噪声鲁棒的轻量级深度遥感场景图像分类检索

目的 基于深度神经网络的遥感图像处理方法在训练过程中往往需要大量准确标注的数据,一旦标注数据中存在标签噪声,将导致深度神经网络性能显著降低。为了解决噪声造成的性能下降问题,提出了一种噪声鲁棒的轻量级深度遥感场景图像分类检索方法,能够同时完成分类和哈希检索任务,有效提高深度神经网络在有标签噪声遥感数据上的分类和哈希检索性能。方法 选取轻量级神经网络作为骨干网,而后设计能够同时完成分类和哈希检索任务的双分支结构,最后通过设置损失基准的正则化方法,有效减轻模型对噪声的过拟合,得到噪声鲁棒的分类检索模型。结果 本文在两个公开遥感场景数据集上进行分类测试,并与8种方法进行比较。本文方法在AID（aerial image datasets）数据集上,所有噪声比例下的分类精度比次优方法平均高出7.8%,在NWPU-RESISC45（benchmark created by Northwestern Polytechnical University for remote sensing image scene classification covering 45 scene classes）数据集上,分类精度比次优方法平均高出8.1%。在效率方面,本文方法的推理速度比CLEOT（classification loss with entropic optimal transport）方法提升了2.8倍,而计算量和参数量均不超过CLEOT方法的5%。在遥感图像哈希检索任务中,在AID数据集上,本文方法的平均精度均值（mean average precision,mAP）在3种不同哈希比特下比MiLaN（metric-learning based deep hashing network）方法平均提高了5.9%。结论 本文方法可以同时完成遥感图像分类和哈希检索任务,在保持模型轻量高效的情况下,有效提升了深度神经网络在有标签噪声遥感数据上的鲁棒性。     

A statistical method for detecting logging-related canopy gaps using high-resolution optical remote sensing

In tropical rainforests, the sustainability of selective logging is closely linked to the extent of collateral stand damage. The capacity to measure the extent of such damage is essential for calculating carbon emissions due to forest degradation under the Reducing Emissions from Deforestation and Forest Degradation (REDD+) process. The use of remote sensing to detect canopy gaps in tropical rainforests is an attractive alternative to ground surveys, which are laborious and imprecise. In French Guiana, the detection of logging-related gaps using very high spatial resolution optical satellite images produced by the Système Pour l'Observation de la Terre (SPOT) 5 sensor is carried out by Office National des Forêts (ONF) (French National Forestry Agency). Gaps are detected using a segmentation method based on computer-assisted photointerpretation. Detection has been automated to improve and accelerate the process. We developed an automatic method, which involves estimating segmentation thresholds using a statistical approach. The principle of the method presented in this article is to model the forest's spectral signature by using a Gaussian distribution and calculate a divergence between that theoretical signature and the image histogram in order to detect gaps that constitute a reduction of forest cover. The segmentation threshold between gap and forest is thus no longer defined in the original radiometric area but as a discrepancy between theoretical distribution and histogram. Computing the divergence to define the threshold made it possible to efficiently automate the detection of all gaps and skid trails with a surface area greater than 100 m². The proportion of misclassified points measured during field surveys is 12%, which is a high level of precision. The proportion of misclassified points obtained is 12%. This tool could be used to assess the quality of logging operations or biomass loss in other areas where the forest is undergoing deterioration while still remaining predominant in the landscape.     

A novel method for vehicle detection in high-resolution aerial remote sensing images using YOLT approach

Multimedia Tools and Applications - Owing to the innovative challenge stood by an intergovernmental military alliance, we have proposed a model to find novel solutions in the areas of data...     

