基于遥感图像分块直线特征检测的机场跑道检测方法

针对遥感图像机场跑道检测问题,提出了一种基于图像分块直线特征检测的机场跑道检测方法。首先,针对遥感图像数据量大带来的计算处理问题,设计了基于直线分割检测子（LSD）的遥感图像分块直线特征检测环节;然后,在总结归纳机场跑道数学特性的基础上,对提取的直线特征进行平行线分组、直线生长、平行线合并,并以Radon变换为基础,找出候选机场跑道区域;最后,使用灰度统计信息并结合梯度方向直方图对候选区域进行处理,筛选出最终的机场道路区域。实验结果表明,在能够提取出有效直线特征的情况下,该方法可以对多类机场跑道进行有效定位。     

图像模板测量技术在零件不规则薄圆孔检测中的应用

针对不规则薄圆孔的检测,提出了一种基于数字图像处理的模板匹配检测方法,运用数字图像处理技术对采集的圆孔图像进行截取、降噪、分割、边缘检测等处理,再把提取出的圆与标定模板上的标准圆进行比较,实现对不规则圆孔尺寸的检测,并通过实验证明了该方法的可行性和实用性。     

基于加权的可见光与红外光图像融合算法

红外图像所含边缘等细节偏少、可见光又容易受外部环境干扰,融合图像可以提供更全面的信息,符合人或机器的视觉特性,为图像进一步分析、识别等提供基础。提出一种比值与梯度加权的可见光与红外光图像融合算法,结合小波变换在图像分解中的特性及信号集中的特点,将小波变换应用于红外光和可见光图像融合中可以提高融合信息的理解能力。针对分解获得的低频系数主要反映图像细节信息的特点,对低频系数采用比值加权分析融合规则;针对分解获得的高频系数主要反映图像边缘信息特征的特点,对高频系数采用改进边缘检测算子梯度加权的融合规则。选取多组图像进行了不同融合规则实验对比分析,通过客观评价指标进行评价,改进的融合算法可以获得较清晰的融合图像,可以增加图像的互补信息,并能较好地提高融合图像的清晰度。     

AFIT neural network research

A brief summary of research done at the Air Force Institute of Technology (AFIT) in the area of neural networks is provided. It has been shown that backpropagation, used for feedforward artificial neural networks, is just a degenerate version of an extended Kalman filter, and that networks can do about as well as the optimum statistical classification technique. A method of finding the importance of features for use by a neural network classifier has been determined. Techniques for using neural networks for image segmentation have been developed. In optical pattern recognition, techniques that allow the processing of real FLIR (forward-looking infrared) images with existing binary spatial light modulators have been devised. An optical direction of arrival detector applicable to laser illumination direction determination has been designed and tested; the design is similar to a fly's eye. Coated mirrors for the optical confocal Fabry-Perot interferometer have been designed, specified, fabricated, and installed. Significant progress has been made in the use of neural networks for processing multiple-feature sets for speech recognition     

Method for searching bridge in IR images

A method for searching bridges in IR images is presented in this paper. It is a time-consuming image understanding task to recognize targets in low SCR images. As in IR images, the bridges usually have almost the same gray level range of the background, the typical segmentation algorithm cannot get correct segmentation labels and edge sites of the bridges. The gray level characters of both the lands, which connect the bridge, and the river are fully considered resulting in a method that can be realized effortlessly and quickly. The criteria are also presented to decide whether there exist bridges or not in the given images, so the method endows the system with the ability to seize the target automatically. Some experimental results are presented demonstrating that the method can effectively recognize bridges in IR images     

一种新的基于Graph cuts方法的SAR图像分割模型

Graph cuts方法是一种快速优化技术,能有效解决计算机视觉的低层次问题,如表面重构、分割、去噪等问题。其优点是迭代计算的高效性并能得到全局最优解。利用Graph cuts方法,将基于活动轮廓模型和水平集方法的SAR图像分割模型转化成一个新的模型,可用最大流/最小割方法来求解。实测SAR图像的分割实验表明：提出的新模型所需运行时间大约是基于水平集的活动轮廓模型所需时间的一半,分割精度也得到了较大的提高。     

