期刊文献+
共找到15篇文章
< 1 >
每页显示 20 50 100
基于图像处理的煤/矸密度识别系统的研究 被引量:8
1
作者 霍平 曾翰林 霍柯言 《选煤技术》 CAS 2015年第2期69-73,共5页
为提高煤与矸石识别的准确性,开发了一套基于图像处理的煤/矸密度识别系统。该系统是以MATLAB为平台,针对煤/矸图像的特点,对获取的煤/矸图像进行同态滤波、中值滤波、图像分割以及形态学滤波处理,得到煤/矸的轮廓;然后利用积分算法,计... 为提高煤与矸石识别的准确性,开发了一套基于图像处理的煤/矸密度识别系统。该系统是以MATLAB为平台,针对煤/矸图像的特点,对获取的煤/矸图像进行同态滤波、中值滤波、图像分割以及形态学滤波处理,得到煤/矸的轮廓;然后利用积分算法,计算出煤/矸的体积;再利用所测煤/矸的质量,计算出煤/矸的密度,最终根据煤和矸石密度的不同实现二者的识别。试验结果表明,该方法能快速、有效地对煤和矸石进行实时检测。 展开更多
关键词 煤/矸密度识别系统 矸石 识别 MATLAB
下载PDF
一种基于卷积神经网络的人群密度识别算法 被引量:1
2
作者 杨博涵 《电脑知识与技术》 2022年第2期82-83,93,共3页
近年来,人群密度的识别成为模式识别领域的热点问题,基于这个问题,该文提出一种基于卷积神经网络的算法,首先将数据集中的Ground-Truth数据转化为人群密度图,然后将生成的密度图送入神经网络中进行训练,得到人群密度数据。该文创新点在... 近年来,人群密度的识别成为模式识别领域的热点问题,基于这个问题,该文提出一种基于卷积神经网络的算法,首先将数据集中的Ground-Truth数据转化为人群密度图,然后将生成的密度图送入神经网络中进行训练,得到人群密度数据。该文创新点在于采用多尺度卷积神经网络,使用多种尺度的卷积核来适应不同尺度的人头大小。通过利用具有不同尺寸接收领域的过滤器,从而可以识别各种分辨率的人群图像和数据。 展开更多
关键词 人工智能 卷积神经网络 人群密度识别
下载PDF
基于智能终端的梭织物密度视觉识别系统 被引量:3
3
作者 赵跃鹏 张雯丹 +1 位作者 徐庆坡 向忠 《天津纺织科技》 2020年第1期38-41,共4页
针对现有梭织物密度视觉识别系统多存有操作灵活性低、实现成本高以及系统复杂不便等问题,文中提出了一种基于智能终端的机织物密度视觉识别系统,该系统通过利用快速傅里叶变换,将接收到的由相机捕获的机织物图像进行自动识别,通过小波... 针对现有梭织物密度视觉识别系统多存有操作灵活性低、实现成本高以及系统复杂不便等问题,文中提出了一种基于智能终端的机织物密度视觉识别系统,该系统通过利用快速傅里叶变换,将接收到的由相机捕获的机织物图像进行自动识别,通过小波变换快速分析机织物的经纬纱线信息,在平台显示界面直接显示出机织物的密度检测结果。文章表明,有效克服了传统机织物密度识别系统灵活性低、实现成本高以及系统复杂不便的缺点,从而极大地提高了工作效率,有效促进我国纺织业的发展。 展开更多
关键词 机织物 密度识别 智能终端 傅立叶变换 自动识别
原文传递
基于MobileViT模型的小麦收获机喂入密度分类方法
4
作者 杨志凯 扶兰兰 +3 位作者 唐灿 王发明 倪昕东 陈度 《农业机械学报》 EI CAS CSCD 北大核心 2023年第S01期172-180,共9页
基于喂入量的作业速度智能化控制技术是优化联合收获机作业效率和质量的重要手段。本文针对传统喂入量自动控制技术时滞明显,在喂入量调整时无法及时适应实际情况的问题,采用基于图像的深度学习方法开展了成熟期小麦植株密度等级分类识... 基于喂入量的作业速度智能化控制技术是优化联合收获机作业效率和质量的重要手段。本文针对传统喂入量自动控制技术时滞明显,在喂入量调整时无法及时适应实际情况的问题,采用基于图像的深度学习方法开展了成熟期小麦植株密度等级分类识别方法研究,通过预先感知作物密度,实现联合收获机作业参数的自动调整。首先基于车载相机和无人机图像构建了小麦植株图像数据集,并细分为低密度、中密度、高密度和特高密度4类;其次构建了基于MobileViT-XS轻量化网络的密度等级识别模型,利用建立的数据集进行模型的训练和测试;最后将其与VGG16、GoogLeNet和ResNet进行了比较。结果表明,MobileViT-XS模型的总体识别准确率达到91.03%,且单幅图像推理时间仅为29.5 ms。与VGG16、ResNet网络相比,总体识别准确率分别高出3.51、2.34个百分点,MobileViT-XS模型可以较好的完成小麦不同密度等级的分类识别任务,为实时预测小麦喂入密度提供了技术支持。 展开更多
关键词 联合收获机 喂入量 MobileViT 图像分类 密度识别
下载PDF
煤矸石识别方法研究现状与展望 被引量:35
5
作者 曹现刚 李莹 +1 位作者 王鹏 吴旭东 《工矿自动化》 北大核心 2020年第1期38-43,共6页
从煤矸石识别特征出发,对煤矸石识别方法的研究现状进行了总结,列举了密度识别法、硬度识别法等以密度、硬度等为识别特征的煤矸石识别方法,以及射线识别法、图像识别法等以灰度、纹理为识别特征的煤矸石识别方法的代表性研究成果,并对... 从煤矸石识别特征出发,对煤矸石识别方法的研究现状进行了总结,列举了密度识别法、硬度识别法等以密度、硬度等为识别特征的煤矸石识别方法,以及射线识别法、图像识别法等以灰度、纹理为识别特征的煤矸石识别方法的代表性研究成果,并对比了各种识别方法的特点。对煤矸石识别方法的研究方向和途径进行了展望,提出应全面分析、理解煤矸石的特征差异,研究符合煤矿绿色发展要求的煤矸石识别方法、快速高效的煤矸石图像识别方法、融合和创新现有方法的新型煤矸石高效识别方法。 展开更多
关键词 煤矸石分选 煤矸石识别 识别特征 密度识别 硬度识别 射线识别 图像识别
下载PDF
基于单CCD摄影的泡状流近焦深度内微气泡的识别 被引量:2
6
作者 张蓉生 张伟华 曹丹 《仪器仪表学报》 EI CAS CSCD 北大核心 2010年第11期2521-2527,共7页
鉴于泡状流气泡各点衍射的差异和它的点扩散函数沿进深方向的随机性以及点扩散函数与进深的映射关系的不可能标定等使得单CCD摄影的泡状流气泡的数密度难以确定,据此提出了从足够长时间的泡状流气泡视频中获得流过焦平面的各气泡灰度标... 鉴于泡状流气泡各点衍射的差异和它的点扩散函数沿进深方向的随机性以及点扩散函数与进深的映射关系的不可能标定等使得单CCD摄影的泡状流气泡的数密度难以确定,据此提出了从足够长时间的泡状流气泡视频中获得流过焦平面的各气泡灰度标准差,并依据它和通过实验所得的200μm近焦深度范围内各静止气泡最小灰度标准差与最大灰度标准差之比来确定200μm近焦深度范围内的泡状流气泡的数目。通过对已知不同进深位置的静止气泡样本的误差评估显示本文方法相对误差大于5%的概率仅占20%,因而能有效地预测单CCD泡状流气泡的数密度。 展开更多
关键词 单CCD气泡流视频 气泡数密度识别 误差评估
下载PDF
舰船通信网络分布式数据多状态识别技术研究
7
作者 曹月 路翔 《舰船科学技术》 北大核心 2018年第8X期94-96,共3页
