多时相遥感影像的深度卷积匹配算法研究

针对传统人工设计的特征描述符在面对几何差异和辐射差异较大、地物变化明显的多时相遥感影像时,容易造成大量误匹配问题,提出一种适用于遥感影像的双筛选双约束的卷积神经网络匹配算法,通过CNN提取影像深层语义特征图,在特征图中筛选同时满足优先最大原则和精确极值原则的关键点,并在对应位置提取512维描述符。在特征匹配阶段,通过由粗到精的反向匹配约束和RANSAC约束相结合的策略,保证了误匹配点有效剔除的同时保留一定数量的正确匹配点对,提高了匹配的精度。实验结果表明：该方法的匹配数量适中,正确匹配率较实验选取的其他算法相比有所提高,影像配准误差减小2个像素左右,匹配运行时间提升明显,匹配效果良好并且具有一定的适应性和鲁棒性。     

Histogram thresholding for unsupervised change detection of remote sensing images

The change-detection problem can be viewed as an unsupervised classification problem with two classes corresponding to changed and unchanged areas. Image differencing is a widely used approach to change detection. It is based on the idea of generating a difference image that represents the modulus of the spectral change vectors associated with each pixel in the study area. To separate out the changed and unchanged classes in the difference image automatically, any unsupervised technique can be used. Thresholding is one of the cheapest techniques among them. However, in thresholding approaches, selection of the best threshold value is not a trivial task. In this work, several non-fuzzy and fuzzy histogram thresholding techniques are investigated and compared for the change-detection problem. Experimental results, carried out on different multitemporal remote sensing images (acquired before and after an event), are used to assess the effectiveness of each of the thresholding techniques. Among all the thresholding techniques investigated here, Liu's fuzzy entropy followed by Kapur's entropy are found to be the most robust techniques.     

基于异常区域感知的多时相高分辨率遥感图像配准

在对多时相高分辨遥感图像进行配准时,由于成像条件差异,图像间存在的地物变化与相对视差偏移两类典型异常区域会影响配准精度。针对上述配准中存在的问题,提出一种基于异常区域感知的多时相高分辨率遥感图像配准方法,包括粗匹配和精配准两个阶段。尺度不变特征变换（SIFT）算法考虑到尺度空间属性,不同尺度空间提取的特征点在图像中对应不同大小的斑块,高尺度空间提取的特征点对应图像中的大斑点,其对应地物相对稳定、不易发生变化。首先,利用SIFT算法提取高尺度空间特征点完成图像快速粗匹配;其次,利用灰度相关性度量对图像块进行相对偏移量统计分类以感知视差偏移区域,同时结合空间约束条件,确定低尺度空间特征点的有效提取区域以及匹配点搜索范围,完成图像精配准。实验结果表明,将该方法用于多时相高分辨遥感图像配准,可有效抑制异常区域对特征点提取的影响进而提高配准精度。     

Fuzzy clustering algorithms for unsupervised change detection in remote sensing images

In this paper, we propose a context-sensitive technique for unsupervised change detection in multitemporal remote sensing images. The technique is based on fuzzy clustering approach and takes care of spatial correlation between neighboring pixels of the difference image produced by comparing two images acquired on the same geographical area at different times. Since the ranges of pixel values of the difference image belonging to the two clusters (changed and unchanged) generally have overlap, fuzzy clustering techniques seem to be an appropriate and realistic choice to identify them (as we already know from pattern recognition literatures that fuzzy set can handle this type of situation very well). Two fuzzy clustering algorithms, namely fuzzy c-means (FCM) and Gustafson-Kessel clustering (GKC) algorithms have been used for this task in the proposed work. For clustering purpose various image features are extracted using the neighborhood information of pixels. Hybridization of FCM and GKC with two other optimization techniques, genetic algorithm (GA) and simulated annealing (SA), is made to further enhance the performance. To show the effectiveness of the proposed technique, experiments are conducted on two multispectral and multitemporal remote sensing images. A fuzzy cluster validity index (Xie-Beni) is used to quantitatively evaluate the performance. Results are compared with those of existing Markov random field (MRF) and neural network based algorithms and found to be superior. The proposed technique is less time consuming and unlike MRF does not require any a priori knowledge of distributions of changed and unchanged pixels.     

