一种改进的SIFT图像立体匹配算法

针对SIFT算法复杂度高、计算时间长、影响立体匹配的实时性等问题,提出了一种改进的立体视觉特征点匹配算法该算法从两个方面对SIFT算法进行改进:首先利用24维特征描述符代替128维特征描述符,以降低计算复杂度;其次在图像对匹配过程中采用改进的BBF搜索算法,通过引入最小优先级队列的限制条件和匹配精度更高的马氏距离判断两幅图像特征点的匹配性.采用经典图像和未知的室外环境下拍摄的图像对本文算法进行实验验证,结果表明,本文提出的算法每100个特征点检测时间为0.01 s,正确匹配率平均为89.65%,相对于原算法,提高了匹配的准确度,并降低了匹配时间.      

Algorithm based on morphological component analysis and scale-invariant feature transform for image registration

In this paper, we proposed a registration method by combining the morphological component analysis (MCA) and scale-invariant feature transform (SIFT) algorithm. This method uses the perception dictionaries, and combines the Basis-Pursuit algorithm and the Total-Variation regularization scheme to extract the cartoon part containing basic geometrical information from the original image, and is stable and unsusceptible to noise interference. Then a smaller number of the distinctive key points will be obtained by using the SIFT algorithm based on the cartoon part of the original image. Matching the key points by the constrained Euclidean distance, we will obtain a more correct and robust matching result. The experimental results show that the geometrical transform parameters inferred by the matched key points based on MCA+SIFT registration method are more exact than the ones based on the direct SIFT algorithm.     

Mobile Robot Hierarchical Simultaneous Localization and Mapping Using Monocular Vision

A hierarchical mobile robot simultaneous localization and mapping (SLAM) method that allows us to obtain accurate maps was presented. The local map level is composed of a set of local metric feature maps that are guaranteed to be statistically independent. The global level is a topological graph whose arcs are labeled with the relative location between local maps. An estimation of these relative locations is maintained with local map alignment algorithm, and more accurate estimation is calculated through a global minimization procedure using the loop closure constraint. The local map is built with Rao-Blackwellised particle filter (RBPF), where the particle filter is used to extending the path posterior by sampling new poses. The landmark position estimation and update is implemented through extended Kalman filter (EKF). Monocular vision mounted on the robot tracks the 3D natural point landmarks, which are structured with matching scale invariant feature transform (SIFT) feature pairs. The matching for multi-dimension SIFT features is implemented with a KD-tree in the time cost of O(lbN). Experiment results on Pioneer mobile robot in a real indoor environment show the superior performance of our proposed method.     

基于深度时频特征的机车轴承故障诊断

针对现有机车轴承诊断方法存在故障特征提取不理想、诊断精度低等问题，提出了一种基于深度时频特征的机车轴承故障诊断新方法；利用双通道一维和二维卷积神经网络(CNN)分别对输入的一维原始信号和连续小波变换(CWT)提取的二维时频信号进行深度特征提取；为使输入的一维原始信号简单而有效地反映出信号在时域的全局特征，上通道使用一维CNN，为使输入的二维时频域信号能多角度地反映出信号的细微局部变化，下通道使用二维CNN；在融合层中将上下通道特征自动融合成一个新的深度时频特征，并将提取到的深度融合时频特征经归一化指数函数进行故障分类识别；在此基础上，分析了某局机务段实测的7种机车轴承数据，验证了本文方法的实际工程应用价值。研究结果表明:基于深度时频特征的机车轴承故障诊断方法对7种机车轴承故障的平均诊断精度达到了100%，与一维CNN模型、二维CNN模型和支持向量机(SVM)模型相比，平均诊断精度分别提高了0.7%、1.9%和2.2%；本文方法提取的深度时频特征中每类故障分布间隔规则有序，类内间距很小，而单个一维CNN模型和二维CNN模型提取的特征的每类故障分布间隔不规则，类内间距较大，说明基于深度时频特征的机车轴承故障诊断方法提取深度特征的能力优越，是一种解决机车轴承故障诊断问题的有效模型。      

