基于条件随机场的遥感图像语义标注

遥感图像包含的信息丰富,纹理复杂,而遥感图像语义标注又为后续的目标识别、检测、场景分析及高层语义的提取提供了重要信息和线索,这使其成为遥感图像理解领域中一个关键且极具挑战性的任务。首先针对遥感图像语义标注问题,提出采用条件随机场(CRF)框架对遥感图像的底层特征和上下文信息建模的方法,将Texton纹理特征与CRF中的自相关势能结合来捕捉遥感图像中的纹理信息及其上下文分布,采用组合Boosting算法进行Texton纹理特征选择和参数学习;然后将Lab空间中的颜色信息与CRF中的互相关势能结合来描述颜色上下文;最后用Graph Cut算法对CRF进行推导求解,得到图像自动语义标注结果。同时,建立了可见光遥感图像数据库Google-4,并对全部图像进行了人工标注。Google-4上的实验结果表明:采用CRF框架与Texton纹理特征和颜色特征相结合对遥感图像建模的方法与基于支持向量机(SVM)的方法相比较,能够取得更准确的语义标注结果。     

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。     

基于Rough/SVM的飞机目标识别模型

研究了基于粗糙集（Rough）和支持向量机（SVM）的模式分类技术,结合遥感图像中军用飞机目标识别进行理论分析和试验研究。基于粗糙集和支持向量机算法的优势,设计了基于粗糙集和决策有向无环图的支持向量机模式识别分类器,并对分类的性能进行了分析研究。利用粗糙集理论中属性约简方法去除冗余属性,降低飞机特征维数,提出了使用决策...     

SRS-Net: Training object detectors from scratch for remote sensing images without pretraining

Most of the current object detection algorithms use pretrained models that are trained on ImageNet and then fine-tuned in the network, which can achieve good performance in terms of general object detectors. However, in the field of remote sensing image object detection, as pretrained models are significantly different from remote sensing data, it is meaningful to explore a train-from-scratch technique for remote sensing images. This paper proposes an object detection framework trained from scratch, SRS-Net, and describes the design of a densely connected backbone network to provide integrated hidden layer supervision for the convolution module. Then, two necessary improvement principles are proposed: studying the role of normalization in the network structure, and improving data augmentation methods for remote sensing images. To evaluate the proposed framework, we performed many ablation experiments on the DIOR, DOTA, and AS datasets. The results show that whether using the improved backbone network, the normalization method or training data enhancement strategy, the performance of the object detection network trained from scratch increased. These principles compensate for the lack of pretrained models. Furthermore, we found that SRS-Net could achieve similar to or slightly better performance than baseline methods, and surpassed most advanced general detectors.     

Automatic recognition of ISAR ship images

Inverse synthetic aperture radar (ISAR) produces images of ships at sea which human operators can be trained to recognize. Because ISAR uses the ship's own varying angular motions (roll, pitch, and yaw) for cross-range resolution, the viewing aspect and cross-range scale factor are continually changing on time scales of a few seconds. This and other characteristics of ISAR imaging make the problem of automatic recognition of ISAR images quite distinct from the recognition of optical images. The nature of ISAR imaging of ships, and single-frame and multiple-frame techniques for segmentation, feature extraction, and classification are described. Results are shown which illustrate a capability for automatic recognition of ISAR ship imagery     

基于海岸线状特征匹配的近海域卫星遥感影像定位

针对卫星轨道参数及传感器姿态角等信息缺乏且无控制点的近海域遥感影像定位难题,提出了基于海岸线状特征匹配的影像定位方法。首先,扩展应用Live-Wire算法,实现待定位影像的海岸线交互式提取;然后,设计一种改进的曲线形状签名和优化的部分匹配算法,实现海岸曲线匹配;最后,根据曲线匹配结果计算变换矩阵,实现近海域卫星遥感影像定位。利用Land Sat和SPOT影像的定位实验验证了该方法的有效性。     

Target localization based on cross-view matching between UAV and satellite

Matching remote sensing images taken by an unmanned aerial vehicle (UAV) with satellite remote sensing images with geolocation information. Thus, the specific geographic location of the target object captured by the UAV is determined. Its main challenge is the considerable differences in the visual content of remote sensing images acquired by satellites and UAVs, such as dramatic changes in viewpoint, unknown orientations, etc. Much of the previous work has focused on image matching of homologous data. To overcome the difficulties caused by the difference between these two data modes and maintain robustness in visual positioning, a quality-aware template matching method based on scale-adaptive deep convolutional features is proposed by deeply mining their common features. The template size feature map and the reference image feature map are first obtained. The two feature maps obtained are used to measure the similarity. Finally, a heat map representing the probability of matching is generated to determine the best match in the reference image. The method is applied to the latest UAV-based geolocation dataset (University-1652 dataset) and the real-scene campus data we collected with UAVs. The experimental results demonstrate the effectiveness and superiority of the method.     

