Moving Target Detection and Tracking for Smartphone Automatic Focusing

In this paper,a non-contact auto-focusing method is proposed for the essential function of auto-focusing in mobile devices.Firstly,we introduce an effective target detection method combining the 3-frame difference algorithm and Gauss mixture model,which is robust for complex and changing background.Secondly,a stable tracking method is proposed using the local binary patter feature and camshift tracker.Auto-focusing is achieved by using the coordinate obtained during the detection and tracking procedure.Experiments show that the proposed method can deal with complex and changing background.When there exist multiple moving objects,the proposed method also has good detection and tracking performance.The proposed method implements high efficiency,which means it can be easily used in real mobile device systems.

Application of Road Information in Ground Moving Target Tracking

A new algorithm is developed to achieve accurate state estimation in ground moving target tracking by means of using road information. It is an adaptive variable structure interacting multiple model estimator with dynamic models modification （DMM VS-IMM for short）. Firstly, road information is employed to modify the target dynamic models used by filter, including modification of state transition matrix and process noise. Secondly, road information is applied to update the model set of a VS-IMM estimator. Predicted state estimation and road information are used to locate the target in the road network on which the model set is updated and finally IMM filtering is implemented. As compared with traditional methods, the accuracy of state estimation is improved for target moving not only on a single road, but also through an intersection. Monte Carlo simulation demonstrates the efficiency and robustness of the proposed algorithm with moderate computational loads.

Dynamic Target Detection and Tracking Based on Quantum Illumination LIDAR

In the detection process of classic radars such as radar/lidar,the detection performance will be weakened due to the presence of background noise and loss.The quantum illumination protocol can use the spatial correlation between photon pairs to improve image quality and enhance radar detection performance,even in the presence of loss and noise.Based on this quantum illumination LIDAR,a theoretic scheme is developed for the detection and tracking of moving targets,and the trajectory of the object is analyzed.Illuminated by the quantum light source as Spontaneous Parametric Down-Conversion(SPDC),an opaque target can be identified from the background in the presence of strong noise.The static objects obtained by classical and quantum illumination are compared,respectively,and the advantages of quantum illumination are verified.The moving objects are taken at appropriate intervals to obtain the images of the moving objects,then the images are visualized as dynamic images,and the three-frame difference method is used to obtain the target contour.Finally,the image is performed by a series of processing on to obtain the trajectory of the target object.Several different motion situations are analyzed separately,and compared with the set object motion trajectory,which proves the effectiveness of the scheme.This scheme has potential practical application value.

RADAR HRR PROFILING FOR GROUND MOVING TARGET USING PHASE-CODED AND HOPPED-FREQUENCY WAVEFORMS

To obtain the radar High Range Resolution (HRR) profile of the slowly moving ground target in strong clutter background, the Phase-Coded Hopped-Frequency (PCHF) waveform is proposed. By multiple-bursts coherent processing, the HRR profile synthesis, target velocity compensation and clutter compression can be accomplished simultaneously. The new waveform is shown to have good ability to suppress ground clutter and good Electronic Counter-CounterMeasures (ECCM) ability as well. The clutter compression performance of the proposed method is verified by the numerical results.

Target location with signal fitting and sub-aperture tracking for airborne multi-channel radar

The location of a moving target based on signal fitting and sub-aperture tracking from an airborne multi-channel radar is dealt with.The proposed approach is applied in two steps：first,the ambiguous slant-range velocity is derived with a modified single-snapshot multiple direction of arrival estimation method,and second,the unambiguous slant-range velocity is found using a track-based criterion.The prominent advantage of the proposed approach is that the unambiguous slant-range velocity can be very large.Besides,the first stage is carried out at the determinate range-Doppler test cell by azimuth searching for fitting best to the moving target signal,therefore,the location performance would not be sacrificed in order to suppress clutter and/or interference.The effectiveness and efficiency of the proposed method are validated with a set of airborne experimental data.

