Noncooperative target classification using hierarchical modeling ofhigh-range resolution radar signatures

The classification of high-range resolution (HRR) radar signatures using multiscale features is considered. We present a hierarchical autoregressive moving average (ARMA) model for modeling HRR radar signals at multiple scales and use spectral features extracted from the model for classifying radar signatures. First, we show that the radar signal at a different scale obeys an ARMA process if it is an ARMA process at the observed scale. Then, an algorithm to estimate model parameters and power spectral density function at different scales using model parameters at the observed scale is presented. A feature set composed of spectral peaks is extracted from the estimated spectral density function using multiscale ARMA models. For HRR radar signature classification, multispectral features extracted from five different scales are used, and a minimum distance classifier with multiple prototypes is used to classify HRR data. The multiscale classifier is applied to two HRR radar data sets. Each data set contains 2500 test samples and 2500 training samples in five classes. For both data sets, about 95% of the radar returns are correctly classified     

Classification of chirp signals using hierarchical Bayesianlearning and MCMC methods

This paper addresses the problem of classifying chirp signals using hierarchical Bayesian learning together with Markov chain Monte Carlo (MCMC) methods. Bayesian learning consists of estimating the distribution of the observed data conditional on each class from a set of training samples. Unfortunately, this estimation requires to evaluate intractable multidimensional integrals. This paper studies an original implementation of hierarchical Bayesian learning that estimates the class conditional probability densities using MCMC methods. The performance of this implementation is first studied via an academic example for which the class conditional densities are known. The problem of classifying chirp signals is then addressed by using a similar hierarchical Bayesian learning implementation based on a Metropolis-within-Gibbs algorithm     

Gait recognition using Pose Kinematics and Pose Energy Image

Many of the existing gait recognition approaches represent a gait cycle using a single 2D image called Gait Energy Image (GEI) or its variants. Since these methods suffer from lack of dynamic information, we model a gait cycle using a chain of key poses and extract a novel feature called Pose Energy Image (PEI). PEI is the average image of all the silhouettes in a key pose state of a gait cycle. By increasing the resolution of gait representation, more detailed dynamic information can be captured. However, processing speed and space requirement are higher for PEI than the conventional GEI methods. To overcome this shortcoming, another novel feature named as Pose Kinematics is introduced, which represents the percentage of time spent in each key pose state over a gait cycle. Although the Pose Kinematics based method is fast, its accuracy is not very high. A hierarchical method for combining these two features is, therefore, proposed. At first, Pose Kinematics is applied to select a set of most probable classes. Then, PEI is used on these selected classes to get the final classification. Experimental results on CMU's Mobo and USF's HumanID data set show that the proposed approach outperforms existing approaches.     

基于多任务学习的番茄叶片图像病害程度分类

针对现有的分类深度神经网络大多为扁平型的网 络架构,很少关注数据类别的层次 性结构,导致分类器训练难度较大的问题,本文提出一种基于数据层次关系的多任务学习分 类网络模型。依托番茄叶片病害的层次结构信息设计了一个带有共享网络的由粗粒度到细粒 度的层次结构进行病害程度分类,网络模型以ResNet-50作为网络主干,包括两个子网络: 粗粒度网络模块负责区分番茄病害共5类,细粒度网络模块在残差网络模块的基础上添加 SE模块负责病害程度的分类共9类。通过对网络架构各个分支的验证,以及同VGG-16、 ResNet-34、ResNet-50 3种扁平型网络在病害程度分类任务上做比较,证明本文网络结构 的 可行性和有效性,最终测试集分类精度达到93.97%。证明本文结合数 据与网络的层次结构 采用多任务分类方法,是一种有效的病害程度分类算法。     

Simultaneous image classification and annotation based on probabilistic model

The paper proposes a novel probabilistic generative model for simultaneous image classification and annotation.The model considers the fact that the category information can provide valuable information for image annotation.Once the category of an image is ascertained,the scope of annotation words can be narrowed,and the probability of generating irrelevant annotation words can be reduced.To this end,the idea that annotates images according to class is introduced in the model.Using variational methods,the approximate inference and parameters estimation algorithms of the model are derived,and efficient approximations for classifying and annotating new images are also given.The power of our model is demonstrated on two real world datasets:a 1 600-images LabelMe dataset and a 1 791-images UIUC-Sport dataset.The experiment results show that the classification performance is on par with several state-of-the-art classification models,while the annotation performance is better than that of several state-of-the-art annotation models.     