传统识别技术手段不能在适应网络通信量改变的同时,调整数据的分布状态。为解决上述问题,提出基于船舶分布式通信网络环境的数据多状态识别技术。通过单点分布框架设计、通信协议选择2个步骤,完成舰船分布式通信网络环境的搭建。在此基... 传统识别技术手段不能在适应网络通信量改变的同时,调整数据的分布状态。为解决上述问题,提出基于船舶分布式通信网络环境的数据多状态识别技术。通过单点分布框架设计、通信协议选择2个步骤,完成舰船分布式通信网络环境的搭建。在此基础上,通过多状态相似度确定、识别密度确定2个步骤,实现新型舰船数据识别技术的顺利运行。分析对比实验结果可知,与传统识别技术手段对比,应用基于船舶分布式通信网络环境数据多状态识别技术后,网络通信量适应程度、数据调整及时性都得到适当提升。 展开更多
关键词 通信网络 分布式状态 数据识别 单点框架 网络协议 相似度 识别密度
下载PDF
基于蚁群算法的大气激光通信中低密度奇偶校验码的盲识别 被引量:5
8
作者 孙韩 郝士琦 +2 位作者 张岱 赵青松 王勇 《光学学报》 EI CAS CSCD 北大核心 2016年第9期70-75,共6页
针对传统线性分组码识别方法对码长较长的低密度奇偶校验(LDPC)码不适用的情况,利用蚁群算法对对偶空间进行优化搜索,完成了对LDPC码的识别。建立了大气激光通信信道模型和LDPC码的识别模型,给出了大气激光通信湍流信道下校验关系对数... 针对传统线性分组码识别方法对码长较长的低密度奇偶校验(LDPC)码不适用的情况,利用蚁群算法对对偶空间进行优化搜索,完成了对LDPC码的识别。建立了大气激光通信信道模型和LDPC码的识别模型,给出了大气激光通信湍流信道下校验关系对数似然比函数表达式;将基本蚁群算法与LDPC码的识别问题结合,将对数似然比函数经过处理作为目标函数,通过不断迭代每次搜索过程中目标函数最优值和最佳搜索路径,实现对LDPC码的识别。仿真结果表明:当码长为256时,在弱湍流条件下,当信噪比不低于8dB时,识别率可达78%;在强湍流条件下,当信噪比不低于10dB时,识别率可达77%。此外,蚁群算法中的参数设置对算法性能有较大影响,应根据实际情况加以选择。 展开更多
关键词 光通信 密度奇偶校验码识别 蚁群算法 优化搜索
原文传递
False anomaly recognition with horizontal differential field lines method in high-density electrical technique and its application in Xinlei Quarry,Jiuquan 被引量:2
9
作者 LIU Lijia ZHU Shi +2 位作者 CAO Xiaoyue BEN Fang YIN Changchun 《Global Geology》 2015年第2期140-144,共5页
As an important geophysical tool,high density electrical technique infers the underground geological structures by processing and inverting the apparent resistivity data.Currently,the false anomalies have been frequen... As an important geophysical tool,high density electrical technique infers the underground geological structures by processing and inverting the apparent resistivity data.Currently,the false anomalies have been frequently occurred in the graph of apparent resistivity pseudo-section or inverted geoelectrical section obtained from high-density electrical technique,and are difficult to remove.In this study,the authors explain the mechanism of the false anomalies and put forward the horizontal differential field method to identify the false anomalies.Based on the analysis of modeling results,this method is applied in the surveying data in Xinlei Quarry of Jiuquan,and the results confirm the effectiveness of the horizontal differential field method. 展开更多
关键词 horizontal differential field method high density electrical technique apparent resistivity false anomaly
下载PDF
Damage Identification in Beam-Type Structures Using Pseudo Strain Energy Density and Grey Relation Coefficient
10
作者 陈晓强 朱宏平 +1 位作者 张俊兵 李林 《Transactions of Tianjin University》 EI CAS 2010年第2期96-103,共8页
Based on pseudo strain energy density (PSED) and grey relation coefficient (GRC), an index is proposed to locate the damage of beam-type structures in time-domain. The genetic algorithm (GA) is utilized to identify th... Based on pseudo strain energy density (PSED) and grey relation coefficient (GRC), an index is proposed to locate the damage of beam-type structures in time-domain. The genetic algorithm (GA) is utilized to identify the structural damage severity of confirmed damaged locations. Furthermore, a systematic damage identification program