基于金字塔特征融合的二阶段三维点云车辆检测

针对三维点云鸟瞰图特征提取不充分导致车辆目标检测性能欠佳问题,本文提出一种基于金字塔特征融合的二阶段三维点云车辆目标检测算法。首先通过降维处理并利用体素占用编码原始三维点云,得到二维特征图输入;然后,利用上采样网络传递高层语义特征,下采样网络传递低层位置特征,构建一阶段金字塔网络结构提取车辆目标特征;最后,通过候选区域提取层得 到不同尺度的候选区域,利用兴趣区域池化层对齐各候选区域尺度,并采用全连接层融合多尺度特征,提取不同感受野下车辆目标特征;此外,在损失函数方面,补充正余弦角度损失并加权到总损失函数中,优化车辆目标航向角预测。基于KITTI公开数据集的实验分析表明,本文算法相较基准网络能够有效补充三维点云鸟瞰图特征提取,在不同难度的检测任务中平均检测精度提高 了5.07%~8.59%。     

应用免疫组织化学方法评价组织芯片的可靠性

目的探讨组织芯片技术在免疫组化试验中的可靠性和提高组织芯片可信性的方法。方法选择82例人乳腺癌标本石蜡蜡块,利用传统制片技术和自行研制的专用器具分别制作常规石蜡切片和组织芯片,采用免疫组化技术检测雌激素受体(ER)、孕激素受体(PR)的表达。结果采用自行研制的专用器具制备组织芯片,所得样本的可分析率均在92.9%以上,且随着对同一标本取材数量的增加,其可分析标本率也明显上升。采用传统方法检测的82例乳腺癌标本中ER和PR的阳性率分别为61%和58.5%;采用组织芯片技术,一式一份取材,其阳性率分别为51.9%和50.0%,一式两份方式取材,其阳性率分别为53.8%和53.8%,采用一式三份方式取材,其阳性率分别为57.1%和60.7%,且三种不同取材方式的检测结果与传统制片法之间并无统计学差异(P>0.75)。结论在采用统一制备标准并保证组织芯片质量的前提下,挖取直径1.5mm的组织样本制备组织芯片,尽管组织芯片技术与传统方法检测的结果的一致率仍随着对同一标本取材次数的增加而提高,但是三种不同取材方式的检测结果之间并无统计学差异。因此,一式一份取材制备组织芯片完全可替代传统制片技术用于免疫组织化学乃至原位杂交、荧光原位杂交技术的研究,且可保证组织芯片的可信性和高通量特征。     

肺癌患者血浆中血小板GMP－140的测定

采用ＧＭＰ－１４０单抗ＳＺ－５１采用酶联免疫吸附试验检测了７４例肺癌患者ＧＭＰ－１４０含量并与４０例健康人作了对照，结果发现肺癌患者血浆ＧＭＰ－１４０均值高于正常人（Ｐ＜０．０１），尤其在肺癌伴转移患者更为明显，且亦高于肺癌未转移患者（Ｐ＜０．０５），为进一步探讨血小板在肿瘤增殖与转移中的作用及临床治疗提供了参考依据。     

Orthogonal discriminant improved local tangent space alignment based feature fusion for face recognition

Improved local tangent space alignment (ILTSA) is a recent nonlinear dimensionality reduction method which can efficiently recover the geometrical structure of sparse or non-uniformly distributed data manifold. In this paper, based on combination of modified maximum margin criterion and ILTSA, a novel feature extraction method named orthogonal discriminant improved local tangent space alignment (ODILTSA) is proposed. ODILTSA can preserve local geometry structure and maximize the margin between different classes simultaneously. Based on ODILTSA, a novel face recognition method which combines augmented complex wavelet features and original image features is developed. Experimental results on Yale, AR and PIE face databases demonstrate the effectiveness of ODILTSA and the feature fusion method.     