Multidimensional incremental parsing for universal source coding

A multidimensional incremental parsing algorithm (MDIP) for multidimensional discrete sources, as a generalization of the Lempel-Ziv coding algorithm, is investigated. It consists of three essential component schemes, maximum decimation matching, hierarchical structure of multidimensional source coding, and dictionary augmentation. As a counterpart of the longest match search in the Lempel-Ziv algorithm, two classes of maximum decimation matching are studied. Also, an underlying behavior of the dictionary augmentation scheme for estimating the source statistics is examined. For an m-dimensional source, m augmentative patches are appended into the dictionary at each coding epoch, thus requiring the transmission of a substantial amount of information to the decoder. The property of the hierarchical structure of the source coding algorithm resolves this issue by successively incorporating lower dimensional coding procedures in the scheme. In regard to universal lossy source coders, we propose two distortion functions, the local average distortion and the local minimax distortion with a set of threshold levels for each source symbol. For performance evaluation, we implemented three image compression algorithms based upon the MDIP; one is lossless and the others are lossy. The lossless image compression algorithm does not perform better than the Lempel-Ziv-Welch coding, but experimentally shows efficiency in capturing the source structure. The two lossy image compression algorithms are implemented using the two distortion functions, respectively. The algorithm based on the local average distortion is efficient at minimizing the signal distortion, but the images by the one with the local minimax distortion have a good perceptual fidelity among other compression algorithms. Our insights inspire future research on feature extraction of multidimensional discrete sources.     

Fusing integrated visual vocabularies-based bag of visual words and weighted colour moments on spatial pyramid layout for natural scene image classification

The bag of visual words (BOW) model is an efficient image representation technique for image categorization and annotation tasks. Building good visual vocabularies, from automatically extracted image feature vectors, produces discriminative visual words, which can improve the accuracy of image categorization tasks. Most approaches that use the BOW model in categorizing images ignore useful information that can be obtained from image classes to build visual vocabularies. Moreover, most BOW models use intensity features extracted from local regions and disregard colour information, which is an important characteristic of any natural scene image. In this paper, we show that integrating visual vocabularies generated from each image category improves the BOW image representation and improves accuracy in natural scene image classification. We use a keypoint density-based weighting method to combine the BOW representation with image colour information on a spatial pyramid layout. In addition, we show that visual vocabularies generated from training images of one scene image dataset can plausibly represent another scene image dataset on the same domain. This helps in reducing time and effort needed to build new visual vocabularies. The proposed approach is evaluated over three well-known scene classification datasets with 6, 8 and 15 scene categories, respectively, using 10-fold cross-validation. The experimental results, using support vector machines with histogram intersection kernel, show that the proposed approach outperforms baseline methods such as Gist features, rgbSIFT features and different configurations of the BOW model.     

A hierarchical Markovian model for multiscale region-based classification of vector-valued images

We propose a new classification method for vector-valued images, based on: 1) a causal Markovian model, defined on the hierarchy of a multiscale region adjacency tree (MRAT), and 2) a set of nonparametric dissimilarity measures that express the data likelihoods. The image classification is treated as a hierarchical labeling of the MRAT, using a finite set of interpretation labels (e.g., land cover classes). This is accomplished via a noniterative estimation of the modes of posterior marginals (MPM), inspired from existing approaches for Bayesian inference on the quadtree. The paper describes the main principles of our method and illustrates classification results on a set of artificial and remote sensing images, together with qualitative and quantitative comparisons with a variety of pixel-based techniques that follow the Bayesian-Markovian framework either on hierarchical structures or the original image lattice.     

