基于多尺度Harris角点检测的图像配准算法

针对现有多尺度Harris算子算法较复杂、运算量大、精确性一般的问题,提出一种高效简便算法。首先建立多尺度空间,令Harris算子在尺度空间提取特征点,用简化的32维SIFT特征向量描述特征。利用最近邻法匹配特征点;然后采用改进的相似三角形法筛选匹配点,再使用改进的K-means算法对特征点分组,使组内特征点聚集,组间特征点远离;最后应用改进的RANSAC算法在不同组中选取特征点求变换矩阵,避免了选取的特征点距离过近,算法陷入局部最优。实验验证了所提算法的性能。

An Improved Harris Hawk Optimization Algorithm for Flexible Job Shop Scheduling Problem

Flexible job shop scheduling problem(FJSP)is the core decision-making problem of intelligent manufacturing production management.The Harris hawk optimization(HHO)algorithm,as a typical metaheuristic algorithm,has been widely employed to solve scheduling problems.However,HHO suffers from premature convergence when solving NP-hard problems.Therefore,this paper proposes an improved HHO algorithm(GNHHO)to solve the FJSP.GNHHO introduces an elitism strategy,a chaotic mechanism,a nonlinear escaping energy update strategy,and a Gaussian random walk strategy to prevent premature convergence.A flexible job shop scheduling model is constructed,and the static and dynamic FJSP is investigated to minimize the makespan.This paper chooses a two-segment encoding mode based on the job and the machine of the FJSP.To verify the effectiveness of GNHHO,this study tests it in 23 benchmark functions,10 standard job shop scheduling problems(JSPs),and 5 standard FJSPs.Besides,this study collects data from an agricultural company and uses the GNHHO algorithm to optimize the company’s FJSP.The optimized scheduling scheme demonstrates significant improvements in makespan,with an advancement of 28.16%for static scheduling and 35.63%for dynamic scheduling.Moreover,it achieves an average increase of 21.50%in the on-time order delivery rate.The results demonstrate that the performance of the GNHHO algorithm in solving FJSP is superior to some existing algorithms.

基于Harris和卡尔曼滤波的农业机器人田间稳像算法

针对田间颠簸环境影响农业机器人采集实时稳定图像问题,提出了基于Harris和卡尔曼滤波的农业机器人田间稳像算法。首先,利用摄像头获取田间抖动视频图像序列,进行图像子区域划分并计算各区域灰度均方差,进而确定各区域Harris角点阈值;通过自适应角点阈值设置,增加角点距离约束,完成图像角点检测。然后,对检测出的角点进行光流跟踪,计算出帧间运动估计参数。最后,利用自适应卡尔曼滤波算法对运动估计参数进行平滑操作并动态调整滤波平滑性能,获得精确运动估计矢量。测试结果表明,改进后的Harris角点检测算法区域平均分布标准差减小;自适应卡尔曼滤波算法在保证平滑随机运动前提下,跟踪主动运动性能平均提升30.75个百分点;稳像后的图像峰间信噪比提升15.93%,单帧处理时间为25.66 ms,满足农业机器人30 f/s高速图像采集时同步稳像对实时性要求。

ARCO 2-4期股骨头坏死MR征象对Harris评分影响分析

目的:分析并确定ARCO 2-4期股骨头坏死(osteonecrosis of femoral head,ONFH)对Harris评分有影响意义的MR征象。方法:回顾性分析2019年1月至2020年6月34例行常规MR、T2 mapping、3D-SPACE序列检查及Harris评分的ARCO 2-4期ONFH患者,排除3例,最终纳入31例,男23例,女8例,年龄18~62(40.0±10.8)岁;其中21例为双侧ONFH,共计52个ONFH,ARC02期17个,ARCO 3期24个,ARCO 4期11个。在医院数字影像信息系统(picture archiving and communication system,PACS)对MR影像征象(股骨头塌陷深度、ONFH指数、骨髓水肿、股骨头骨质增生、软骨损伤分级、软骨T2值及关节积液)进行评估及测量,在Siemens后处理工作站计算软骨定量参数T2值并测量。采用Pearson相关分析评估MR各征象与Harris评分的相关性,采用多重线性回归分析评估与Harris评分有相关性的MR征象对Harris评分的影响。结果:Pearson相关分析显示股骨头塌陷深度(r=-0.563,P=0.000)、软骨损伤分级(r=-0.500,P=0.000)及关节积液(r=-0.535,P=0.000)与Harris评分呈负相关。多重线性回归分析显示关节积液(β=-6.198,P=0.001)、股骨头塌陷深度(β=-4.085,P=0.014)对Harris评分呈负相关。结论:关节积液、股骨头塌陷深度对Harris评分有显著的负向影响关系,建议影像医师常规对股骨头塌陷深度、关节积液进行定量及等级评估,以高效精准地辅助临床诊疗。

