基于序列图像的小目标检测

 针对序列图像中小目标的运动具有运动的连续性和轨迹的一致性等特征,提出了采用单帧检测和多帧检测相结合的处理方法。对单帧图像进行预处理和图像分割,得到去掉大部分背景和噪声点的图像,并在图像中选取候选目标点进行标记。然后对处理后的序列图像进行N帧叠加。对叠加图中的标定点利用8邻域搜索法进行目标筛选,进而检测出目标。实验结果表明,该方法实用性强,能简单、快速、有效地检测出序列图像中的运动小目标。     

动摄像机和动目标跟踪模式下的目标检测新方法

动摄像机和动目标跟踪是图像分析中的一个难点。根据应用光学知识和坐标变换理论,提出了映射变换差分方法(mappingtransformationdifferentialmethod,MTDM)。该方法首先利用映射变换将动摄像机和动目标模式下的目标检测问题转化为技术比较成熟的静摄像机和动目标模式下的目标检测,然后利用图像差分方法检测出被跟踪目标。实验结果表明:MTDM方法在复杂天空背景下能有效地抑制背景噪声,能准确地检测出被跟踪目标。     

图像序列的显著性目标区域检测方法

针对传统视觉显著性模型在自顶向下的任务指导和动态信息处理方面的不足,设计并实现了融入运动特征的视觉显著性模型。利用该模型提取了图像的静态特征和动态特征,静态特征的提取在图像的亮度、颜色和方向通道进行,运动特征的提取采用基于多尺度差分的特征提取方法实现,然后各通道分别通过滤波、差分得到显著图,在生成全局显著图时,提出多通道参数估计方法,计算图像感兴趣区域与眼动感兴趣区域的相似度,从而可在图像上准确定位目标位置。针对20组视频图像序列(每组50帧)进行了实验,结果表明:本文算法提取注意焦点即目标区域的平均相似度为0.87,使用本文算法能够根据不同任务情境,选择各特征通道的权重参数,从而可有效提高目标搜索的效率。     

红外序列图像中运动弱小目标检测

为检测红外序列图像中的运动弱小目标,分析了目标在序列图像中的运动特性和概率分布特性,以及目标和噪声在序列中的能量分布特性。提出连续M帧高阶累积方法来增强运动弱目标能量,用假设检验对目标和背景进行分割,通过搜寻序列运动能量中心来实现目标的多帧关联检测。通过仿真实验证明了算法对红外弱小目标检测有效性。     

Confidence-driven infrared target detection

The confidence of target detection can be used to evaluate the reliability and risk level of the detected targets and can effective help to exclude the false alarms, but very little investigation was involved in the past. In this letter, a confidence-driven infrared target detection method is proposed. We develop three confidence evaluating methods: (1) the median classification confidence of the cascade classifier; (2) the context confidence based on the number and the confidence of the merged detection rectangles around the detected target; and (3) the contrast confidence based on the difference between the detected target distribution and the around background distribution. The three confidences are combined to form the final confidence of the detected targets. We then use the confidence to refine the localization of the targets. The evaluation using real infrared images demonstrates the good performance of the proposed confidence-driven infrared detection algorithm on both undetected error and false alarm.     

利用环境噪声进行安静目标探测*

该文回顾了近年来该课题组利用环境噪声互相关方法和环境噪声自相关方法进行安静目标探测的主要工作。首先简单回顾了利用环境噪声互相关方法和环境噪声自相关方法进行安静目标探测的理论,然后介绍了两次利用海浪噪声进行安静目标探测的实验。通过海浪噪声实验验证了利用环境噪声互相关和自相关进行安静目标探测的可行性。最后对利用环境噪声互相关进行安静目标探测所需要的累积时间进行了讨论,并给出了累积时间的下界。     

A robust infrared dim target detection method based on template filtering and saliency extraction

Dim target detection in infrared image with complex background and low signal-clutter ratio (SCR) is a significant and difficult task in the infrared target tracking system. A robust infrared dim target detection method based on template filtering and saliency extraction is proposed in this paper. The weighted gray map is obtained from the infrared image to highlight the target which is brighter than its neighbors and has weak correlation with its background. The target saliency map is then calculated by phase spectrum of Fourier Transform, so that the dim target detection could be converted to salient region extraction. The potential targets are finally extracted by combining the two maps. Moreover, position discrimination between targets in the two maps is used to exclude the false alarms and extract the targets. Experimental results on measured images indicate that our method is feasible, adaptable and robust in different backgrounds. The ROC (Receiver Operating Characteristic) curves obtained from the simulated images demonstrate the proposed method outperforms some existing typical methods in both detection rate and false alarm rate, for target detection with low SCR.     

