基于生物视觉center-surround机制的光团目标检测与跟踪

基于生物视觉的center-surround机制,提出一种用改进的LoG(Laplacian of Gaussian)算子检测光团目标的方法。首先明确了光团目标的成像模型,分析了LoG算子的性质及其响应,接着提出了归一化的LoG算子。理论上指出该算子可用于检测光团目标。仿真和实验证明：该算子可以用于检测图像中已知大小和未知大小的光团目标,并且实用性优于其他常规方法。结合Kalman滤波和粒子滤波,该算子还可以用于序列图像中单目标和刚体的跟踪。理论推导和实验结果表明,该方法是稳健和高效的。     

层次卷积滤波红外弱小目标检测方法

针对单帧复杂背景红外图像点目标检测算法存在复杂背景下处理效果不理想、处理时间长的问题,提出了一种层次卷积滤波检测算法。主要分为两个部分：第一,根据红外小目标特性,设计一种层次卷积滤波的算子,对图像进行滤波处理,实现图像中小目标的增效和背景抑制的效果;第二,采用基于最大值的自适应阈值方法,对图像进行二值化操作,过滤背景杂波,最终提取到待检测的目标。在大量不同背景红外图像中进行实验,论文算法在背景抑制因子和信噪比增益的性能量化结果上优于现有5种典型红外弱小目标检测算法的性能结果,且平均处理时间仅为高斯拉普拉斯（Laplacian of Gaussian,LoG）滤波算法的30.42%。通过实验对比,表明该层次卷积滤波算法可以有效解决在不同复杂背景下的红外图像中对小目标检测的问题。     

基于改进Canny算子的SOP贴片元件的定位识别

SOP贴片元件的定位识别主要采用的是Canny算子进行图像边缘检测,传统的Canny算子在滤波和阀值分割方面不能很好地满足SOP元件的识别精度。针对此问题,对Canny算子进行改进,采用中值滤波及形态学闭运算滤波替代Canny算子的高斯滤波器,能更好达到去噪效果;提出一种基于改进的最大类间方差法自适应的搜索出Canny算子的双阀值,解决了SOP元件对外界环境变化敏感问题;利用Canny算子提取出边缘轮廓结合基于邻接矩阵的搜索方法和最小二乘法实现元件的定位识别。仿真结果表明,改进后的算法能更好的提高SOP元件的识别精度,具有较好的自适应能力。     

基于形态学4子带分解金字塔的图像融合

提出了一种基于数学形态学滤波的多分辨力图像融合。这种融合方法使用了形态学开闭运算构造了低通与高通滤波器,将原始图像分解为4子带图像金字塔和4子带方向衬比度图像金字塔。然后利用方向衬比度和区域标准差进行图像融合得到融合的4子带图像金字塔,最后应用子带图像重构得到融合图像。融合实验表明,该方法优于传统的形态学金字塔图像融合,衬比度金字塔图像融合和小波分解图像融合。     

基于改进遗传算法优化的形态学修正TOP-HAT滤波器设计方法

针对红外序列图像中运动弱小点目标的检测问题,设计了一种基于改进遗传算法优化的修正Top-Hat形态学滤波器算子。其中,优化的修正Top-Hat形态学滤波器可以很好地抑制背景和噪声的影响;改进遗传算法采用新的区间离散化编码和自适应的主次式交叉与变异算子,通过优化搜索全局空间得到的形态学滤波器参量具有较好的滤波性及时效性。并且针对不同信噪比的点目标检测建立了自适应门限。实测数据的处理结果表明:在虚警概率小于5%情况下,优化的修正Top-Hat形态学滤波器算子对信噪比约为2的复杂图像检测概率大于等于70%,与固定结构元素的Top-Hat形态学滤波器相比检测概率提高了近10%,与用经典遗传算法训练的传统Top-Hat形态学滤波器相比检测概率提高了4%。     

多尺度形态算子融合图像滤波技术及滤波质量评价

针对舰载红外警戒系统的红外和电视图像,提出了一种新的海空背景下受强杂波、噪声污染的图像目标滤波算法和滤波效果的定量评价算子。算法采用多尺度的形态算子对输入的图像并行滤波,大尺度形态算子抑制图像噪声,小尺度形态算子提取目标边缘细节信息。处理后的图像进行基于树状小波帧变换的图像信息融合,融合图像可完备提取不同尺度滤波后的图像信息。针对目标检测跟踪的图像滤波算法的评价,提出了目标与背景的交叉分辨力评价算子及评价准则。仿真实验表明。该滤波算法要优于中值滤波、自适应滤波、小波变换滤波算法,滤波质量的定量评价算法是合理的、有效的。算法适用于舰载红外警戒系统。     