群智能方法在遥感信息提取中的应用分析

遥感数据作为重要的空间数据源,在众多领域发挥着不可或缺的作用。遥感信息获取技术的不断发展与遥感数据应用领域的不断扩展,促进了遥感信息提取方法的不断进步。随着人工智能算法不断被提出及成功应用,遥感信息提取领域也在逐步引入智能算法实现高效的信息提取。在对遥感信息提取方法的研究进展进行深入分析的基础上,剖析了群智能方法应用于遥感信息提取领域的潜力与优势。并应用微粒群优化方法进行遥感数据的分类,实现了微粒群优化方法应用于遥感数据分类的技术流程,取得了很好的实验结果。因此,群智能方法能够为遥感信息提取领域提供一种新的有效智能处理方法。     

A multi-scale target detection method for optical remote sensing images

Multimedia Tools and Applications - Faster RCNN is a region proposal based object detection approach. It integrates the region proposal stage and classification stage into a single pipeline, which...     

采用分裂Bregman的遥感影像亮度不均变分校正方法

目的：遥感影像成像过程由于受到传感器自身以及其他一些外部环境因素的影响,往往会呈现出整体的亮度不均,导致遥感影像解译和制图精度的降低。因此,需要对遥感影像进行亮度不均匀校正,提高影像的质量。方法：感知驱动的亮度不均变分校正方法,是一种新型的单幅遥感影像亮度不均校正方法,它受人眼视觉系统特性的启发,能够在有效校正影像整体亮度的同时增强局部对比度。本文用分裂Bregman迭代实现了对感知驱动亮度不均变分校正模型的最优化求解,在实现对影像整体亮度不均校正的同时,大幅提高了计算效率。结果：模拟实验和真实实验结果均表明采用分裂Bregman的亮度不均变分校正模型需要较少的计算时间,从效率上比采用最速下降法的校正模型提高了约6到7倍。结论：分裂Bregman方法能够有效求解感知驱动亮度不均变分模型,在保证校正结果整体亮度均匀,局部对比度增强的前提下,大大提高运算效率。     

Iterative regularization method for lidar remote sensing

In this paper we present an inversion algorithm for ill-posed problems arising in atmospheric remote sensing. The proposed method is an iterative Runge-Kutta type regularization method. Those methods are better well known for solving differential equations. We adapted them for solving inverse ill-posed problems. The numerical performances of the algorithm are studied by means of simulations concerning the retrieval of aerosol particle size distributions from lidar observations.     

Multi-parameter regularization method for atmospheric remote sensing

The iteratively regularized Gauss-Newton algorithm with simple bounds on the variables is extended to the multi-parameter case. The global regularization matrix is computed by using the L-curve method for a sequence of one-parameter regularization problems. Numerical results concerning the joint retrieval of O₃ and NO₂ profiles using the scattered light from the limb of the atmosphere are presented.     

A lightweight remote user authentication scheme for IoT communication using elliptic curve cryptography

Internet of things (IoT) has become a new era of communication technology for performing information exchange. With the immense increment of usage of smart devices, IoT services become more accessible. To perform secure transmission of data between IoT network and remote user, mutual authentication, and session key negotiation play a key role. In this research, we have proposed an ECC-based three-factor remote user authentication scheme that runs in the smart device and preserves privacy, and data confidentiality of the communicating user. To support our claim, multiple cryptographic attacks are analyzed and found that the proposed scheme is not vulnerable to those attacks. Finally, the computation and communication overheads of the proposed scheme are compared with other existing protocols to confirm that the proposed scheme is lightweight. A formal security analysis using AVISPA simulation tool has been done that confirms the proposed scheme is robust against relevant security threats.

     

遥感图像融合方法研究

为了使融合图像在高空间分辨率的基础上较好地保留光谱信息,研究了高分辨率图像和多光谱图像中的高频信息的关系;在基于小波变换的图像融合方法中引入ISM模型（Inter-Band Structure Model）,改进了原有的融合方法;提出了基于ISM模型与小波变换（Wavelet Transform）（简称I-W）的图像融合方法;通过与HIS方法及PCA方法进行了实验对比,结果证明：文中所提出的方法能较好地保留图像的空间和光谱信息。     

多源多时相遥感影像镶嵌方法探讨

为解决县级森林资源规划设计调查中多源多时相遥感影像镶嵌难题,本文提出一种基于合理直方图的影像镶嵌方法.在云南省多个县(市、区)的遥感影像镶嵌中应用此方法,获得较为理想的镶嵌影像图.结果表明,此方法在实践中具有较高的应用价值.     

