Novel histogram descriptor for global feature extraction and description

A novel histogram descriptor for global feature extraction and description was presented. Three elementary primitives for a 2×2 pixel grid were defined. The complex primitives were computed by matrix transforms. These primitives and equivalence class were used for an image to compute the feature image that consisted of three elementary primitives. Histogram was used for the transformed image to extract and describe the features. Furthermore, comparisons were made among the novel histogram descriptor, the gray histogram and the edge histogram with regard to feature vector dimension and retrieval performance. The experimental results show that the novel histogram can not only reduce the effect of noise and illumination change, but also compute the feature vector of lower dimension. Furthermore, the system using the novel histogram has better retrieval performance.

An automated detection of glaucoma using histogram features

Glaucoma is a chronic and progressive optic neurodegenerative disease leading to vision deterioration and in most cases produce increased pressure within the eye. This is due to the backup of fluid in the eye; it causes damage to the optic nerve. Hence, early detection diagnosis and treatment of an eye help to prevent the loss of vision. In this paper, a novel method is proposed for the early detection of glaucoma using a combination of magnitude and phase features from the digital fundus images. Local binary patterns(LBP) and Daugman’s algorithm are used to perform the feature set extraction.The histogram features are computed for both the magnitude and phase components. The Euclidean distance between the feature vectors are analyzed to predict glaucoma. The performance of the proposed method is compared with the higher order spectra(HOS)features in terms of sensitivity, specificity, classification accuracy and execution time. The proposed system results 95.45% output for sensitivity, specificity and classification. Also, the execution time for the proposed method takes lesser time than the existing method which is based on HOS features. Hence, the proposed system is accurate, reliable and robust than the existing approach to predict the glaucoma features.

Vibration-Based Fault Diagnosis Study on a Hydraulic Brake System Using Fuzzy Logic with Histogram Features

The requirement of fault diagnosis in the field of automobiles is growing higher day by day.The reliability of human resources for the fault diagnosis is uncertain.Brakes are one of the major critical components in automobiles that require closer and active observation.This research work demonstrates a fault diagnosis technique for monitoring the hydraulic brake system using vibration analysis.Vibration signals of a rotating element contain dynamic information about its health condition.Hence,the vibration signals were used for the brake fault diagnosis study.The study was carried out on a brake fault diagnosis experimental setup.The vibration signals under different fault conditions were acquired from the setup using an accelerometer.The condition monitoring of the hydraulic brake system using the vibration signal was processed using a machine learning approach.The machine learning approach has three phases,namely,feature extraction,feature selection,and feature classification.Histogram features were extracted from the vibration signals.The prominent features were selected using the decision tree.The selected features were classified using a fuzzy classifier.The histogram features and the fuzzy classifier combination produced maximum classification accuracy than that of the statistical features.

Comparative Study on Tree Classifiers for Application to Condition Monitoring ofWind Turbine Blade through Histogram Features Using Vibration Signals: A Data-Mining Approach

Wind energy is considered as a alternative renewable energy source due to its low operating cost when compared with other sources.The wind turbine is an essential system used to change kinetic energy into electrical energy.Wind turbine blades,in particular,require a competitive condition inspection approach as it is a significant component of the wind turbine system that costs around 20-25 percent of the total turbine cost.The main objective of this study is to differentiate between various blade faults which affect the wind turbine blade under operating conditions using a machine learning approach through histogram features.In this study,blade bend,hub-blade loose connection,blade erosion,pitch angle twist,and blade cracks were simulated on the blade.This problem is formulated as a machine learning problem which consists of three phases,namely feature extraction,feature selection and feature classification.Histogram features are extracted from vibration signals and feature selection was carried out using the J48 decision tree algorithm.Feature classification was performed using 15 tree classifiers.The results of the machine learning classifiers were compared with respect to their accuracy percentage and a better model is suggested for real-time monitoring of a wind turbine blade.

Face mask detection algorithm based on HSV+HOG features and SVM

To automatically detecting whether a person is wearing mask properly,we propose a face mask detection algorithm based on hue-saturation-value(HSV)+histogram of oriented gradient(HOG)features and support vector machines(SVM).Firstly,human face and five feature points are detected with RetinaFace face detection algorithm.The feature points are used to locate to mouth and nose region,and HSV+HOG features of this region are extracted and input to SVM for training to realize detection of wearing masks or not.Secondly,RetinaFace is used to locate to nasal tip area of face,and YCrCb elliptical skin tone model is used to detect the exposure of skin in the nasal tip area,and the optimal classification threshold can be found to determine whether the wear is properly according to experimental results.Experiments show that the accuracy of detecting whether mask is worn can reach 97.9%,and the accuracy of detecting whether mask is worn correctly can reach 87.55%,which verifies the feasibility of the algorithm.

