Pan-sharpening of multi-spectral images using a new variational model

In remote-sensing image processing, pan-sharpening is used to obtain a high-resolution multi-spectral image by combining a low-resolution multi-spectral image with a corresponding high-resolution panchromatic image. In this article, to preserve the geometry, spectrum, and correlation information of the original images, three hypotheses are presented, i.e. (1) the geometry information contained in the pan-sharpened image should also be contained in the panchromatic bands; (2) the upsampled multi-spectral image can be seen as a blurred form of the fused image with an unknown kernel; and (3) the fused bands should keep the correlation between each band of the upsampled multi-spectral image. A variational energy functional is then built based on the assumptions, of which the minimizer is the target fused image. The existence of a minimizer of the proposed energy is further analysed, and the numerical scheme based on the split Bregman framework is presented. To verify the validity, the new proposed method is compared with several state-of-the-art techniques using QuickBird data in subjective, objective, and efficiency aspects. The results show that the proposed approach performs better than some compared methods according to the performance metrics.     

Mapping multi-spectral remote sensing images using rule extraction approach

To improve the accurate rate of mapping multi-spectral remote sensing images, in this paper we construct a class of HyperRectangular Composite Neural Networks (HRCNNs), integrating the paradigms of neural networks with the rule-based approach. The supervised decision-directed learning (SDDL) algorithm is also adopted to construct a two-layer network in a sequential manner by adding hidden nodes as needed. Thus, the classification knowledge embedded in the numerical weights of trained HRCNNs can be extracted and represented in the form of If-Then rules. The rules facilitate justification on the responses to increase accuracy of the classification. A sample of remote sensing image containing forest land, river, dam area, and built-up land is used to examine the proposed approach. The accurate recognition rate reaching over 99% demonstrates that the proposed approach is capable of dealing with image mapping.     

Discovering hierarchical object models from captioned images

We address the problem of automatically learning the recurring associations between the visual structures in images and the words in their associated captions, yielding a set of named object models that can be used for subsequent image annotation. In previous work, we used language to drive the perceptual grouping of local features into configurations that capture small parts (patches) of an object. However, model scope was poor, leading to poor object localization during detection (annotation), and ambiguity was high when part detections were weak. We extend and significantly revise our previous framework by using language to drive the perceptual grouping of parts, each a configuration in the previous framework, into hierarchical configurations that offer greater spatial extent and flexibility. The resulting hierarchical multipart models remain scale, translation and rotation invariant, but are more reliable detectors and provide better localization. Moreover, unlike typical frameworks for learning object models, our approach requires no bounding boxes around the objects to be learned, can handle heavily cluttered training scenes, and is robust in the face of noisy captions, i.e., where objects in an image may not be named in the caption, and objects named in the caption may not appear in the image. We demonstrate improved precision and recall in annotation over the non-hierarchical technique and also show extended spatial coverage of detected objects.     

Repair approach for DMC images based on hierarchical location using edge curve

The color composite digital mapping camera (DMC) images are produced by the post-processing software of Z/I imaging. But the failure of radiometric correction in post-processing leads to residual radiometric differences between CCD images, which then affect the quality of the images in further applications. This paper, via analyzing the characters and causes of such a phenomenon, proposes a repair approach based on hierarchical location using edge curve. The approach employs a hierarchical strategy to locate the transition area and seam-line automatically and then repair the image through the global reconstruction between CCD images and the local reconstruction in the transition area. Experiments indicate that the approach proposed by this paper is feasible and can improve the quality of images effectively. Supported by the National Basic Research Program of China (Grant No. 2006CB701302) and the Youth Fundation Plan of Wuhan (Grant No. 200750731253)     

A method for multi-spectral image segmentation evaluation based on synthetic images

