A novel evaluation metric based on visual perception for moving target detection algorithm

Traditional performance evaluation index for moving target detection algorithm, whose each index’s emphasis is different when it is used to evaluate the performance of the moving target detection algorithm, is inconvenient for people to make an evaluation of the performance of algorithm comprehensively and objectively. Particularly, when the detection results of different algorithms have the same number of the foreground point and the background point, the algorithm’s each traditional index is the same, and we can’t use the traditional index to compare the performance of the moving target detection algorithms, which is the disadvantage of traditional evaluation index that takes pixel as a unit when calculating the index. To solve this problem, combining with the feature of human’s visual perception system, this paper presents a new evaluation index-Visual Fluctuation (VF) based on the principle of image block to evaluate the performance of moving target detection algorithm. Experiments showed that the new evaluation index based on the visual perception makes up for the deficiency of traditional one, and the calculation results are not only in accordance with visual perception of human, but also evaluate the performance of the moving target detection algorithm more objectively.     

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。     

Moving object detection based on improved VIBE and graph cut optimization

Extracting foreground moving objects from video sequences is an important task and also a hot topic in computer vision and image processing. Segmentation results can be used in many object-based video applications such as object-based video coding, content-based video retrieval, intelligent video surveillance and video-based human–computer interaction. In this paper, we present a novel moving object detection method based on improved VIBE and graph cut method from monocular video sequences. Firstly, perform moving object detection for the current frame based on improved VIBE method to extract the background and foreground information; then obtain the clusters of foreground and background respectively using mean shift clustering on the background and foreground information; Third, initialize the S/T Network with corresponding image pixels as nodes (except S/T node); calculate the data and smoothness term of graph; finally, use max flow/minimum cut to segmentation S/T network to extract the motion objects. Experimental results on indoor and outdoor videos demonstrate the efficiency of our proposed method.     

Fisher’s linear discriminant ratio based threshold for moving human detection in thermal video

In video surveillance, the moving human detection in thermal video is a critical phase that filters out redundant information to extract relevant information. The moving object detection is applied on thermal video because it penetrate challenging problems such as dynamic issues of background and illumination variation. In this work, we have proposed a new background subtraction method using Fisher’s linear discriminant ratio based threshold. This threshold is investigated automatically during run-time for each pixel of every sequential frame. Automatically means to avoid the involvement of external source such as programmer or user for threshold selection. This threshold provides better pixel classification at run-time. This method handles problems generated due to multiple behavior of background more accurately using Fisher’s ratio. It maximizes the separation between object pixel and the background pixel. To check the efficacy, the performance of this work is observed in terms of various parameters depicted in analysis. The experimental results and their analysis demonstrated better performance of proposed method against considered peer methods.     

一种背景误差累积的高光谱图像异常检测算法

针对背景信息对高光谱图像异常检测的强干扰问题,提出了一种背景误差累积的异常检测算法.该算法通过构造背景子空间,利用各像素到该子空间的正交投影,得到有效抑制背景并突显目标的背景误差数据,用于后续的异常目标检测.最后用真实的高光谱数据进行仿真实验,理论分析比较和实验结果表明该算法具有较好的检测效果.     

复杂背景下运动点目标的检测算法

在复杂背景红外序列图像中,运动点目标的检测一直是研究的重点和难点。介绍了一种新的复杂背景下运动点目标的检测算法。首先根据点目标、背景干扰和噪声在红外图像中的差异,运用窗口大小不同的均值滤波器进行背景抑制以提高图像的信噪比,然后用一种门限法得到新的分割序列图像,最后采用改进后的隔帧差分光流场算法可有效地检测出点目标。仿真实验表明该算法优于传统光流场算法,能够检测帧间位移小于一个像元的运动目标,具有较好的检测性能,且实时性强。     

