Influence of Data Clouds Fusion From 3D RealTime Vision System on Robotic Group Dead Reckoning in Unknown Terrain

This paper proposes the solution of tasks set required for autonomous robotic group behavior optimization during the mission on a distributed area in a cluttered hazardous terrain.The navigation scheme uses the benefits of the original real-time technical vision system(TVS)based on a dynamic triangulation principle.The method uses TVS output data with fuzzy logic rules processing for resolution stabilization.Based on previous researches,the dynamic communication network model is modified to implement the propagation of information with a feedback method for more stable data exchange inside the robotic group.According to the comparative analysis of approximation methods,in this paper authors are proposing to use two-steps post-processing path planning aiming to get a smooth and energy-saving trajectory.The article provides a wide range of studies and computational experiment results for different scenarios for evaluation of common cloud point influence on robotic motion planning.

基于Vision Transformer的小麦病害图像识别算法

小麦白粉病、赤霉病和锈病是危害小麦产量的三大病害。为提高小麦病害图像的识别准确率,构建一种基于Vision Transformer的小麦病害图像识别算法。首先,通过田间拍摄的方式收集包含小麦白粉病、赤霉病和锈病3种病害在内的小麦病害图像,并对原始图像进行预处理,建立小麦病害图像识别数据集;然后,基于改进的Vision Transformer构建小麦病害图像识别算法,分析不同迁移学习方式和数据增强对模型识别效果的影响。试验可知,全参数迁移学习和数据增强能明显提高Vision Transformer模型的收敛速度和识别精度。最后,在相同时间条件下,对比Vision Transformer、AlexNet和VGG16算法在相同数据集上的表现。试验结果表明,Vision Transformer模型对3种小麦病害图像的平均识别准确率为96.81%,相较于AlexNet和VGG16模型识别准确率分别提高6.68%和4.94%。

基于Vision Transformer的电缆终端局部放电模式识别

电缆终端缺陷类型一般与局部放电信号特征密切相关,因此可以通过对局部放电信号进行模式识别来实现缺陷分类。对15 kV XLPE电缆终端4种典型缺陷的放电脉冲波形和时频谱图特征进行分析处理,得到可用于识别的数据样本,然后分别采用Vision Transformer模型、LeNet5、AlexNet和支持向量机对数据进行训练,对比不同算法的识别准确率。结果显示在数据充足的情况下,Vision Transformer模型的识别精度高于其他识别算法。所提方法及结论可为电缆附件的绝缘评估提供可靠依据,具有一定的指导意义。

An Example of Machine Vision Applied in Printing Quality Checking——Research on the Checking of Printing Quality by Image Processing

The traditional printing checking method always uses printing control strips,but the results are not very well in repeatability and stability. In this paper,the checking methods for printing quality basing on image are taken as research objects. On the base of the traditional checking methods of printing quality,combining the method and theory of digital image processing with printing theory in the new domain of image quality checking,it constitute the checking system of printing quality by image processing,and expound the theory design and the model of this system. This is an application of machine vision. It uses the high resolution industrial CCD(Charge Coupled Device) colorful camera. It can display the real-time photographs on the monitor,and input the video signal to the image gathering card,and then the image data transmits through the computer PCI bus to the memory. At the same time,the system carries on processing and data analysis. This method is proved by experiments. The experiments are mainly about the data conversion of image and ink limit show of printing.

INS/Vision组合导航中视觉系统动态定位方法研究

研究了动态情况下的视觉系统定位方法。针对现阶段视觉定位算法难以适应车载系统的要求,提出了一种INS/Vision组合导航中视觉系统的快速定位方法,在惯导系统的辅助下视觉系统在单个地标一次识别的情况下能够精确定位。为了使视觉系统达到更高的定位精度,通过实验标定的方法解决了视觉定位滞后和组合导航时间同步的问题,最后利用实验验证了该方法在车载系统的应用中的定位精度。

Robust estimation algorithm for multiple-structural data

This paper proposes a robust method of parameter estimation and data classification for multiple-structural data based on the linear error in variable（EIV） model.The traditional EIV model fitting problem is analyzed and a robust growing algorithm is developed to extract the underlying linear structure of the observed data.Under the structural density assumption,the C-step technique borrowed from the Rousseeuw＇s robust MCD estimator is used to keep the algorithm robust and the mean-shift algorithm is adopted to ensure a good initialization.To eliminate the model ambiguities of the multiple-structural data,statistical hypotheses tests are used to refine the data classification and improve the accuracy of the model parameter estimation.Experiments show that the efficiency and robustness of the proposed algorithm.