Saliency detection based on self-adaptive multiple feature fusion for remote sensing images

ABSTRACT

Saliency detection has been revealed an effective and reliable approach to extract the region of interest (ROI) in remote sensing images. However, most existing saliency detection methods employing multiple saliency cues ignore the intrinsic relationship between different cues and do not distinguish the diverse contributions of different cues to the final saliency map. In this paper, we propose a novel self-adaptively multiple feature fusion model for saliency detection in remote sensing images to take advantage of this relationship to improve the accuracy of ROI extraction. First, we take multiple feature channels, namely colour, intensity, texture and global contrast into consideration to produce primary feature maps. Particularly, we design a novel method based on dual-tree complex wavelet transform for remote sensing images to generate texture feature pyramids. Then, we introduce a novel self-adaptive multiple feature fusion method based on low-rank matrix recovery, in which the significances of feature maps are ranked by the low rank constraint recovery, and subsequently multiple features’ contributions are allocated adaptively to produce the final saliency map. Experimental results demonstrate that our proposal outperforms the state-of-the-art methods.     

Image fusion techniques for remote sensing applications

Image fusion refers to the acquisition, processing and synergistic combination of information provided by various sensors or by the same sensor in many measuring contexts. The aim of this survey paper is to describe three typical applications of data fusion in remote sensing. The first study case considers the problem of the synthetic aperture radar (SAR) interferometry, where a pair of antennas are used to obtain an elevation map of the observed scene; the second one refers to the fusion of multisensor and multitemporal (Landsat Thematic Mapper and SAR) images of the same site acquired at different times, by using neural networks; the third one presents a processor to fuse multifrequency, multipolarization and mutiresolution SAR images, based on wavelet transform and multiscale Kalman filter (MKF). Each study case presents also the results achieved by the proposed techniques applied to real data.     

Hierarchical fusion and divergent activation based weakly supervised learning for object detection from remote sensing images

Object detection and location from remote sensing (RS) images is challenging, computationally expensive, and labor intense. Benefiting from research on convolutional neural networks (CNNs), the performance in this field has improved in the recent years. However, object detection methods based on CNNs require a large number of images with annotation information for training. For object location, these annotations must contain bounding boxes. Furthermore, objects in RS images are usually small and densely co-located, leading to a high cost of manual annotation. We tackle the problem of weakly supervised object detection under such conditions, aiming to learn detectors with only image-level annotations, i.e., without bounding box annotations. Based on the fact that the feature maps of a CNN are localizable, we hierarchically fuse the location information from the shallow feature map with the class activation map to obtain accurate object locations. In order to mitigate the loss of small or densely distributed objects, we introduce a divergent activation module and a similarity module into the network. The divergent activation module is used to improve the response strength of the low-response areas in the shallow feature map. Densely distributed objects in RS images, such as aircraft in an airport, often exhibit a certain similarity. The similarity module is used to improve the feature distribution of the shallow feature map and to suppress background noise. Comprehensive experiments on a public dataset and a self-assembled dataset (which we made publicly available) show the superior performance of our method compared to state-of-the-art object detectors.     

Region-driven distance regularized level set evolution for change detection in remote sensing images

Change detection is a fundamental task in the interpretation and understanding of remote sensing images. The aim is to partition the difference images acquired from multitemporal satellite images into changed and unchanged regions. Level set method is a promising way for remote sensing images change detection among the existed methods. Unfortunately, re-initialization, a necessary step in classical level set methods is known a complex and time-consuming process, which may limits their practical application in remote sensing images change detection. In this paper, we present an unsupervised change detection approach for remote sensing image based on an improved region-based active contour model without re-initialization. In order to eliminate the process for re-initialization and reduce the numerical errors caused by re-initialization, we describe an improving level set method for remote sensing images change detection. The proposed method introduced a distance regularization term into the energy function which could maintain a desired shape of the level set function and keep a signed distance profile near the zero level set. The experimental results on real multi-temporal remote sensing images demonstrate the advantages of our method in terms of human visual perception and segmentation accuracy.     