A Novel Speckle Filter for SAR Images Based on Informationtheoretic Heterogeneity Measurements

Most adaptive speckle filters are based on the local coefficient of variation, which serves to measure the heterogeneity of synthetic aperture radar (SAR) images. However, the sensitivity of the measurements to speckle and noise of SAR images would greatly deteriorate the speckle reduction. This article, based upon the information theory, presents a novel parameter for the heterogeneity measurement as a general index to quantitate the SAR image heterogeneity. Further, as a new speckle reduction algorithm based on the aforesaid quantitative heterogeneity measurements, it puts forward a heterogeneity-based speckle reduction filter (HBSRF), which uses the information-theoretic heterogeneity measurements as a criterion to classify the SAR images as belonging to homogeneous or heterogeneous regions. Then the finite iteration procedure and edge detection algorithms are adopted to strike the best balance between speckle reduction and edge preservation. The results from the computer simulation have demonstrated that the proposed effective method is superior to the conventional speckle filters based on the local coefficient of variation both in textural preservation and speckle reduction.     

Target tracking using infrared measurements and laser illumination

A missile target tracker is designed using a filter/correlator (with adaptive target shape identification) based on forward-looking infrared (FLIR) sensor measurements to track the center-of-intensity of the hardbody/plume combination, and another filter using Doppler and/or speckle information in the return from a low-power laser illuminator to estimate the offset between the intensity centroid and the hardbody center-of-mass. The Doppler information is shown to yield smaller bias and error variance from the tracker than the speckle information. Performance of trackers based on just Doppler or both Doppler and speckle information from the laser return is portrayed as a function of important parameters in the tracking environment     

基于区域分割的红外与可见光图像融合算法的研究(英文)

由于红外图像和可见光图像的成像特点不同,因此在航空监视领域红外图像和可见光图像融合有重要的研究意义。由于非下采Contourlet变换具有更好的方向性、较高的逼近精度和更好的稀疏表达性能,能有效的提取图像的特征信息。因此我们在非下采Contourlet域,以空间频率为度量标准对红外图像进行阈值分割,经过分割将红外图像和可见光图像分别划分为目标区域以及背景,随后对红外图像和可见光图像进行边缘检测从而得到边缘区域,针对三个不同区域分别选择不同的融合规则进行融合。通过两组不同灰度差异的红外与可见光图像的实验,将基于像素点,窗口策略的融合算法和本文所提出基于区域算法进行了主观和客观的对比,试验结果表明基于区域分割的红外与可见光图像融合算法不仅能有效提取出红外图像中的目标信息还能有效的保持可见光图像的所反映的光谱信息,因此本文提出的算法是一种有效且可行的图像融合算法。     

Novel Approach for ISAR Image Cross-Range Scaling

Inverse synthetic aperture radar (ISAR) imaging systems produce electromagnetic images of targets in the range-Doppler domain. In order to rescale the image in a homogeneous range-cross range domain (meters by meters), the modulus of the target effective rotation vector must be known. Although in some cases it can be retrieved by means of ancillary data, in most cases the modulus of the target effective rotation vector must be estimated. A blind technique is proposed for estimating the modulus of the target effective rotation vector that exploits information carried by the chirp rate of scattering centres. A technique based on image segmentation, local polynomial Fourier transform (LPFT), and image contrast (IC) maximisation is used in order to extract the scattering centres and estimate their chirp rate. Simulated and real data analyses are provided to confirm the effectiveness of the proposed algorithm.     