铁路运输信息数据分类算法的研究与实现

介绍两种基于统计的自动分类技术(朴素贝叶斯分类器、支持向量机分类器)，剖析了基于统计的自动分类的优势及不足。基于统计的自动分类的不足主要表现为：当类别之间分类特征的交叉变大时，分类精度呈下降趋势，在多层分类的情况下，此局限尤为突出。针对此局限性．为了提高自动分类的精度，我们引入了基于规则的自动分类来对其进行改进和扩充，并整合两种自动分类技术的优点，设计出了混合分类器系统，应用于铁路运输信息系统，进行分类分析，从而获得了比较理想的分类效果。     

Spatial/spectral endmember extraction by multidimensional morphological operations

Spectral mixture analysis provides an efficient mechanism for the interpretation and classification of remotely sensed multidimensional imagery. It aims to identify a set of reference signatures (also known as endmembers) that can be used to model the reflectance spectrum at each pixel of the original image. Thus, the modeling is carried out as a linear combination of a finite number of ground components. Although spectral mixture models have proved to be appropriate for the purpose of large hyperspectral dataset subpixel analysis, few methods are available in the literature for the extraction of appropriate endmembers in spectral unmixing. Most approaches have been designed from a spectroscopic viewpoint and, thus, tend to neglect the existing spatial correlation between pixels. This paper presents a new automated method that performs unsupervised pixel purity determination and endmember extraction from multidimensional datasets; this is achieved by using both spatial and spectral information in a combined manner. The method is based on mathematical morphology, a classic image processing technique that can be applied to the spectral domain while being able to keep its spatial characteristics. The proposed methodology is evaluated through a specifically designed framework that uses both simulated and real hyperspectral data.     

Hierarchical maximum-likelihood classification for improvedaccuracies

Among the supervised parametric classification methods, the maximum-likelihood (MLH) classifier has become popular and widespread in remote sensing. Reliable prior probabilities are not always freely available, and it is a common practice to perform the MLH classification with equal prior probabilities. When equal prior probabilities are used, the advantages in MLH classification may not be attained. This study has explored a hierarchical pixel classification (HPC) method to estimate prior probabilities for the spectral classes from the Landsat thematic mapper (TM) data and spectral signatures. The TM pixels were visualized in multidimensional feature space relative to the spectral class probability surfaces. The pixels that fell within more than one probability region or outside all probability regions were categorized as the pixels likely to misclassify. Prior probabilities were estimated from the pixels that fell within spectral class probability regions. The pixels most likely to be correctly classified do not need extra information and were classified according to the probability region in which they fell. The pixels likely to be misclassified need additional information and were classified by MLH classification with the estimated prior probabilities. The classified image resulting from the HPC showed increased accuracy over three classification methods. Visualization of pixels in multidimensional feature space, relative to the spectral class probability reforms, overcome the practical difficulty in estimating prior probabilities while utilizing the available information     

Unsupervised image classification, segmentation, and enhancementusing ICA mixture models

An unsupervised classification algorithm is derived by modeling observed data as a mixture of several mutually exclusive classes that are each described by linear combinations of independent, non-Gaussian densities. The algorithm estimates the data density in each class by using parametric nonlinear functions that fit to the non-Gaussian structure of the data. This improves classification accuracy compared with standard Gaussian mixture models. When applied to images, the algorithm can learn efficient codes (basis functions) for images that capture the statistically significant structure intrinsic in the images. We apply this technique to the problem of unsupervised classification, segmentation, and denoising of images. We demonstrate that this method was effective in classifying complex image textures such as natural scenes and text. It was also useful for denoising and filling in missing pixels in images with complex structures. The advantage of this model is that image codes can be learned with increasing numbers of classes thus providing greater flexibility in modeling structure and in finding more image features than in either Gaussian mixture models or standard independent component analysis (ICA) algorithms.     