Integrating Color and Spatial Feature for Content-Based Image Retrieval

In this paper, we present a novel and efficient scheme for extracting, indexing and retrieving color images. Our motivation was to reduce the space overhead of partition-based approaches taking advantage of the fact that only a relatively low number of distinct values of a particular visual feature is present in most images. To extract color feature and build indices into our image database we take into consideration factors such as human color perception and perceptual range, and the image is partitioned into a set of regions by using a simple classifying scheme. The compact color feature vector and the spatial color histogram, which are extracted from the seqmented image region, are used for representing the color and spatial information in the image. We have also developed the region-based distance measures to compare the similarity of two images. Extensive tests on a large image collection were conducted to demonstrate the effectiveness of the proposed approach.

Classifying Machine Learning Features Extracted from Vibration Signal with Logistic Model Tree to Monitor Automobile Tyre Pressure

Tyre pressure monitoring system(TPMS)is compulsory in most countries like the United States and European Union.The existing systems depend on pressure sensors strapped on the tyre or on wheel speed sensor data.A difference in wheel speed would trigger an alarm based on the algorithm implemented.In this paper,machine learning approach is proposed as a new method to monitor tyre pressure by extracting the vertical vibrations from a wheel hub of a moving vehicle using an accelerometer.The obtained signals will be used to compute through statistical features and histogram features for the feature extraction process.The LMT(Logistic Model Tree)was used as the classifier and attained a classification accuracy of 92.5%with 10-fold cross validation for statistical features and 90.5% with 10-fold cross validation for histogram features.The proposed model can be used for monitoring the automobile tyre pressure successfully.

Feature-Based Vibration Monitoring of a Hydraulic Brake System Using Machine Learning

Hydraulic brakes in automobiles are an important control component used not only for the safety of the passenger but also for others moving on the road.Therefore,monitoring the condition of the brake components is inevitable.The brake elements can be monitored by studying the vibration characteristics obtained from the brake system using a proper signal processing technique through machine learning approaches.The vibration signals were captured using an accelerometer sensor under a various fault condition.The acquired vibration signals were processed for extracting meaningful information as features.The condition of the brake system can be predicted using a feature based machine learning approach through the extracted features.This study focuses on a mechatronics system for data acquisitions and a signal processing technique for extracting features such as statistical,histogram and wavelets.Comparative results have been carried out using an experimental study for finding the effectiveness of the suggested signal processing techniques for monitoring the condition of the brake system.

Product Image Classification Based on Fusion Features

Two key challenges raised by a product images classification system are classification precision and classification time. In some categories, classification precision of the latest techniques, in the product images classification system, is still low. In this paper, we propose a local texture descriptor termed fan refined local binary pattern, which captures more detailed information by integrating the spatial distribution into the local binary pattern feature. We compare our approach with different methods on a subset of product images on Amazon/e Bay and parts of PI100 and experimental results have demonstrated that our proposed approach is superior to the current existing methods. The highest classification precision is increased by 21% and the average classification time is reduced by 2/3.

基于SIFT特征点提取的ICP配准算法

为解决传统迭代最近点(ICP)算法对点云配准的起始点对选择不佳而导致配准时间长、效率低的问题,提出一种基于尺度不变特征变换(SIFT)特征点提取的ICP点云配准算法(ST-ICP)。首先使用SIFT算法进行原始点云与目标点云的SIFT特征点提取,根据提取特征点完成快速点特征直方图(FPFH)特征运算,通过采样一致性初始配准算法(SAC-IA)搜索对应点对、求解变换矩阵,再进一步运用ICP算法进行点云精细配准。实验结果表明:与ICP算法相比较,ST-ICP算法的配准误差在迭代次数为5次时减小了1.019 cm,迭代次数为10次时减小了0.443 cm;在配准误差达到10^(-2) cm级别时,ST-ICP算法所用时间比传统ICP算法减少了12.829 s。ST-ICP算法优化了对应点对的选择,提升了配准精度和配准效率。

