利用高斯混合模型的SAR图像目标CFAR检测新方法

SAR（合成孔径雷达）图像杂波分布模型种类繁多且对实际地物的建模能力有限。在使用基于杂波统计模型的CFAR(恒虚警率)算法对SAR图像进行目标检测时,杂波统计模型的失配会导致检测结果产生较大的CFAR损失,算法精度不高。提出了一种基于高斯混合模型的CFAR检测新方法。该方法以理论上可以拟合任意形状概率密度分布的高斯混合模型对实际SAR图像的背景杂波进行拟合,利用拟合后得到的分布模型,根据CFAR检测的原理推导出目标检测阈值的计算公式完成目标的检测。新方法对服从不同分布模型的背景杂波,使用形式上统一的模型进行描述,克服了CFAR检测高度依赖背景杂波分布的缺点,提高了CFAR的通用性。实验结果表明,即使在背景杂波类型未知的情况下,新方法依然得到了良好的目标检测效果。     

Scene-specific pedestrian detection based on transfer learning and saliency detection for video surveillance

Pedestrian detection is a fundamental problem in video surveillance and has achieved great progress in recent years. However the performance of a generic pedestrian detector trained on some public datasets drops significantly when it is applied to some specific scenes due to the difference between source training samples and pedestrian samples in target scenes. We propose a novel transfer learning framework, which automatically transfers a generic detector to a scene-specific pedestrian detector without manually labeling training samples from target scenes. In our method, we get initial detected results and several cues are used to filter target templates whose labels we are sure about from the initial detected results. Gaussian mixture model (GMM) is used to get the motion areas in each video frame and some other target samples. The relevancy between target samples and target templates and the relevancy between source samples and target templates are estimated by sparse coding and later used to calculate the weights for source samples and target samples. Saliency detection is an essential work before the relevancy computing between source samples and target templates for eliminating interference of non-salient region. We demonstrate the effectiveness of our scene-specific detector on a public dataset, and compare with the generic detector. Detection rates improves significantly, and also it is comparable with the detector trained by a lot of manually labeled samples from the target scene.     

Pearson-based mixture model for color object tracking

To track objects in video sequences, many studies have been done to characterize the target with respect to its color distribution. Most often, the Gaussian mixture model (GMM) is used to represent the object color density. In this paper, we propose to extend the normality assumption to more general families of distributions issued from the Pearson’s system. Precisely, we propose a method called Pearson mixture model (PMM), used in conjunction with Gaussian copula, which is dynamically updated to adapt itself to the appearance change of the object during the sequence. This model is combined with Kalman filtering to predict the position of the object in the next frame. Experimental results on gray-level and color video sequences show tracking improvements compared to classical GMM. Especially, the PMM seems robust to illumination variations, pose and scale changes, and also to partial occlusions, but its computing time is higher than the computing time of GMM.     

基于位置和速度的点状运动目标Bayes跟踪

采用结合概率数据关联的卡尔曼滤波方法,研究一种基于位置、速度信息的微弱点动目标Bayes跟踪技术。其关键是在跟踪区域检测时,检测器以Basyes模式进行工作,检测门限随目标先验概率比变化。提出一种新的门限计算方法。与基于恒虚警概率准则的跟踪技术相比,跟踪过程中检测到的虚警目标明显减少,仿真结果验证了该算法的实时性与精确性。     

一种多目标环境下的SAR图像自适应CFAR检测方法

多数CFAR检测器在多目标检测环境下需要关于干扰目标的先验信息,当检测环境发生变化时,这些检测器很难维持稳定的检测性能。针对多目标环境下的SAR图像目标检测,提出一种新的自适应CFAR（恒虚警）检测器。该检测器利用局部的杂波功率水平估计以及目标和杂波的方差特征筛选出参考窗中的均匀杂波像素,同时剔除掉干扰目标像素;在筛选过程中,每一步使用的判决门限根据上一步的判决结果自动更新;最后对筛选出的样本点作单元平均处理形成检验统计量;完全不需要干扰目标的任何先验信息。利用实测数据仿真研究了该检测器的检测性能与运行效率,实验结果表明,相对单元平均CFAR检测器及有序统计量CFAR检测器,该检测器提高了检测性能,保留了目标精细的结构特征,而运行效率与有序统计量CFAR检测器相当,很具实用性。     