3D-CNNHSR: A 3-Dimensional Convolutional Neural Network for Hyperspectral Super-Resolution

Hyperspectral images can easily discriminate different materials due to their fine spectral resolution.However,obtaining a hyperspectral image(HSI)with a high spatial resolution is still a challenge as we are limited by the high computing requirements.The spatial resolution of HSI can be enhanced by utilizing Deep Learning(DL)based Super-resolution(SR).A 3D-CNNHSR model is developed in the present investigation for 3D spatial super-resolution for HSI,without losing the spectral content.The 3DCNNHSR model was tested for the Hyperion HSI.The pre-processing of the HSI was done before applying the SR model so that the full advantage of hyperspectral data can be utilized with minimizing the errors.The key innovation of the present investigation is that it used 3D convolution as it simultaneously applies convolution in both the spatial and spectral dimensions and captures spatial-spectral features.By clustering contiguous spectral content together,a cube is formed and by convolving the cube with the 3D kernel a 3D convolution is realized.The 3D-CNNHSR model was compared with a 2D-CNN model,additionally,the assessment was based on higherresolution data from the Sentinel-2 satellite.Based on the evaluation metrics it was observed that the 3D-CNNHSR model yields better results for the SR of HSI with efficient computational speed,which is significantly less than previous studies.

Human and Machine Vision Based Indian Race Classification Using Modified-Convolutional Neural Network

The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.

A Novel Computationally Efficient Approach to Identify Visually Interpretable Medical Conditions from 2D Skeletal Data

Timely identification and treatment of medical conditions could facilitate faster recovery and better health.Existing systems address this issue using custom-built sensors,which are invasive and difficult to generalize.A low-complexity scalable process is proposed to detect and identify medical conditions from 2D skeletal movements on video feed data.Minimal set of features relevant to distinguish medical conditions:AMF,PVF and GDF are derived from skeletal data on sampled frames across the entire action.The AMF(angular motion features)are derived to capture the angular motion of limbs during a specific action.The relative position of joints is represented by PVF(positional variation features).GDF(global displacement features)identifies the direction of overall skeletal movement.The discriminative capability of these features is illustrated by their variance across time for different actions.The classification of medical conditions is approached in two stages.In the first stage,a low-complexity binary LSTM classifier is trained to distinguish visual medical conditions from general human actions.As part of stage 2,a multi-class LSTM classifier is trained to identify the exact medical condition from a given set of visually interpretable medical conditions.The proposed features are extracted from the 2D skeletal data of NTU RGB+D and then used to train the binary and multi-class LSTM classifiers.The binary and multi-class classifiers observed average F1 scores of 77%and 73%,respectively,while the overall system produced an average F1 score of 69%and a weighted average F1 score of 80%.The multi-class classifier is found to utilize 10 to 100 times fewer parameters than existing 2D CNN-based models while producing similar levels of accuracy.

基于Data Transfer功能的FANUC机器人与第三方视觉通讯

介绍第三方机器视觉与工业机器人的常用通讯方式。以FANUC机器人为例,基于FANUC的DataTransfer功能,通过RS-232串口通讯接口,与第三方视觉通讯。在上位机上通过串口调试助手软件进行试验,顺利完成数据的发送和接收。

Development of a tracking-based system for automated traffic data collection for roundabouts

Traffic data collection is essential for performance assessment, safety improvement and road planning. While automated traffic data collection for highways is relatively mature, that for roundabouts is more challenging due to more complex traffic scenes, data specifications and vehicle behavior. In this paper, the authors propose an automated traffic data collection system dedicated to roundabout scenes. The proposed system has mainly four steps of processing. First, camera calibration is performed for roundabout traffic scenes with a novel circle-based calibration algorithm. Second, the system uses enhanced Mixture of Gaussian algorithm with shaking removal for video segmentation, which can tolerate repeated camera displacements and background movements. Then, Kalman filtering, Kemel-based tracking and overlap-based opti- mization are employed to track vehicles while they are occluded and to derive the complete vehicle trajectories. The resulting vehicle trajectory of each individual vehicle gives the position, size, shape and speed of the vehicle at each time moment. Finally, a data mining algorithm is used to automatically extract the interested traffic data from the vehicle trajectories. The overall traffic data collection system has been implemented in software and runs on regular PC. The total processing time for a 3-hour video is currently 6 h. The automated traffic data collection system can significantly reduce cost and improve efficiency compared to manual data collection. The extracted traffic data have been compared to accurate manual measurements for 29 videos recorded on 29 different days, and an accuracy of more than 90% has been achieved.

