Spatial and temporal bilateral filter for infrared small target enhancement

This paper presents a spatial and temporal bilateral filter (BF) to detect target trajectories, by extracting spatial target information using a spatial BF and temporal target information using a temporal BF. Background prediction when it is covered by targets is the key to small target detection. In order to apply the BF to a small target detection field for this purpose, this paper presents a novel spatial and temporal BF with an adaptive standard deviation to predict spatial background and temporal background profiles, based on analysis of the blocks surrounding a spatial and temporal filter window. In order to discriminate between the edge or object regions with a flat background and the target region spatially and temporally, spatial and temporal variances of the blocks surrounding the filter window are calculated in a spatial infrared (IR) image and temporal profile. The spatial and temporal variances adjust standard deviations of the spatial and temporal BF. Through this procedure, spatial background and temporal background profiles are predicted, and then small targets can be detected by subtracting the predicted spatial background (and temporal background profile) from the original IR image (and original temporal profile) and multiplying spatial and temporal target information. To compare existing target detection methods and the proposed method, signal-to-clutter ratio gain (SCRG) and background suppression factor (BSF) are employed for spatial performance comparison and receiver operating characteristics (ROC) is used for detection-performance comparison of the target trajectory. Experimental results show that the proposed method has a superior target detection rate and a lower false-alarm rate.     

An ensemble template algorithm for extracting targets from blurred infrared images

In this paper, an ensemble template algorithm is proposed to extract targets from blurred infrared images. First, the image pixels are divided according to their gray values into three pixel sets, a target set, a background set and the third set without class label. Second, the neighborhood statistical characteristics for each pixel are calculated as its template features. Third, ensemble detectors are designed using target pixels and background pixels based on their template features, and these ensemble detectors are used to detect the third pixel set. To evaluate the performance of the proposed extraction algorithm, this paper compares the ensemble template with other extraction algorithms using blurred infrared image of hand trace. Experimental results show that the ensemble template algorithm proposed in this paper exhibits better extraction performance.     

一种新的空谱联合探测高光谱影像目标探测算法

高光谱遥感影像不但具有高分辨率的空间信息还包含连续的光谱信息,因此在目标探测领域具有独特的应用优势。传统的高光谱遥感影像目标探测侧重于光谱信息的应用,形成了确定性算法和统计学算法。确定性算法通过计算目标光谱与待检测光谱之间的距离来查找目标,不能检测亚像素目标,而且容易受到噪声的影响;统计学目标检测计算背景统计特性,通过探测异常点来检测目标,可以检测亚像素目标和小目标,但容易受到目标尺寸的影响,不能很好的检测大目标。随着高光谱遥感影像的空间分辨率的增加,探测目标已有亚像素目标逐步转换为单像素及多像素目标,此时,在高光谱图像中,相同类别的地物在空间分布上呈现聚类特性, 因此,在利用高光谱遥感影像进行目标探测时,需要将其空间信息融入算法中。将空间特征引入传统目标探测算法。提出了一种新的空谱结合的高光谱目标探测算法,将传统的基于统计的目标探测算子与空域邻域聚类算法相结合,首先利用目标探测算子将影像划分为潜在目标区域与背景区域;通过计算潜在目标区域的质心,以质心为中心进行邻域聚类,剔除潜在目标区域中的背景区域,通过迭代计算获取最终目标探测结果。传统的基于统计的目标探测算子,将整个探测区域定义为背景区域,实现对背景区域的统计特征提取,而该方法将背景区域与潜在目标区域分离,剔除了目标区域对背景区域的统计干扰。将本算子与传统的约束能量最小化算子和自适应余弦探测算子进行分析比较可知,该算子的大目标探测性能优于传统的统计算子。     

Target extraction from blurred trace infrared images with a superstring galaxy template algorithm

Accurate and efficient targets extraction from blurred trace infrared images has very important meaning for latent trace evidence collection in crime scene. Based on the superstring theory, a superstring galaxy template extraction algorithm for infrared trace target is presented. First, all of the pixels are divided into three classes: target pixels, background pixels and blurred pixels. Next, the superstring template characteristics for every pixel in a blurred infrared image are calculated as the features of each pixel. Finally, a galaxy covering algorithm is proposed, target pixels and background pixels are used for training the galaxy covering domain of every galaxy classifiers, and these classifiers will divide each blurred pixel into two classes: a target pixel or a background pixel. Experimental results indicate that the superstring galaxy template algorithm can improve the target extraction rate and reduce the extraction error rate.     