Harris与SURF特征点检测的手术器械机器视觉识别方法

针对手术器械快速识别与定位需求,提出一种基于改进Harris与SURF特征点检测的手术器械机器视觉检测方法。通过MASK匀光算法消除金属表面不均匀光泽反射,并设计改进的Harris角点检测算法实现无堆叠手术器械的快速检测。利用SURF算法提取图像特征信息,采用KD-Tree搜索相似特征矢量,以实现堆叠手术器械的准确识别与定位。实验结果表明:本文方法的识别准确率和识别时间分别为92.4%和3.15 s,可有效实现典型手术器械的视觉识别与定位。

基于改进Harris的消音壁亚像素级角点检测算法

在计算机视觉领域,角点检测作为图像拼接、三维重建等算法的关键,能够直接影响视觉处理的最终效果。为了进一步提高角点检测在消音壁视觉检测应用场景下的精度,提出了一种亚像素级角点检测算法,首先以Harris算法获得像素级角点为中心角点,然后通过最小二乘法迭代计算不断逼近,最后计算得出亚像素级角点坐标。实验结果表明,算法角点检测的平均偏移量为0.18像素,相较Harris角点检测算法的偏移量降低0.56像素,在确保正确率的基础上更加接近真实值,能够满足在消音壁视觉检测应用场景下的精度需求。

一种改进的Harris-RANSAC长焦相机标定算法

长焦相机采集近距离棋盘格图像时易出现相机离焦现象,导致棋盘格图像产生散焦模糊,极大地增加了相机标定的难度,同时传统的Harris角点检测算法对散焦模糊的棋盘格图像进行角点检测的结果即使经过非极大值抑制处理也仍然存在大量冗余角点.针对上述问题,基于随机抽样一致(random sample consensus,RANSAC)算法提出一种改进的Harris-RANSAC长焦相机标定算法.首先,引入感兴趣区域将Harris角点检测的区域缩小到棋盘格区域以避免背景干扰;其次,采用随机抽样一致算法替代传统的非极大值抑制方法剔除冗余角点;最后,针对模糊棋盘格图像的特性构造新的响应函数,进行亚像素级角点定位,从而得到精确的角点坐标.结果表明,改进的Harris-RANSAC算法对模糊棋盘格图像进行角点检测时耗时短且精度较高,角点检测的反投影误差仅为0.432像素.

早期康复护理对股骨颈骨折术后患者Barthel指数及Harris髋关节评分的影响

目的探讨早期康复护理对股骨颈骨折术后患者Barthel指数及Harris评分的影响。方法选取2018年10月至2020年10月在我院接受手术治疗的80例股骨颈骨折患者作为研究对象,根据随机编号将其分为对照组和研究组,各40例。对照组采用常规护理,研究组采用早期康复护理。比较两组的并发症发生情况、Barthel指数、Harris髋关节评分及生活质量。结果研究组的并发症总发生率低于对照组(P<0.05)。护理1、2、4周后,两组的Barthel指数及Harris髋关节评分均升高,且研究组高于对照组(P<0.05)。研究组的心理功能、躯体功能、社会功能及物质生活评分均高于对照组(P<0.05)。结论早期康复护理应用于股骨颈骨折术后患者中能有效减少并发症,促进髋关节功能及活动能力的恢复,提高Barthel指数及Harris髋关节评分,改善生活质量。