based on GA is developed on MATLAB platform. ANSYS is employed to conduct the finite element analysis of complicated civil engineering structures, which is embedded with interface technique. The two-step damage identification is verified by a finite element model of Xinxingtang Highway Bridge and a laboratory beam model based on polyvinylidens fluoride (PVDF). The bridge model was constructed with 57 girder segments, and simulated with 58 measurement points. The damaged segments were located accurately by GRC index regardless of damage extents and noise levels. With stiffness reduction factors of detected segments as variables, the GA program evolved for 150 generations in 6 h and identified the damage extent with the maximum errors of 1% and 3% corresponding to the noise to signal ratios of 0 and 5%, respectively. In contrast, the common GA-based method without using GRC index evolved for 600 generations in 24 h, but failed to obtain satisfactory results. In the laboratory test, PVDF patches were used as dynamic strain sensors, and the damage locations were identified due to the fact that GRC indexes of points near damaged elements were smaller than 0.6 while those of others were larger than 0.6. The GA-based damage quantification was also consistent with the value of crack depth in the beam model. 展开更多
关键词 damage identification strain test data pseudo strain energy density grey relation coefficient genetic algorithm polyvinylidens fluoride
下载PDF
Fracture property identification method based on shrinkage factor particle swarm optimization 被引量:2
11
作者 ZHOU Chao FENG Xuan +3 位作者 ZHANG Bing LU Xiaoman JIN Zelong XU Cong 《Global Geology》 2015年第4期232-237,共6页
In the multi-wave and multi-component seismic exploration,shear-wave will be split into fast wave and slow wave,when it propagates in anisotropic media. Then the authors can predict polarization direction and density ... In the multi-wave and multi-component seismic exploration,shear-wave will be split into fast wave and slow wave,when it propagates in anisotropic media. Then the authors can predict polarization direction and density of crack and detect the development status of cracks underground according to shear-wave splitting phenomenon. The technology plays an important role and shows great potential in crack reservoir detection. In this study,the improved particle swarm optimization algorithm based on shrinkage factor is combined with the Pearson correlation coefficient method to obtain the fracture azimuth angle and density. The experimental results show that the modified method can improve the convergence rate,accuracy,anti-noise performance and computational efficiency. 展开更多
关键词 shear-wave splitting particle swarm optimization Pearson correlation coefficient shrinkage factor
下载PDF
Crack fluid identification of shale reservoir based on stress-dependent anisotropy
12
作者 Zhang Jia-Jia Zhang Guang-Zhi Huang Lan-Hua 《Applied Geophysics》 SCIE CSCD 2019年第2期209-217,254,共10页