一种单摄像机虚拟鼠标的标定方法

建立单摄像机虚拟鼠标的数学模型,提出一种虚拟鼠标的现场标定方法.以二维实体靶标为中介.利用计算机屏幕生成的虚拟靶标,确定摄像机坐标系到屏幕坐标系的变换.建立空间三维控制点图像坐标到鼠标指针的映射,实现了单摄像机虚拟鼠标的现场标定.提出的方法无需高成本的辅助设备,现场操作简单.在30 cm作用距离内采用640 pixel×480 pixel图像中50个特征点,当图像噪声方差达到1 pixel时,试验中控制点映射为屏幕坐标的均方根(RMS)误差小于3 pixel.该方法应用于研发的虚拟鼠标演示程序.表明切实可行,适用于虚拟鼻尖鼠标的现场标定.     

光电成像系统超分辨成像技术方法研究

提出一种提高现有光电观瞄系统成像空间分辨率的新方法.在不改变阵列探测器件像元尺寸和不移动探测器的前提下,利用双光楔的较大移动使像平面发生微小位移,实现对探测器各相邻像元和不感光间隔目标进行微位移采样,提高目标信息的采样率,通过超分辨重建技术来提高系统的分辨能力,达到提高光电观瞄系统空间分辨率的目的.实验结果表明:该方法绕开了微小位移探测器需要克服的技术难题,同时避开了直接减少像元尺寸的工艺问题,且成像分辨率高.     

Edge directional 2D LMS filter for infrared small target detection

In this paper, we introduce an edge directional 2D least mean squares (LMSs) filter for small target detection in infrared (IR) images. Generally, the 2D LMS filter functions as a background prediction to apply to IR small target detection field. In order to accurately predict background objects as well as regions covered by small targets, the proposed 2D LMS filter take full advantage of edge information of prediction pixels corresponding to surrounding blocks around current filter window. And, to adjust adaptively its step size in the background and small target region, the adaptive region-dependent nonlinear step size is calculated by using the variance of the prediction pixels of the surrounding blocks. This prediction structure and adaptive step size of the proposed 2D LMS filter is applied to the background region including objects such as cloud edge and small target region differently. Through this way, the proposed 2D LMS filter predicts the background excluding small targets. Then, by subtracting the predicted background from the original IR image, small targets can be extracted. Experimental results show that the proposed 2D LMS filter has stronger target extraction and better background suppression ability compared to the existing 2D LMS filters.     

一种新的准确提取离散采样点光谱值的方法

在建立遥感信息反演模型中,是利用离散的采样点实测数据与相应的影像对应像元的光谱值建立关系,从而实现目标信息反演。准确提取光谱值是建立模型的关键,提取光谱值通常采用的方法是把目标点图层转化为感兴趣区ROI,然后保存ROI为ASCII。用ENVI软件依据原始坐标提取采样点光谱值,分析提取的坐标和光谱值发现,提取出的部分采样点的坐标和原始坐标不一致,即光谱值非本像元,以致基于此而建立的反演模型不能真实反映目标属性与光谱值的关系,即模型无意义。我们把像元均分为4个区域,总结规律发现只有采样点落在像元左上角区域时,提取的光谱值为本像元光谱值。在上述方法的基础上,深入研究其提取目标点坐标和光谱值的原理,并总结规律。介绍了实现提取采样点在遥感影像上对应像元光谱值的一种新方法,该方法首先是提取采样点所在像元的4个顶点坐标之一,通过对比原始坐标和提取坐标的经纬度差值判断采样点在像元中分布所属区域,采用对称原则进行调整采样点在像元中分布位置,最终使全部采样点均分布在所属像元的左上角区域,最后再次进行光谱值提取,经验证提取的光谱值准确无误。通过OLI,TM和ETM+影像验证,结果表明该方法能够有效准确提取离散点光谱值,同时原理清晰,操作简单可行,适用性较强,为遥感影像提取离散点光谱值提供了新思路。     

Two-dimensional temporal coherence coding for super resolved imaging

In this paper, we present an approach that can be used for transmission of 2D spatial information through space-limited systems capable of transmitting even only a single spatial pixel. The input 2D object is illuminated with temporally incoherent illumination. The axial coherence length is very short and it equals only a few microns. Attached to the input object spatial random phase mask generates different axial shift for every pixel of the input. The temporal delays of the encoding (axial shifts) of every pixel are longer than the coherence length of the illuminating source. Therefore no temporal correlation exists between the various pixels of the input. A lens combines all spatial pixels into one point at its focal plane. Although the various spatial pixels were mixed together, since the random mask provided axial delay which was larger than the coherence length of the light source, the orthogonality between the spatial content of every pixel is preserved. The decoding system includes a lens that is positioned at the output of the resolution reduction system and it converts the output light into a plane wave containing all the spatial information of the original image mixed together in all of its pixels. By interfering this plane wave with the same plane wave after passing through the same random spatial coding mask, the spatial information of every pixel of the input object is recovered.     