基于改进YOLOX与多级数据关联的行人多目标跟踪算法研究

目标跟踪是计算机视觉领域的基本问题,行人多目标跟踪在智能监控、智慧交通等多个领域有着广泛的应用前景。然而实际跟踪场景中存在频繁遮挡、尺度变化等情况,给多目标跟踪算法带来了极大的挑战。为了进一步提升跟踪精度,在DeepSORT的基础上,提出一种基于改进YOLOX与多级数据关联的行人多目标跟踪算法。对于检测器,为了增强网络的特征表达能力,提高检测精度,在YOLOX骨架网络与颈部网络分别引入ECA通道注意力模块与ASFF自适应特征融合模块。对于身份识别特征,为了减少数据关联步骤的错误匹配数量,提高跟踪效率,使用轻量的OSNet重识别网络与NSA卡尔曼滤波获取目标特征。对于数据关联,为了减少身份切换次数,避免目标丢失,将检测与跟踪都进行分类处理,使用不同的相似性计算方法,实现基于检测置信度与轨迹状态的多级数据关联。实验结果表明:与改进前YOLOX与DeepSORT简单结合的算法相比,在YOLOX中引入ECA模块与ASFF模块使误检数量大幅降低,使用YOLOX-s模型时降幅可达17%;结合OSNet模型与NSA卡尔曼滤波的特征提取方法能提高跟踪稳定性,IDF1指标提高0.77%,IDSW减少947;基于检测置信度与轨迹状态的多级数据关联算法可以明显改善跟踪性能,MOTA指标提升3.36%。算法最终在MOT17与MOT20测试集上的MOTA达80.4%与77.7%,IDF1达78.4%与76.7%。提出的行人多目标跟踪方法相较于其他先进算法在跟踪精度与跟踪速度上达到更好的平衡,可为工业上在线行人多目标跟踪应用提供参考。

基于视觉与加速度测量的结构动态位移融合估计

结构动态位移测量与精准估计对于结构安全运营和性态评估具有重要意义.基于计算机视觉的位移监测方法具有精度高、非接触式、成本低、设备安装简便等优点,在实际复杂工程环境中,设备难以架设,视觉测量方法较传统接触式位移监测方法具有明显的优势.图像分辨率和拍摄帧率等因素在一定程度上限制了视觉方法的使用.针对视觉位移测量技术高频振动识别精度低的问题,提出了一种基于视觉与加速度测量的结构动态位移重构方法,通过融合视觉低频与加速度高频振动响应信号,实现结构动态位移精准识别.首先,利用光流法从结构振动视频数据中提取结构位移响应,引入前后向误差与离群值过滤机制,提升特征点追踪精度,避免漂移问题.然后,利用逐次变分模态分解方法分别从视觉位移与加速度二次积分得到的位移信号中提取相应的本征模态函数(intrinsic mode function,IMF)分量.最后,基于互相关函数筛选机制,确定融合模态分量,融合基于视觉测量的低阶IMF与基于加速度测量的高阶IMF,重构结构位移响应.通过一个钢筋混凝土框架结构振动台试验,对提出的位移融合估计方法进行了试验验证.结果表明:与单一视觉测量方法相比,所提出的方法能够更为准确地估计结构动态位移,并且通过引入加速度测量中的动态位移分量,融合后的位移比基于视觉测量的结果具有更宽的频率范围.

机械加工质量预测研究现状与发展趋势

机械加工质量预测是智能制造的重要组成内容,也是实现质量闭环控制的前提条件,对推动智能制造系统真正落地应用具有极其重要的作用.在对机械加工质量预测的历史进行简要回顾时发现,学者多将研究重点放在机床某一关键部件对加工质量影响的机理研究,却鲜见部件耦合影响的关联性研究.基于上述难题,本文首先剖析影响机械加工质量的7类要素,包括刀具几何参数、切削参数、切削液类型、热误差与热变形、数控机床零部件性能退化、切削颤振以及系统特性;随后,根据各要素数据种类和测量方式的不同,将机械加工质量监测与预测方法划分为4大类,包括机器视觉测量、功率测量、振动测量以及其他测量方法,并对各方法的技术特点、局限性和发展动态进行了阐述;最后,考虑各机械加工质量监测与预测方法的不足,指出材料切削机制研究、数据质量评估方法、面向工业现场数据库构建的标准以及质量预测信息的智能表征与可视化等方面可能是未来的发展趋势.