Automatic Detection of Geospatial Objects Using Multiple Hierarchical Segmentations

The object-based analysis of remotely sensed imagery provides valuable spatial and structural information that is complementary to pixel-based spectral information in classification. In this paper, we present novel methods for automatic object detection in high-resolution images by combining spectral information with structural information exploited by using image segmentation. The proposed segmentation algorithm uses morphological operations applied to individual spectral bands using structuring elements in increasing sizes. These operations produce a set of connected components forming a hierarchy of segments for each band. A generic algorithm is designed to select meaningful segments that maximize a measure consisting of spectral homogeneity and neighborhood connectivity. Given the observation that different structures appear more clearly at different scales in different spectral bands, we describe a new algorithm for unsupervised grouping of candidate segments belonging to multiple hierarchical segmentations to find coherent sets of segments that correspond to actual objects. The segments are modeled by using their spectral and textural content, and the grouping problem is solved by using the probabilistic latent semantic analysis algorithm that builds object models by learning the object-conditional probability distributions. The automatic labeling of a segment is done by computing the similarity of its feature distribution to the distribution of the learned object models using the Kullback-Leibler divergence. The performances of the unsupervised segmentation and object detection algorithms are evaluated qualitatively and quantitatively using three different data sets with comparative experiments, and the results show that the proposed methods are able to automatically detect, group, and label segments belonging to the same object classes.     

基于视点差异和多分类器的三维模型分类

基于视图的3维模型分类方法与深度学习融合能有效提升模型分类的准确率。但目前的方法将相同类别的3维模型所有视点上的视图归为一类,忽略了不同视点上的视图差异,导致分类器很难学习到一个合理的分类面。为解决这一问题,该文提出一个基于深度神经网络的3维模型分类方法。该方法在3维模型的周围均匀设置多个视点组,为每个视点组训练1个视图分类器,充分挖掘不同视点组下的3维模型深度信息。这些分类器共享1个特征提取网络,但却有各自的分类网络。为了使提取的视图特征具有区分性,在特征提取网络中加入注意力机制;为了对非本视点组的视图建模,在分类网络中增加了附加类。在分类阶段首先提出一个视图选择策略,从大量视图中选择少量视图用于分类,以提高分类效率。然后提出一个分类策略通过分类视图实现可靠的3维模型分类。在ModelNet10和ModelNet40上的实验结果表明,该方法在仅用3张视图的情况下分类准确率高达93.6%和91.0%。     

Data mapping by probabilistic modular networks andinformation-theoretic criteria

The quantitative mapping of a database that represents a finite set of classified and/or unclassified data points may be decomposed into three distinctive learning tasks: (1) detection of the structure of each class model with locally mixture clusters; (2) estimation of the data distributions for each induced cluster inside each class; and (3) classification of the data into classes that realizes the data memberships. The mapping function accomplished by the probabilistic modular networks may then be constructed as the optimal estimator with respect to information theory, and each of the three tasks can be interpreted as an independent objective in real-world applications. We adapt a model fitting scheme that determines both the number and kernel of local clusters using information-theoretic criteria. The class distribution functions are then obtained by learning generalized Gaussian mixtures, where a soft classification of the data is performed by an efficient incremental algorithm. Further classification of the data is treated as a hard Bayesian detection problem, in particular, the decision boundaries between the classes are fine tuned by a reinforce or antireinforce supervised learning scheme. Examples of the application of this framework to medical image quantification, automated face recognition, and featured database analysis, are presented as well     

Unsupervised texture classification using vector quantization anddeterministic relaxation neural network