Iteratively regularized Gauss-Newton method for atmospheric remote sensing

In this paper we present an inversion algorithm for nonlinear ill-posed problems arising in atmospheric remote sensing. The proposed method is the iteratively regularized Gauss-Newton method. The dependence of the performance and behaviour of the algorithm on the choice of the regularization matrices and sequences of regularization parameters is studied by means of simulations. A method for improving the accuracy of the solution when the identity matrix is used as regularization matrix is also discussed. Results are presented for atmospheric temperature retrievals from a far infrared spectrum observed by an airborne uplooking heterodyne instrument.     

The iterative flux-profile method for remote sensing applications

Iterative flux-profile methods allow calculation of sensible heat and momentum fluxes using temperature gradients and wind speed data obtained in the lower atmosphere. Flux-profile methods are also applied to the problem of regional evapotranspiration evaluation by the use of satellite imagery. The large number of pixels in these images and the long image time series that have become available make it necessary to develop reliable, fast and accurate algorithms to process the data. In this paper an analysis is made of the equations underlying the flux-profile method with the practical objective to improve the existing procedures for application with large datasets. After a review of the iterative methods to arrive at the solution, simple changes are suggested to improve estimates of the initial value and to speed up function evaluation. As an illustration of the suggested changes, a NOAA Advanced Very High Resolution Radiometer (AVHRR) case study from western Turkey is discussed. It is shown that the improved iterative algorithm is in this case a factor of 4-5 faster than the standard method. The results are also compared with those obtained by a recent analytical approximation.     

Boosting: a classification method for remote sensing

This article sets out to demonstrate how boosting can serve as a supervised classification method, and to compare its results with those of conventional methods. The comparison begins with a theoretical example in which several criteria are varied: number of pixels per class, overlapping (or not) of radiometric values between classes, and presence and absence of spatial structuring of classes within the geographical space. The results are then compared with a real case study of land cover based on a multispectral SPOT image of the Sousson catchment area (South of France). It is seen that (1) maximum likelihood gives better results than boosting when the radiometric values for each class are clearly separated. This advantage is lost as the number of pixels per class increases; (2) boosting is systematically better than maximum likelihood in the event of overlapping radiometric variable classes, whether or not there is a spatial structure.     

遥感卫星图像自动导航方法研究

遥感卫星图像自动导航方法用来自动地确定遥感卫星图像中每一个像素的地理经纬度,目前已经在气象、海洋、资源、环境、军事等领域得到了广泛应用,并且产生了巨大的社会和经济效益。介绍了一种新的基于最大相关系数的遥感卫星图像自动导航方法。首先给出了问题的描述;其次介绍了图像自动导航数据流程;然后设计并实现了一种新的基于最大相关系数的自动图像导航方法,它是整个遥感卫星自动导航的关键部分;最后给出了实例,验证了方法的可行性以及高精度。     

A regularised model-based pan-sharpening method for remote sensing images with local dissimilarities

Combining the spectral information of a low-resolution multispectral (LRMS) image and the spatial information of a high-resolution panchromatic (HRP) image to generate a high-resolution multispectral (HRMS) image has become an important and interesting issue. Local dissimilarities between the LRMS image and the HRP image affect the performance of the pan-sharpening technique. This paper presents a model-based pan-sharpening method with global and nonlocal spatial similarity regularisers to reduce the effects of the local dissimilarities. The degraded model relating the LRMS image to the unknown HRMS image is employed as the data-fitting term to keep spectral fidelity. Two spatial similarity constraints are utilized to further enhance the spatial resolution of the unknown HRMS image. The first regularisation term is under the assumption that the high-pass component of each HRMS band has the similar geometry structure with the adjusted high-pass component of the HRP image. A modulation matrix is constructed to reduce the contrast differences. Moreover, nonlocal self-similarity characteristic of the high-pass component extracted from each HRMS band is considered as another regulariser, which is an effective structural prior to improve the local spatial quality of the HRMS image. The weights of nonlocal similarity model are learned from the high-pass component of available HRP image. Experiments conducted on QuickBird and IKONOS data validate that the proposed pan-sharpening method can achieve better performance compared with several traditional and state-of-the-art pan-sharpening algorithms in terms of quantitative evaluation and visual analysis.     

