Locality preserving fusion of multi-source images for sea-ice classification

We present a novel sea-ice classification framework based on locality preserving fusion of multi-source images information.The locality preserving fusion arises from two-fold,i.e.,the local characterization in both spatial and feature domains.We commence by simultaneously learning a projection matrix,which preserves spatial localities,and a similarity matrix,which encodes feature similarities.We map the pixels of multi-source images by the projection matrix to a set fusion vectors that preserve spatial localities of the image.On the other hand,by applying the Laplacian eigen-decomposition to the similarity matrix,we obtain another set of fusion vectors that preserve the feature local similarities.We concatenate the fusion vectors for both spatial and feature locality preservation and obtain the fusion image.Finally,we classify the fusion image pixels by a novel sliding ensemble strategy,which enhances the locality preservation in classification.Our locality preserving fusion framework is effective in classifying multi-source sea-ice images(e.g.,multi-spectral and synthetic aperture radar(SAR)images)because it not only comprehensively captures the spatial neighboring relationships but also intrinsically characterizes the feature associations between different types of sea-ices.Experimental evaluations validate the effectiveness of our framework.

Multi-Scale PIIFD for Registration of Multi-Source Remote Sensing Images

This paper aims at providing multi-source remote sensing images registered in geometric space for image fusion.Focusing on the characteristics and differences of multi-source remote sensing images,a feature-based registration algorithm is implemented.The key technologies include image scale-space for implementing multi-scale properties,Harris corner detection for keypoints extraction,and partial intensity invariant feature descriptor(PIIFD)for keypoints description.Eventually,a multi-scale Harris-PIIFD image registration algorithm framework is proposed.The experimental results of fifteen sets of representative real data show that the algorithm has excellent,stable performance in multi-source remote sensing image registration,and can achieve accurate spatial alignment,which has strong practical application value and certain generalization ability.

Accuracy Analysis on the Automatic Registration of Multi-Source Remote Sensing Images Based on the Software of ERDAS Imagine

The automatic registration of multi-source remote sensing images (RSI) is a research hotspot of remote sensing image preprocessing currently. A special automatic image registration module named the Image Autosync has been embedded into the ERDAS IMAGINE software of version 9.0 and above. The registration accuracies of the module verified for the remote sensing images obtained from different platforms or their different spatial resolution. Four tested registration experiments are discussed in this article to analyze the accuracy differences based on the remote sensing data which have different spatial resolution. The impact factors inducing the differences of registration accuracy are also analyzed.

Image Processing on Geological Data in Vector Format and Multi-Source Spatial Data Fusion

The geological data are constructed in vector format in geographical information system (GIS) while other data such as remote sensing images, geographical data and geochemical data are saved in raster ones. This paper converts the vector data into 8 bit images according to their importance to mineralization each by programming. We can communicate the geological meaning with the raster images by this method. The paper also fuses geographical data and geochemical data with the programmed strata data. The result shows that image fusion can express different intensities effectively and visualize the structure characters in 2 dimensions. Furthermore, it also can produce optimized information from multi-source data and express them more directly.

ANALYSIS OF SPECTRAL CHARACTERISTICS AMONG DIFFERENT SENSORS BY USE OF SIMULATED RS IMAGES

This research,by use of RS image_simulating method,simulated apparent reflectance images at sensor level and ground_reflectance images of SPOT_HRV,CBERS_CCD,Landsat_TM and NOAA14_AVHRR’s corresponding bands.These images were used to analyze sensor’s differences caused by spectral sensitivity and atmospheric impacts.The differences were analyzed on Normalized Difference Vegetation Index(NDVI).The results showed that the differences of sensors’ spectral characteristics cause changes of their NDVI and reflectance.When multiple sensors’ data are applied to digital analysis,the error should be taken into account.Atmospheric effect makes NDVI smaller,and atmospheric correction has the tendency of increasing NDVI values.The reflectance and their NDVIs of different sensors can be used to analyze the differences among sensor’s features.The spectral analysis method based on RS simulated images can provide a new way to design the spectral characteristics of new sensors.