基于灰度形态学和邻域熵值的弱小目标检测

 提出了一种弱小目标检测的新方法。从实际应用出发，考虑到复杂的背景和大量的干扰噪声，对传统熵值检测算法进行了改进，采用邻域熵值变化为检测标准。为了提高此方法的有效性，结合了灰度形态学滤波来对图像进行预处理。该检测算法的全过程为:首先对图像进行形态运算;然后对形态波后的图像进行邻域熵的计算;接着以计算所得的邻域熵的最大值和最小值为依据对图像进行分割,得到目标或目标边缘所处位置;最后用实地拍摄的空中弱小目标真实图像进行了实验验证。结果发现：该新方法可对弱小目标、大目标、多目标进行检测，且检测速度快，抗噪声干扰能力强。     

基于形态学的不完全性骨折CT图像裂痕定位

针对不完全性骨折的CT图像损伤位置不易明确定位的问题,提出了一种基于数学形态学的裂痕定位算法。为了从CT图像中获得准确的骨质区域,在CIE Lab均匀色彩空间对原始图像进行双边滤波去噪,利用最大类间方差法计算出最佳阈值,从而分离出骨质区域,采用数学形态学中的黑帽运算结合Canny边缘检测算子对裂痕位置进行精确定位。实验结果表明,能够自动提取并定位不完全性骨折CT图像的裂痕区域。算法易于实现,具有较强的鲁棒性和实用性,方便了医学影像诊断。     

一种红外搜索系统中弱小目标自适应检测算法

为解决红外搜索系统中场景起伏造成的背景预测不准确这一问题,提出了一种自适应调整的空间滤波方法。该算法在估计背景的同时,对背景残差进行计算,根据残差值调整滤波参数,使背景残差趋于最小,以适应背景的起伏。当背景包含较多复杂因素时,不利于目标提取,多尺度形态学算子通过不同尺度不同形态的结构体参与计算,可以全面地估计背景,进一步抑制背景残差,再通过计算图像全局阈值,自适应分割出潜在目标。采用并行运算,可将算法实现于现场可编程器件(FPGA)上。试验结果表明:即使当场景较复杂,场景信噪比较低时,依然可以使处理后的图像信噪比大于3,从而可显著提高红外搜索系统的检测概率,实现弱小目标的检测。     

基于数学形态学的声纳主动探测信息净化方法

针对主动声呐探测画面中混响和被动条状干扰问题,提出了一种基于数学形态学滤波的主动探测信息净化方法。该算法通过研究数学形态学滤波器的频响特性,构造与主动声呐探测画面中目标频率特性匹配的结构元素,然后对主动声呐探测画面进行形态学滤波处理,估计主动声呐探测画面的干扰背景,最后进行探测信息净化,并利用形态学滤波对净化后图像进行增强。海试数据处理结果表明,该文方法能够有效抑制低频被动条状干扰以及混响背景,使点状目标在图像中表现更为明显,更有利于目标检测。     

An improved infrared dim and small target detection algorithm based on the contrast mechanism of human visual system

To achieve higher detection rate and lower false alarm rate in dim and small target detection, this paper proposed an improved algorithm based on the contrast mechanism of human visual system (HVS) for infrared small target detection in an image with complicated background. According to the contrast mechanism of HVS, Laplacian of Gaussian (LoG) filter is exploited to deal with the input image, which can not only suppress the background noise and clutter but also enhances the target intensity significantly. As a result it increases the contrast ratio between target and background. To further eliminate residual clutter, we process the filtered image with morphological method in all directions. True target is finally obtained by applying local thresholding segmentation to the pre-processed image. Experimental results demonstrate its superior and reliable detection performance by high detection rate and low false alarm rate.     

An effusion-evaporation model for image edge detection

A novel quasi-physical edge detection model is presented. The model, referred to as the effusion-evaporation model (EEM), is inspired by the natural phenomenon that the water effusing from the ground evaporates in the sunshine and leaves a wire like water stain on the ground surface, which reflects the physiognomy of the terrain. Based on the simulation of water effusing and evaporating, an EEM regards the complement of gradient magnitude image as a three-dimensional terrain, and the concave regions, which contain the residual water in the evolution final state, are used to determine the edges. Subjective and objective comparisons are performed on the proposed algorithm and two conventional edge detectors, namely Canny and LoG. The comparison results show that the proposed method outperforms Canny and LoG detectors for the real images and the standard test images with Gaussian noise.     