This paper describes the use of a neural network architecture for classifying textured images in an unsupervised manner using image-specific constraints. The texture features are extracted by using two-dimensional (2-D) Gabor filters arranged as a set of wavelet bases. The classification model comprises feature quantization, partition, and competition processes. The feature quantization process uses a vector quantizer to quantize the features into codevectors, where the probability of grouping the vectors is modeled as Gibbs distribution. A set of label constraints for each pixel in the image are provided by the partition and competition processes. An energy function corresponding to the a posteriori probability is derived from these processes, and a neural network is used to represent this energy function. The state of the network and the codevectors of the vector quantizer are iteratively adjusted using a deterministic relaxation procedure until a stable state is reached. The final equilibrium state of the vector quantizer gives a classification of the textured image. A cluster validity measure based on modified Hubert index is used to determine the optimal number of texture classes in the image.     

Image classification using spectral and spatial information basedon MRF models

A new criterion for classifying multispectral remote sensing images or textured images by using spectral and spatial information is proposed. The images are modeled with a hierarchical Markov Random Field (MRF) model that consists of the observed intensity process and the hidden class label process. The class labels are estimated according to the maximum a posteriori (MAP) criterion, but some reasonable approximations are used to reduce the computational load. A stepwise classification algorithm is derived and is confirmed by simulation and experimental results.     

Data streams classification with ensemble model based on decision-feedback简

The main challenges of data streams classification include infinite length, concept-drifting, arrival of novel classes and lack of labeled instances. Most existing techniques address only some of them and ignore others. So an ensemble classification model based on decision-feedback（ECM-BDF） is presented in this paper to address all these challenges. Firstly, a data stream is divided into sequential chunks and a classification model is trained from each labeled data chunk. To address the infinite length and concept-drifting problem, a fixed number of such models constitute an ensemble model E and subsequent labeled chunks are used to update E. To deal with the appearance of novel classes and limited labeled instances problem, the model incorporates a novel class detection mechanism to detect the arrival of a novel class without training E with labeled instances of that class. Meanwhile, unsupervised models are trained from unlabeled instances to provide useful constraints for E. An extended ensemble model Ex can be acquired with the constraints as feedback information, and then unlabeled instances can be classified more accurately by satisfying the maximum consensus of Ex. Experimental results demonstrate that the proposed ECM-BDF outperforms traditional techniques in classifying data streams with limited labeled data.     

Multiresolution image classification by hierarchical modeling withtwo-dimensional hidden Markov models

This paper treats a multiresolution hidden Markov model for classifying images. Each image is represented by feature vectors at several resolutions, which are statistically dependent as modeled by the underlying state process, a multiscale Markov mesh. Unknowns in the model are estimated by maximum likelihood, in particular by employing the expectation-maximization algorithm. An image is classified by finding the optimal set of states with maximum a posteriori probability. States are then mapped into classes. The multiresolution model enables multiscale information about context to be incorporated into classification. Suboptimal algorithms based on the model provide progressive classification that is much faster than the algorithm based on single-resolution hidden Markov models     

Structured Output SVM for Remote Sensing Image Classification

Traditional kernel classifiers assume independence among the classification outputs. As a consequence, each misclassification receives the same weight in the loss function. Moreover, the kernel function only takes into account the similarity between input values and ignores possible relationships between the classes to be predicted. These assumptions are not consistent for most of real-life problems. In the particular case of remote sensing data, this is not a good assumption either. Segmentation of images acquired by airborne or satellite sensors is a very active field of research in which one tries to classify a pixel into a predefined set of classes of interest (e.g. water, grass, trees, etc.). In this situation, the classes share strong relationships, e.g. a tree is naturally (and spectrally) more similar to grass than to water. In this paper, we propose a first approach to remote sensing image classification using structured output learning. In our approach, the output space structure is encoded using a hierarchical tree, and these relations are added to the model in both the kernel and the loss function. The methodology gives rise to a set of new tools for structured classification, and generalizes the traditional non-structured classification methods. Comparison to standard SVM is done numerically, statistically and by visual inspection of the obtained classification maps. Good results are obtained in the challenging case of a multispectral image of very high spatial resolution acquired with QuickBird over a urban area.