EDGE DETECTION METHOD OF REMOTE SENSING IMAGES BASED ON MATHEMATICAL MORPHOLOGY OF MULTI-STRUCTURE ELEMENTS

This paper puts forward an effective, specific algorithm for edge detection. Based on multi-structure elements of gray mathematics morphology, in the light of difference between noise and edge shape of RS images, the paper establishes multi-structure elements to detect edge by utilizing the grey form transformation principle. Compared with some classical edge detection operators, such as Sobel Edge Detection Operator, LOG Edge Detection Operator, and Canny Edge Detection Operator, the experiment indicates that this new algorithm possesses very good edge detection ability, which can detect edges more effectively, but its noise-resisting ability is relatively low. Because of the bigger noise & remote sensing image, the authors probe into putting forward other edge detection method based on combination of wavelet directivity checkout technology and small-scale Mathematical Morphology finally. So, position at the edge can be accurately located, the noise can be inhibited to a certain extent and the effect of edge detection is obvious.

THE HYPERMEDIA DATA MODEL BASED ON THE INFINITY IMAGE

This paper presents the hypermedia data model based on the infinity RS image information system we have developed.The hypermedia data model consists of different semantic units called nodes,and the associations between nodes are called links.This paper proposes three kinds of nodes (interior node,physical node and complex node) and two kinds of links (plane network structure link,hyper_cube network structure links).The hypermedia information system,based on the model and the basic data layer (the infiniy RS image),represents a digital globe.An approach to the “Getting Lost in the Hyper_space” problem is presented.The approach using the hypermedia data model is an efficient way of handling a large number of RS images in various geographical information systems.

基于YOLOv7-RS的遥感图像目标检测研究

针对遥感图像目标检测过程中存在的背景复杂、目标特征不明显、小目标排列密集的问题,基于YOLOv7算法,提出了一种改进的遥感图像目标检测算法YOLOv7-RS(YOLOv7-Remote Sensing),提高了遥感图像的目标检测精度。首先,向特征提取网络中融合SimAM减少背景噪声的干扰;其次,提出了D-ELAN网络增强遥感目标的特征提取能力;再次,利用SIOU损失函数以提高算法模型的收敛速度;最后,优化了正负样本分配策略,改善了遥感图像中小目标密集排列时的漏检问题。实验结果表明,YOLOv7-RS在NWPU VHR-10和DOTA数据集上的mAP达到95.4%和74.1%,相较于其他主流算法有了明显提升。

基于SmartImage的低空影像快速拼接应用案例分析

通过对低空数字航空摄影系统中的航摄数据使用Smart Image软件进行影像数据拼接案例的介绍和分析,叙述了影像拼接的具体作业流程及特点。从数据操作的快速性和简便性上详细分析了其在应急测绘中的应用,为更好地利用无人机航摄数据做好快速应急测绘保障提供了技术思路。

GIS与RS集成的高分辨率遥感影像分类技术在地类识别中的应用

为提高高分辨率遥感影像的分类精度 ,本文提出了一种 GIS与 RS集成的分类技术。它从遥感影像和 GIS矢量数据一体化的角度出发 ,充分利用了矢量数据的图斑边界信息 ,通过提取单一地类图斑内的灰度特征、纹理特征和形态特征识别图斑所属地类。经研究表明 :无论在实验结果上还是在分类的机理上都证明了 ,在高分辨率遥感影像的土地利用分类中 ,这种 GIS与

基于RS的绿地信息提取方法的研究——以延安市及环城地区为例

以延安市及环城地区为例,探讨了提取绿地信息的遥感(RS)数字图像处理最佳方法。对研究区遥感图像进行了波段组合、对比度拉伸、几何纠正,并对3种图像增强方法(密度分割、差值运算、植被指数)进行了比较,对植被指数图像进行了无监分类处理。结果表明,图像几何纠正时地形复杂地区应选取更多的控制点,一般为理论值的6倍;植被指数为该区绿地信息提取的理想方法,通过对此图像进行无监分类,可以得到比较理想的绿地面积信息。

基于RS和GIS的小型城市土地利用动态分析——以杨凌示范区为例

根据1986年,1995年和2003年3期TM遥感影像,利用遥感技术和地理信息系统空间分析方法,研究了1986—2003年间杨凌示范区的土地利用动态变化情况。分析结果显示:(1)在1986—2003年间,耕地面积逐年下降,17 a间下降了20 km2多。1986年,1995年及2003年耕地分别占总土地面积的74%,59.7%和50.8%;而园地面积增加幅度最大,增加了近12 km2,年变化率近10%;林地和交通用地也有了明显的增加,增长幅度分别为7.4%,7.1%;此外,居民点用地也有明显增加。(2)杨凌在1986—1995年间,居民点用地几乎没有变化,而1995—2003年间居民点用地有了大幅度的增加。另外,2003年交通用地比1995年在总土地面积中所占的比例增加了1.6%,这充分说明了杨凌的城市化步伐不断加快。