基于点云配准的航空发动机数字孪生模型构建

点云配准是实物和场景数字孪生模型构建的关键技术。为了适应航空工业高效、精确的虚实结合工业模式,提出了基于快速点特征直方图FPFH(Fast Point Feature Histogram)特征识别配准算法的数字孪生模型构建方法。该方法在保障精确性的前提下,通过数字化检测、信息采集、数据处理与融合,构建物理与虚拟高效互通的数字孪生模型。最后,以燃气涡轮式航空发动机中尾喷管风扇类零件为实例,验证该方法应用于该类发动机零件用于构建数字孪生模型的可行性,并最终将该方法作用于整个涡扇发动机。

复杂特征全景图像视觉传达效果优化仿真

由于全景拍摄中不同相机镜头的焦点距离不固定,因此在拼接之前相邻两个局部图像间就会产生视差,且距离越近的物体产生视差会越大。全景图像效果的优化是提升视觉质量的关键。提出一种复杂特征全景图像视觉传达效果优化方法。利用两种色彩空间模型与二维经验小波变换法,提取出图像的光谱特征与纹理特征。采用马拉特算法完成小波变换与小波分解,得到复杂特征融合后的全景图像重构结果。基于能量函数及负相关性,界定视觉传达效果的降噪优化目标,设计四阶偏微分方程的降噪模型,完成图像降噪处理。基于此,融合冲击滤波器与直方图均衡化,根据各连通分量对应的子图像,拉伸图像灰度级分布形式,增强细节信息,实现视觉传达效果优化。选取一幅具有复杂特征的全景图像,从感官与数据量化两方面评价不同方法下全景图像的优化效果。实验结果验证了上述方法提高了图像的对比度、清晰度、丰富度,且处理时间更短,具备良好的实践性与实时性。

基于多特征融合的百香果品质识别分类方法

百香果销售需按外观和口感的品质进行分类定价。目前分类主要针对果实外表进行人眼判断,易受视觉疲劳和主观经验影响,缺乏量化标准。基于此种情况提出一种基于机器视觉多特征融合的方法对百香果品质进行自动识别并分类。分别提取百香果的颜色和纹理表观特征进行优化并融合,然后使用SVM分类器对融合特征与果实果糖含量高低进行二分类关联训练和预测。实验结果的分类准确率最高可达到91.48%,表明百香果的外观特征与口感品质有较大的关联性。由此可见采用机器视觉方法对百香果以及其他水果的外观特征进行品质判断具有较高的可行性。其中所使用的算法实现简单,计算速度快,效果良好,具有很大的应用价值。

面向边缘端设备的轻量化视频异常事件检测方法

现有基于CNN模型的视频异常事件检测方法在精度不断提升的同时,面临架构复杂、参数庞大、训练冗长等问题,致使硬件算力需求高,难以适配无人机等计算资源有限的边缘端设备。为此,提出一种面向边缘端设备的轻量化异常事件检测方法,旨在平衡检测性能与推理延迟。首先,由原始视频序列提取梯度立方体与光流立方体作为事件表观与运动特征表示;其次,设计改进的小规模PCANet获取梯度立方体对应的高层次分块直方图特征;再次,根据每个局部分块的直方图特征分布情况计算表观异常得分,同时基于内部像素光流幅值累加计算运动异常得分;最后,依据表观与运动异常得分的加权融合值判别异常分块,实现表观与运动异常事件联合检测与定位。在公开数据集UCSD的Ped1与Ped2子集上进行实验验证,该方法的帧层面AUC分别达到86.7%与94.9%,领先大多数对比方法,且参数量明显降低。实验结果表明,该方法在低算力需求下,可以实现较高的异常检测稳定性和准确率,能够有效兼顾检测精度与计算资源,因此适用于低功耗边缘端设备。

基于复合知识蒸馏的骨科影像诊断分类研究

针对医疗设备存储资源有限的问题,提出一种基于复合知识蒸馏的诊断分类方法,旨在确保骨科影像诊断模型的高精度性能。该方法首先采用自适应直方图均衡化对数据集进行增强;其次引入知识蒸馏,选用EfficientNet-B7作为教师网络、EfficientNet-B0作为学生网络,同时对学生网络引入渐进式自蒸馏,以提升特征挖掘和泛化能力。在MURA(Musculoskeletal Radiographs)数据集上进行验证的结果表明,复合知识蒸馏(CKD)模型的准确率为96.26%,其参数量仅为EfficientNet-B7模型参数量的8.48%,并且在准确率方面仅下降了1.16%,验证了此模型的有效性。

