An adaptive segmentation method combining MSRCR and mean shift algorithm with K-means correction of green apples in natural environment

During the recognition and localization process of green apple targets,problems such as uneven illumination,occlusion of branches and leaves need to be solved.In this study,the multi-scale Retinex with color restoration(MSRCR)algorithm was applied to enhance the original green apple images captured in an orchard environment,aiming to minimize the impacts of varying light conditions.The enhanced images were then explicitly segmented using the mean shift algorithm,leading to a consistent gray value of the internal pixels in an independent fruit.After that,the fuzzy attention based on information maximization algorithm(FAIM)was developed to detect the incomplete growth position and realize threshold segmentation.Finally,the poorly segmented images were corrected using the K-means algorithm according to the shape,color and texture features.The users intuitively acquire the minimum enclosing rectangle localization results on a PC.A total of 500 green apple images were tested in this study.Compared with the manifold ranking algorithm,the K-means clustering algorithm and the traditional mean shift algorithm,the segmentation accuracy of the proposed method was 86.67%,which was 13.32%,19.82%and 9.23%higher than that of the other three algorithms,respectively.Additionally,the false positive and false negative errors were 0.58%and 11.64%,respectively,which were all lower than the other three compared algorithms.The proposed method accurately recognized the green apples under complex illumination conditions and growth environments.Additionally,it provided effective references for intelligent growth monitoring and yield estimation of fruits.

Error-CompensatingFive-SamplePhase-Shifting Algorithm Based on Phase-Shift Error Estimation

A new error compensating five sample phase shifting algorithm which is insensitive to phase shift error is proposed to retrieve the phase distribution of a fringe pattern. It includes two steps. First, the linear phase shift error is estimated using four sample images. Then, the phase distribution is calculated with error corrected by using the phase shift error estimated in the first step. As the equations of error estimation and phase calculation are simple, this new algorithm is practical as well as effective. Computer simulations were carried out to verify the effectiveness of the algorithm. Results of two other well known error compensating algorithms are also presented, which show the new algorithm is the least sensitive to phase shift error.

Rapid and robust medical image elastic registration using mean shift algorithm

In landmark-based image registration, estimating the landmark correspondence plays an important role. In this letter, a novel landmark correspondence estimation technique using mean shift algorithm is proposed. Image corner points are detected as landmarks and mean shift iterations are adopted to find the most probable corresponding point positions in two images. Mutual information between intensity of two local regions is computed to eliminate mis-matching points to improve the stability of corresponding estimation correspondence landmarks is exact. The proposed experiments of various mono-modal medical images. Multi-level estimation （MLE） technique is proposed Experiments show that the precision in location of technique is shown to be feasible and rapid in the

Research on Modified Shifting Balance Genetic Algorithms

The increasing overlap of core and colony populations during the anaphase of evolution may limit the performance of shifting balance genetic algorithms. To decrease such overlapping,so as to increase the local search capability of the core population,the sub-space method was used to generate uniformly distributed initial colony populations over the decision variable space. The core population was also dynamically divided,making simultaneous searching in several local spaces possible. The algorithm proposed in this paper was compared to the original one by searching for the optimum of a complicated multi-modal function. The results indicate that the solutions obtained by the modified algorithm are better than those of the original algorithm.

Generation and Analysis of Hybrid-Electric Vehicle Transmission Shift Schedules with a Torque Split Algorithm

The increased concern over global climate change and lack of long-term sustainability of fossil fuels in the projected future has prompted further research into advanced alternative fuel vehicles to reduce vehicle emissions and fuel consumption. One of the primary advanced vehicle research areas involves electrification and hybridization of vehicles. As hybrid-electric vehicle technology has advanced, so has the need for more innovative control schemes for hybrid vehicles, including the development and optimization of hybrid powertrain transmission shift schedules. The hybrid shift schedule works in tandem with a cost function-based torque split algorithm that dynamically determines the optimal torque command for the electric motor and engine. The focus of this work is to develop and analyze the benefits and limitations of two different shift schedules for a position-3 (P3) parallel hybrid-electric vehicle. a traditional two-parameter shift schedule that operates as a function of vehicle accelerator position and vehicle speed (state of charge (SOC) independent shift schedule), and a three-parameter shift schedule that also adapts to fluctuations in the state of charge of the high voltage batteries (SOC dependent shift schedule). The shift schedules were generated using an exhaustive search coupled with a fitness function to evaluate all possible vehicle operating points. The generated shift schedules were then tested in the software-in-the-loop (SIL) environment and the vehicle-in-the-loop (VIL) environment and compared to each other, as well as to the stock 8L45 8-speed transmission shift schedule. The results show that both generated shift schedules improved upon the stock transmission shift schedule used in the hybrid powertrain comparing component efficiency, vehicle efficiency, engine fuel economy, and vehicle fuel economy.

