed algorithm effectively improves system performance as compared with existing algorithms. 展开更多
关键词 5G D2D communications power allocation algorithm resource optimization
暂未订购 下载PDF
3维Douglas-Peucker算法及其在DEM自动综合中的应用研究 认领 引用 被引量:49
16
作者 费立凡 何津 +1 位作者 马晨燕 颜辉武 《测绘学报》 EI 北大核心 2006年第3期278-284,共7页
在分析2维Douglas-Peucker算法原理实质的基础上,提出3维Douglas-Peucker算法,并将此法应用到对DEM的基础———3维离散点的自动综合上。采用计算机程序对新算法进行的验证,初步结果表明该算法能较好地筛选出DEM整体及局部范围的地貌特... 在分析2维Douglas-Peucker算法原理实质的基础上,提出3维Douglas-Peucker算法,并将此法应用到对DEM的基础———3维离散点的自动综合上。采用计算机程序对新算法进行的验证,初步结果表明该算法能较好地筛选出DEM整体及局部范围的地貌特征点,其计算效率也较令人满意。 展开更多
关键词 Douglas—Peucker算法 2维曲线综合 3维Douglas—Peucker算法 3维离散点综合 DEM综合
暂未订购 下载PDF
TESLA-Based Authentication for BeiDou Civil Navigation Message 认领 引用 被引量:4
17
作者 Zhijun Wu Yun Zhang +1 位作者 Liang Liu Meng Yue 《China Communications》 SCIE CSCD 2020年第11期194-218,共25页
Due to the civil BeiDou navigation system is open,unauthenticated,and non-encrypted,civilian BeiDou navigation signals may have great security loopholes during transmission or reception.The main security loophole here... Due to the civil BeiDou navigation system is open,unauthenticated,and non-encrypted,civilian BeiDou navigation signals may have great security loopholes during transmission or reception.The main security loophole here is spoofing attacks.Spoofing attacks make the positioning or timing results of BeiDou civilian receivers wrong.Such errors may cause a series of security problems,which lays a serious hidden danger for Bei-Dou satellite information security.This article proposes an anti-spoofing method for BeiDou navigation system based on the combination of SM commercial cryptographic algorithm and Timed Efficient Stream Loss-tolerant Authentication(TESLA)for spoofing attacks.In this solution,we use the SM3 algorithm to generate a TESLA key chain with time information,and then use the key in the key chain to generate the message authentication code for the BeiDou D2 navigation message.The message authentication code is inserted into a reserved bit of the D2 navigation message.In addition,this solution uses the SM2 algorithm to protect and encrypt time information in the TESLA key chain to prevent key replay attacks in TESLA.The experimental results tested on the experimental platform built in this paper show that this scheme reduces the possibility of the BeiDou navigation system being deceived and enhances the safety of the BeiDou navigation system. 展开更多