基于神经免疫生长可免域网络的红外光谱图像分割算法

管道运输对远距离输送石油天然气有着较大优势,而与之伴随的管道安全问题使得管道安全检测至关重要。为确保任何时间下管道状况的有效检测,红外成像技术由于其根据对象的热辐射信息反映目标特征的特殊性,能够忽视可见光的影响检测管道状态,因而在管道检测领域有重要意义。但由于户外环境的多样性,交错的管道和复杂环境使得采集的红外管道图像具有目标特征分布不均匀,目标遮挡和背景类目标干扰等问题。这些问题增加了提取管道目标的难度,不利于管道的分割和检测。生物免疫系统在抗原检测、提取和消除上表现出识别、学习、记忆、耐受和协调配合等目前复杂系统优化策略所缺乏的优异特性,借鉴生物神经系统调控免疫系统的机理,设计一种基于神经免疫网络的复杂背景下红外管道目标的检测与提取算法。根据生物神经网络在免疫系统中的调控机制,利用基础管道形状特征模型构建用于红外管道目标定位的神经网络,并将最优神经免疫可免域和区域种子生长结合,解决管道遮挡影响提取目标完整性的问题。选择三种典型的红外管道图像,将传统目标检测算法与基于神经免疫网络的算法进行了效果对比分析。结果表明,传统算法的平均真阳性率为40.56%,Jaccard相似性指数为27.18%,绝对误差率为11.75%,而基于神经免疫网络算法的真阳性率为98.05%,Jaccard相似性指数为94.44%,绝对误差率为1.18%。对比可知,神经免疫网络算法的真阳性率比传统方法高57.49%,绝对误差率则低10.57%,验证了复杂背景下,本文算法相比传统方法能够更加准确地提取完整的红外管道目标,这对管道安全检测效率的提高有着重要意义。     

复杂背景灰度图像下的多特征融合运动目标跟踪

为解决低对比度、低信噪比、目标旋转、缩放等非理想状态给跟踪算法的研究带来的诸多困难,本文提出灰度图像多特征融合目标跟踪算法,保证在满足工程实践需要的条件下,能够对目标进行稳定的跟踪。算法首先对灰度图像利用Sobel算子求出梯度特征,将X、Y双方向的梯度特征与灰度特征相融合得到新特征,新特征在核密度函数下对低对比度,目标轮廓形状变化较大的情况有较高的适应性和稳定性,再利用背景建模的方法对提取的运动目标区域进行加权,降低非跟踪目标的权值,最后对融合后的加权特征目标利用改进MeanShift算法进行跟踪。通过大量的实验表明,该算法适应目标和背景的复杂变化,并且具有较强的鲁棒性,基本满足在复杂背景灰度图像下目标跟踪的工程实际需求。     

图像序列中目标关键帧快速搜索算法

在目标测量时所获得的图像序列中,如何定位目标关键帧(最有利于目标测量的图像)的位置,对目标识别的效率和测量设备的性能有着显著的影响.针对具有复杂特性的目标图像序列,提出了一种基于帧间像素灰度差值来定位目标关键帧的快速搜索算法.该算法仅仅利用像素灰度值这一最基本的特征,将图像序列中相邻两张图像的同一像素的灰度差值与给定阈值相比较,统计高于阈值的像素个数,再与另一给定阈值相比较,进而确定目标关键帧的位置.实验结果表明,该算法对目标大小不同、形状不同,环境不同,信噪比较高的图像序列都具有快速、稳定的搜索效果.     

复杂背景下实时运动目标的提取

提出了一种结合帧间减法与背景自适应更新的算法,结合高速图像处理平台,以满足实时运动目标的提取。着眼于算法的高速性并提出一种足够快的方法用于弹道测量系统。用高斯分布建立每个像素的灰度模型,这个分布用来区分前景和背景像素以便用来更新背景模型。实验表明该系统可以满足靶场弹道测量任务实时性的要求,传统大量占用系统资源的算法在该系统中得到改善,大大提高了系统的实时性。     

