Moving Target Tracking Based on LogGabor Wavelet and Mean-shift Algorithm

Tracking moving target from image or video sequence is a hot research topic in computer vision. An algorithm based on LogGabor wavelet and Mean-shift has been proposed for moving target tracking under fixed camera setting and complicated environment. Phase coherency of LogGabor wavelet facilitates to extract the edge of moving target and check noise. According to the edge detection,the starting location of Mean-shift can be estimated using the target center coordinate. Eventually,a real-time moving target can be extracted by doing iterative matching pursuit,and experimental results proved the effectiveness of the method proposed.

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。

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.

改进Mean Shift目标跟踪算法实现

目标跟踪技术目前具有较好的应用前景,但在嵌入式处理平台中面临着实时性要求高、跟踪场景复杂等情况,加上受成本和嵌入式处理平台算力的限制,其处理效果往往很难满足现实需求,因此目标跟踪等图像处理技术的落地实现是当前研究的热点内容。针对此问题,本文在FPGA平台实现了改进Mean Shift目标跟踪算法,该算法首先通过目标的概率密度分布梯度爬升来寻找目标,然后采用Kalman滤波的预测机制来预估下一帧搜寻计算的位置,从而减少Mean Shift的迭代次数。该算法实现充分利用FPGA能够并行和流水线处理的特点,实现了在1 920×1 080@60 Hz高清视频图像场景下的实时目标跟踪,其中Kalman滤波算法使其在较复杂场景下也能具备一定的抗遮挡干扰的能力。

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

基于Mean-shift聚类算法的导航欺骗干扰源定位技术

对导航干扰的现状进行了分析,针对北斗导航面临的威胁,对现有导航欺骗干扰源的定位方法和功率预测方法进行分析总结。针对现有技术水平的不足和未来战场的需求,提出了基于Mean-shift聚类算法的干扰源定位方法,对算法进行了分析,给出算法实现与优化的过程,通过仿真与实验测试对算法的性能进行了分析。外场实测数据表明,提出的导航欺骗干扰定位算法具有较高的定位精度。提出的干扰源定位方法,将为导航对抗环境下的导航态势感知提供一种新的手段和方法。

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Mean Shift算法的卡尔曼滤波红外摄像头的目标跟踪系统设计

红外图像具有被动成像、抗干扰性强、目标识别能力强和全天候工作的特点,已经被广泛应用于军事侦察、监控和制导等领域.在背景干扰或者遮挡情况下传统的Mean Shift跟踪算法的跟踪存在不连续的问题.针对人体目标的活跃性和特殊性,设计一种在Mean Shift算法基础上结合卡尔曼滤波和Bhattacharyya系数遮挡判定因子的目标跟踪系统.当遮挡发生时,通过滤波器预测目标下一帧的位置,继续实现跟踪.测试结果表明:在背景干扰或者遮挡的情况下该跟踪系统可以有效地对目标进行准确跟踪.

无人机立体视觉识别船舶航行风险仿真

由于船舶交通受碰撞、搁浅、走锚等随机干扰因素的影响,导致对船舶航行目标的跟踪与风险预警具有较大难度。为增强海上航行的安全性,提出一种基于无人机立体视觉的船舶航行风险识别方法。引入双目视觉立体技术,获得目标船舶在航行过程中的图像数据。利用卡尔曼预测器优化连续性自适应均值漂移算法,跟踪目标船舶,通过高斯混合模型识别船舶航行风险。实验结果表明,研究方法对不同海域的船舶跟踪曲线与船舶实际航行曲线具有较高拟合度,且上述方法的船舶航行风险识别正确率高于90%,且误报率低于0.2%,说明提出方法的应用可靠性较高。

基于主成分分析和VU分解法的两步随机相移算法

为了平衡相位计算的精度和速度,大量的两步随机相移算法发展起来。提出了一种基于主成分分析和VU分解法的快速、高精度两步随机相移算法。首先,采用两步主成分分析法对经过滤波的两幅相移干涉图进行计算求出迭代初始相位;然后,利用没有滤波的两幅相移干涉图进行VU分解、迭代求出最终相位。通过模拟和实验结果对比表明:与四种性能良好的两步随机相移算法相比,对于不同的条纹类型、噪声、相移值及条纹数量,提出的算法综合性能最好,其精度最高,有效相移范围和有效条纹数量范围最大,当干涉图像素数为401 pixel×401 pixel时,提出的算法仅比格兰-施密特正交化法和两步主成分分析法多花费0.035 s。在理想情况下,提出的算法可以得到完全正确的结果。如果需要得到较高精度,最好能够提前抑制噪声,同时设置相移值远离0和π,条纹数量大于2。主成分分析和VU分解法无需滤波,花费近似非迭代算法的时间获得迭代算法的精度,其打破了迭代算法花费时间较多的限制,适合高精度光学在线检测,有广泛的发展前景。

双模三维索引调制差分混沌移位键控系统的设计及性能分析

针对传统差分混沌移位键控系统速率低、误码性能差的问题,提出了一种双模三维索引调制差分混沌移位键控系统。该系统利用时隙、正交码和顺序索引,在选中与未选中的时隙上均传输信息比特。在接收端,通过采用降噪技术,减小了噪声的方差,提升了系统误码性能。推导了在加性白高斯噪声信道和多径瑞利衰落信道下的比特差错率公式。仿真结果显示,与相似的混沌键控系统相比,所提系统具备更高的数据速率和更为优越的误码性能。

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。