基于改进SURF算法的无人机遥感图像拼接方法

针对传统SIFT算法在无人机遥感图像拼接中存在的运算缓慢、误匹配较多且计算过于复杂,无法满足遥感图像处理的实时性要求等缺陷,以及由于采集到的图像之间存在曝光差异等情况,直接进行叠加拼接后极大可能会在边界处产生重影错位的情况,文章提出了一种改进的SURF算法与融合算法用于无人机的遥感图像拼接。首先,在特征检测阶段,将SURF算法与Harris角点检测算法2种算法相结合,快速得到图像的特征点与特征描述子;在特征匹配阶段分为粗匹配与精匹配2个步骤:通过KNN算法对待拼接图像间特征点的粗匹配,以及应用RANSAC算法去除误匹配点的精匹配;在图像融合阶段,采用了基于距离的加权平均算法进行图像融合;最后,实验表明:文章所提出的算法处理速度相比于传统SUFT算法提升了近5倍,相比于其他改进算法,匹配精度也有所提高,并且该算法能够有效提高图像拼接后的质量与效果,解决了拼接痕印明显、重影、错位等现象可能发生的问题。     

基于改进Yolov3 算法的舰船目标检测识别系统

针对复杂战场环境下对海目标检测识别的需求,设计了一种基于改进Yolov3 算法的海面舰船目标实 时检测识别系统。使用微调分类网络、增加训练尺度、聚类目标边框维度、二级特征分类等方法对Yolov3 检 测识别网络模型进行了优化,在提高识别精度的同时有效降低了漏检率和虚警率。实验结果表明,优化后的网 络模型在自建的舰船图像数据库中将检测识别平均准确率提高到了79.3%,对真实海上航拍视频中舰船目标识 别的平均准确率达到了81% 以上。     

一种基于纹理特征的卫星遥感图像云探测方法

 针对卫星遥感图像中的云探测问题,提出了一种有效的纹理特征分析方法。该方法使用反映图像灰度性质和空间关系的分形和灰度共生矩阵两类纹理,分别来描述云区域和无云的下垫面区域,并从这两个纹理的共5个特征参数构成的多维空间中简化出最小的二维分类空间,使该空间能够完全地区分卫星遥感图像中的云和各种下垫面,利用它设计的线性分类器可以高效地实现云的自动探测功能。大量实际图像测试结果正确率达到98%,证实了该方法的有效性。     

基于改进SSD的舰船目标精细化检测方法

以SSD为代表的主流深度学习方法在目标检测领域取得了显著的成绩,但由于该类方法只能以矩形框给出目标的概略位置,检测结果具有很大的背景冗余区域,特别是港口密集停泊的舰船在图像中会出现区域重叠,导致误检和漏检。针对以上问题,提出了一种具有旋转不变性的舰船目标精细化检测方法,该方法综合利用可变形卷积、可变形池化、旋转的边框回归和旋转的非极大值抑制等模块的优点,借鉴MobileNet架构对网络加速,通过学习密集区域目标的几何形变,有效预测目标的旋转角度,最终以旋转的矩形框给出目标的位置。实验结果表明,该算法可实现多类舰船目标类型区分和目标朝向判定的功能,有效地解决了实际应用中的目标精确定位定向难题,提高了自动目标识别的精确性,并满足工程应用的实时性要求。     

一种航空铆钉自动检测系统研制

研究并实现了一种图像识别的铆钉自动尺寸检测系统,主要介绍了系统的工作流程和原理,给出了系统硬件组成,并在对CCD相机的采集图像清晰度评价函数分析基础上,提出了一种适合多种铆钉检测的自动调焦方法。通过对图像滤波处理、边缘检测算法的论证分析,建立了适合铆钉检测的图像特征提取方案,最后给出了系统主要功能界面。     

Model-based segmentation of FLIR images

The use of gray-scale intensities together with the edge information present in a forward-looking infrared (FLIR) image to obtain a precise and accurate segmentation of a target is presented. A model of FLIR images based on gray-scale and edge information is incorporated in a gradient relaxation technique which explicitly maximizes a criterion function based on the inconsistency and ambiguity of classification of pixels with respect to their neighbors. Four variations of the basic technique which provide automatic selection of thresholds to segment FLIR images are considered. These methods are compared, and several examples of segmentation of ship images are given     