面向对象特征融合的高分辨率遥感图像变化检测方法*

针对高分辨率遥感图像变化检测的难点和传统像元级变化检测方法的局限性,提出了基于面向对象的思想,利用分割后图像对象的光谱特征、纹理特征、形状特征分别进行变化检测,然后将不同对象特征检测结果进行融合得到最终结果。实验表明了本方法比传统的像素级方法对高分辨率遥感图像变化检测有较强的优势。     

模糊Bayes 理论在遥感影像变化检测中的应用

针对传统基于Bayes 决策规则的遥感影像变化检测方法中参数估计的不足以及分类过程中的硬划分问题,采用动态更新变化和未变化两类像元模糊子集的方法,实现对两类像元模糊子集中参数的动态更新,利用估计参数获得各子集的后验概率函数,再将后验概率函数转化为模糊子集的模糊隶属函数,从而获得各子集的指标函数,根据指标函数对影像中未分类的像元值进行判断,实现遥感影像的变化区域提取。实验结果表明：与现有的基于Bayes 决策规则的遥感影像变化检测方法及ERDAS 软件生成结果相比,提出的方法具有更好的变化检测精度。     

基于全变分模型的多时相遥感影像厚云去除算法

针对多时相遥感影像厚云去除出现的亮度不一致和明显边界的问题,提出了一种结合全变分模型和泊松方程的多时相遥感影像厚云去除算法。首先,通过多时相遥感影像间共同区域的亮度信息计算亮度校正系数,对图像的亮度进行校正,降低亮度差异对去云结果的影响。然后,基于选择多源全变分模型对亮度校正后的多时相遥感影像进行重建,提高融合结果的空间平滑性及其与原始影像的相似性。最后,利用泊松方程对重建图像的局部区域进行优化。实验结果表明,该算法能够有效解决亮度不一致和边界问题。     

Geometrical processing of multi-sensoral multi-temporal satellite images for change detection studies

A technique for geometrical processing of multi-sensoral and multispectral satellite images for the purposes of change detection studies is presented here. The technique involves geometrical rectification (geocoding), and image registration with two-dimensional image correlation. The application of the technique has been demonstrated in an area within the Niger Sahel in West Africa. The study was conducted with MSS and TM image data. The procedure results in image registration accuracy of 0.28pixel, which in this instance is good for change detection purposes.     

遥感图像Contourlet变换域压缩融合

基于传统分块压缩感知(BCS)的图像融合中,由于空间域BCS采样缺乏考虑图像的全局特性,导致融合图像重构质量差,且存在分块效应。首先将输入图像在Contourlet变换(CT)域稀疏表示,并对CT分解系数进行分块压缩感知;再对压缩采样线性加权融合;最后用迭代阈值投影(ITP)方法重构融合图像,并消除分块效应。提出了基于Contourlet变换域分块压缩感知(CTBCS)的遥感图像压缩融合方法,并给出算法的详细实现流程。基于BCS和CTBCS进行压缩采样,再用ITP算法进行图像重构,仿真结果显示,与BCS相比,CTBCS采样有效考虑了图像的全局特性,基于CTBCS的ITP重构收敛速度更快,重构计算复杂度更小,重构精度更好,对应的重构图像峰值信噪比(PSNR)更高;实际资料测试结果表明,基于CTBCS的压缩融合效果比基于BCS的压缩融合效果更好,更接近常规CT融合效果。CTBCS压缩融合用较少量采样点获得与常规CT相比拟的融合结果,有效实现了大数据量遥感图像的压缩融合。     

Accelerated genetic algorithm based on search-space decomposition for change detection in remote sensing images