不确定广义系统的鲁棒严格无源控制

讨论了不确定线性广义系统的严格无源性和严格无源控制问题.为了解决广义系统严格无源条件中的等式限制问题,通过引入松驰变最描述广义系统快变子系统与慢变子系统之间的代数关系,以严格线性矩阵不等式的形式,给出了广义系统严格尤源的充分条件.基于该条件,设计了鲁棒严格开源控制器,并用具体实例说明所设计的控制器能保证闭环控制系统是严格无源的.     

融合式空间塔式算子和HIK-SVM的交通标志识别研究

在交通标志识别问题上,提出了一种基于融合式的空间塔式算子和直方图交叉核支持向量机(HIK-SVM)的分类方法.在该方法中,通过提取图像的灰度塔式词袋直方图(Gray-PHOW)特征、颜色塔式词袋直方图(Color-PHOW)特征和塔式边缘方向梯度直方图(PHOG)特征来对交通标志的外观、颜色和轮廓信息进行描述.通过提取空间塔式直方图特征,能很好地对图像各种特征的空间分布状况进行描述.提取到图像的外观、颜色、轮廓和特征的空间分布信息后,对其进行融合,最后得到的融合式的空间塔式特征具有很强的鲁棒性.将该融合式特征送入HIK-SVM进行训练和分类,取得了极其高的识别效果.     

顾及小目标特征的视频人流量智能统计方法

人流量统计对智能安防等领域具有重要研究价值. 针对视频监控系统中人流量统计准确率较低的问题,提出一种顾及小目标特征的视频人流量智能统计方法,重点研究用于小目标检测的Faster R-CNN （Faster region-convolutional neural network）改进算法、运动目标关联匹配以及双向人流量智能统计等关键技术,根据人头目标的小尺度特点对Faster R-CNN网络结构进行适应性改进,利用图像浅层特征提高网络对于小目标的特征提取能力,通过基于轨迹预测的跟踪算法实现运动目标的实时追踪,同时设计双向人流量智能统计算法,以实现人流量高准确率统计;为证明方法的有效性,在密集程度不同的场景中进行了测试. 测试结果表明:改进的目标检测算法相较于原始算法,在Brainwash测试集和Pets2009基准数据集上的平均准确率分别提高了7.31%、10.71%,视频人流量智能统计方法在多种场景下的综合评价指标F值均能达到90.00%以上,相较于SSD-Sort算法和Yolov3-DeepSort算法,其F值提高了1.14% ~ 3.04%.      

基于点特征和边缘特征的无人机影像配准方法

为解决变形较大的无人机影像配准问题,提出了点特征和边缘特征相结合的配准方法.用尺度不变特征变换(SIFT)算法提取点特征,完成影像的初步配准,并通过多项式函数对影像进行粗校正.在此基础上提取影像的边缘特征信息,根据距离相似性对边缘特征信息进行配准;依据色彩能量差筛选点特征信息配准结果和边缘特征信息配准结果,采用小面元微分校正的方法对变形影像进行校正.实验结果表明:提出的配准方法能够弥补点特征配准方法和边缘特征配准方法的不足,其配准的鲁棒性提高10%左右,可以较好地完成变形较大的无人机影像配准.      

等参局部平均随机场的随机有限元分析

本文提出了一种正交化等参局部平均的随机场模型,并给出了分析该随机场模型的随机有限元列式。算例表明,本文的方法具有较高的计算精度,且输入数据较少。     

一种结合2DLPP与2DPCA的人脸识别方法

为解决二维局部保持投影(2DLPP)需要较多数据表示人脸特征的缺陷,提出了一种新的二维局部保持投影主成分分析方法(2DLPP-PCA).通过对人脸图像在行、列方向同时进行2DLPP和2DPCA投影,2DLPP-PCA 不仅能减少保存人脸特征所需要的数据量,而且能有效地提取人脸的局部特征和全局特征.在ORL、Yale和CAS-PEAL-R1人脸数据库上的实验结果表明,2DLPP-PCA是一种高性能的特征提取方法,当训练样本数为6时,2DLPP-PCA在ORL数据库上的最佳平均识别率达到99％以上.     