Small tracking error correction for moving targets of intelligent electro-optical detection systems

Small tracking error correction for electro-optical systems is essential to improve the tracking precision of future mechanical and defense technology.Aerial threats,such as“low,slow,and small(LSS)”moving targets,pose increasing challenges to society.The core goal of this work is to address the issues,such as small tracking error correction and aiming control,of electro-optical detection systems by using mechatronics drive modeling,composite velocity–image stability control,and improved interpolation filter design.A tracking controller delay prediction method for moving targets is proposed based on the Euler transformation model of a two-axis,two-gimbal cantilever beam coaxial configuration.Small tracking error formation is analyzed in detail to reveal the scientific mechanism of composite control between the tracking controller’s feedback and the motor’s velocity–stability loop.An improved segmental interpolation filtering algorithm is established by combining line of sight(LOS)position correction and multivariable typical tracking fault diagnosis.Then,a platform with 2 degrees of freedom is used to test the system.An LSS moving target shooting object with a tracking distance of S=100 m,target board area of A=1 m^(2),and target linear velocity of v=5 m/s is simulated.Results show that the optimal method’s distribution probability of the tracking error in a circle with a radius of 1 mrad is 66.7%,and that of the traditional method is 41.6%.Compared with the LOS shooting accuracy of the traditional method,the LOS shooting accuracy of the optimized method is improved by 37.6%.

METHOD OF MULTI-TARGET TRACKING IN WIDE AREA SURVEILLANCE AIRBORNE RADAR SYSTEM BASING ON CLUSTERING ANALYSIS

This paper proposed a robust method based on the definition of Mahalanobis distance to track ground moving target. The feature and the geometry of airborne ground moving target tracking systems are studied at first. Based on this feature, the assignment relation of time-nearby target is calculated via Mahalanobis distance, and then the corresponding transformation formula is deduced. The simulation results show the correctness and effectiveness of the proposed method.

Highly robust ground moving target detection and relocation method for distributed satellites

The performance of ground moving target detection for distributed satellites will be affected signifi-cantly when there is an image registration error,clutter decorrelation and array error.In this paper,a new approach to moving target detection and relocation is proposed based on multi-channel and multi-pixel adap-tive signal processing in an image domain.First,multi-channel and multi-pixel joint data are equated to a simple array model.Given that there is an image registration error,the real steering vector of the moving target can be estimated through a space projection approach.The optimal beam forming approach is used to cancel clutter,and at the same time the cross-track velocity of the mov-ing target can be determined by searching for the peak value of the cost function.The moving target can then be relocated on the SAR image.The simulation results indicate that this method has a good robustness to image registration error,clutter decorrelation and array error.The detection performance and the estimation accuracy are significantly improved.

Ground Moving Target Tracking with VS-IMM Using Mean Shift Unscented Particle Filter

In order to track ground moving target, a variable structure interacting multiple model （VS-IMM） using mean shift unscented particle filter （MS-UPF） is proposed in this paper. In model-conditioned filtering, sample particles obtained from the unscented particle filter are moved towards the maximal posterior density estimation of the target state through mean shift. On the basis of stop model in VS-IMM, hide model is proposed. Once the target is obscured by terrain, the prediction at prior time is used instead of the measurement at posterior time; in addition, the road model set used is not changed. A ground moving target indication （GMTI） radar is employed in three common simulation scenarios of ground target： entering or leaving a road, crossing a junction and no measurement. Two evaluation indexes, root mean square error （RMSE） and average normalized estimation error squared （ANEES）, are used. The results indicate that when the road on which the target moving changes, the tracking accuracy is effectively improved in the proposed algorithm. Moreover, track interruption could be avoided if the target is moving too slowly or masked by terrain.

Target detection method for moving cows based on background subtraction

Target detection is the fundamental work for perceiving the behavior of cows using video analysis automatically.The videos captured in farming scenes often suffer from a complex background,which leads to difficulty in detecting the target and inconvenience in the subsequent images analysis.In this study,a method was proposed to detect the moving target accurately for cows based on background subtraction.Firstly,the bounding rectangle of cows was calculated using the frames difference method to extract the local background in frames,which were averaged and spliced into one image as the entire background image.Secondly,the size and location of a cow’s body were determined by the bounding rectangle of cows,and the body area was tracked through the video by the binary images.Thirdly,the summation coefficients on RGB channels were adjusted to improve the contrast between the target and background images.Finally,taking the body area in every frame as reference area,the performance of target detection was evaluated by the reference area to determine the optimal summation coefficients on RGB channels,and then background subtraction was processed again to finish the detection.A total of 129 videos were used to test the detection algorithm,and the accuracy of the algorithm was 88.34%,which was 24.85%higher than the classical background subtraction method.The study shows that the algorithm proposed in this study is feasible to detect the target accurately and timely when cows are walking straight in the farming environment under natural light,and this method can improve the detection performance and is an extension to the classical background subtraction method.