基于改进3D-Harris角点检测算法的电厂地下管廊点云拼接方法研究

提出一种基于改进3D-Harris角点检测算法的电厂地下管廊点云拼接方法。以电厂地下管廊多组海量点云数据为分析对象,利用主成分分析法获取目标检测点在邻域点云微切平面上的法向信息,进而提取点云的边界点;构建基于目标检测点法向信息的协方差矩阵,计算并比较其角点响应强度函数,从中选出部分待筛选点作为真伪角点检测对象;利用基于高斯曲率极值点的伪角点检测方法,滤除伪角点并筛选出真角点;最后通过快速点特征直方图方法匹配各组点云间的相似角点,利用最近点搜索点云配准算法实现地下管廊多组点云间的拼接,并与传统3D-Harris角点检测算法的结果进行比较。对比表明,所提出算法计算耗时短且角点提取正确率高,可实现电厂地下管廊海量点云的精确拼接。

Computing Connected Resolvability of Graphs Using Binary Enhanced Harris Hawks Optimization

In this paper,we consider the NP-hard problem offinding the minimum connected resolving set of graphs.A vertex set B of a connected graph G resolves G if every vertex of G is uniquely identified by its vector of distances to the ver-tices in B.A resolving set B of G is connected if the subgraph B induced by B is a nontrivial connected subgraph of G.The cardinality of the minimal resolving set is the metric dimension of G and the cardinality of minimum connected resolving set is the connected metric dimension of G.The problem is solved heuristically by a binary version of an enhanced Harris Hawk Optimization(BEHHO)algorithm.This is thefirst attempt to determine the connected resolving set heuristically.BEHHO combines classical HHO with opposition-based learning,chaotic local search and is equipped with an S-shaped transfer function to convert the contin-uous variable into a binary one.The hawks of BEHHO are binary encoded and are used to represent which one of the vertices of a graph belongs to the connected resolving set.The feasibility is enforced by repairing hawks such that an addi-tional node selected from V\B is added to B up to obtain the connected resolving set.The proposed BEHHO algorithm is compared to binary Harris Hawk Optimi-zation(BHHO),binary opposition-based learning Harris Hawk Optimization(BOHHO),binary chaotic local search Harris Hawk Optimization(BCHHO)algorithms.Computational results confirm the superiority of the BEHHO for determining connected metric dimension.

基于Hough-Harris的消音壁顶点检测

在消音壁领域中,消音壁的顶点检测是后续对消音壁毁伤评估、三维重建等任务的关键,检测出的顶点准确率直接影响后续任务的精确度。为提高检测出消音壁顶点的准确率,提出一种基于Hough-Harris的消音壁顶点检测算法。首先,使用Hough算法检测出的角点作为基点;然后,利用Harris检测出消音壁边框上的角点,选取以基点步长为10个像素的领域内角点作为样本点;最后,建立回归模型,利用高斯提出的最小二乘法求出最小误差,预测出消音壁顶点坐标。实验结果表明,本文算法预测顶点坐标与真实顶点坐标偏差量都小于Hough算法和Harris算法检测出的角点,IoU评估指标高达98%以上,高于Hough算法和Harris算法的IoU指标。

递进式护理在人工髋关节置换术患者中的应用效果及对Harris评分的影响

目的探讨递进式护理在人工髋关节置换术(THA)患者中的应用效果及对Harris评分的影响。方法选取2019年5月至2021年5月进入本院接受THA治疗的98例患者作为研究对象,以随机数字表法将其分为对照组和观察组,每组49例。对照组给予常规护理,观察组给予递进式护理。比较两组的护理效果。结果护理前,两组的Harris髋关节功能量表各项评分及总分无显著差异(P>0.05);护理后,观察组的Harris髋关节功能量表各项评分及总分均显著高于对照组,差异具有统计学意义(P<0.05)。护理前,两组的6 min步行距离、步频及步速无显著差异(P>0.05);护理后,观察组的6 min步行距离长于对照组,步频及步速均显著大于对照组,差异具有统计学意义(P<0.05)。护理前,两组的自我效能感量表(GSES)、Barthel指数评分无显著差异(P>0.05);护理后,观察组的GSES、Barthel指数评分均显著高于对照组,差异具有统计学意义(P<0.05)。结论递进式护理应用于THA患者中可明显提高其自我效能感,促进关节功能恢复及步态改善,进而提升其日常生活能力。

