Target detection based on a dynamic subspace

For hyperspectral target detection, it is usually the case that only part of the targets pixels can be used as target signatures, so can we use them to construct the most proper background subspace for detecting all the probable targets? In this paper, a dynamic subspace detection (DSD) method which establishes a multiple detection framework is proposed. In each detection procedure, blocks of pixels are calculated by the random selection and the succeeding detection performance distribution analysis. Manifold analysis is further used to eliminate the probable anomalous pixels and purify the subspace datasets, and the remaining pixels construct the subspace for each detection procedure. The final detection results are then enhanced by the fusion of target occurrence frequencies in all the detection procedures. Experiments with both synthetic and real hyperspectral images (HSI) evaluate the validation of our proposed DSD method by using several different state-of-the-art methods as the basic detectors. With several other single detectors and multiple detection methods as comparable methods, improved receiver operating characteristic curves and better separability between targets and backgrounds by the DSD methods are illustrated. The DSD methods also perform well with the covariance-based detectors, showing their efficiency in selecting covariance information for detection.     

Hybrid detectors for subpixel targets

Subpixel detection is a challenging problem in hyperspectral imagery analysis. Since the target size is smaller than the size of a pixel, detection algorithms must rely solely on spectral information. A number of different algorithms have been developed over the years to accomplish this task, but most detectors have taken either a purely statistical or a physics-based approach to the problem. We present two new hybrid detectors that take advantage of these approaches by modeling the background using both physics and statistics. Results demonstrate improved performance over the well known AMSD and ACE subpixel algorithms in experiments that include multiple targets, images, and area types--especially when dealing with weak targets in complex backgrounds.     

结合孪生网络和像素配对的高光谱图像异常检测

目的 高光谱遥感中,通常利用像素的光谱特征来区分背景地物和异常目标,即通过二者之间的光谱差异来寻找图像中的异常像元。但传统的异常检测算法并未有效挖掘光谱的深层特征,高光谱图像中丰富的光谱信息没有被充分利用。针对这一问题,本文提出结合孪生神经网络和像素配对策略的高光谱图像异常检测方法,利用深度学习技术提取高光谱图像的深层非线性特征,提高异常检测精度。方法 采用像素配对的思想构建训练样本,与原始数据集相比,配对得到的新数据集数量呈指数增长,从而满足深度网络对数据集数量的需求。搭建含有特征提取模块和特征处理模块的孪生网络模型,其中,特征处理模块中的卷积层可以专注于提取像素对之间的差异特征,随后利用新的训练像素对数据集进行训练,并将训练好的分类模型固定参数,迁移至检测过程。用滑动双窗口策略对测试集进行配对处理,将测试像素对数据集送入网络模型,得到每个像素相较于周围背景像素的差异性分数,从而识别测试场景中的异常地物。结果 在异常检测的实验结果中,本文提出的孪生网络模型在San Diego数据集的两幅场景和ABU-Airport数据集的一幅场景上,得到的AUC （area under the curve）值分别为0.993 51、0.981 21和0.984 38,在3个测试集上的表现较传统方法和基于卷积神经网络的异常检测算法具有明显优势。结论 本文方法可以提取输入像素对的深层光谱特征,并根据其特征的差异性,让网络学习到二者的区分度,从而更好地赋予待测像素相对于周围背景的异常分数。本文方法相对于卷积神经网络的异常检测方法可以有效地降低虚警,与传统方法相比能够更加明显地突出异常目标,提高了检测率,同时也具有较强的鲁棒性。     

空域协同自编码器的高光谱异常检测

目的 自编码器作为一种无监督的特征提取算法,可以在无标签的条件下学习到样本的高阶、稠密特征。然而当训练集含噪声或异常时,会迫使自编码器学习这些异常样本的特征,导致性能下降。同时,自编码器应用于高光谱图像处理时,往往会忽略掉空域信息,进一步限制了自编码器的探测性能。针对上述问题,本文提出一种基于空域协同自编码器的高光谱异常检测算法。方法 利用块图模型优良的背景抑制能力从空域角度筛选用于自编码器训练的背景样本集。自编码器采用经预筛选的训练样本集进行网络参数更新,在提升对背景样本表达能力的同时避免异常样本对探测性能的影响。为进一步将空域信息融入探测结果,利用块图模型得到的异常响应构建权重,起到突出目标并抑制背景的作用。结果 实验在3组不同尺寸的高光谱数据集上与5种代表性的高光谱异常检测算法进行比较。本文方法在3组数据集上的AUC(area under the curve)值分别为0.990 4、0.988 8和0.997 0,均高于其他算法。同时,对比了不同的训练集选择策略,与随机选取和使用全部样本进行对比。结果表明,本文基于空域响应的样本筛选方法相较对比方法具有较明显的优势。结论 提出的基...     