基于灰度极小值的路面裂缝检测算法

为提高路面裂缝检测的识别准确率、提高检测效率和降低检测成本,提出一种基于灰度极小值的路面裂缝检测算法。算法在不对路面灰度图像做任何预处理和标注训练的前提下,依据路面裂缝灰度极小值直方图提取不同对比度的裂缝特征;根据不同对比度裂缝的灰度空间分布特点,设计不同对比度裂缝多方向激活重构算法;依据裂缝的线性特点设计伪裂缝去除算法,在保留裂缝细节信息的前提下去除伪裂缝。在公共数据集上进行测试,结果表明算法能够检测不同类型的路面裂缝,具有一定的实际应用价值。

基于改进3D-NDT机器人自定位算法

针对机器人在自定位过程中,传统3D-NDT点云配准在未给定初始旋转矩阵的情况下,存在配准效果不佳、误差大、配准时间长的缺陷,提出一种相对高效的改进3D-NDT点云配准算法。首先,对输入点云进行ISS特征点提取,并计算这些特征点的特征直方图(FPFH);然后,根据直接对应估计对特征点进行匹配,使用RANSAC去除错误对应关系,得到初始旋转矩阵;最后,将得到的初始旋转矩阵代入3D-NDT算法进行匹配,得到最终的匹配结果。采用室内外场景点云进行测试,实验结果表明,改进后的3D-NDT算法能输出较好的匹配结果,并且精度有所提高,但该算法的复杂度有待进一步优化。

基于自适应局部邻域条件下的点云匹配

为了应对传统迭代最近点(ICP)算法在处理复杂点云空间特征时,面临噪声干扰和数据缺失等问题导致收敛速度缓慢、配准精度不高以及鲁棒性较差等问题,本文提出了一种基于自适应局部邻域条件下的点云匹配算法。首先,采用体素网格滤波对数据进行预处理,根据不同半径邻域内邻近点的分布情况,定义邻域表面的弯曲程度,在此基础上,充分考虑到法向量分布和邻域曲率特征,从而得到更精确的特征点提取;其次,通过运用最小二乘曲面拟合方法,进一步提取出邻域曲率变化最为显著的特征点,采用快速点特征直方图(FPFH)对特征点进行描述,并通过设定距离阈值的采样一致性算法来匹配相似的特征点对,计算出关键的坐标转换参数,完成初始配准。最后,利用线性最小二乘优化点到面的ICP算法,以实现更精确的配准结果。通过一系列实验对比发现相较于现有的几种配准算法(ICP,SAC-IA+ICP,K4PCS+ICP),在存在噪声干扰和数据缺失的情况下,所提方法的配准准确度平均提高45%,配准速度平均提高38%,充分验证了该方法在应对大数据量、低重叠率点云配准方面具备出色的稳健性能。

基于正则化正交非负矩阵分解的旋转目标检测方法

小样本的旋转目标检测是指在样本数少的情况下进行旋转目标检测模型的训练,深度学习在旋转目标检测领域往往需要庞大的样本数和计算算力。现有的基于机器学习的旋转目标检测方法大多有着对目标尺度和姿态敏感的缺点。因此提出一种基于正则化正交非负矩阵分解的旋转目标检测方法,来解决小样本的旋转目标检测难题。首先,针对样本不具有各种角度的图片,对样本进行旋转后进行背景填充,这样便于更好的表征学习。其次,提出一种基于正则化正交非负矩阵分解算法对旋转样本的梯度直方图特征进行表征学习。最后,为了测试算法在特征学习后的有效性,利用支持向量机对特征提取后的数据进行训练和测试。实验结果表明本文的目标检测方法在多个数据集中可以取得不错的效果。

基于相关滤波的铁路异物侵限跟踪方法研究

针对铁路异物侵限频繁发生导致的列车运行安全问题,提出一种基于背景感知相关滤波器的铁路异物侵限跟踪方法。利用方向梯度直方图(HOG,Histogram of Oriented Gradient)特征提取铁路侵限异物自身特征,结合剪裁矩阵,以增加视频帧中实际背景的负样本;使用交替方向乘子法(ADMM,Alternating Direction Method of Multipliers)训练背景感知相关滤波器,减少计算复杂度,在保证跟踪速度的前提下,提升跟踪侵限异物的准确性,从而适应铁路沿线环境中由于侵限异物的形变、快速移动或天气等原因造成的目标丢失及跟踪框漂移等情况。实验结果表明,该方法对铁路侵限异物的跟踪精确度和AUC(Area Under Curve)值分别达到93%和71.9%,均高于SRDCF、KCF、ASLA和CSK等算法,具有更好的准确性。