自适应阈值Harris算法遥感图像配准的FPGA实现

针对Harris角点检测器响应值R的阈值选择而导致角点失真问题,文章提出了一种基于现场可编程门阵列(FPGA)的自适应Harris角点检测器实现遥感图像的配准方式。该方式依据非最大值抑制(NMS)处理后的响应值对阈值进行实时变化。实验结果显示,优化架构在硬件资源仅增加2.76%的情况下,准确率相应提升了8.31%。因此,文章提出的遥感图像配准架构适用于硬件资源有限的平台。

Enhanced Harris Hawks Optimization Integrated with Coot Bird Optimization for Solving Continuous Numerical Optimization Problems

Harris Hawks Optimization(HHO)is a novel meta-heuristic algorithm that imitates the predation characteristics of Harris Hawk and combines Lévy flight to solve complex multidimensional problems.Nevertheless,the basic HHO algorithm still has certain limitations,including the tendency to fall into the local optima and poor convergence accuracy.Coot Bird Optimization(CBO)is another new swarm-based optimization algorithm.CBO originates from the regular and irregular motion of a bird called Coot on the water’s surface.Although the framework of CBO is slightly complicated,it has outstanding exploration potential and excellent capability to avoid falling into local optimal solutions.This paper proposes a novel enhanced hybrid algorithm based on the basic HHO and CBO named Enhanced Harris Hawks Optimization Integrated with Coot Bird Optimization(EHHOCBO).EHHOCBO can provide higher-quality solutions for numerical optimization problems.It first embeds the leadership mechanism of CBO into the population initialization process of HHO.This way can take full advantage of the valuable solution information to provide a good foundation for the global search of the hybrid algorithm.Secondly,the Ensemble Mutation Strategy(EMS)is introduced to generate the mutant candidate positions for consideration,further improving the hybrid algorithm’s exploration trend and population diversity.To further reduce the likelihood of falling into the local optima and speed up the convergence,Refracted Opposition-Based Learning(ROBL)is adopted to update the current optimal solution in the swarm.Using 23 classical benchmark functions and the IEEE CEC2017 test suite,the performance of the proposed EHHOCBO is comprehensively evaluated and compared with eight other basic meta-heuristic algorithms and six improved variants.Experimental results show that EHHOCBO can achieve better solution accuracy,faster convergence speed,and a more robust ability to jump out of local optima than other advanced optimizers in most test cases.Finally,EHHOCBOis applied to address four engineering design problems.Our findings indicate that the proposed method also provides satisfactory performance regarding the convergence accuracy of the optimal global solution.

Multiobjective Economic/Environmental Dispatch Using Harris Hawks Optimization Algorithm

The eminence of Economic Dispatch(ED)in power systems is signifi-cantly high as it involves in scheduling the available power from various power plants with less cost by compensating equality and inequality constrictions.The emission of toxic gases from power plants leads to environmental imbalance and so it is highly mandatory to rectify this issues for obtaining optimal perfor-mance in the power systems.In this present study,the Economic and Emission Dispatch(EED)problems are resolved as multi objective Economic Dispatch pro-blems by using Harris Hawk’s Optimization(HHO),which is capable enough to resolve the concerned issue in a wider range.In addition,the clustering approach is employed to maintain the size of the Pareto Optimal(PO)set during each itera-tion and fuzzy based approach is employed to extricate compromise solution from the Pareto front.To meet the equality constraint effectively,a new demand-based constraint handling mechanism is adopted.This paper also includes Wind energy conversion system(WECS)in EED problem.The conventional thermal generator cost is taken into account while considering the overall cost functions of wind energy like overestimated,underestimated and proportional costs.The quality of the non-dominated solution set is measured using quality metrics such as Set Spacing(SP)and Hyper-Volume(HV)and the solutions are compared with other conventional algorithms to prove its efficiency.The present study is validated with the outcomes of various literature papers.