Detecting change areas among two or more remote sensing images is a key technique in remote sensing. It usually consists of generating and analyzing a difference image thus to produce a change map. Analyzing the difference image to obtain the change map is essentially a binary classification problem, and can be solved by optimization algorithms. This paper proposes an accelerated genetic algorithm based on search-space decomposition (SD-aGA) for change detection in remote sensing images. Firstly, the BM3D algorithm is used to preprocess the remote sensing image to enhance useful information and suppress noises. The difference image is then obtained using the logarithmic ratio method. Secondly, after saliency detection, fuzzy c-means algorithm is conducted on the salient region detected in the difference image to identify the changed, unchanged and undetermined pixels. Only those undetermined pixels are considered by the optimization algorithm, which reduces the search space significantly. Inspired by the idea of the divide-and-conquer strategy, the difference image is decomposed into sub-blocks with a method similar to down-sampling, where only those undetermined pixels are analyzed and optimized by SD-aGA in parallel. The category labels of the undetermined pixels in each sub-block are optimized according to an improved objective function with neighborhood information. Finally the decision results of the category labels of all the pixels in the sub-blocks are remapped to their original positions in the difference image and then merged globally. Decision fusion is conducted on each pixel based on the decision results in the local neighborhood to produce the final change map. The proposed method is tested on six diverse remote sensing image benchmark datasets and compared against six state-of-the-art methods. Segmentations on the synthetic image and natural image corrupted by different noise are also carried out for comparison. Results demonstrate the excellent performance of the proposed SD-aGA on handling noises and detecting the changed areas accurately. In particular, compared with the traditional genetic algorithm, SD-aGA can obtain a much higher degree of detection accuracy with much less computational time.     

A novel change detection approach for VHR remote sensing images by integrating multi-scale features

A novel change detection (CD) method for very high-resolution images is proposed by integrating multi-scale features. First, a novel edge density matching index was designed, and the structural similarity of textures, including grey level co-occurrence matrix, Gaussian Markov random field, and Gabor features between bitemporal images, were extracted to measure changes. Then, an adaptive approach was proposed to select optimal textures based on the majority consistency between spectrum and textures. Afterward, all features were decomposed into multi-scale features and fused into initial CD maps using Dempster–Shafer evidence theory. Finally, advantage fusion was implemented to generate the final CD map by fusing initial CD maps to remove noise and preserve details. Experiments conducted on real SPOT 5 and simulated QuickBird datasets, which achieved the total error ratios of 8.74% and 2.50%, respectively, indicate the effectiveness of the proposed approach.     

用于遥感舰船细粒度检测与识别的关键子区域融合网络

目的 遥感图像中的舰船目标细粒度检测与识别在港口海域监视以及情报搜集等应用中有很高的实际应用价值,但遥感图像中不同种类的舰船目标整体颜色、形状与纹理特征相近,分辨力不足,导致舰船细粒度识别困难。针对该问题,提出了一种端到端的基于关键子区域特征的舰船细粒度检测与识别方法。方法 为了获得更适于目标细粒度识别的特征,提出多层次特征融合识别网络,按照整体、局部子区域两个层次从检测网络得到的候选目标区域中提取特征。然后结合候选目标中所有子区域的信息计算每个子区域的判别性显著度,对含有判别性组件的关键子区域进行挖掘。最后基于判别性显著度将子区域特征与整体特征进行自适应融合,形成表征能力更强的特征,对舰船目标进行细粒度识别。整个检测与识别网络采用端到端一体化设计,所有候选目标特征提取过程只需要经过一次骨干网络的计算,提高了计算效率。结果 在公开的带有细粒度类别标签的HRSC2016(high resolution ship collection)数据集L3任务上,本文方法平均准确率为77.3%,相较于不采用多层次特征融合识别网络提升了6.3%;在自建的包含45类舰船目标的FGSAID(fine-gr...     