Shale reservoirs are typically very tight, and crack are only a small part of the reservoir. The directional arrangement of cracks leads to the anisotropic characteristics of shale, and the type of fluid filled in cra... Shale reservoirs are typically very tight, and crack are only a small part of the reservoir. The directional arrangement of cracks leads to the anisotropic characteristics of shale, and the type of fluid filled in cracks affects the shale reservoir evaluation and late development. Many rock physics theories and methods typically use second-and fourthorder crack density tensors to characterize the elastic anisotropy induced by cracks as well as the normal-to-tangential crack compliance ratio to distinguish between dry and saturated cracks. This study def ines an anisotropic crack f luid indicator for vertical transversely isotropy(VTI) media with vertical symmetry axis which is the integration of the normal-to-tangential crack compliance ratio in three directions. A new dimensionless fourth-order tensor, including crack f luid type, azimuth distribution, and geometric shape, is constructed by substituting the normal and tangential compliance into the fourth-order crack density tensor, which can also be used to identify the type of crack fluid in the VTI media. Using the Callovo–Oxfordian shale experimental data, the variation of the elastic properties of dry and saturated shale samples with axial stress is analyzed. The results demonstrate that the anisotropic crack f luid indicator of water-bearing shale samples is less than that of the dry shale samples and that the dimensionless fourth-order tensor of water-bearing shale samples is nearly one order of magnitude greater than that of the dry shale samples. Therefore, the anisotropic crack f luid indicator and dimensionless fourth-order tensor can ref lect the crack f luid type in shale samples and can be used for shale reservoir prediction and f luid identif ication. 展开更多
关键词 cracks fluid identification crack density tensor crack fluid indicator dimensionless fourth-order tensor
下载PDF
Application of Fuzzy Cluster Analysis Method in Evaluating Relevant Index and Recognizing Risks of Coronary Heart Disease in the Aged
13
作者 耿辉 杨玉坤 《Journal of Donghua University(English Edition)》 EI CAS 2003年第3期134-137,共4页
The risk recognition model for preventing and monitoring the Coronary Heart Diseases (CHD) in the aged is proposed, which is based on the testing results of four indexes and includes Low Density Lipoprotein (LDL), Tot... The risk recognition model for preventing and monitoring the Coronary Heart Diseases (CHD) in the aged is proposed, which is based on the testing results of four indexes and includes Low Density Lipoprotein (LDL), Total Cholesterol (TC), Triglyceridemia (TG)and age. Some people who took the health checkup in Shanghai Xinhua Hospital are classified into 3 groups,and each group is associated with prevalence risk of contracting CHD. Then the fuzzy recognition method is applied to evaluate the risk of CHD. The accuracy rate is up to 85%. The model is applicable to not only analysis of risk in medical but also analysis of risk in finance, insurance and some other fields. 展开更多