A general framework for testing the quality of the segmentation of a multi-spectral satellite image is proposed. The method is based on the production of synthetic images with the spectral characteristics of the image pixels extracted from a signature multi-spectral image. The knowledge of the location of objects in the synthetic image provides a reference segmentation, which allows for a quantitative evaluation of the quality provided by a segmentation algorithm. The Hammoude metric and three external similarity indices (Rand, Corrected Rand, and Jaccard) were chosen to perform this evaluation, but other metrics can also be used. The proposed methodology can be used for any type of satellite image (or multi-spectral image), set of land cover types, and segmentation algorithms.A practical application was carried out to illustrate the value of the proposed method. A SPOT satellite image was used to extract the spectral signature of 8 land cover types. Three test images were produced using the 8 land cover classes and two different 5 class sub-sets. The segmentation results provided by a standard algorithm were compared with the reference or expected segmentation. The results clearly indicate that the quality of a segmentation obtained from a multi-spectral image not only depends on the geometric properties of the objects present in the image, but also on their spectral characteristics. The results suggest that a specific evaluation should be carried out for each particular experiment, as the segmentation results are very dependent on the choice of land cover types.     

Comparing images using joint histograms

Color histograms are widely used for content-based image retrieval due to their efficiency and robustness. However, a color histogram only records an image's overall color composition, so images with very different appearances can have similar color histograms. This problem is especially critical in large image databases, where many images have similar color histograms. In this paper, we propose an alternative to color histograms called a joint histogram, which incorporates additional information without sacrificing the robustness of color histograms. We create a joint histogram by selecting a set of local pixel features and constructing a multidimensional histogram. Each entry in a joint histogram contains the number of pixels in the image that are described by a particular combination of feature values. We describe a number of different joint histograms, and evaluate their performance for image retrieval on a database with over 210,000 images. On our benchmarks, joint histograms outperform color histograms by an order of magnitude.     

梯度分层重构的彩色图像分水岭分割

目的 现实生活中的彩色图像往往因噪声、色彩不均匀、有较多弱边界等问题的存在导致难以准确分割,结合分水岭变换与形态学重构的优势,提出了一种基于同态滤波与形态学分层重构的分水岭分割算法。方法 首先提取彩色图像的梯度图,接着对该梯度图采用同态滤波修正梯度图。然后利用形态学开闭重构的方法,对滤波后的梯度图进行分层重构。根据梯度图像的累积分布函数及滤波后的梯度像素直方图的分布信息,给出了梯度分层数的计算公式,同时确定了形态学结构元素尺寸。最后对修正后的梯度图像应用标准分水岭变换实现了图像分割。结果 对不同类型的4幅彩色图像进行分割实验,采用区域一致性与差异性相结合的综合指标对分割结果进行无监督评价。这4幅图像的综合评价指标分别为0.6333、0.6656、0.6293、0.6484,均高于文献中两种现有分水岭算法的指标值：0.6295、0.6641、0.6230、0.6454与0.5861、0.5907、0.5704、0.5852,分割性能较好。结论 提出一种新的彩色图像分割算法,应用同态滤波保留了图像的弱边界,采用自适应形态学重构,抑制了分水岭变换中过分割。算法的分割结果更加接近人眼对图像的感知,无论从评价指标还是分割性能看,均表现出色。算法对噪声不敏感,鲁棒性较好,可广泛应用于计算机视觉、交通控制、生物医学等方面的目标分割。     

全卷积神经网络下的多光谱遥感影像分割

目的 传统的遥感影像分割方法需要大量人工参与特征选取以及参数选择,同时浅层的机器学习算法无法取得高精度的分割结果。因此,利用卷积神经网络能够自动学习特征的特性,借鉴处理自然图像语义分割的优秀网络结构,针对遥感数据集的特点提出新的基于全卷积神经网络的遥感影像分割方法。方法 针对遥感影像中目标排列紧凑、尺寸变化大的特点,提出基于金字塔池化和DUC（dense upsampling convolution）结构的全卷积神经网络。该网络结构使用改进的DenseNet作为基础网络提取影像特征,使用空间金字塔池化结构获取上下文信息,使用DUC结构进行上采样以恢复细节信息。在数据处理阶段,结合遥感知识将波段融合生成多源数据,生成植被指数和归一化水指数,增加特征。针对遥感影像尺寸较大、采用普通预测方法会出现拼接痕迹的问题,提出基于集成学习的滑动步长预测方法,对每个像素预测14次,每次预测像素都位于不同图像块的不同位置,对多次预测得到的结果进行投票。在预测结束后,使用全连接条件随机场（CRFs）对预测结果进行后处理,细化地物边界,优化分割结果。结果 结合遥感知识将波段融合生成多源数据可使分割精度提高3.19%;采用基于集成学习的滑动步长预测方法可使分割精度较不使用该方法时提高1.44%;使用全连接CRFs对预测结果进行后处理可使分割精度提高1.03%。结论 针对宁夏特殊地形的遥感影像语义分割问题,提出基于全卷积神经网络的新的网络结构,在此基础上采用集成学习的滑动步长预测方法,使用全连接条件随机场进行影像后处理可优化分割结果,提高遥感影像语义分割精度。     