Random selection-based adaptive saliency-weighted RXD anomaly detection for hyperspectral imagery

With recent advances in hyperspectral imaging sensors, subtle and concealed targets that cannot be detected by multispectral imagery can be identified. The most widely used anomaly detection method is based on the Reed–Xiaoli (RX) algorithm. This unsupervised technique is preferable to supervised methods because it requires no a priori information for target detection. However, two major problems limit the performance of the RX detector (RXD). First, the background covariance matrix cannot be properly modelled because the complex background contains anomalous pixels and the images contain noise. Second, most RX-like methods use spectral information provided by data samples but ignore the spatial information of local pixels. Based on this observation, this article extends the concept of the weighted RX to develop a new approach called an adaptive saliency-weighted RXD (ASW-RXD) approach that integrates spectral and spatial image information into an RXD to improve anomaly detection performance at the pixel level. We recast the background covariance matrix and the mean vector of the RX function by multiplying them by a joint weight that in fuses spectral and local spatial information into each pixel. To better estimate the purity of the background, pixels are randomly selected from the image to represent background statistics. Experiments on two hyperspectral images showed that the proposed random selection-based ASW RXD (RSASW-RXD) approach can detect anomalies of various sizes, ranging from a few pixels to the sub-pixel level. It also yielded good performance compared with other benchmark methods.     

结合置信度加权融合与视觉注意机制的前景检测

目的 在视频前景检测中,像素级的背景减除法检测结果轮廓清晰,灵活性高。然而,基于样本一致性的像素级分类方法不能有效利用像素信息,遇到颜色伪装和出现静止前景等复杂情形时无法有效检测前景。为解决这一问题,提出一种基于置信度加权融合和视觉注意的前景检测方法。方法 通过加权融合样本的颜色置信度和纹理置信度之和判断前景,进行自适应更新样本的置信度和权值;通过划分子序列结合颜色显著性和纹理差异度构建视觉注意机制判定静止前景目标,使用更新置信度最小样本的策略保持背景模型的动态更新。结果 本文方法在CDW2014（change detection workshops 2014）和SBM-RGBD（scene background modeling red-green-blue-depth）数据集上进行检测,相较于5种主流算法,本文算法的查全率和精度相较于次好算法分别提高2.66%和1.48%,综合性能最优。结论 本文算法提高了在颜色伪装和存在静止前景等复杂情形下前景检测的精度和召回率,在公开数据集上得到更好的检测效果。可将其应用于存在颜色伪装和静止前景等复杂情形的视频监控中。     

利用深度卷积特征的无人机视觉跟踪

由于无人机视觉跟踪视角范围广且环境复杂,常遇到无人机飞行震动、目标遮挡、相似目标等问题,导致无人机跟踪目标发生漂移.因此,对具有回归计算的全卷积孪生网络跟踪算法(SiamRPN)进行改进,提出一种加强深度特征相关性的无人机视觉跟踪算法(SiamDFT).首先,将全卷积神经网络后三层卷积的网络宽度提升一倍,充分利用目标的外观信息,完成对模板帧和检测帧的特征提取;其次,在检测帧和模板帧分别提出注意力信息融合模块和特征深度卷积模块,两个深度的特征相关性计算方法能够有效抑制背景信息,增强像素对之间的关联性,高效完成分类和回归任务;然后,采用深度互相关运算完成相似性计算,并引入距离交并比的计算方法完成对目标的定位.实验结果表明, SiamDFT在无人机短时跟踪场景下精确率和成功率分别达到79.8%和58.3%,在无人机长时跟踪场景下精确率和成功率分别达到73.4%和55.2%,实景测试结果充分验证了所提出算法的有效性.     

Kernel-based regularized-angle spectral matching for target detection in hyperspectral imagery

Target detection is one of the most important applications of hyperspectral imagery in the field of both civilian and military. In this letter, we firstly propose a new spectral matching method for target detection in hyperspectral imagery, which utilizes a pre-whitening procedure and defines a regularized spectral angle between the spectra of the test sample and the targets. The regularized spectral angle, which possesses explicit geometric sense in multidimensional spectral vector space, indicates a measure to make the target detection more effective. Furthermore Kernel realization of the Angle-Regularized Spectral Matching (KAR-SM, based on kernel mapping) improves detection even more. To demonstrate the detection performance of the proposed method and its kernel version, experiments are conducted on real hyperspectral images. The experimental tests show that the proposed detector outperforms the conventional spectral matched filter and its kernel version.     