基于深度学习的无人机航拍目标检测研究综述

目标检测是提高无人机（UAV）感知能力的关键技术之一,其研究对于无人机的应用有着重要意义。与基于手工特征的传统方法相比,基于卷积神经网络的深度学习方法具有强大的特征学习和表达能力,成为目前目标检测任务的主流算法。近年来,目标检测技术已经在自然场景图像上取得了一系列突破性进展,在无人机领域的研究也逐渐成为热点。首先系统阐述了基于深度学习的目标检测算法的研究进展,并总结了相关算法的优缺点。对常见的航空影像数据集进行了梳理并介绍了迁移学习的方法;从无人机影像背景复杂、目标较小、视场大、目标具有旋转性的特点出发,对无人机目标检测在近期的研究进行了归纳和分析。最后讨论了存在的问题和未来可能的发展方向。     

基于运动特征和中心环绕模型的空对地车辆检测方法

平台的移动基于空基车辆检测以其视野广、速度快、适应性强等优点,近些年成为了智能交通和航空应急救援等领域内的一个热点课题。然而,在城市背景的交通环境下,由于复杂背景造成的干扰、车辆运动的不规律性以及光照等条件变化带来的噪声,有效地获取运动对象特征是空对地视觉监视方法面临的一个难题。为有效解决这一问题,提出了结合运动特征的中心环绕模型进行空对地车辆检测的算法。现有的空对地车辆检测算法,大多是针对固定的摄像头的情况下,基于运动特征进行检测,例如光流法、背景差法等。这些方法在对高速公路等背景相对较为简单的环境下获得了良好的检测结果,但当面对城市复杂背景条件或摄像头自身运动的状况时,难以有效地检测出运动目标。而在对颜色、强度等静态特征进行显著度分析的基础上,加入了对运动特征的分析,可以解决在复杂环境下准确提取车辆目标有效特征的问题。试验表明,相较于基于图像相减的检测算法和单一显著度算法,该算法可以获得更高的检测率与更低的误报率。     

基于图像特征融合的粉末床缺陷检测方法

针对单一特征对粉末床缺陷表达不明确导致检测效果不佳的问题,提出了一种基于特征融合的增材制造过程粉末床缺陷视觉检测方法。该算法分别使用SIFT方法、灰度共生矩阵和Hu不变矩提取尺度空间特征、纹理特征和几何特征,借助词袋模型对每张图像构建3组视觉单词直方图,通过串行融合3组视觉单词直方图得到新的特征矩阵,采用特征选择对融合后特征矩阵进行降维,并传入随机森林分类器中进行训练。实验结果表明,不同特征对粉末床不同类型缺陷检测具有不同的贡献,优化特征融合参数后,算法平均准确率达到97.46%,缺陷检测效果明显提升。     

Sea fog detection based on unsupervised domain adaptation

Sea fog detection with remote sensing images is a challenging task. Driven by the different image characteristics between fog and other types of clouds, such as textures and colors, it can be achieved by using image processing methods. Currently, most of the available methods are datadriven and relying on manual annotations. However, because few meteorological observations and buoys over the sea can be realized, obtaining visibility information to help the annotations is difficult. Considering t...     

一种基于肤色和脸部特征的人脸特征点检测算法

人脸检测通常是人机系统中人机交互的第一步,像人机系统中基于人体特征的用户身份识别,计算机对用户感情和意图的理解等.本文提出了一种用于办公室环境下的彩色图像中人脸检测算法.基于一种新的肤色检测算法,对图像进行肤色区域检测.算法通过构建眼,嘴模板来进行人脸的校验.实验结果表明,该算法可以实现在图像中出现照明,人脸表情,尺度较大范围变化情况下的人脸检测.     

基于ICA的遥感图像的色彩分类方法

根据独立成分分析（ICA）方法和多频谱卫星遥感图像的特点,提出了一种基于ICA的遥感图像色彩分类法。方法使用FastICA算法提取遥感图像的色彩独立成分,是RGB反转的结合,具有互补的分布,不受照明的影响。使用最大相似度分类算法对像素进行色彩分类,实验结果表明,方法的色彩分类效果较好,对多频谱遥感图像进行色彩分类十分有效。     

A new bearing fault diagnosis method based on modified convolutional neural networks

Fault diagnosis is vital in manufacturing system. However, the first step of the traditional fault diagnosis method is to process the signal, extract the features and then put the features into a selected classifier for classification. The process of feature extraction depends on the experimenters’ experience, and the classification rate of the shallow diagnostic model does not achieve satisfactory results. In view of these problems, this paper proposes a method of converting raw signals into two-dimensional images. This method can extract the features of the converted two-dimensional images and eliminate the impact of expert’s experience on the feature extraction process. And it follows by proposing an intelligent diagnosis algorithm based on Convolution Neural Network (CNN), which can automatically accomplish the process of the feature extraction and fault diagnosis. The effect of this method is verified by bearing data. The influence of different sample sizes and different load conditions on the diagnostic capability of this method is analyzed. The results show that the proposed method is effective and can meet the timeliness requirements of fault diagnosis.