基于空时联合稀疏重构的红外小弱运动目标检测方法

提出了一种基于空时联合稀疏重构的红外小弱运动目标检测算法。通过学习序列图像内容而构建的空时联合字典能同时刻画目标或背景的形态特征和运动信息;利用多元高斯运动模式从空时联合字典中提取出目标空时字典和背景空时字典,目标空时过完备字典描述移动的目标,背景空时过完备字典表征背景噪声。将连续多帧图像在空时联合字典上进行稀疏分解,然后分别利用目标空时字典和背景空时字典中的最大稀疏系数及其空时原子重构信号,获取重构残余能量差异来区分目标和背景。试验结果表明,由同源的空时字典重构的残余能量小,而由异构的空时字典恢复的残余能量大,该方法不仅能提高序列信号表示的稀疏度,还能有效提高小运动目标的探测能力。     

拉普拉斯约束低秩表示的高光谱图像异常检测

伴随高光谱图像的广泛使用,高光谱图像技术得到长足的发展,其中高光谱图像异常检测技术越发受到重视。为了解决传统高光谱图像异常检测技术的实用性和检测效果不佳的问题,提出一种新颖的低秩表示检测算法。对于高光谱图像,大部分背景像元均可以被少量主要的背景像元组合近似地表示,且它们的表示系数将会位于低秩的空间中。在剩下无法被主要背景像元表示的稀疏部分中存在着异常像元,则可以被检测算法提取出来。在低秩表示中,背景像元字典的构建将会影响高光谱图像中背景像元的表示。如直接从现有高光谱图像中提取背景像元构建字典,会导致异常像元对背景像元字典的污染。而利用待检测高光谱图像观测数据和由光谱组成原理可合成的潜在未观测数据来构建背景像元字典,提取出背景像元的主要特征,有利于更好地分离出稀疏异常像元的信息。并且高光谱图像数据存在高维几何结构特点,通过引入拉普拉斯矩阵来约束空间中局部相似的像元对于待检测像元的表示作用,获得更接近于真实的表示系数。实验结果分别在仿真数据和真实数据上验证,与传统方法相比,提出的方法通过有效地突出异常像元提高了检出率和抑制了背景像元,降低了误检率。     

基于随机聚类的复杂背景建模与前景检测算法

为了构建鲁棒的背景模型和提高前景目标检测的准确性, 综合考虑同一位置的像素点在时间上的关联性和与其相邻像素的空间关联性, 基于经典的ViBe算法中的随机聚类思想提出了一种复杂背景建模和前景检测方法. 利用样本一致性原理, 采用前n帧序列图像得到初始化背景, 避免了Ghost现象的发生; 根据实际复杂背景的动态反馈获取自适应聚类阈值和自适应更新阈值进行随机聚类, 从而实现了对动态背景的适应性; 通过全局扰动阈值和局部像素级判断阈值的结合, 实现了对光照缓慢变化、快速变化以及突然变化的免疫性, 准确地分割前景目标. 对多组数据集的测试结果表明, 本文算法较大地提高了背景模型对动态背景、光照变化及相机抖动的复杂背景的适应性和鲁棒性. 算法还能很好地适用于红外图像检测运动目标的场合, 扩展了本算法的应用范围. 在没有进行任何图像预处理和形态学后处理情况下, 得到的原始前景检测精度优于其他对比算法.     

A novel spatial–temporal detection method of dim infrared moving small target

Moving small target detection under complex background in infrared image sequence is one of the major challenges of modern military in Early Warning Systems (EWS) and the use of Long-Range Strike (LRS). However, because of the low SNR and undulating background, the infrared moving small target detection is a difficult problem in a long time. To solve this problem, a novel spatial–temporal detection method based on bi-dimensional empirical mode decomposition (EMD) and time-domain difference is proposed in this paper. This method is downright self-data decomposition and do not rely on any transition kernel function, so it has a strong adaptive capacity. Firstly, we generalized the 1D EMD algorithm to the 2D case. In this process, the project has solved serial issues in 2D EMD, such as large amount of data operations, define and identify extrema in 2D case, and two-dimensional signal boundary corrosion. The EMD algorithm studied in this project can be well adapted to the automatic detection of small targets under low SNR and complex background. Secondly, considering the characteristics of moving target, we proposed an improved filtering method based on three-frame difference on basis of the original difference filtering in time-domain, which greatly improves the ability of anti-jamming algorithm. Finally, we proposed a new time–space fusion method based on a combined processing of 2D EMD and improved time-domain differential filtering. And, experimental results show that this method works well in infrared small moving target detection under low SNR and complex background.     