一种相变热图的图像处理方法

相变热图技术中,为了得到风洞试验模型表面的热流分布,必须对相变热图序列进行相变线提取.首先通过特殊的时-空变换,将所有原始序列图像的直接分割转化为对少量合成图像的分割,在减小计算量的同时较好地解决了原始图像中由于相变区域模糊而难以分割的问题.同时,为了解决由于模型表面存在镜面反射造成的模型头部区域相变线提取不准确,引入镜面反射模型,并通过分割和参数求取过程的迭代执行计算出反射模型各参数,对合成图像进行整体性亮度补偿并最终得到良好的分割结果.最后根据提取出的相变线位置和材料相变温度,完成热流值的计算.通过比较表明本文结果更为准确合理,也验证了所提出分割方法的有效性,促进相变测温技术的广泛应用.     

Aerial-BiSeNet: A real-time semantic segmentation network for high resolution aerial imagery

The aircraft system has recently gained its reputation as a reliable and efficient tool for sensing and parsing aerial scenes. However, accurate and fast semantic segmentation of high-resolution aerial images for remote sensing applications is still facing three challenges: the requirements for limited processing resources and low-latency operations based on aerial platforms, the balance between high accuracy and real-time efficiency for model performance, and the confusing objects with large intra-class variations and small inter-class differences in high-resolution aerial images. To address these issues, a lightweight and dual-path deep convolutional architecture, namely Aerial Bilateral Segmentation Network (Aerial-BiSeNet), is proposed to perform real-time segmentation on high-resolution aerial images with favorable accuracy. Specifically, inspired by the receptive field concept in human visual systems, Receptive Field Module (RFM) is proposed to encode rich multi-scale contextual information. Based on channel attention mechanism, two novel modules, called Feature Attention Module (FAM) and Channel Attention based Feature Fusion Module (CAFFM) respectively, are proposed to refine and combine features effectively to boost the model performance. Aerial-BiSeNet is evaluated on the Potsdam and Vaihingen datasets, where leading performance is reported compared with other state-of-the-art models, in terms of both accuracy and efficiency.     

基于路面分割的高精度地图创建优化方法研究

高精度地图主要利用已采集图像的地面信息生成,但是在真实环境中图像的地面信息容易受动态障碍物遮挡,同时GPS难免会有抖动误差,导致地图拼接效果并不理想。针对上述问题提出了一种基于路面分割的动态障碍物去除与图像配准方法。使用深度学习对全景图像进行语义分割并提取路面信息,在去除动态障碍物干扰后,利用路面特征进行图像配准。融合GPS与里程计信息进行定位优化,利用多帧图像叠加填补空缺形成地图。最终,实验验证了该方法在去除动态障碍物的同时也提高了地图的精度。     

用RTR技术研究固体发动机燃烧室中粒子运动轨迹(Ⅱ)图象处理技术应用

针对采用RTR技术获取固体火箭发动机（SRM）燃烧室中凝相粒子运动图象的特点，应用了背景减影、图象增强、图象分割、噪声过滤、图象叠加等图象处理手段对其进行处理，获得了较清晰的粒子运动轨迹图象。结果表明图象处理技术是开展利用RTR技术进行SRM二相流研究的关键环节之一。     

MTI data clustering and formation recognition

Image exploitation technology approaches have generally focused on the detection and spatial analysis of stationary groups of objects on the ground using various sensors. While spatial arrangement is clearly necessary in analyzing military formations, it is usually not sufficient. Typically the arrangement must be examined within some context in order to interpret a pattern of deployment. For moving objects the spatial arrangement of the group relative to the direction of motion is key to recognizing the formation. By examining ground moving target indicator (MTI) radar data over time, motion can be inferred and used to establish a context for interpreting the spatial arrangement of the data. New techniques that exploit the multitemporal nature of MTI data are described. The first is a space-time clustering technique that locates compact groups of objects that persist in time. The technique Is an application of Marr and Hildreth's edge detection methodology to the dual problem of region segmentation, or more accurately, volumetric segmentation of space-time. The second technique is based on the use of the Hough transform for recognizing moving formations such as columns, wedges, and lines abreast by analyzing the shape of clustered MTI detections (specifically the orientation of linear arrangements within the group) with respect to their direction of motion. Preliminary results from simulated MTI data sets are presented     