RS-Turbo级联码的性能仿真及其在图像传输中的应用

RS码是一种纠突发错误能力很强的信道编码方式,T urbo码是一种巧妙的将卷积码和随机交织器结合在一起,同时采用软输出并通过不断迭代的方法译码来逼近最大似然编码的一种新的纠错能力很强的信道编码方式;本文分析了两种编码方式并研究了将二者级联后RS T urbo的性能,给出了将其级联码在图像传输中的应用。

基于RS流域枯水资源的判读识别

在GIS和RS技术的支持下,以单个水文站所控制的流域为统计单元,借助于ArcView软件强大的计算功能、ERDARSIMAGE软件强大的图象处理功能,在TM影像确定单个水文站所控制的流域面并数字化,通过SPSS软件进行多元回归分析,提出从TM影像判读枯水资源的多元回归方程。

基于RS、GIS重庆市都市圈生态绿地特征研究

在TM影像的基础上,应用REDAS和GIS软件,对重庆市都市区的绿地生态进行了研究。为了提取正确的生态绿地专题信息,对TM影像进行了波段组合从而完成解译、监督分类,导入GIS软件进行绿地属性信息的提取。分析了重庆绿地的总体情况,并提出了一定的建议。

基于CBERS-2遥感数据的艾比湖流域景观生态分类系统

景观生态分类是景观生态学研究的一项重要内容,是开展景观评价、规划与管理等工作的基础。应用CBERS-2遥感影像数据,以地质地貌、土地利用/土地覆被状况、地表植被等因子为分类依据,对艾比湖流域景观生态类型进行了自上而下地划分。研究认为:景观生态分类是建立在尺度的基础之上,不同尺度上的分类单元在纵向上构成了景观带至景观元的多等级景观生态分类体系;艾比湖流域景观生态类型可划分为2个景观类(4个景观亚类)、14个景观系、27个景观型,且该分类系统属于景观生态分类等级阶梯中的中尺度分类段;艾比湖流域景观生态分类系统,对进一步认识和科学合理地利用、规划及管理干旱区内陆湖泊流域的景观具有重要意义。

无线数据传输中RS-LT级联码的应用

提出了一种RS频域编码和LT编码级联的方法,探讨了其在无线数据传输中的应用。分析了RS-LT级联编码相对传统LT码在提高可译码概率方面的优点。该方法在低信噪比情况下的大数据量信息传输应用中具有很好的性能。仿真结果表明,在低信噪比的环境下可以有效恢复传输信息,提高接收图像品质。

基于RS、GIS重庆市都市区生态绿地分析

基于TM影像的基础上,应用REDAS和GIS软件,对重庆市都市区的绿地生态进行了研究.为了提取正确的生态绿地专题信息,对TM影像进行了波段组合从而进行解译,监督分类,导入GIS软件进行绿地属性信息的提取,分析了重庆绿地的总体情况,并提出了一定的建议.

QuickBird(快鸟)高分辨率卫星数据、gis与rs技术在城市绿地系统调查与测试中的应用——以六盘水市中心城为例

城市绿地系统调查与测试是绿地系统规划建设的基本前提,可为其提供决策性依据。传统的城市绿地调查主要以人工调查为主,工作量大,耗时长。以六盘水市中心城绿地系统调查与测试为例,探讨QuickBird卫星高分辨率的遥感影象、GIS与RS技术在绿地系统调查与测试中的应用,并得出切实可行的应用技术路线。

基于CBERS的喀斯特山区土地利用专题信息提取方法研究——以贵州省都匀市为例

以“3S”技术为技术背景,以遥感数字图像处理技术为主要技术支持,以中巴地球资源卫星CBERS和美国L andsat-7 TM影像为遥感数据源,探索CBERS数据在喀斯特山区的土地利用遥感解译中最理想的图像处理方法及分类方法,对比研究CBERS和TM在喀斯特地区土地利用分类实验中的各自优势。通过多次遥感图像处理技术实验与分析,摸索出了利用数学建模解决CBERS在喀斯特山区水体与阴影的混分问题以及建设用地与旱地、水田的混分问题的新方法,并以基于最佳指数波段选择法推算出了431波段为喀斯特地区土地利用分类的最佳波段组合。实验证明,中巴资源卫星影像较好地实现喀斯特地区大比例尺土地利用分类,完全可以替代国外遥感影像TM而运用于喀斯特山区土地利用调查中。