Target detection algorithm in side-scan sonar image based on pixel importance value measurement

Side-scan sonar detection application always combines with unstable results.A two-stage novel pixel importance value measurement algorithm is proposed to stabilize the detection ability and false alarm probability simultaneously.In first stage of the algorithm,a new feature defined as pixel importance value(PIV) is proposed in terms of distances between the target pixel and each other pixels.PIV measurement of current pixel is defined as the weighted sum of all remaining segmented pixels.The weighted part refers to Gaussian kernel,which means closer pixels gets higher weight.Thus,targets with higher PIV can be located.In the second stage,we use convolutional neural network as classifier to eliminate the dot-like false targets.Our experiment data is obtained by autonomous underwater vehicle,where we demonstrate superior performance of our algorithm over the state-of-the-art sonar detection algorithms in terms of 90.39% recall rate and 2.39% false alarm probability.     

像素重要性测量特征下的侧扫声呐目标检测

研究了在较低信噪比下,在保证检测概率的前提下尽量降低虚警概率的目标检测,提出了一种针对特定目标的两阶段筛选算法.第一阶段中,首先使用阈值分割出有效点,并定义了一种新的像素重要性测量特征用于初步筛选目标。即通过有效像素点之间的距离来赋以高斯分布的权值,当前像素重要性的值定义为剩余有效点的距离加权和,具有较高的像素重要性值的聚集性强的区域内像素点会被定位出来。第二阶段,使用卷积神经网络分类器排除虚假目标.在实验中,使用近期无人潜器获得的海底数据,召回率与虚警概率分别达到90.39%与2.39%,证明了其相比声呐目标检测主流算法有更好的检测能力。      

时空域双边滤波背景抑制算法研究

红外图像中的强边缘一直是制约红外弱小目标检测概率的重要因素,同时是产生目标虚警的重要来源。采用能够同时利用邻域空间欧式距离和灰度值相似性的双边滤波,并针对天基红外系统中帧间背景缓慢变化的特点,设计一种基于时空域的双边滤波法,实验验证该方法对复杂背景的强边缘具有很好地抑制效果,信杂比增益大于3.6,同时能够很好地保留目标能量,目标能量损失因子D factor小于0.2,有效地提高目标的局域信杂比。     

INFRARED SMALL TARGET DETECTION ALGORITHM BASED ON SELF-ADAPTIVE BACKGROUND FORECAST

A background forecast filter is presented to detect a small target under an infrared (IR) nature scene. By calculating the correlation of image pixels, the background around the small target could be forecasted. Subtracting the forecast background from original scene, the small targets would become outstanding. Experimental results show that the algorithm proposed has better performance with respect to probability of detection and less computation complexity.     

Improving spatio-temporal resolution of infrared images to detect thermal activity of defect at the surface of inorganic glass

This paper proposes a noise suppression methodology to improve the spatio-temporal resolution of infrared images. The methodology is divided in two steps. The first one consists in removing the noise from the temporal signal at each pixel. Three basic temporal filters are considered for this purpose: average filter, cost function minimization (FIT) and short time Fast Fourier Transform approach (STFFT). But while this step effectively reduces the temporal signal noise at each pixel, the infrared images may still appear noisy. This is due to a random distribution of a residual offset value of pixels signal. Hence in the second step, the residual offset is identified by considering thermal images for which no mechanical loading is applied. In this case, the temperature variation field is homogeneous and the value of temperature variation at each pixel is theoretically equal to zero. The method is first tested on synthetic images built from infrared computer-generated images combined with experimental noise. The results demonstrate that this approach permits to keep the spatial resolution of infrared images equal to 1 pixel. The methodology is then applied to characterize thermal activity of a defect at the surface of inorganic glass submitted to cyclic mechanical loading. The three basic temporal filters are quantitatively compared and contrasted. Results obtained demonstrate that, contrarily to a basic spatio-temporal approach, the denoising method proposed is suitable to characterize low thermal activity combined to strong spatial gradients induced by cyclic heterogeneous deformations.     