CT扫描对小肺癌的诊断

分析了４８例经病理证实，直径≤３ｃｍ小肺癌的ＣＴ表现。认为支气管壁的局限性增厚、管壁内面不平在有小的局部隆起，管腔狭窄变形及单侧性肺门区小肿块是早期中心型肺癌的主要ＣＴ征象；分叶征、棘状突起、空泡征和胸膜凹陷征是周围型小肺癌的主要特征。ＣＴ在发现和显示肺癌的特征方面比普通ｘ线敏感，表明薄层ＣＴ扫描是诊断小肺癌的有效方法。     

GNN-CRC: Discriminative Collaborative Representation-Based Classification via Gabor Wavelet Transformation and Nearest Neighbor

Collaborative representation-based classification (CRC) is a distance based method, and it obtains the original contributions from all samples to solve the sparse representation coefficient. We find out that it helps to enhance the discrimination in classification by integrating other distance based features and/or adding signal preprocessing to the original samples. In this paper, we propose an improved version of the CRC method which uses the Gabor wavelet transformation to preprocess the samples and also adapts the nearest neighbor (NN) features, and hence we call it GNN-CRC. Firstly, Gabor wavelet transformation is applied to minimize the effects from the background in face images and build Gabor features into the input data. Secondly, the distances solved by NN and CRC are fused together to obtain a more discriminative classification. Extensive experiments are conducted to evaluate the proposed method for face recognition with different instantiations. The experimental results illustrate that our method outperforms the naive CRC as well as some other state-of-the-art algorithms.     

Calculation of strain amplification matrix for strain invariant failure theory based on representative volume element models with periodical boundary condition

Strain invariant failure theory (SIFT) is a micro-mechanics-based failure theory for multi-scale failure analysis of composite materials originally proposed by Gosse and Christensen. In this paper, the approach for obtaining strain amplification matrix which is a key step for the execution of SIFT is improved by adopting representative volume element (RVE) finite element models considering periodical boundary condition, based on which more actual deformation mode is reflected. The deformation modes and strain data at the characteristic points of the centroid cell of multi-cell RVE model are analyzed and taken as a reference. It can be concluded that more reasonable deformation mode and relationship between the micro-mechanical and macro-mechanical strain states are obtained by employing the new model. Finally, numerical examples are provided to illustrate the determination of strain amplification factors within the RVEs considering periodical boundary condition at the characteristic points.     

Magnetic flux leakage signal inversion of corrosive flaws based on modified genetic local search algorithm

In this paper, a modified genetic local search algorithm (MGLSA) is proposed. The proposed algorithm is resulted from employing the simulated annealing technique to regulate the variance of the Gaussian mutation of the genetic local search algorithm (GLSA). Then, an MGLSA-based inverse algorithm is proposed for magnetic flux leakage (MFL) signal inversion of corrosive flaws, in which the MGLSA is used to solve the optimization problem in the MFL inverse problem. Experimental results demonstrate that the MGLSA-based inverse algorithm is more robust than GLSA-based inverse algorithm in the presence of noise in the measured MFL signals.     

基于自适应尺度LE的轮廓编组算法

在图嵌入框架下，以编组线索的聚类来实现轮廓编组的方法，不仅可以有效地将局部特征和全局特征结合起来，而且更加符合人类视觉感知以流形存在的特点．本文在分析相似度矩阵对样本结构表示意义的基础上，提出了一种基于自适应尺度LaplacianEigenmap的轮廓编组算法．该算法能够根据编组线索多维特征的不同局部统计特性，自适应地改变相似度计算模型中的尺度因子，使相似度矩阵更准确地反映编组线索数据集的结构特性．在此基础上通过降维实现编组元的聚类，从而得到轮廓编组的结果．实验证明，该算法对于局部统计特性差异较大的编组线索有着良好的适应性，尤其对于有遮挡的感知目标，表现出比图分割方法更为优越的性能．