关键词 fuzzy cluster analysis fuzzy pattern recognition analysis of risk
下载PDF
An efficient approach for shadow detection based on Gaussian mixture model 被引量:2
14
作者 韩延祥 张志胜 +1 位作者 陈芳 陈恺 《Journal of Central South University》 SCIE EI CAS 2014年第4期1385-1395,共11页
An efficient approach was proposed for discriminating shadows from moving objects. In the background subtraction stage, moving objects were extracted. Then, the initial classification for moving shadow pixels and fore... An efficient approach was proposed for discriminating shadows from moving objects. In the background subtraction stage, moving objects were extracted. Then, the initial classification for moving shadow pixels and foreground object pixels was performed by using color invariant features. In the shadow model learning stage, instead of a single Gaussian distribution, it was assumed that the density function computed on the values of chromaticity difference or bright difference, can be modeled as a mixture of Gaussian consisting of two density functions. Meanwhile, the Gaussian parameter estimation was performed by using EM algorithm. The estimates were used to obtain shadow mask according to two constraints. Finally, experiments were carried out. The visual experiment results confirm the effectiveness of proposed method. Quantitative results in terms of the shadow detection rate and the shadow discrimination rate(the maximum values are 85.79% and 97.56%, respectively) show that the proposed approach achieves a satisfying result with post-processing step. 展开更多
关键词 shadow detection Gaussian mixture model EM algorithm
下载PDF
Decision Cost Feature Weighting and Its Application in Intrusion Detection
15
作者 QIANQuan GENGHuan-tong WANGXu-fa 《Wuhan University Journal of Natural Sciences》 CAS 2004年第5期765-769,共5页
This paper introduces the cost-sensitive feature weighting strategy and its application in intrusion detection. Cost factors and cost matrix are proposed to demonstrate the misclassification cost for IDS. How to get t... This paper introduces the cost-sensitive feature weighting strategy and its application in intrusion detection. Cost factors and cost matrix are proposed to demonstrate the misclassification cost for IDS. How to get the whole minimal risk, is mainly discussed in this paper in detail. From experiments, it shows that although decision cost based weight learning exists somewhat attack misclassification, it can achieve relatively low misclassification costs on the basis of keeping relatively high rate of recognition precision. Key words decision cost - feature weighting - intrusion detection CLC number TP 393. 08 Foundation item: Supported by the National Natural Science Foundation Key Research Plan of China (90104030) and “20 Century Education Development Plan”Biography: QIAN Quan(1972-), male, Ph. D. research direction: computer network, network security and artificial intelligence 展开更多
关键词 decision cost feature weighting intrusion detection
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部