遥感影像小目标检测研究进展

独特的拍摄视角和多变的成像高度使得遥感影像中包含大量尺寸极其有限的目标,如何准确有效地检测这些小目标对于构建智能的遥感图像解译系统至关重要。本文聚焦于遥感场景,对基于深度学习的小目标检测进行全面调研。首先,根据小目标的内在特质梳理了遥感影像小目标检测的3个主要挑战,包括特征表示瓶颈、前背景混淆以及回归分支敏感。其次,通过深入调研相关文献,全面回顾了基于深度学习的遥感影像小目标检测算法。选取3种代表性的遥感影像小目标检测任务,即光学遥感图像小目标检测、SAR图像小目标检测和红外图像小目标检测,系统性总结了3个领域内的代表性方法,并根据每种算法使用的技术思路进行分类阐述。再次,总结了遥感影像小目标检测常用的公开数据集,包括光学遥感图像、SAR图像及红外图像3种数据类型,借助于3种领域的代表性数据集SODA-A（small object detection datasets）、AIR-SARShip和NUAA-SIRST（Nanjing University of Aeronautics and Astronautics,single-frame infrared small target）,进一步对主流的遥感影像目标检测算法在面对小目标时的性能表现进行横向对比及深入评估。最后,对遥感影像小目标检测的应用现状进行总结,并展望了遥感场景下小目标检测的发展趋势。     

遥感图像变化区域的无监督压缩感知

传统的基于结构特征的遥感图像变化检测方法,易受成像稳定性的影响而误差很大。针对图像内在的稀疏性结构信息,提出基于压缩感知(CS)的遥感图像变化检测方法。通过自适应构造超完备字典将图像局部信息投影到高维空间中,实现图像的稀疏表示,并运用随机矩阵得到了数据在高维空间中的低维特征子空间。最后利用模糊C均值(FCM)聚类算法进行无监督聚类,实现遥感图像变化区域信息的重构。实验结果表明,本文方法不仅能够很好的检测出图像的轮廓变化和图像的区域变化,而且对噪声具有很好的鲁棒性。     

航空遥感图像深度学习目标检测技术研究进展

航空遥感图像目标检测旨在定位和识别遥感图像中感兴趣的目标,是航空遥感图像智能解译的关键技术,在情报侦察、灾害救援和资源勘探等领域具有重要应用价值。然而由于航空遥感图像具有尺寸大、目标小且密集、目标呈任意角度分布、目标易被遮挡、目标类别不均衡以及背景复杂等诸多特点,航空遥感图像目标检测目前仍然是极具挑战的任务。基于深度卷积神经网络的航空遥感图像目标检测方法因具有精度高、处理速度快等优点,受到了越来越多的关注。为推进基于深度学习的航空遥感图像目标检测技术的发展,本文对当前主流遥感图像目标检测方法,特别是2020—2022年提出的检测方法,进行了系统梳理和总结。首先梳理了基于深度学习目标检测方法的研究发展演化过程,然后对基于卷积神经网络和基于Transformer目标检测方法中的代表性算法进行分析总结,再后针对不同遥感图象应用场景的改进方法思路进行归纳,分析了典型算法的思路和特点,介绍了现有的公开航空遥感图像目标检测数据集,给出了典型算法的实验比较结果,最后给出现阶段航空遥感图像目标检测研究中所存在的问题,并对未来研究及发展趋势进行了展望。     

A data-distributed parallel algorithm for wavelet-based fusion of remote sensing images

With the increasing importance of multiplatform remote sensing missions, the fast integration or fusion of digital images from disparate sources has become critical to the success of these endeavors. In this paper, to speed up the fusion process, a Data-distributed Parallel Algorithm for wavelet-based Fusion (DPAF for short) of remote sensing images which are not geo-registered remote sensing images is presented for the first time. To overcome the limitations on memory space as well as the computing capability of a single processor, data distribution, data-parallel processing and load balancing techniques are integrated into DPAF. To avoid the inherent communication overhead of a wavelet-based fusion method, a special design called redundant partitioning is used, which is inspired by the characteristics of wavelet transform. Finally, DPAF is evaluated in theory and tested on a 32-CPU cluster of workstations. The experimental results show that our algorithm has good parallel performance and scalability.