Optimization of the seismic processing phase-shift plus finite-difference migration operator based on a hybrid genetic and simulated annealing algorithm

Although the phase-shift seismic processing method has characteristics of high accuracy, good stability, high efficiency, and high-dip imaging, it is not able to adapt to strong lateral velocity variation. To overcome this defect, a finite-difference method in the frequency-space domain is introduced in the migration process, because it can adapt to strong lateral velocity variation and the coefficient is optimized by a hybrid genetic and simulated annealing algorithm. The two measures improve the precision of the approximation dispersion equation. Thus, the imaging effect is improved for areas of high-dip structure and strong lateral velocity variation. The migration imaging of a 2-D SEG/EAGE salt dome model proves that a better imaging effect in these areas is achieved by optimized phase-shift migration operator plus a finite-difference method based on a hybrid genetic and simulated annealing algorithm. The method proposed in this paper is better than conventional methods in imaging of areas of high-dip angle and strong lateral velocity variation.

基于自适应核带宽度Mean Shift算法的单木识别研究

为提高多树种森林中单木识别的精度,利用机载激光雷达点云数据作为研究对象,提出一种基于自适应核带宽度Mean Shift算法的单木识别方法。该方法先采用直方图分析法分离树冠点云和冠层下点云,再采用基于二维增量网格投影的区域生长法,估算单木冠幅有效半径,然后以单木冠幅有效半径作为自适应核带宽度,对树冠点云进行自适应Mean Shift聚类分析,得到树冠点簇,最后采用包络盒方法根据树冠点簇和树干点云的空间关系识别单木。试验结果表明,检测树与实际树的位置、树冠形态近似一致,单木召回率达到86.1%,准确率达到91.5%,高于2个对比试验的结果。研究证明设置的自适应核带宽度能够自动调整以反映局部树冠的实际大小,在多树种森林的单木识别中表现良好。

Improved mean-shift-based pitch determination

The underlying principle of pitch determination based on the mean shift algorithm is studied, and the cause of pitch error propagation in the original pseudo code is analyzed. The problem of error propagation is solved by choosing an appropriate initial pitch candidate F00. The theoretical choice guideline in a pitch epoch is obtained as ensuring the true pitch F0 satisfying F00/2 〈 F0 〈 3F00/2. The validity of the choice guideline is verified by the F00 experiment. Meanwhile, the algorithm is extended to the pitch determination in the noisy case and compared with the method of subharmonic-to-harmonic ratio （SHR）. The experimental results show that the improved algorithm bears comparison with SHR and it runs much faster than SHR.

基于改进Mean-Shift与自适应Kalman滤波的视频目标跟踪

提出一种改进的Mean-Shift和自适应Kalman滤波器相结合的视频运动目标跟踪算法。对选定的跟踪目标,采用三帧差和区域增长法分割目标并得到主颜色信息。在跟踪过程中,利用自适应的Kalman滤波器估计每一帧的起始迭代位置,再利用改进的Mean-Shift算法得到跟踪位置并作为测量值反馈给自适应Kalman滤波器,并引入遮挡率因子以自适应地调节Kalman估计参数。实验结果表明,该算法能对视频中的运动目标实现检测和连续跟踪,对遮挡也有较好的鲁棒性。

基于粒子滤波和Mean-shift的跟踪算法

粒子滤波作为一种基于贝叶斯估计的算法,在处理非线性运动目标跟踪问题上具有特殊的优势。基于此,提出一种基于粒子滤波和Mean-shift的混合跟踪算法(KMSEPF)。KMSEPF算法对一般的Mean-shift和粒子滤波混合算法进行改进。结果证明,KMSEPF算法与混合算法MSEPF相比,在计算效率提高的同时,跟踪准确性和处理遮挡的能力没有下降。

基于Mean Shift随机游走图像分割算法

针对传统随机游走算法分割目标轮廓易受自然纹理背景干扰,并且算法运行效率低的问题,提出一种基于Mean Shift随机游走图像分割算法.首先应用Mean Shift算法对图像进行预分割,将图像分成许多同质区域,再将其代替经典随机游走算法中节点来建立对应的无向图;将彩色直方图作为区域描述算子,采用欧氏距离与高斯权函数相结合来建立区域间相似性权函数;最后应用离散电势理论计算图中节点间电势值,并根据节点电势值的大小对预分割得到的同质区域进行分类,以实现图像分割.实验结果表明,与传统方法相比,该算法在分割精度和运行效率上都有很大提高.

结合卡尔曼滤波和Mean Shift的抗遮挡跟踪算法

针对卡尔曼滤波和Mean Shift算法结合后对严重遮挡和遮挡后复出失效且实时性差的问题,提出一种基于卡尔曼滤波和Mean Shift动态结合的改进算法.通过在算法中加入Bhattacharyya系数进行遮挡程度判断,并根据遮挡系数的阈值选择使用卡尔曼滤波或线性预测法更新Mean Shift迭代起点.实验结果表明,该方法能成功实现大范围连续遮挡和目标复出情况下红外目标的跟踪,并且迭代次数和跟踪时间分别减少了9.68%和17.58%,提高了跟踪的鲁棒性和实时性.