Harris Hawks Optimizer with Graph Convolutional Network Based Weed Detection in Precision Agriculture

Precision agriculture includes the optimum and adequate use of resources depending on several variables that govern crop yield.Precision agriculture offers a novel solution utilizing a systematic technique for current agricultural problems like balancing production and environmental concerns.Weed control has become one of the significant problems in the agricultural sector.In traditional weed control,the entire field is treated uniformly by spraying the soil,a single herbicide dose,weed,and crops in the same way.For more precise farming,robots could accomplish targeted weed treatment if they could specifically find the location of the dispensable plant and identify the weed type.This may lessen by large margin utilization of agrochemicals on agricultural fields and favour sustainable agriculture.This study presents a Harris Hawks Optimizer with Graph Convolutional Network based Weed Detection(HHOGCN-WD)technique for Precision Agriculture.The HHOGCN-WD technique mainly focuses on identifying and classifying weeds for precision agriculture.For image pre-processing,the HHOGCN-WD model utilizes a bilateral normal filter(BNF)for noise removal.In addition,coupled convolutional neural network(CCNet)model is utilized to derive a set of feature vectors.To detect and classify weed,the GCN model is utilized with the HHO algorithm as a hyperparameter optimizer to improve the detection performance.The experimental results of the HHOGCN-WD technique are investigated under the benchmark dataset.The results indicate the promising performance of the presented HHOGCN-WD model over other recent approaches,with increased accuracy of 99.13%.

基于Harris角点和SURF特征的遥感图像匹配算法

Harris是一种高效的角点检测算法,但不具备尺度不变性。SURF(speeded-up robust features)算法虽然能很好地解决图像尺度变化问题,但是在特征点提取方面没有Harris稳定。针对Harris和SURF两种算法的特点,提出一种新的Harris-SURF特征点提取算法。首先用Harris算法检测图像角点,再用SURF算法提取图像特征点;然后合并角点和特征点,并剔除重复点获得新的特征点集,确定新特征点的主方向并生成特征描述符,再对图像使用比值法进行初匹配;最后利用RANSAC剔除错误匹配点实现精确匹配。实验结果表明,该算法对图像存在旋转、缩放、光照及噪声变化有较强的鲁棒性,同时提高了运行效率。

Harris尺度不变性关键点检测子的研究

在特定的参数设置下Harris尺度不变性检测子不能提供足够数目的稳定关键点,以往研究据此断定Harris尺度不变性检测子不稳定,不是有效的特征检测子.在构造Harris角点值的尺度空间过程中,存在一系列参数影响着Harris角点值在尺度空间中极值点的数目,从而决定了Harris尺度不变性检测子所能获取的稳定关键点的数目.对这个参数空间进行了系统研究,发现积分尺度与微分尺度的比值对Harris尺度不变性检测子能否检测到足够数目的稳定关键点具有决定性的影响.当这一比值减少时,Harris尺度不变性检测子所获取的稳定关键点的数目快速增长;当这一比值小于0.8时,Harris尺度不变性检测子所能获取的稳定关键点的数目开始超出DoG检测子所能获取的稳定关键点的数目.这个有效的参数区间大大增加了Harris-Laplace检测子所能获取的稳定关键点的数目.与Harris-Laplace检测子以及DoG检测子进行比较,具有有效参数的Harris尺度不变性检测子具有最佳的稳定性能,这个结果纠正了关于Harris尺度不变性检测子不稳定的错误结论.

一种改进的多尺度Harris特征点检测方法

多尺度Harris方法检查到的特征点存在很多冗余点,虽然Harris-Laplace方法可以除去一些冗余点,但是还会出现一个局部结构内存在多个特征点的情况或一个特征点代表多个不同尺度的局部结构。为此,提出一种改进的方法,在检测多尺度Harris特征点时进行跟踪分组,使代表同一个局部结构的特征点被分为一组,用归一化的Laplace函数去除冗余点,再利用点的度量值选出最能代表该局部结构的特征点。实验结果证明,该方法能够有效去除冗余点,在模糊和旋转变换时性能优于Harris-Laplace方法,具有尺度不变的特性。

运用SI-Harris算子提取遥感图像点特征

推导了SI-Harris算子(尺度不变Harris算子)的理论公式,并将其应用于遥感图像的点特征提取。重点对Harris算子与SI-Harris算子在不同空间分辨率遥感图像上的点特征提取进行实验比较,利用"重复率"指标对实验结果进行定量评价。实验表明:SI-Harris算子"重复率"较Harris算子有明显提升,可用于不同空间分辨率遥感图像的点特征提取,进而可服务于不同空间分辨率遥感图像的匹配。