基于改进SSD的车辆小目标检测方法

地面车辆目标检测问题中由于目标尺寸较小,目标外观信息较少,且易受背景干扰等的原因,较难精确检测到目标。围绕地面小尺寸目标精准检测的问题,从目标特征提取的角度提出了一种特征融合的子网络。该子网络引入了重要的局部细节信息,有效地提升了小目标检测效果。针对尺度、角度等的变换问题,设计了基于融合层的扩展层预测子网络,在扩展层的多个尺度空间内匹配目标,生成目标预测框对目标定位。在车辆小目标VEDAI(vehicle detection in aerial imagery)数据集上的实验表明,算法保留传统SSD(single-shot multibox detector)检测速度优势的同时,在精度方面有了明显提升,大幅提升了算法的实用性。     

一种基于正负差图像的运动目标检测新方法

运动目标检测领域中现有的差图像法是利用绝对值差图像检测差图像上运动目标区域，用现有方法检测时易受噪声干扰，而且当摄像机有自运动时需要进行背景运动补偿。因此，提出一种新算法，即首先分别计算正差图像与负差图像，然后利用运动目标区域在正差图像与负差图像中的幅值、形状以及运动等信息的对称性对其进行检测，最后给出针对飞机尾焰序列图像进行检测的结果。实验结果表明：该方法可提高运动目标检测的可靠性与效率。     

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.     

Dim small targets detection based on self-adaptive caliber temporal-spatial filtering

To boost the detect ability of dim small targets, this paper began by using improved anisotropy for background prediction (IABP), followed by target enhancement by improved high-order cumulates (HQS). Finally, on the basis of image pre-processing, to address the problem of missed and wrong detection caused by fixed caliber of traditional pipeline filtering, this paper used targets’ multi-frame movement correlation in the time-space domain, combined with the scale-space theory, to propose a temporal-spatial filtering algorithm which allows the caliber to make self-adaptive changes according to the changes of the targets’ scale, effectively solving the detection-related issues brought by unchanged caliber and decreased/increased size of the targets. Experiments showed that the improved anisotropic background predication could be loyal to the true background of the original image to the maximum extent, presenting a superior overall performance to other background prediction methods; the improved HQS significantly increased the signal-noise ratio of images; when the signal-noise ratio was lower than 2.6 dB, this detection algorithm could effectively eliminate noise and detect targets. For the algorithm, the lowest signal-to-noise ratio of the detectable target is 0.37.     

Complex background suppression based on fusion of morphological Open filter and nucleus similar pixels bilateral filter

To reduce the influences of the heavy clutter on infrared small target detection, a new background suppression algorithm is presented in this paper which depends on fusion of two different filters. The Nucleus Similarity Degree (NSD) of each pixel is analyzed first, then morphological Open filter which favors point target enhancement and the Nucleus Similar Pixels Bilateral Filter (NSPBF) which favors background prediction are fused. The complex background suppression and target enhancement can be accomplished more effectively by the fusion. Experimental results indicates that the method is efficient for background suppression under the condition of heavy clutter.     

基于数学形态学的弱点状运动目标的检测

提出了一种新的基于数学形态学的红外图像序列中弱点状运动目标的非参数检测算法。采用数学形态学抑制背景杂波干扰和增强目标,用沿时间轴投影和二维空域搜索代替复杂的时空三维搜索形成组合帧,然后在每条可能的轨迹上将进行目标能量累加,实现了一种快速检测前跟踪(TBD)检测算法。仿真实验表明:在恒虚警概率条件下,该检测算法能高效地检测信噪比约为2的弱点状运动目标,检测性能对噪声分布不敏感,能精确地得到目标的即时位置和速度信息,适合于实时图像处理和目标探测,具有很高的实用价值。