基于SAR图像目标检测的优化CFAR检测器算法研究

在目前的SAR目标检测中CFAR检测器被广泛的应用,而对相同或不同分辨率的图像,优化的CFAR检测器可以作为无偏检测。本文对优化的CFAR．检测器进行了研究。     

基于GLRT的光学卫星遥感图像舰船目标检测

传统的CFAR检测应用到光学卫星遥感图像舰船目标检测中时不能对黑极性目标进行判断,针对此提出改进的基于广义似然比检验(Generalized Likelihood Ratio Test,GLRT)的舰船目标检测算法。该算法采用滑动窗口检测形式,在假设背景和目标灰度均服从高斯分布的前提下,通过GLRT判断背景窗口与目标窗口是否同分布来检测目标,兼顾了目标黑白两种极性的情况。算法实现中对图像进行了分块检测,并通过形态学处理对检测结果进行了目标聚类。采用SPOT5与CBERS实测数据进行实验,验证了海背景服从高斯分布的假设。典型数据检测结果表明,该算法可以检测黑极性目标,且相比CFAR虚警率更低,大量数据计算ROC曲线的结果以及比CFAR检测少约40%的耗时进一步表明该算法性能更优。     

基于CUDA的多信道锋电位实时分类方法

为提高多信道神经元锋电位分类任务的计算效率,满足其在实时场景下的应用需求,提出基于统一计算设备架构(compute unified device architecture,CUDA)的掩蔽高斯混合模型的并行化实现和优化方案。利用高维锋电位数据的稀疏特性和高斯混合模型的强抗干扰性以及良好并行性,借助GPU图形处理器,对特征掩蔽高斯混合模型(Masked Gaussian mixture model,Masked GMM)进行并行实现,进行针对性优化。实验结果表明,在32信道的锋电位数据集上,与原有的CPU串行实现相比,该方案分类速度提高了170倍左右,达到了实时计算,为高维信道锋电位实时分类提供了可行的解决方案。     

基于混合高斯模型的窄带目标跟踪方法

基于混合高斯模型的轨迹分布融合方法适用于窄带目标跟踪系统.这种算法针对宽带跟踪结果的不精确,目标模糊,窄带跟踪需要依赖人工实现的问题,提出了一种基于混合高斯模型的自动窄带目标跟踪技术.该方法首先将目标方位分布看做是混合高斯模型,利用期望最大化算法估计混合高斯模型中的参数,然后利用混合高斯模型对目标方位进行聚类,最后利用平均加权法对目标方位进行融合,得到清晰稳定的目标跟踪结果.     

Target detection algorithm for dance moving images based on sensor and motion capture data

The effectiveness of classification based on motion capture data to identify the human skeleton dance types. The goal is based on the body joint's information is to perform the characteristic posture obtained by the ultra-high Kinect sensor, identifying for each dance. The proposed Target Detection (TD) algorithm is used to dance moving object identification based on the improved Gaussian Mixture Model (GMM). The proposed Target Detection (TD) algorithm based on a Gaussian Mixture Model is a widely used method for modeling background from a Kinect sensor moving objects. The used data set contains six folk dance sequences and their variations. Gesture recognition scheme using a plurality of time constraints, spatial information, and spatial distribution characteristics to create a training data set appropriate application. The Gaussian Mixed Model distribution background model account, the algorithm, and their frame difference can be extracted in straight lines to obtain target dance areas with less background and background photo station under motor damage conditions. Through real-time Target Detection (TD) algorithm dance moving images based on the Gaussian Mixture Model (GMM), these two algorithms effectively detect dance moving image targets.     