Kalman滤波融合优化Mean Shift的目标跟踪算法

目标跟踪中,目标的背景变化、形状改变、遮挡,往往会导致跟踪失败,而跟踪的实时性和准确性是必须考虑的问题。本文首先对Mean Shift算法进行了介绍,接着对Mean Shift算法进行了优化:修正Mean Shift算法迭代权值,修正后主要信息贡献更加突出,次要信息受到抑制,避免了开方的繁琐运算,降低了运算量。提出了目标模板更新算法,解决了背景变化和目标形状改变时跟踪失败的问题。然后在水平位置和竖直位置建立Kalman滤波器,同时将优化Mean Shift算法与Kalman滤波融合,解决了目标完全遮挡后无法继续跟踪的问题。仿真实验表明,本文提出的目标跟踪算法在目标遮挡,目标形状改变,目标跟踪失败的情况下具有更高的跟踪精度,更高的实时性和鲁棒性。

基于Mean Shift算法视频跟踪研究

为改善Mean Shift算法的跟踪性能,分析了Mean Shift算法跟踪局限性,对Mean Shift算法流程进行了改进。Harris特征角点具有对光照、旋转、部分仿射变化以及噪声干扰具有很好的鲁棒性的特性可解决Mean Shift算法在背景过于复杂时的跟踪失败问题。Surf算法则具有对旋转、尺度缩放、亮度变化保持不变性,检测和匹配速度快等优点,能辅助Mean Shift算法在帧速过快情况下解决跟踪失败问题。提出了融合Harris角点和Surf算法的改进型Mean Shift算法。实验表明改进后的算法改善了Mean Shift算法在背景复杂以及帧速过快情况下的跟踪性能。

Mean Shift算法的收敛性分析

作为迭代算法,Mean Shift的收敛性研究是应用的基础,而Comaniciu和李乡儒分别证明了Mean Shift的收敛性,但证明过程存在错误.首先指出了Comaniciu和李乡儒的证明过程存在错误;然后,从数学上重新证明了Mean Shift算法的局部收敛性,并指出其收敛到局部极大值的条件;最后,从几何上举反例分析了Mean Shift的收敛性,并进行了深入比较和讨论.这为Mean Shift算法的深入研究及应用奠定了基础.

融合mean shift和区域显著性的彩色图像分割算法

提出了一种无监督的提取图像中显著区域的彩色图像分割算法。首先,运用meanshift算法对图像进行分割,得到初始的分割结果;然后,根据给出的区域显著性的定义和区域合并策略,对初始分割结果进行合并,得到最终的分割结果。仿真结果表明,对于大多数测试图像,该算法都能获得很好的分割结果,并且具有较高的运行效率。

尺度方向自适应Mean Shift跟踪算法

在分析尺度空间理论和Mean Shift跟踪算法的基础上,提出了一种尺度方向自适应Mean Shift跟踪算法。根据起始帧图像中目标和背景的差异,分割出目标覆盖区域,并根据尺度空间理论对目标建立最佳描述椭圆。对于后续帧,以上一帧目标的最佳椭圆描述为初始值,根据Mean Shift迭代原理依次更新椭圆参数。实验结果表明,新算法可以有效、稳健地适应目标旋转缩放等复杂运动。

采用改进Mean Shift算法的移动机器人行人跟踪

为了提高移动机器人目标跟踪系统在复杂环境中的跟踪性能,提出在双层定位机制下采用基于自适应核函数的Mean Shift算法实现目标跟踪。利用射频识别器件(RFID)检测携带标签的目标,实现外层粗定位并确定感兴趣区域(ROI);在内层则根据对视差图的ROI的处理结果确定初始搜索窗口,然后应用基于自适应核函数的Mean Shift算法在从立体相机获得的左图中应用基于自适应核函数的Mean Shift算法实现对目标的精确定位。自适应核函数由目标的区域特征与Epanechnikov函数相融合构成,克服了目标边缘处背景像素对目标颜色概率分布的影响。与传统的Mean Shift算法相比,所提方法在同色背景干扰下仍能准确跟踪目标。另外,RFID限定了图像搜索范围,节省了运算开支,图像处理的平均时间为62.11 ms/frame,满足实时跟踪的要求。实验结果表明,该方法可实现移动机器人在同色背景干扰、遮挡、目标快速移动等情况下的目标跟踪。

核函数带宽自适应的Mean-Shift跟踪算法

为了实现Mean-Shift跟踪算法中的核函数带宽自适应更新,提出基于比较Bhattacharyya系数的新方法。首先用模板中心加权与目标边缘加权的直方图计算巴氏系数,跟踪时用候选目标边缘加权直方图与模板中心加权直方图计算新的巴氏系数,根据两个系数的大小对核带宽进行10%的缩放。实验表明,该方法有效克服了带宽只能缩小的问题,实现了跟踪窗对目标缩放的自适应性。