结合Faster R-CNN的多类型火焰检测

目的 火焰检测可有效防止火灾的发生。针对目前火焰检测方法,传统图像处理技术的抗干扰能力差、泛化性不强,检测效果对数据波动比较敏感;机器学习方法需要根据不同的场景设定并提取合适火焰的特征,过程比较繁琐。为此提出一种基于Faster R-CNN的多类型火焰检测方法,避免复杂的人工特征提取工作,在面对复杂背景、光照强度变化和形态多样的火焰图像时依然保证较好的检测精度。方法 基于深度学习的思想,利用卷积神经网络自动学习获取图像特征。首先,利用自建数据集构建视觉任务。根据火焰的尖角特性、直观形态和烟雾量等,将火焰类数据划分为单尖角火焰、多尖角火焰和无规则火焰3类。此外,通过深度网络特征可视化实验发现,人造光源与火焰在轮廓上具有一定的相似性,为此建立了人造光源圆形和方形两个数据集作为干扰项来保证检测模型的稳定性;然后,细化训练参数并调整预训练的卷积神经网络结构,改动分类层以满足特定视觉任务。将经过深度卷积神经网络中卷积层和池化层抽象得到的图像特征送入区域生成网络进行回归计算,利用迁移学习的策略得到每一类目标物体相应的探测器;最后,得到与视觉任务相关的目标检测模型,保存权重和偏置参数。并联各类目标物体的子探测器作为整体探测器使用,检测时输出各类探测器的分数,得分最高的视为正确检测项。结果 首先,利用训练好的各探测器与相应测试集样本进行测试,然后,再利用各类目标物的测试集来测试其他类探测器的检测效果,以此证明各探测器之间的互异性。实验结果表明,各类探测器都具有较高的专一性,大大降低了误判的可能性,对于形变剧烈和复杂背景的火焰图像也具有良好的检测准确率。训练得到的检测模型在应对小目标、多目标、形态多样、复杂背景和光照变化等检测难度较大的情况时,均能获得很好的效果,测试集结果表明各类探测器的平均准确率提高了3.03% 8.78%不等。结论 本文提出的火焰检测方法,通过挖掘火焰的直观形态特征,细分火焰类别,再利用深度卷积神经网络代替手动特征设置和提取过程,结合自建数据集和根据视觉任务修改的网络模型训练得到了检测效果良好的多类型火焰检测模型。利用深度学习的思想,避免了繁琐的人工特征提取工作,在得到较好的检测效果的同时,也保证了模型具有较强的抗干扰能力。本文为解决火焰检测问题提供了更加泛化和简洁的解决思路。     

Laser‐speckle properties and their effect on target detection

Abstract— Laser projectors are currently being developed for use in high‐fidelity wide‐field‐of‐view displays. In order to assess the effects of laser speckle on target detection, contrast thresholds as a function of target spatial frequency on both a laser‐speckle background and a uniform‐luminance field have been measured. For all spatial‐frequency targets tested, speckle increased contrast thresholds relative to those obtained on the uniform field. In addition, a power‐spectral‐density metric for characterizing laser speckle and predicting its effect on target detection has been developed. To evaluate themetric, contrast‐energy thresholds on both a laser‐speckle background and backgrounds consisting of randomly modulated pixel luminance (i.e., pixel noise) have been measured. The results of previous studies, concerned with the detection of targets in wideband noise, suggest that these thresholds should be the same when the power spectral densities of the backgrounds are equated. It was found, however, that, for the same background power spectral density, energy thresholds on pixel noise were slightly higher than those obtained with laser‐speckle noise. This small difference could be accounted for, however, by the well‐documented individual differences in the optical parameters of the eye, particularly pupil size.     

Fully Polarimetric SAR Ship Detection based onPCDM Shannon Entropy#br#

Polarimetric Synthetic Aperture Radar（PolSAR）data contains rich polarization information about the scattering properties of ground objects,having beenwidely used in maritime monitoring and objects detection.The polarization reaction differences between ship targets and sea clutters are analyzed.A ship detection method using the Shannon entropy of the Polarimetric Covariance Difference Matrix (PCDM) is proposed in this paper,which is applied to fully polarimetric SAR images.To enhance the contrast between the ship targets and sea background,the PCDM is generated by calculating the elemental differences between the polarimetric covariance matrix at each pixel and its neighbors.Then the Shannon entropy of SAR images are extracted on the basis of the Shannon entropy calculation formula,and the character difference between the ships and background in the Shannon entropy map is presented for ship detection.The false alarms in the detection result caused by the azimuth ambiguities are removed,based on the displacement distance and energy ratio relationship,between the target and azimuth ambiguity.The Radarsat\|2 Fine Quad data and the Chinese GF\|3 Quad\|Polarimetric Stripmap Ⅰ data are used,to verify the effectiveness of the proposed method,and the SPAN method,HV channel image and polarimetric whitening filter (PWF) method are applied for comparison.The detection and comparison results indicate that the proposed method is able to effectively enhance the ship\|sea contrast,and has higher detection accuracy.     