Morphological center operator for enhancing small target obtained by infrared imaging sensor

Infrared small target in image obtained by infrared imaging sensor is usually different from the surrounding regions, which is the important region in infrared image for different applications. However, the infrared small target is dim and embedded in clutter background, which makes the small target difficult to be detected or recognized. So, it is important to enhance infrared small target. Morphological center operator could smooth important image features, which may be well used for infrared small target enhancement. To well enhance infrared small target, a morphological center operator based method is proposed. The morphological center operator is specified to suppress most of the background of the infrared image through the strategy of feature extraction. Then, the infrared small target is well enhanced. Experimental results show that, the proposed method performs well for enhancing infrared small target and the performance is better than some other methods. So, the proposed method could further improve the performance of infrared imaging sensor.     

Infrared small moving target detection using sparse representation-based image decomposition

Infrared small moving target detection is one of the crucial techniques in infrared search and tracking systems. This paper presents a novel small moving target detection method for infrared image sequence with complicated background. The key points are given as follows: (1) since target detection mainly depends on the incoherence between target and background, the proposed method separate the target from the background according to the morphological feature diversity between target and background; (2) considering the continuity of target motion in time domain, the target trajectory is extracted by the RX filter in random projection. The experiments on various clutter background sequences have validated the detection capability of the proposed method. The experimental results show that the proposed method can robustly provide a higher detection probability and a lower false alarm rate than baseline methods.     

FD: A feature difference based image clutter metric for targeting performance

Previous image clutter metrics were proposed based on the sensitivity of human visual perception to one feature of image. In this paper, a novel feature difference based image clutter metric is proposed by fully considering low-level image features, such as step edges, lines and Mach bands. As phase congruency is an invariant property of image features, the phase congruency (PC) is used to quantify the feature difference between the target and clutter images. Because PC is invariant to changes in image contrast while human visual perception is sensitive to contrast changes, a directional contrast (DC) feature is developed to calculate the contrast difference between the two images. Then we utilize the DC of the target image as an information content weighting measure to pool the local difference map to be a clutter metric. Comparative experiments demonstrate that this clutter metric correlates stronger with detection probabilities, false alarm probabilities and mean search times than previously proposed metrics.     

基于视觉认知的红外目标分割算法

研究了红外图像中目标分割算法,针对基于灰度分割算法存在的过分割或分割不足,以及对低灰度目标的不敏感问题,提出了一种基于视觉认知的红外目标分割算法。将红外图像的灰度信息转换为图像方差信息;运用单边切比雪夫不等式理论,获取目标数据分布与其k倍标准差之间的非线性关系,完成目标边缘的预分割;由形态学填充运算,得到用于目标分割的二值掩膜图像。实验表明,该算法能够有效的分割出红外图像中处于不同灰度等级下的目标信息,且误分率较低。     

Multifocus image fusion and denoising scheme based on homogeneity similarity

A novel image fusion algorithm based on homogeneity similarity is proposed in this paper, aiming at solving the fusion problem of clean and noisy multifocus images. Firstly, the initial fused image is acquired with one multiresolution image fusion method. The pixels of the source images, which are similar to the corresponding initial fused image pixels, are considered to be located in the sharply focused regions. By this method, the initial focused regions are determined. In order to improve the fusion performance, morphological opening and closing are employed for post-processing. Secondly, the homogeneity similarity is introduced and used to fuse the clean and noisy multifocus images. Finally, the fused image is obtained by weighting the neighborhood pixels of the point of source images which are located at the focused region. Experimental results demonstrate that, for the clean multifocus image fusion, the proposed method performs better than some popular image fusion methods in both subjective and objective qualities. Furthermore, it can simultaneously resolve the image restoration and fusion problem when the source multifocus images are corrupted by the Gaussian white noise, and can also provide better performance than the conventional methods.     

基于形态学带通滤波和尺度空间理论的红外弱小目标检测

针对复杂背景下的红外弱小目标检测问题,提出了一种基于形态学带通滤波和尺度空间理论的红外弱小目标检测算法。采用形态学带通滤波对红外图像进行预处理,得到红外弱小目标的潜在区域;利用高斯差分算子获得预处理后的红外图像的尺度空间,并通过尺度空间的极大值检测获得候选目标的位置和尺度;通过对候选目标的信杂比进行阈值化实现红外弱小目标的检测。实验结果和现有方法的对比证明了算法的有效性和稳健性。