民用航空器注册号识别的鲁棒性方法研究

为了提高空管自动化水平并降低运行成本,提出一种基于计算机图像处理技术的民用航空器注册号识别方法.首先将全局阈值分割算法与形态学分割算法结合,实现对航空器图像中注册号的精确定位.然后采用主成分分析法解决注册号倾斜校正问题,并分别针对粘连和非粘连情况的注册号字符进行有效切割.最后利用基于特征提取的模板匹配算法,完成对注册号字符的准确识别.在此基础上,基于MATLAB搭建实验测试平台对上述方法进行仿真验证.实验结果表明,方法能够针对不同角度拍摄的航空器图像快速、准确地识别其注册号,单幅图像识别耗时在0.5 s左右.相比于其他方法,在图像拍摄方面要求较低,有效性与鲁棒性较高,计算速度较快,可以满足实时监控的需求.     

Moving Object Detecting Method in Video

A method of moving object detection that integrates image gradient information with motion information is described herein. One multi-scale morphological gradient operator is used to detect gradient information. This operator has a very good effect on the detail of the edge location. The result is superior to the traditional method in edge continuity and isotropy. Past approaches have used methods of detection based on motion information and edge information, but this is the first to use a multi-scale morphological gradient operator. The implementation described can operate on lower resolution images under difficult conditions. Novel contributions include: 1. Based on multi-scale morphological gradient operator, this algorithm is robust to noise, object shadow, and illumination. 2. Using interframe difference and only the first two frames, this detection method uses very little computation and is suitable for real-time applications. 3. This method can detect rigid-body or non-rigid-body moving objects among video sequences with complicated backgrounds.     

基于改进HOG特征的空间非合作目标检测

传统的非合作目标检测方法大都基于一定的匹配模板,这不仅需要预先指定先验信息,进而设计合适的检测模板,而且同一模板只能对具有相似形状的目标进行检测,不易直接用于检测形状未知的非合作目标。为降低检测过程中对目标形状等先验信息的要求,借鉴基于规范化梯度的物体区域估计方法,提出一种基于改进方向梯度直方图特征的目标检测方法,首先构建包含有自然图像和目标图像的训练数据集;然后提取标记区域的改进方向梯度直方图特征,以更好地保持局部特征的结构性,并根据级联支持向量机训练模型,从数据集中自动学习目标物体的判别特征;最后,将训练后的模型用于检测测试集图像中的目标。实验结果表明,算法在由4953幅和100幅图像构成的测试集中分别取得94.5%和94.2%的检测率,平均每幅图像的检测时间约为0.031 s,具有较低的时间开销,且对目标的旋转及光照变化具有一定的鲁棒性。     

示温漆图像等温线提取算法

分析示温漆（TIP）图像特征，根据等温线附近产生局部梯度极值的特点，实验对比了4种边缘提取算法效果。根据实验结果，选用Canny算子提取等温线。提出在边缘提取前进行K means聚类处理，并对K means聚类算法和Canny算子进行了改进。提出了两种K means初始聚类中心的选择方法，更适于示温漆图像的分割。改进了Canny算子的内核，提升了等温线的质量。结果表明:该算法能够快速提取清晰、连续的等温线，效果良好，满足工程应用要求，已用于示温漆自动判读软件开发。      

基于边缘相似性的异源图像匹配

异源图像匹配是视觉导航、多源图像融合分析的关键步骤之一。对于成像机理差别较大的异源图像,如SAR图像和可见光图像,采用传统的异源图像匹配算法难以得到满意结果。本文提出一种基于边缘相似性的异源图像匹配方法,首先分别提取待匹配图像的边缘特征点集;然后计算基准图的边缘距离场;最后基于边缘相似性模型,通过实时图边缘图和基准图边缘距离场计算边缘相似度,寻找相似度最大的变换参数即为最终匹配参数。采用SAR与可见光图对方法进行了测试,结果表明,这种方法能够快速可靠地实现异源图像匹配。