Pingxiang Li

Classification and Extraction of Spatial Features in Urban Areas Using High-Resolution Multispectral Imagery

Classification and extraction of spatial features are investigated in urban areas from high spatial resolution multispectral imagery. The proposed approach consists of three steps. First, as an extension of our previous work [pixel shape index (PSI)], a structural feature set (SFS) is proposed to extract the statistical features of the direction-lines histogram. Second, some methods of dimension reduction, including independent component analysis, decision boundary feature extraction, and the similarity-index feature selection, are implemented for the proposed SFS to reduce information redundancy. Third, four classifiers, the maximum-likelihood classifier, backpropagation neural network, probability neural network based on expectation-maximization training, and support vector machine, are compared to assess SFS and other spatial feature sets. We evaluate the proposed approach on two QuickBird datasets, and the results show that the new set of reduced spatial features has better performance than the existing length-width extraction algorithm and PSI

A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery

Shape and spectra are both important features of high spatial resolution remotely sensed (HSRRS) imagery, and they are concrete manifestation of textures on such imagery. This paper presents a spatial feature index, pixel shape index (PSI), to describe the shape feature in a local area surrounding a pixel. PSI is a pixel-based feature which measures the gray similarity distance in every direction. As merely the shape feature is inadequate for classifying HSRRS imagery, a transformed spectral feature extracted by independent component analysis is added to the input vectors of our classifier, and this replaces the original multispectral bands. Meanwhile, a fast fusion algorithm that integrates both shape and spectral features using the support vector machine has been developed to interpret the complex input vectors. The results by PSI are compared with some spatial features extracted using wavelet transform, gray level co-occurrence matrix, and the length-width extraction algorithm to test its effectiveness. The experiments demonstrate that PSI is capable of describing shape features effectively and result in more accurate classifications than other methods. While it is found that spectral and shape features can complement each other and their integration can improve classification accuracy, the transformed spectral components are also found to be more suitable for classification

An unsupervised artificial immune classifier for multi/hyperspectral remote sensing imagery

A new method in computational intelligence namely artificial immune systems (AIS), which draw inspiration from the vertebrate immune system, have strong capabilities of pattern recognition. Even though AIS have been successfully utilized in several fields, few applications have been reported in remote sensing. Modern commercial imaging satellites, owing to their large volume of high-resolution imagery, offer greater opportunities for automated image analysis. Hence, we propose a novel unsupervised machine-learning algorithm namely unsupervised artificial immune classifier (UAIC) to perform remote sensing image classification. In addition to their nonlinear classification properties, UAIC possesses biological properties such as clonal selection, immune network, and immune memory. The implementation of UAIC comprises two steps: initially, the first clustering centers are acquired by randomly choosing from the input remote sensing image. Then, the classification task is carried out. This assigns each pixel to the class that maximizes stimulation between the antigen and the antibody. Subsequently, based on the class, the antibody population is evolved and the memory cell pool is updated by immune algorithms until the stopping criterion is met. The classification results are evaluated by comparing with four known algorithms: K-means, ISODATA, fuzzy K-means, and self-organizing map. It is shown that UAIC is an adaptive clustering algorithm, which outperforms other algorithms in all the three experiments we carried out.

Dimensionality Reduction Based on Clonal Selection for Hyperspectral Imagery

A new stochastic search strategy inspired by the clonal selection theory in an artificial immune system is proposed for dimensionality reduction of hyperspectral remote-sensing imagery. The clonal selection theory is employed to describe the basic features of an immune response to an antigenic stimulus in order to meet the requirement of diversity in the antibody population. In our proposed strategy, dimensionality reduction is formulated as an optimization problem that searches an optimum with less number of features in a feature space. In line with this novel strategy, a feature subset search algorithm, clonal selection Feature-Selection (CSFS) algorithm, and a feature-weighting algorithm, Clonal-Selection Feature-Weighting (CSFW) algorithm, have been developed. In the CSFS, each solution is evolved in binary space, and the value of each bit is either 0 or 1, which indicates that the corresponding feature is either removed or selected, respectively. In CSFW, each antibody is directly represented by a string consisting of integer numbers and their corresponding weights. These algorithms are compared with the following four well-known algorithms: sequential forward selection, sequential forward floating selection, genetic-algorithm-based feature selection, and decision-boundary feature extraction using the hyperspectral remote-sensing imagery acquired by the Pushbroom Hyperspectral Imager and the Airborne Visible/Infrared Imaging Spectrometer, respectively. Experimental results demonstrate that CSFS and CSFW outperform other algorithms and hence provide effective new options for dimensionality reduction of hyperspectral remote-sensing imagery.