基于色彩空间非线性变换的彩色图像边缘检测

为了在边缘检测中有效的利用图像的色彩信息,提出了基于色彩空间非线性变换的彩色图像边缘检测算法。该算法利用了ιαβ空间信道相关性低的优点,采用基于Sobel算子的色度差算子进行边缘检测。实验结果表明:该算法不但可以检测出亮度变化剧烈区域内的物体边缘,而且还可以检测出在光线很暗的区域内不同颜色物体的边缘。因而可以极大的提高图像边缘的检测效果。     

红外序列图像多运动目标检测

针对背景不动情况下提取红外图像运动目标,提出了一种基于连续四帧序列图像精确检测多运动目标的算法,并用软件仿真了该算法处理图像的效果并与其他方法进行了对比。经试验证明该方法算法简单,实时性好。对单目标、多目标、室内、室外、简单和复杂背景的红外序列都可以得到较好的检测效果。能够有效地去除背景和噪声,精确地确定运动目标位置,有利于后续的目标跟踪,算法适于实时应用。     

Research on target photoelectricity track method and improved image processing arithmetic in dynamic targets detection system

To solve the problem that the complexity background affects the dynamic target detection performance, which causes detection performance instability in dynamic target track system, this paper is to study target photoelectricity track method based on revolving image sensor, analyze dynamic targets track principle and track geometry relation on optical image track instrument, put forward the improved Mean Shift target track arithmetic and the improved difference image processing arithmetic to eliminate the background effect; research the positive and negative difference image processing algorithm and image target region extraction, analyze the flow of image processing arithmetic and derivate their calculation method by gathering target image in track detection system. Through experimentation gathering and processing target sequence image, the results show the target track method and processing arithmetic are accurate and feasible.     

Infrared dim target detection technology based on background estimate

Accurate and fast detection of infrared (IR) dim target has very important meaning for infrared precise guidance, early warning, video surveillance, etc. In this paper, two new algorithms – background estimate and frame difference fusion method, and building background with neighborhood mean method are presented. The basic principles and the implementing procedure of these algorithms for target detection are described. Using these algorithms, the experiments on some real-life IR images are performed. The whole algorithm implementing processes and results are analyzed, and those algorithms for detection targets are evaluated from the two aspects of subjective view and objective view. The results prove that the proposed method has satisfying detection effectiveness and robustness. Meanwhile, it has high detection efficiency and can be used for real-time detection.     

基于序列图像的运动目标检测

针对动态环境下运动目标检测中噪声多、目标检测不完整等情况,提出了一种基于金字塔多分辨率模型的运动目标检测方法,在低分辨率下获取目标的区域,在高分辨率下获取目标的细节。对于复杂的环境,还提出了运用高低双阈值替代传统的单阈值进行图像差分运算的方案,阈值可以根据图像自动分析得到。该方法首先将当前帧和背景帧进行尺度变换,得到不同分辨率下的图像组,然后在不同尺度下得到高低阈值差分图像,最后从高层向低层进行有效融合,得到噪声少的完整目标图像。实验表明,该方法提取运动目标的精度比较高,单目标达到0.802,多目标达到0.615,尤其是在复杂的动态环境下,优势比较明显。     

强背景下模糊闪烁成像目标探测与跟踪

 强背景下空中运动目标主要表现为边缘残缺、模糊,甚至出现闪烁、间断等复杂成像特性,这成为制约目标探测和成像跟踪的瓶颈问题。结合跟踪过程反馈信息来确定目标点扩展函数,利用一种新的Ben-Ezra图像复原模型,解决了目标运动模糊的图像复原问题;采用基于特征伴随值的相似性判断方法,构造联结机制的联想网络模型,来解决目标闪烁和残缺特征的联想问题。对提出的方法进行了图像序列的仿真,取得了较好的实验结果。     

Algorithms of target detection on hyperspectral imagery

With the development of airborne and spaceborne remote sensing from the 1980s, as a new and growing technology, hyperspectral imaging is widely used in different fields, such as military investigation, battlefield information acquisition, environmental monitoring, mineral exploration and public security. Because of the unique characteristic of acquiring spectral and spatial information simultaneously, it brings the hyperspectral detection advantages when dealing with target detection problem under complex conditions. Target detecting models of hyperspectral image are established, including the target subspace model and the probability statistical model. And several algorithms are introduced, which are based on original spectral features, sub-space projection and probability statistical model separately. Comparison shows that if the background includes fault objectives, GLRT is the best algorithm, and its SINR is the largest; on condition of anomaly target detection, LPTD is the best, and have a quite high SINR.     