改进的基于Parzen窗算法的SAR图像目标检测

传统的Parzen窗检测算法假设目标占整个背景中较小的一部分,将SAR图像中的所有像素用于估计杂波概率密度函数,容易造成检测阈值的增大从而对不太明显的SAR图像舰船目标产生漏检。对此,提出了一种改进的Parzen窗检测算法,该算法通过自适应地设置目标窗口,将潜在的目标从检测图像中剔除,对剔除后的杂波背景采用Parzen窗进行非参数化的杂波模型估计,进而确定检测阈值,完成目标的检测。相比传统的Parzen窗检测算法,提出的SAR图像舰船目标检测算法减少了漏检数量,改善了检测性能。实测SAR图像的检测结果表明了该方法的有效性。     

融合目标增强与稀疏重构的显著性检测

目的 为了解决图像显著性检测中存在的边界模糊,检测准确度不够的问题,提出一种基于目标增强引导和稀疏重构的显著检测算法（OESR）。方法 基于超像素,首先从前景角度计算超像素的中心加权颜色空间分布图,作为前景显著图;由图像边界的超像素构建背景模板并对模板进行预处理,以优化后的背景模板作为稀疏表示的字典,计算稀疏重构误差,并利用误差传播方式进行重构误差的校正,得到背景差异图;最后,利用快速目标检测方法获取一定数量的建议窗口,由窗口的对象性得分计算目标增强系数,以此来引导两种显著图的融合,得到最终显著检测结果。结果 实验在公开数据集上与其他12种流行算法进行比较,所提算法对具有不同背景复杂度的图像能够较准确的检测出显著区域,对显著对象的提取也较为完整,并且在评价指标检测上与其他算法相比,在MSRA10k数据集上平均召回率提高4.1%,在VOC2007数据集上,平均召回率和F检验分别提高18.5%和3.1%。结论 本文提出一种新的显著检测方法,分别利用颜色分布与对比度方法构建显著图,并且在显著图融合时采用一种目标增强系数,提高了显著图的准确性。实验结果表明,本文算法能够检测出更符合视觉特性的显著区域,显著区域更加准确,适用于自然图像的显著性目标检测、目标分割或基于显著性分析的图像标注。     

SEDMI: Saliency based edge detection in multispectral images

Detecting edges in multispectral images is difficult because different spectral bands may contain different edges. Existing approaches calculate the edge strength of a pixel locally, based on the variation in intensity between this pixel and its neighbors. Thus, they often fail to detect the edges of objects embedded in background clutter or objects which appear in only some of the bands.We propose SEDMI, a method that aims to overcome this problem by considering the salient properties of edges in an image. Based on the observation that edges are rare events in the image, we recast the problem of edge detection into the problem of detecting events that have a small probability in a newly defined feature space. The feature space is constructed by the spatial gradient magnitude in all spectral channels. As edges are often confined to small, isolated clusters in this feature space, the edge strength of a pixel, or the confidence value that this pixel is an event with a small probability, can be calculated based on the size of the cluster to which it belongs.Experimental results on a number of multispectral data sets and a comparison with other methods demonstrate the robustness of the proposed method in detecting objects embedded in background clutter or appearing only in a few bands.     