一种基于自适应背景杂波模型的宽幅SAR图像CFAR舰船检测算法

利用海洋宽幅SAR图像进行大范围海域舰船检测在海洋监视、军事侦察等方面具有重要应用。由于海况的复杂性,宽幅SAR图像背景杂波特性随海域不同而变化。采用双参数CFAR检测算法和基于K分布CFAR检测算法在处理宽幅SAR图像时,由于在待检测的所有区域采用同种背景杂波模型,导致使用的杂波模型在不适应区域失配,使CFAR检测性能下降。针对这个问题,提出了一种基于自适应背景杂波模型的CFAR宽幅SAR图像舰船检测算法,该算法通过背景窗口的多尺度统计方差判断目标所处的杂波环境,自适应选择对应的背景杂波分布模型,最后根据已知的恒虚警率及选择的杂波概率密度函数进行CFAR检测。对20多幅宽幅SAR图像进行了试验,实验结果表明:该算法在检测精度上有明显的改善。     

免锚检测的行人多目标跟踪算法

针对复杂环境下行人目标因检测器漏检和频繁遮挡而导致的数据关联不正确、跟踪实时性差的问题,提出了一种基于免锚检测的多目标跟踪算法.算法采用预测目标中心点热力图的方法实现目标检测定位,改善了因锚点框回归歧义所导致的漏检问题.同时在检测模型中嵌入深度表观特征提取分支,构建联合检测与跟踪的多任务网络用于提升实时性.为解决跟踪阶...     

基于NSCT 的自适应乘性水印局部最优非线性盲检测算法

图像水印算法研究是多媒体技术领域中的重要议题。比较并结合当前两类主流的 图像水印算法,提出了一种基于非下采样Contourlet 变换的自适应乘性水印算法。借鉴Barni 的“pixel-wise masking”模型和冗余小波域掩盖效应建模的做法,建立非下采样Contourlet 变换域 掩盖效应计算模型。用广义高斯分布模型和Cauchy 分布模型描述非下采样Contourlet 变换系数 的统计特性,将水印的检测问题表述为一个复合假设检验。通过理论推导分别建立了乘性水印 的两种局部最优非线性盲检测器及检测门限的自适应确定方法。实验结果表明,非下采样 Contourlet 变换域掩盖效应计算模型使得水印嵌入算法具有良好的视觉不可见性,两种检测器在 无原始图像和自适应嵌入强度系数参与检测的情况下均能准确地检测到水印信息的存在。实验 结果同时显示,基于Cauchy 分布的盲检测器在检测效果和检测时间方面优于基于广义高斯分 布的盲检测器。     

基于贝叶斯通用背景模型的图像标注

在高斯图特征提取过程中,通用背景模型(Universal background model, UBM) 方法常用于根据总体分布估计每一幅图像中特征点分布的高斯混合模型(Gaussian mixture model, GMM)参数. 然而UBM估计的GMM权重参数中有很多接近零的数值,它们所对应的高斯分量对分布估计贡献小却又都参与了计算, 因此UBM的时间复杂度较高. 为解决这个问题,本文提出Bayes UBM方法. 通过引入受限的对称Dirichlet分布来描述GMM权重参数的先验分布,利用Bayes最大后验概率对GMM参数集进行估计. 实验表明Bayes UBM方法不仅有效地降低了时间复杂度,而且提高了Corel数据集上的图像标注精度.     

基于改进的YOLO与GMM相结合的地铁行人检测算法

针对目前已有的行人检测算法存在的误检率高、实时性差等问题,首先基于Yolov3-tiny网络模型进行算法改进,提出一种Ped-tiny网络模型。通过采用深度可分离卷积层替代部分原始网络中的传统卷积层来适当加深特征提取网络,同时增加一尺度的预测层,保证各个尺度的行人目标被精准检测到;其次结合GMM(混合高斯模型)的运动目标检测算法,该算法能有效利用目标运动时所产生的运动信息对行人目标进行检测、定位;最后将两算法的目标框进行对比,并对目标框进行修正。实验结果表明,在应对不同地铁场景、不同行人姿态和不同遮挡等情况时,文中方法具有更低的误检率,更高的检测精度并能满足检测的实时性要求。     

改进多层尺度特征融合的目标检测算法

为提高小目标检测任务的准确率和稳定性,解决SSD(single shot MultiBox detector)算法在小目标识别和定位过程中准确率较低的问题,基于SSD算法提出一种改进方法.在原始的SSD卷积网络结构上进行修改和优化,通过特征图之间的特征融合,重构卷积预测特征图上的物体特征信息.考虑到网络复杂度增加带来的...     