A novel retrieval method for remote sensing image based on statistical model

With the increasing number of high-resolution remote sensing (HRRS) image technologies, there is an interest in seeking a way to retrieve images efficiently. In order to describe the images with abundant texture information more concisely and accurately, we propose a novel remote sensing image retrieval approach based on the statistical features of non-subsampled shearlet transform (NSST) coefficients, according to which we set up a model using Bessel K form (BKF). First, the remote sensing (RS) image is decomposed into several subbands of frequency and orientation using the non-subsampled shearlet transform. Then, we use the Bessel K distribution model is utilized to describe the coefficients of NSST high-frequency subband. Next, the BKF parameters are selected to serve as the texture feature to represent the characteristics of image, namely BKF statistical model feature (BSMF), and the feature vector of each image is created by combination with parameters at each high-pass subband. Both the experiment and theory indicate that the BKF distribution is highly matched with the statistical features of NSST coefficients within high-pass subbands. In our experiments, we applied the proposed method to two general RS image datasets- The UC Merced land use dataset and the Sydney dataset. The results show that our proposed method can achieve a more robust and commendable performance than the state-of-the-art approaches.     

Facial emotion and gesture reproduction method for substitute robot of remote person

CEOs of big companies may travel frequently to give their philosophies and policies to the employees who are working at world wide branches. Video technology makes it possible to give their lectures anywhere and anytime in the world very easily. However, 2-dimentional video systems lack the reality. If we can give natural realistic lectures through humanoid robots, CEOs do not need to meet the employees in person. They can save their time and money for traveling.We propose a substitute robot of remote person. The substitute robot is a humanoid robot that can reproduce the lecturers’ facial expressions and body movements, and that can send the lecturers to everywhere in the world instantaneously with the feeling of being at a live performance. There are two major tasks for the development; they are the facial expression recognition/reproduction and the body language reproduction.For the former task, we proposed a facial expression recognition method based on a neural network model. We recognized five emotions, or surprise, anger, sadness, happiness and no emotion, in real time. We also developed a facial robot to reproduce the recognized emotion on the robot face. Through experiments, we showed that the robot could reproduce the speakers’ emotions with its face.For the latter task, we proposed a degradation control method to reproduce the natural movement of the lecturer even when a robot rotary joint fails. For the fundamental stage of our research for this sub-system, we proposed a control method for the front view movement model, or 2-dimentional model.     

滑坡高分辨率遥感多维解译方法及其应用

目的:高分辨率遥感影像技术的发展使得对于地质灾害体的要素组成、形态结构的遥感解译成为可能。目前,遥感影像解译存在着过度依赖影像色彩、纹理、阴影等光学要素,片面追求影像解译标志,DEM数据利用程度低,对基于DEM、GIS的影像复合分析、空间分析、3D可视化等技术方法的应用较少等问题。方法：本文以灾前灾后高精度DEM和高分辨率遥感影像为基础,探讨了地质灾害滑坡的一维、二维、三维三种遥感解译方法,分析了三者之间的互补关系,并应用三种遥感解译方法对贵州关岭“6.28”特大滑坡进行了遥感解译分析,文章最后对有关滑坡多维遥感解译方法体系的建立进行了讨论。结果：研究结果表明：滑坡高分辨率遥感多维解译方法中,一维高程曲线计算、二维影像对比分析、三维场景精细解译分别属于滑坡遥感解译的初判方法、动态分析方法、定量计算方法;结论：其中,一维高程曲线计算为滑坡遥感的二、三维解译提供了有关滑坡崩塌区、滑坡区、堆积区的可能分区参考框架,而二维影像对比分析向三维场景精细解译的发展则体现了以人机交互方式为主要手段的滑坡高分辨率遥感影像解译由定性监测向定量计算的发展。