运动显著性概率图提取及目标检测

目的 动态场景图像中所存在的静态目标、背景纹理等静态噪声,以及背景运动、相机抖动等动态噪声,极易导致运动目标检测误检或漏检。针对这一问题,本文提出了一种基于运动显著性概率图的目标检测方法。方法 该方法首先在时间尺度上构建包含短期运动信息和长期运动信息的构建时间序列组;然后利用TFT（temporal Fourier transform）方法计算显著性值。基于此,得到条件运动显著性概率图。接着在全概率公式指导下得到运动显著性概率图,确定前景候选像素,突出运动目标的显著性,而对背景的显著性进行抑制;最后以此为基础,对像素的空间信息进行建模,进而检测运动目标。结果 对提出的方法在3种典型的动态场景中与9种运动目标检测方法进行了性能评价。3种典型的动态场景包括静态噪声场景、动态噪声场景及动静态噪声场景。实验结果表明,在静态噪声场景中,F_score提高到92.91%,准确率提高到96.47%,假正率低至0.02%。在动态噪声场景中,F_score提高至95.52%,准确率提高到95.15%,假正率低至0.002%。而在这两种场景中,召回率指标没有取得最好的性能的原因是,本文所提方法在较好的包络目标区域的同时,在部分情况下易将部分目标区域误判为背景区域的,尤其当目标区域较小时,这种误判的比率更为明显。但是,误判的比率一直维持在较低的水平,且召回率的指标也保持在较高的值,完全能够满足于实际应用的需要,不能抵消整体性能的显著提高。另外,在动静态噪声场景中,4种指标均取得了最优的性能。因此,本文方法能有效地消除静态目标干扰,抑制背景运动和相机抖动等动态噪声,准确地检测出视频序列中的运动目标。结论 本文方法可以更好地抑制静态背景噪声和由背景变化（水波荡漾、相机抖动等）引起的动态噪声,在复杂的噪声背景下准确地检测出运动目标,提高了运动目标检测的鲁棒性和普适性。     

Small target detection using cross product based on temporal profile in infrared image sequences

This paper presents a new small target detection method using cross product of temporal pixels based on temporal profiles in infrared (IR) image sequences. Temporal characteristics of small targets and various backgrounds are different. A new algorithm classifies target pixels and background pixels through hypothesis testing using the cross product of pixels on temporal profile and predicts the temporal backgrounds based on the results. Small target pixels are detected by subtracting the predicted temporal background profile from the original temporal profile. For performance comparison between the proposed method and the conventional methods, the receiver operating characteristics (ROC) curves were computed experimentally. Experimental results show that the proposed algorithm has better discrimination of target and clutter pixels and lower false alarm rates than conventional methods.     

选煤厂智能视频监控中的运动人体目标检测方法

针对数字视频监控系统人工监视方式可能因监视人员疲劳而导致失误的问题,提出了一种选煤厂运动人体目标检测方法。该方法采用背景减除法来分割运动目标,选用混合高斯模型对背景进行建模,通过不断更新背景模型来提高运动目标检测的准确性;在准确检测出运动目标的基础上,结合人体形状信息,将人体目标检测并标记出来。实验结果表明,该方法能较准确地分割出运动人体目标,并且满足实时性要求,但是无法分割遮挡或连接在一起的运动人体目标,需进一步研究。     

Novel target segmentation and tracking based on fuzzy membership distribution for vision-based target tracking system

One of the basic processes of a vision-based target tracking system is the detection process that separates an object from the background in a given image. A novel target detection technique for suppression of the background clutter is presented that uses a predicted point that is estimated from a tracking filter. For every pixel, the three-dimensional feature that is composed of the x-position, the y-position and the gray level of its position is used for evaluating the membership value that describes the probability of whether the pixel belongs to the target or to the background. These membership values are transformed into the membership level histogram. We suggest an asymmetric Laplacian model for the membership distribution of the background pixel and determine the optimal membership value for detecting the target region using the likelihood criterion. The proposed technique is applied to several infra-red image sequences and CCD image sequences to test segmentation and tracking. The feasibility of the proposed method is verified through comparison of the experimental results with the other techniques.     

基于混合高斯模型和模板匹配的目标测速

针对目前视觉测速方法存在检测精度低、鲁棒性差的问题,研究了一种结合模板匹配和混合高斯模型的测速方法。首先,利用混合高斯模型进行背景建模,提取出仅包含目标轮廓信息的前景区域图像。其次,使用参数优化的模板匹配法获取目标的高精度像素位移。最后,使用改进的二维测量模型法精确获取目标对应的像素尺寸。利用目标物理尺寸与图像中目标像素尺寸的比例关系来计算实际速度。实验结果显示,该方法对不同形状目标在不同速度下的测速结果的相对误差均在5%以内,准确度较高。     

基于高维几何特性的高光谱异常检测算法研究

提出了一种新的高光谱图像异常检测算法。作为一种多元数据集合,高光谱数据一般呈现出共超平面的几何特性,我们利用这一特点来求取垂直于超平面的法线矢量,并将数据投影到这一法线矢量方向,从而分离出异常点,达到异常检测的目的。本算法适合于对小目标的检测,且不需要先验的光谱信息。对算法的可行性进行了仿真并将它应用于高光谱数据,取得了较好的结果。