基于精确背景运动补偿的机器人运动目标检测与跟踪

为实现动态场景下机器人快速准确地检测与跟踪运动目标,提出一种基于精确背景补偿的运动目标检测方法,并利用Kalman滤波扩展的KCF算法进行目标跟踪。针对传统ORB算法存在特征点分布不均匀、误匹配率高导致背景补偿效果不佳的问题,采用小波变换及图像分块处理保证提取的特征点数目及均匀分布,通过SURF算法提取具有尺度不变性的特征点并构建ORB描述子。利用KNN算法与对称约束相结合的特征匹配法提高匹配精度,同时引入改进的RANSAC方法精确求解全局运动参数完成背景运动补偿,最后通过帧差法及形态学处理获得完整的运动目标,并将KCF算法融合Kalman滤波实现对被遮挡目标进行再跟踪。实验结果表明:该方法特征匹配正确率达到98.4%,在背景运动状态下能够实时准确地检测出运动目标,并且能够连续稳定地跟踪目标。

High-speed ground moving target detection research using triangular modulation FMCW

The frequency modulated continuous wave(FMCW)radar has the characteristics of low probability of interception,good hidden property and the ability to counter anti-radiation missiles.This paper proposes a new method for high-speed ground moving target detection(GMTD)using triangular modulation FMCW.According to the characteristic of the opposite range shift induced by the upslope and downslope modulation FMCW,the upslope and downslope are imaged,respectively.After compensation of continuous motion of the platform and time difference between upslope and downslope signals for imaging,the moving target can be detected through displaced phase center antenna(DPCA)technology.When the moving target is detected,the moving target image is extracted,and correlation processing is used to obtain the range shift,which can be used to estimate the target radial velocity,and further to find the real position of the target.The effectiveness of this method is verified by the result of computer simulation.

基于激光跟踪小空间搜索的运动轨迹生成方法

以实时跟踪监控多个运动目标为出发点,提出基于激光跟踪小空间搜索的运动轨迹生成方法。激光跟踪测距仪以采集到的激光点和运动目标像素坐标为依据,构建激光自主瞄准模式瞄准运动目标,引导激光靠近运动目标并缩短二者间距离,利用激光跟踪测距仪的小空间搜索性能确定运动目标质心,实现运动目标精准定位检测;采用均值漂移粒子滤波跟踪算法,以检测所得的运动目标位置作为初始粒子跟踪运动目标,获取运动目标跟踪效果图;结合轨迹生成模块,生成运动目标轨迹。实际应用结果表明,检测及跟踪多个运动目标时,准确性高,且生成运动目标轨迹完整且与实际运动轨迹一致,生成结果准确无遗漏可达100%,检测目标车辆的时间均在2.5 s以下,分别低于文献方法2.5 s和1.9 s,降低了检测时间,并且具备性能稳定、实用性强优势。

基于卷积神经网络的动目标检测

合成孔径雷达(SAR)动目标检测技术是雷达信号处理领域中的重要技术。文中利用深度学习高维特征提取能力,提出了一种基于卷积神经网络(CNN)的多通道SAR地面动目标检测算法,并针对雷达实测数据较少、动目标样本难以获得的问题,提出了基于仿真-实测混合样本集的网络训练方法完成网络的高精度训练。实测数据检测结果表明,此类方法能够有效地完成地面动目标检测,与传统动目标检测方法相比,具有显著的优势。