关键词 BeiDou navigation system SM commercial cryptographic algorithm TESLA message authentication code D2 navigation message
暂未订购 下载PDF
基于改进麻雀算法的最大2维熵分割方法 认领 引用 被引量:15
18
作者 柳长安 冯雪菱 +1 位作者 孙长浩 赵丽娟 《激光技术》 CAS CSCD 北大核心 2022年第2期274-282,共9页
为了提高最大2维熵分割的性能,提出了基于改进麻雀算法的最大2维熵分割方法,可减小运算量并且缩短计算时间。首先,融合反向学习策略和自适应t分布变异,引入精英粒子,以扩大算法搜索范围,增加算法后期局部搜索能力;其次,使用萤火虫机制,... 为了提高最大2维熵分割的性能,提出了基于改进麻雀算法的最大2维熵分割方法,可减小运算量并且缩短计算时间。首先,融合反向学习策略和自适应t分布变异,引入精英粒子,以扩大算法搜索范围,增加算法后期局部搜索能力;其次,使用萤火虫机制,对最优解进行扰动变异,进一步增加种群多样性;最后,采用提出的改进麻雀算法寻找图像最大2维熵,得到最优阈值分割图像。结果表明,4幅图像的平均运行时间为0.3695s,远低于基础2维熵算法的1.7547s和基础2维Otsu算法的5.7936s。所提出的改进麻雀算法的全局搜索和局部寻优能力相比原麻雀算法有较大改善,缩短了传统最大2维熵图像分割方法的运行时间,在峰值信噪比和结构相似度指标上均得到提升,具有一定的应用价值。 展开更多
关键词 图像处理 智能优化算法 麻雀搜索算法 最大2维熵 t分布
暂未订购 下载PDF
基于TDLAS检测技术的甲烷体积分数场重建研究 认领 引用 被引量:7
19
作者 张旭 曹树亚 +4 位作者 郭腾霄 董力强 杨柳 原博 丁学全 《激光技术》 CAS CSCD 北大核心 2018年第4期577-582,共6页
为了实现对甲烷体积分数场的2维分布重建,基于可调谐半导体激光吸收光谱(TDLAS)检测技术,以甲烷为目标气体,采用直接吸收的测量方式,探测了甲烷氮气混合气的吸收光谱信号,通过代数重建算法对甲烷体积分数进行了模拟重建和实验研究,模拟... 为了实现对甲烷体积分数场的2维分布重建,基于可调谐半导体激光吸收光谱(TDLAS)检测技术,以甲烷为目标气体,采用直接吸收的测量方式,探测了甲烷氮气混合气的吸收光谱信号,通过代数重建算法对甲烷体积分数进行了模拟重建和实验研究,模拟重建采用了6×6共36个方格的正方形重建区域,假定一个方形区域内具有空穴的体积分数分布,模拟24条光束从4个方向穿过重建区域,获取了模拟光线下的投影值。结果表明,经过重复实验统计均方根误差在2.58%,对模拟投影信号加入不同信噪比(5%,10%,20%)的高斯白噪声之后再进行重建,均方根误差分别在4.17%~9.30%之间;实验研究采取面源泄露式扩散方式,并通过在中心附近放置石英柱的方式人为制造体积分数空穴,形成非均匀体积分数场,通过对放置障碍物前后的重建结果对比,能够看到在空穴位置有明显的体积分数下降。TDLAS技术与计算机断层重建技术在气体体积分数场的局部分布检测上有可行性,具备作为有毒有害气体云团体积分数分布检测手段的潜力。 展开更多
关键词 光谱学 2维分布重建 代数重建算法 可调谐半导体激光吸收光谱检测技术
暂未订购 下载PDF
基于改进遗传算法的最大2维熵图像分割 认领 引用 被引量:11
20
作者 李丽宏 华国光 《激光技术》 CAS CSCD 北大核心 2019年第1期119-124,共6页
为了解决传统最大2维熵分割算法计算量大、耗时较多等缺陷,提出一种基于改进遗传算法的最大2维熵图像分割法。通过对遗传算法变异操作方式进行改进,提高遗传算法寻找最大2维熵分割阈值的速度,加速分割算法对图像的分割,并进行了仿真实... 为了解决传统最大2维熵分割算法计算量大、耗时较多等缺陷,提出一种基于改进遗传算法的最大2维熵图像分割法。通过对遗传算法变异操作方式进行改进,提高遗传算法寻找最大2维熵分割阈值的速度,加速分割算法对图像的分割,并进行了仿真实验验证。结果表明,改进模型的运行时间被压缩到了0.95s,远远低于传统的最大2维熵分割法。改进的分割方法实现了分割效率的提高,同时也保证了图像的分割精度。 展开更多
关键词 图像处理 最大2维熵 遗传算法 变异操作
暂未订购 下载PDF
上一页 1 2 8 下一页 到第
在线咨询 使用帮助 返回顶部 意见反馈