Deep learning-based circular disk type radar target detection in complex environment

Target identification is one of the most popular radar uses in real life. Target identification is a classifier that analyzes whether a signal contains an echo from a target (target-present) or is merely noise (target-absent). Deep learning techniques are a popular topic in classification, and they have evinced to be effective in a range of applications. In this paper, a 64 layers Circular Disk type RADAR Target Detection (CDRTD) model is proposed based on Transfer Learning using the SqueezeNet architecture of Convolutional Neural Network (CNN) that functions directly with processed radar target return eco signal and minimize the requirement of conventional laborious radar signal processing. Further, the proposed 64 layers SqueezeNet-based CNN CDRTD model was then implemented to identify circular disk type targets in complex environment. Finally, the target return eco data was tested to identify the circular disk type radar target in complex environments. We further analyzed target detection probability, false alarm rate, precision, recall, F1 in a complex environment and compared it with the ideal case. We found that our proposed CDRTD model can classify 83.3% of the test samples correctly with an overall accuracy of 94.59% in a noisy and cluttered environment whereas 100% of the test samples are classified correctly with an overall accuracy of 100% in an ideal environment.     

A new infrared small and dim target detection algorithm based on multi-directional composite window

This work presents a new method based on gray characteristic analysis for infrared dim small target detection under complex backgrounds. Firstly, an improved detection window with eight directions and three layers is introduced to investigate the gray distribution characteristic of different structure in an infrared image. Secondly, we adopt a pretreatment process based on morphology filter and mean filter to reduce the running time and propose a detection rule on characteristic analysis for infrared targets. Meanwhile a new parameter optimization algorithm based on fuzzy control theory is employed so that the detection rule could be independent of the initial parameters. Finally, experimental results indicate that the proposed method can effectively detect the dim small targets and has better tracking performance.     

The improved defects detection method of optical fiber winding

The paper discusses mainly how to check the defects such as fiber-stacking fiber-cut and fiber-uneven with an improved method in the process of fiber optic gyroscope coil winding. In the paper, it is aimed at the gray level image of optic fiber coil winding to get binary image using mathematical morphology and to get optic fiber position image using the improved moving target detection algorithm, on the base of the optic fiber position image, to figure out the relative position of adjacent optic fiber. Through the value of the relative position of adjacent optic fiber, the status of optic fiber winding can be estimated. Experimental results show that the entire image processing and defect detection method can effectively distinguish the defects in the process of optical fiber coil winding.     

基于纹理显著性的微光图像目标检测

微光图像对比度较低,目标显著性不明显,目标自动探测难度大.针对此问题,本文提出一种噪声鲁棒性较好的图像局部纹理粗糙度算法,并给出一种适用于微光图像显著分析的纹理显著性算法.首先,提出一种新的局部纹理粗糙度算法,该算法利用最佳尺寸计算局部纹理粗糙度,对纹理图像进行加噪实验,与基于局部分形维的粗糙度方法相比,本文局部纹理粗糙度算法表现出较好的噪声鲁棒性;其次,在提取图像粗糙度特征图的基础上,给出一种针对纹理的显著性度量算法;最后,将纹理显著性算法应用于微光图像目标检测,实验结果证明了该算法的有效性.     

Improved approach for target detection and recognition on optoelectronic hybrid joint transform correlator

A conventional joint transform correlator (JTC) often generates large correlation sidelobes as well as a large correlation peak width, strong zero-order peak, and low diffraction efficiency in target detection and recognition, which make the detection ability of JTC lower. To conquer these difficulties, firstly, a joint power spectrum (JPS) subtraction technique was proposed in Fourier plane, where power spectrum of reference image and power spectrum of object image are subtracted from the JPS before inverse Fourier-transform operation, it is evident that the improved JPS removes the zero-order term. Secondly, a fringe-adjusted filter (FAF) was presented to restrain sidelobes and noises. The revised JPS is multiplied by a FAF before the inverse Fourier-transform operation to obtain the cross-correlation peak. Computer simulations showed the improved method can markedly eliminate zero-order diffraction and effectively control the sidelobes and noises compared to traditional JTC, and then enhance the detection ability for JTC. Experimental results presented the sharp correlation peak and also demonstrated this approach effectiveness.     

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.