基于Gerschgorin理论稀疏度估计的宽带频谱感知算法

针对在低信噪比(SNR)情况下稀疏度欠估计和高信噪比情况下稀疏度过估计的问题,提出了一种基于Gerschgorin理论稀疏度估计的宽带频谱感知算法。首先,该算法利用Gerschgorin理论分离信号圆盘与噪声圆盘得到稀疏度估计值;然后,利用正交匹配追踪(OMP)算法得到频谱支撑集;最后,完成宽带频谱感知。仿真结果表明,所提算法、AIC-OMP算法和MDL-OMP算法频谱感知的检测概率达到95%信噪比分别需要4.6 dB、8.5 dB和9.7 dB;所提算法频谱感知的虚警概率在信噪比大于13 dB时趋近于0,明显低于BPD-OMP和GDRI-OMP算法的虚警概率,因此,所提算法对于压缩感知(CS)的信号稀疏度估计兼顾了低信噪比和高信噪比时的稀疏度估计性能,频谱感知性能优于AIC-OMP算法、MDL-OMP算法、BPD-OMP算法和GDRI-OMP算法。     

Fuzzy ARTMAP supervised classification of multi-spectral remotely-sensed images

The fuzzy ARTMAP has been applied to the supervised classification of multi-spectral remotely-sensed images. This method is found to be more efficient, in terms of classification accuracy, compared to the conventional maximum likelihood classifier and also multi-layer perceptron with back propagation learning. The results have been discussed.     

基于A* OMP算法的压缩感知声纳成像

传统声纳成像系统所要采集的数据量巨大,给硬件设备以及数据的存储和传输带来很大的压力。压缩感知作为一种全新的采样理论,可以从很少的采样数据中以很大的概率重建原始信号。将压缩感知用于声纳成像,减少数据采集传输量。考虑到水下环境的复杂性,提出了A* OMP作为声纳成像算法,该算法使用A*搜索方法寻找最优原子,得到全局最优路径。实验结果表明,相比于传统OMP算法,所提算法有效地提高了声纳成像的质量。     

基于多标签层次聚类的GPR 图像双曲波提取方法

探地雷达(GPR)图像双曲波提取是分析地下目标位置和结构的重要方法,但在真 实环境中,由于噪声和杂波的干扰,使得提取出的双曲波存在结构不完整、碎片化和形状异 常等问题,不利于数据分析和三维建模等后续操作。为此,提出了一种基于多标签层次聚类 的双曲波提取方法(MHCE)。首先通过信息熵评价像素邻域的稳定性,构造了基于信息熵的 距离度量来进行层次聚类;然后利用聚类后的邻接空间进行多标签聚类以降低杂波和噪声对 双曲波提取的影响;最后结合多标签聚类结果的拟合形状和纹理方向提取双曲波。实验表明, 该方法对于真实GPR 图像双曲波具有较好的鲁棒性,能够获得规范化的双曲波形状和位置 参数。     

Unsupervised multi-class segmentation of SAR images using triplet Markov fields models based on edge penalty

Non-Gaussian triplet Markov random fields (TMF) model is suitable for dealing with multi-class segmentation of nonstationary and non-Gaussian synthetic aperture radar (SAR) images. However, the segmentation of SAR images utilizing this model still fails to resolve the misclassifications due to the inaccuracy of edge location. In this paper, we propose a new unsupervised multi-class segmentation algorithm by fusing the traditional energy function of TMF model with the principle of edge penalty. Through the introduction of the penalty function based on local edge strength information, the new energy function could prevent segment from smoothing across boundaries. Then we optimize the objective function that stems from the new energy function to obtain an iterative multi-region merging Bayesian maximum posterior mode (MPM) segmentation equation for the new segmentation algorithm. The effectiveness of the proposed algorithm is demonstrated by application to simulated data and real SAR images.     