基于局部Gabor二进制模式的高光谱伪装目标图像分类(英文)

为提高光谱伪装目标图像分类精度,提出了一种基于局部Gabor二进制模式(LGBP)的空间分类方法。LGBP作为一种多尺度算法,被用来提取高光谱图像的纹理特征。然后高光谱图像中的每一个像元可以用一个光谱特征向量及一个纹理特征向量表示。通过这种方法,增大类间距离。最后使用多核支持向量机结合光谱信息和空间纹理信息实现对高光谱伪装目标图像的分类。实验证明了该方法的有效性,分类总体精度和Kappa系数分别达到了95.6%和0.937。所提出的方法对于提高分类精度及鲁棒性具有重要意义。     

一种实用的X型靶标亚像素角点提取方法

为了提取亚像素角点和实现高精度的标定,提出了一种基于Harris算子和空间矩的亚像素角点提取方法。利用Harris算子,在优化后的范围内提取像素级角点;运用改进后的梯度模板提取像素级角点周围部分边界点,并利用空间矩的方法得到边界点的亚像素级坐标;将亚像素边界点进行直线拟合,并将交点的平均值作为该角点的亚像素坐标。实际测试证明:利用该方法提取到的角点精度可以达到0.1pixel,可满足实际的公差要求,为X型靶标的角点提取提供了一种新的思路,目前已经将该方法应用到了嵌入式机器视觉工业现场。     

Fast image enlargement using predefined codebook and eigenspace backprojection for lost pixel

In this paper, a new image enlargement method applying the backprojection for lost pixel (BPLP) to the predefined codebook-based method is proposed. BPLP is a method for image restoration. In BPLP, the eigenspace reflecting the characteristics of an input image is generated from the remained pixels and is used to restore the missing pixels. In the proposed method, the eigenspace is replaced by one generated from the predefined codebook (PDC). PDC represents edge-blurring properties in a small image patch and consists of pairs of low- and high-frequency image patches on various edge patterns. By replacing the PDC-based estimation of lost high-frequency components with BPLP, a fast image enlargement method retaining its performance can be developed. Through some experiments, the effectiveness of the proposed method was demonstrated. Especially, it was confirmed that the processing time of the proposed method was shortened to about 1/50 that of the PDC-based method.     

Detection of infrared small target based on fusion of multi-filters北大核心CSCD

Aiming at solving accuracy problem of infrared small target detection in sky and ocean background scenarios of infrared image sequences, a novel infrared small target detection based on multi-filters algorithm fusion method is presented in this paper. Firstly infrared small target and imaging, time and space characteristics of the corresponding background noise are analyzed. Tophat algorithm with improved Robinson guard filter are then integrated to highlight target and suppress clutter background by using infrared small target imaging features. Adaptive threshold segmentation is used to extract candidate targets, while Unger smoothing filter and multi-objects association filter are used to eliminate random noise and false targets in the candidate targets. Multiple experiments of infrared small target image sequences are implemented, and experimental results show that proposed method can detect infrared small targets at 99% detection rate with high reliability and good real-time performance. © 2017, Editorial Board, Journal of Applied Optics. All right reserved.     

A novel infrared small target detection method based on BEMD and local inverse entropy

Compared to other targets, it is more difficult to detect infrared small targets due to several aspects such as the low signal to noise ratio, low contrast, small size, the lack of shape and texture information of the targets, especially under complex background. In this paper, a novel infrared small target detection method based on peer group filter (PGF), bi-dimensional empirical mode decomposition (BEMD) and local inverse entropy (LIE) is proposed to overcome these difficulties. The PGF is implemented to remove the noise and improve the signal-to-noise ratio of the initial image. Our proposed BEMD algorithm is able to estimate the background effectively and get the target image by removing the background from the original image and segmenting the Intrinsic Mode Functions (IMFs) making use of the local inverse entropy. Experimental results demonstrate that the novel method can extract the small targets validly and accurately.     

结合稀疏编码和空间约束的红外图像聚类分割研究

提出了结合稀疏编码和空间约束的红外图像聚类分割新算法, 在稀疏编码的基础上融合聚类算法, 扩展了传统的基于K-means聚类的图像分割方法. 结合稀疏编码的聚类分割算法能有效融合图像的局部信息, 便于利用像素之间的内在相关性, 但是对于分割会出现过分割和像素难以归类的问题.为此, 在字典的学习过程中, 将原子的聚类算法引入其中, 有助于缩减字典中原子所属类别的数目, 防止出现过分割; 考虑到像素及其邻域像素具有类别属性一致性的特点, 引入了空间类别属性约束信息, 并给出了一种交替优化算法. 联合学习字典、稀疏系数、聚类中心和隶属度, 将稀疏编码系数同原子对聚类中心的隶属程度相结合, 构造像素归属度来判断像素所属的类别. 实验结果表明, 该方法能够有效提高红外图像重要区域的分割效果, 具有较好的鲁棒性. 关键词： 图像分割 稀疏编码 聚类 空间约束