机载多通道广角凝视SAR地面动目标指示技术研究

机载广角凝视合成孔径雷达(WasSAR)是一种可对观测区域实施多角度长时间凝视成像探测的新兴SAR成像技术。将机载WasSAR成像与地面运动目标指示(GMTI)技术相结合,则可对重点区域内出现的地面运动目标实施持续成像跟踪监视,从而获取准确的动态感知信息。该文首先建立了机载多通道WasSAR动目标回波模型,分析了WasSAR动目标特性;然后,通过采用偏移相位校正和改进二维自适应校正方法,消除了载机姿态误差与通道非均衡的影响;在此基础上,提出了机载多通道Was SAR动目标检测跟踪算法,实现了复杂路况上行驶动目标的准确检测与跟踪;最后,提出了机载多通道WasSAR动目标行驶轨迹重构算法,实现了起伏路面下的动目标行驶轨迹精确重构。此外,该文中给出了作者团队利用自主研制机载多通道WasSAR-GMTI系统开展的外场飞行试验和实测数据处理结果,验证了地面运动目标持续跟踪监视的有效性和实用性,为后续开展更加深入的研究提供基础。

基于截获因子评价的双基地面动目标指示LPI探测设计

电子战装备的无源探测对作战飞机的生存构成严重威胁。地面动目标指示作为机载雷达的重要功能,亟需提升其抗截获能力。结合双基雷达低截获特征,提出了基于截获因子评价的双基机载雷达地面动目标指示低截获探测设计方法。针对双基机载雷达地面动目标指示,简要分析了距离分辨率、最小可检测速度,推导了截获因子表达式,在满足探测性能前提下,设计了基于截获因子评价的低截获探测方法。仿真结果表明,所提出的方法能明显提升机载火控雷达地面动目标指示功能的抗截获性能。

反无人机视觉检测与跟踪技术进展分析

为应对无人机“黑飞”“滥飞”等对国防和公共安全造成的巨大威胁,反无人机技术研究成为当前迫切的现实需求。首先,对比分析雷达、无线电、声音、机器视觉4类典型的反无人机检测技术;其次,重点针对反无人机的视觉检测与跟踪技术,从目标检测、无人机识别、无人机跟踪等角度,详细分析视觉检测与跟踪关键技术的优势与不足,以及各项技术在反无人机检测跟踪中的应用情况及改进策略;最后,探讨应用中较为突出的检测精度、跟踪遮挡、实时性、数据集收集标准、多技术融合5个方面问题和发展趋势,为相关技术研究提供参考。

星载SAR-GMTI系统目标定位误差概率分析方法

本文研究了星载运动目标检测(Ground Moving Target Indication,GMTI)系统中的目标定位问题。首先,采用几何向量法解释GMTI系统同时实现杂波相消和目标定位的基本原理。然后,基于高斯白噪声假设,推导了干涉相位误差的概率密度函数,该函数描述了目标定位精度与目标信噪比(Signal-to-Noise Ratio,SNR)和基线之间的关系。应用推导的概率密度函数,对现有的几个星载SAR-GMTI系统的目标定位性能进行分析比较,分析了基线误差对定位性能的影响。仿真结果验证了提出的概率密度函数的有效性。

运动弱小目标先跟踪后检测技术的研究进展

对低信噪比下图像序列运动小目标先跟踪后检测技术进行了较为系统地研究。首先针对运动弱小目标检测问题,分析比较了先检测后跟踪技术与先跟踪后检测技术;详细阐述了先跟踪后检测技术的主流算法,包括时空域匹配滤波器、基于投影变换与三维匹配滤波相结合的算法、多阶假设检验、动态规划算法、高阶相关方法、递推贝叶斯滤波等算法,并比较了其中几种算法。

复杂环境下多无人机协作式地面移动目标跟踪

针对多无人机(UAV)协同地面移动目标跟踪问题展开研究.提出一种基于主动感知的问题求解框架,建立多UAV协同目标跟踪问题模型;在此基础上,采用分布式无色信息滤波实现目标状态融合估计与预测;然后,基于预测目标状态,结合滚动时域控制与遗传算法设计一种多UAV在线协同航迹规划算法.仿真结果表明:结合预测目标状态在线优化UAV航迹能够获得更好的目标跟踪性能.