基于颜色和纹理特征的伪装色矿工目标检测

针对矿井下某些地段低光照低对比度导致矿工目标与环境颜色相似,呈现伪装色特点,一般场景目标检测方法易产生矿工漏检、误检的问题,提出了采用高斯混合模型(GMM)和局部二值模式(LBP)纹理模型线性融合的方法对目标矿工进行检测。首先利用高斯混合模型拟合背景颜色信息,然后通过局部二值模式纹理模型提取图像纹理信息,最后将颜色信息和纹理信息线性融合对矿工进行检测。实验结果表明,在满足实时性的同时,减少了矿工目标出现漏检、误检的问题,该方法可对具有伪装色特征的矿工目标进行实时检测,准确性高。     

Multiple Speaker Tracking and Detection: Handset Normalization and Duration Scoring

Sönmez, Kemal, Heck, Larry, and Weintraub, Mitchel, Multiple Speaker Tracking and Detection: Handset Normalization and Duration Scoring, Digital Signal Processing10(2000), 133–142.We describe SRI's speaker tracking and detection system in the NIST 1998 Speaker Detection and Tracking Development Evaluation. The system is designed for tracking switchboard conversations and uses a two-speaker and silence hidden Markov model (HMM) with a minimum state duration constraint and Gaussian mixture model (GMM) state distributions adapted from a single gender- and handset-independent imposter model distribution. Speaker tracking is used to segment waveforms for speaker detection, which is carried out by averaging frame scores of the Viterbi path and normalizing for handset variation via a novel parameter interpolation extension of HNORM for use with waveform segments of arbitrary lengths. A short-duration penalty to augment the acoustic scores is also introduced via a nonlinear combination function. Results on the NIST 1998 Speaker Detection and Tracking Development Evaluation dataset are reported.     

Gaussian mixture spline trajectory: learning from a dataset,generating trajectories without one

Most optimization-based motion planners use a naive linear initialization, which does not use previous planning experience. We present an algorithm called ‘Gaussian mixture spline trajectory’ (GMST) that leverages motion datasets for generating trajectories for new planning problems. Unlike other trajectory prediction algorithms, our method does not retrieve trajectories from a dataset. Instead, it first uses a Gaussian mixture model (GMM) to modelize the likelihood of the trajectories to be inside the dataset and then uses the GMM's parameters to generate new trajectories. As the use of the dataset is restricted only to the learning phase it can take advantage of very large datasets. Using both abstract and robot system planning problems, we show that the GMST algorithm decreases the computation time and number of iterations of optimization-based planners while increasing their success rates as compared to that obtained with linear initialization.     

An adaptive cell averaging-based CFAR detector for interfering targets and clutter-edge situations

In practice, there are two common situations when the independent and identically distributed (IID) assumption no longer holds: (i) there is a clutter edge and (ii) there is an outlier, e.g., a clutter spike, an impulsive interference, or another interfering target. These can result in masking of weaker targets near stronger ones and excessive false alarms at clutter edge transitions. In this paper, a new constant false alarm (CFAR) detector is proposed, which uses a goodness of fit test to verify the IID assumption. If it is decided that the data in the reference window is IID, the cell averaging (CA)-detector is applied. Otherwise, a range-heterogeneous detection algorithm is applied to provide homogeneous samples to develop a CA-based detector. The performance study shows that the proposed detector performs like the CA detector in the homogeneous situation and outperforms other competing CFAR detectors in heterogeneous situations caused by multiple targets and clutter edge.