DYANA: Best-first hierarchical diagnosis based on differential equation models

In this paper we evaluate and extend existing methods for an intended application for monitoring and diagnosis of a combined heat-power system. Only a few methods in model based diagnosis take advantage of the available design model by using (semi-)qualitative abstractions of ordinary differential equations, e.g. by Dvorak and Kuipers (1989), Ng (1990) and Lackinger and Nejdl (1991). Diagnosis of complex devices benefits from hierarchical models, both from a modelling perspective and from a computational perspective. This leads us to prefer the hierarchical diagnosis methoddiamon (Lackinger and Nejdl, 1991). We propose an extension of diamon, calleddyana, that is suitable for on-line diagnosis and uses an alternative method for dynamic model zooming which is based on heuristics regarding parsimony of diagnoses and consistency of fault models.dyana also uses numerical simulation, based on differential equations, instead of qualitative simulation.This article is dedicated to the memory of Martin Reinders. During the preparation of this paper, Martin died in an air accident. Please send any correspondence concerning this article to Hans Akkermans, at the above address (E-mail: akkermans@ecn.nl or akkerman@cs.utwente.nl).     

Multipass hierarchical stereo matching for generation of digital terrain models from aerial images

This paper presents a new multi-pass hierarchical stereo-matching approach for generation of digital terrain models (DTMs) from two overlapping aerial images. Our method consists of multiple passes which compute stereo matches with a coarse-to-fine and sparse-to-dense paradigm. An image pyramid is generated and used in the hierarchical stereo matching. Within each pass, the DTM is refined by using the image pyramid from the coarse to the fine level. At the coarsest level of the first pass, a global stereo-matching technique, the intra-/inter-scanline matching method, is used to generate a good initial DTM for the subsequent stereo matching. Thereafter, hierarchical block matching is applied to image locations where features are detected to refine the DTM incrementally. In the first pass, only the feature points near salient edge segments are considered in block matching. In the second pass, all the feature points are considered, and the DTM obtained from the first pass is used as the initial condition for local searching. For the passes after the second pass, 3D interactive manual editing can be incorporated into the automatic DTM refinement process whenever necessary. Experimental results have shown that our method can successfully provide accurate DTM from aerial images. The success of our approach and system has also been demonstrated with a flight simulation software. Received: 4 November 1996 / Accepted: 20 October 1997     

Extraction of spectral reflectance images from multi-spectral images by the HIS transformation model

The process is a completely closed system employing only image data, and it can be applied to any digital multi-spectral data set. A computer technique has been developed to produce spectral reflectance images from multi-spectral images. Hue, intensity and saturation (HIS) colour spatial transformation is used to compute the hue of a three-band colour composite image, and the image pixels with the same hue value are taken as a single material. The average brightness values of the pixels with the same hue are calculated for each band separately, and the distribution of the average values is taken as spectral reflectance image. This spectral reflectance image, which is essentially free of topographic modulation function, but includes spectral information, can be used in image classification, or other image processing. This technique has been successfully applied to recognize ore bearing rock in Inner Mongolia, China by Landsat TM images. The HIS transformation model is a new, very simple and practical technique. It is potentially useful for extracting spectral reflectance information and suppressing the terrain effect.     

Vector quantization of images using modified adaptive resonancealgorithm for hierarchical clustering

A modified adaptive resonance theory (ART2) learning algorithm, which we employ in this paper, belongs to the family of NN algorithms whose main goal is the discovery of input data clusters, without considering their actual size. This feature makes the modified ART2 algorithm very convenient for image compression tasks, particularly when dealing with images with large background areas containing few details. Moreover, due to the ability to produce hierarchical quantization (clustering), the modified ART2 algorithm is proved to significantly reduce the computation time required for coding, and therefore enhance the overall compression process. Examples of the results obtained are presented, suggesting the benefits of using this algorithm for the purpose of VQ, i.e., image compression, over the other NN learning algorithms.