基于扩展卡尔曼滤波与机器视觉融合的道路侧向坡度估计

为解决现有算法难以准确估计前方道路侧向坡度的问题,提出了一种基于扩展卡尔曼滤波(EKF)与机器视觉(VB)融合的道路侧向坡度估计方法。首先,建立含有侧向坡度的车辆2自由度模型,通过EKF估计出侧向坡度与车辆侧倾角的叠加态,由侧向加速度乘以适当增益解耦出车辆侧倾角,得到EKF道路侧向坡度估计值;其次,通过视觉成像原理分析二维图像中道路侧向坡度与图像中相关参数的几何关系,得到VB道路侧向坡度估计值;最后,通过数据融合得到最终的道路侧向坡度估计值,使估计结果冗余互补。仿真和实车试验结果表明,该融合算法能够适用于道路侧向坡度变化的坡道,并显著提高了估计精度。

基于骨骼的人体行为识别方法研究综述

人体行为识别在视频理解中发挥了重要作用.近年来,基于骨骼的行为识别方法因其对复杂环境的干扰更具鲁棒性而受到广泛关注.文中共整理了102种基于骨骼的人体行为识别方法,并在9个公开数据集上对其进行了对比分析.按照特征学习方式的不同,分别介绍了基于手工特征的方法和基于深度学习的方法.其中,基于手工特征的方法按特征描述符的不同分为几何描述符、动力学描述符、统计描述符3个子类;基于深度学习的方法按网络主体的不同分为循环神经网络、卷积神经网络、图卷积网络、Transformer和混合网络5个子类.通过以上分析,不仅阐述了基于骨骼的行为识别方法的发展历程,还剖析了现有方法存在的泛化能力不强、计算成本高等局限.最后,从网络结构设计、相似动作区分、领域数据集拓展、多人交互等方面对未来研究方向进行了展望.

基于改进K-means与机器视觉的档案数据分析技术

为了提升医疗信息系统对健康档案数据的分析效率,文中采用图像采集、降噪、配准与差分等技术提取医疗图像信息,进而有效提升信息系统的数据采集效率。同时还对传统的K-means算法加以改进,并提出了一种基于类间、类内距离的聚类初始化评价指标体系(BWP),将其应用于采集到的档案数据中,以实现快速的聚类分析。将所提算法在CUDA计算平台上进行了实现,测试结果表明,该方法的聚类精度和运行效率较现有算法均有显著提升。此外,改进后K-means算法的正确聚类样本数量占比提升了4.88%,高于现有的主流指标体系,且当聚类数k的取值为16或32时,运行时间大幅降低。

基于改进DDNet的皮带输送机位移故障诊断研究

针对煤矿带式输送机皮带位移故障诊断中存在局限性大、耗时长的问题,将故障数据进行多源异构处理,并在数据处理的基础上将边缘检测算法与深度细节网络,构建了一种结合边缘检测算法与改进深度细节网络的多源异构数据故障诊断模型;首先利用边缘检测算法提取输送机图像中的边缘特征,然后结合多源异构数据,并通过改进后的深度细节网络进行故障识别,并构建故障诊断模型;结果表明检测模型在皮带边缘图像数据处理的检测准确率平均值为95.27%,比目标检测算法和K最邻近分类算法的准确率高出了5.34%和10.21%;同时检测模型的图像数据查全率平均值为93.46%,比目标检测算法和K最邻近分类算法的查全率高出了4.09%和7.18%;这说明研究构建的多源异构数据故障诊断模型能够显著提升皮带位移检测的可靠性和鲁棒性,具有重要的研究价值和实际应用前景。

基于计算机视觉的下肢运动检测系统设计

目的:设计基于计算机视觉和人体关键点检测神经网络模型的人体下肢运动检测系统,以非接触的方式实现三维空间中的人体下肢运动情况检测。方法:首先,搭建运动数据采集平台,获取人体下肢运动图像,并基于OpenPose神经网络模型提取每一帧图像中下肢关键点的二维图像坐标。其次,结合运动数据采集平台中的视觉传感器的位姿信息,基于计算机视觉算法解算关键点的空间坐标,解析三维空间中的下肢运动情况。最后,以骑行运动为例、以动作捕捉系统同时采集的运动数据为标准,分析该系统在不同运动速度时的数据解算情况。结果:骑行速度为0.8、1.3、2.1 m/s时,该系统解算的数据和动作捕捉系统获得的数据的皮尔逊相关系数分别为0.950、0.917、0.828,均在强相关范围内。结论:该系统解算的数据可反映下肢运动情况,对三维空间的下肢运动检测有一定效果。

数据安全保护积极刑法观的理论证成与制度型构

数据安全保护的刑法立场选择上存在消极刑法观、积极刑法观及折中刑法观,消极刑法观与折中刑法观在逻辑和内容构造上基本无异。无论是法益保护原则的坚守,还是数据犯罪背后的法益不断翻新的客观事实需要,抑或立法漏洞日益凸显的现实困境,都决定了坚持积极刑法观是权宜之策。积极刑法观并非情绪性立法,增设新的数据犯罪并不违反刑法的谦抑性和补充性,且与象征性刑法并无直接关联,更有明确的处罚界限,与此同时也利于我国刑法的国际化。基于此,我国应当增设非法访问数据罪、非法分析数据罪,同时完善非法获取计算机信息系统数据罪。