A super-resolution reconstruction algorithm for surveillance images

In many surveillance video applications, it is of interest to recognize a region of interest (ROI), which often occupies a small portion of a low-resolution, noisy video. This paper proposes an edge-preserving maximum a posteriori (MAP) estimation based super-resolution algorithm using a weighted directional Markov image prior model for a ROI from more than one low-resolution surveillance image. Conjugate gradient (CG) optimization based on standard operations on images is then developed to improve the computational efficiency of the algorithm. The proposed algorithm is tested on different series of surveillance images. The experimental results indicate that the proposed algorithm has considerable effectiveness in terms of both objective measurements and visual evaluation.

A new sub-pixel mapping algorithm based on a BP neural network with an observation model

The mixed pixel is a common problem in remote sensing classification. Even though the composition of these pixels for different classes can be estimated with a pixel un-mixing model, the output provides no indication of how such classes are distributed spatially within these pixels. Sub-pixel mapping is a technique designed to use the output information with the assumption of spatial dependence to obtain a sharpened image. Pixels are divided into sub-pixels, representing the land cover class fractions. This paper proposes a new algorithm based on a back-propagation (BP) network combined with an observation model. This method provides an effective method of obtaining the sub-pixel mapping result and can provide an approximation of the reference classification image. With the upscale factor, the model was tested on both a simple artificial image and a remote sensing image, and the results confirm that the proposed mapping algorithm has better performance than the original BPNN model.

Classification of High Spatial Resolution Imagery Using Improved Gaussian Markov Random-Field-Based Texture Features

Gaussian Markov random fields (GMRFs) are used to analyze textures. GMRFs measure the interdependence of neighboring pixels within a texture to produce features. In this paper, neighboring pixels are taken into account in a priority sequence according to their distance from the center pixel, and a step-by-step least squares method is proposed to extract a novel set of GMRF texture features, named as PS-GMRF. A complete procedure is first designed to classify texture samples of QuickBird imagery. After texture feature extraction, a subset of PS-GMRF features is obtained by the sequential floating forward-selection method. Then, the maximum a posteriori iterated conditional mode classification algorithm is used, involving the selected PS-GMRF texture features in combination with spectral features. The experimental results show that the performance of classifying texture samples on high spatial resolution QuickBird satellite imagery is improved when texture features and spectral features are used jointly, and PS-GMRF features have a higher discrimination power compared to the classical GMRF features, making a notable improvement in classification accuracy from 71.84% to 94.01%. On the other hand, it is found that one of the PS-GMRF texture features - the lowest order variance - is effective for residential-area detection. Some results for IKONOS and SPOT-5 images show that the integration of the lowest order variance with spectral features improves the classification accuracy compared to classification with purely spectral features

Super-Resolution Reconstruction Algorithm To MODIS Remote Sensing Images

In this paper, we propose a super-resolution image reconstruction algorithm to moderate-resolution imaging spectroradiometer (MODIS) remote sensing images. This algorithm consists of two parts: registration and reconstruction. In the registration part, a truncated quadratic cost function is used to exclude the outlier pixels, which strongly deviate from the registration model. Accurate photometric and geometric registration parameters can be obtained simultaneously. In the reconstruction part, the L1 norm data fidelity term is chosen to reduce the effects of inevitable registration error, and a Huber prior is used as regularization to preserve sharp edges in the reconstructed image. In this process, the outliers are excluded again to enhance the robustness of the algorithm. The proposed algorithm has been tested using real MODIS band-4 images, which were captured in different dates. The experimental results and comparative analyses verify the effectiveness of this algorithm.

Adaptive Multiple-Frame Image Super-Resolution Based on U-Curve

Image super-resolution (SR) reconstruction has been a hot research topic in recent years. This technique allows the recovery of a high-resolution (HR) image from several low-resolution (LR) images that are noisy, blurred and down-sampled. Among the available reconstruction frameworks, the maximum a posteriori (MAP) model is widely used. In this model, the regularization parameter plays an important role. If the parameter is too small, the noise will not be effectively restrained; conversely, the reconstruction result will become blurry. Therefore, how to adaptively select the optimal regularization parameter has been widely discussed. In this paper, we propose an adaptive MAP reconstruction method based upon a U-curve. To determine the regularization parameter, a U-curve function is first constructed using the data fidelity term and prior term, and then the left maximum curvature point of the curve is regarded as the optimal parameter. The proposed algorithm is tested on both simulated and actual data. Experimental results show the effectiveness and robustness of this method, both in its visual effects and in quantitative terms.

A Supervised Artificial Immune Classifier for Remote-Sensing Imagery

The artificial immune network (AIN), which is a new computational intelligence model based on artificial immune systems inspired by the vertebrate immune system, has been widely utilized for pattern recognition and data analysis. However, due to the inherent complexity of current AIN models, their application to remote-sensing image classification has been rather limited. This paper presents a novel supervised classification algorithm based on a multiple-valued immune network, which is a novel AIN model, to perform remote-sensing image classification. The proposed method trains the immune network using the samples of regions of interest and obtains an immune network with memory to classify the remote-sensing imagery. Two experiments with different types of images are performed to evaluate the performance of the proposed algorithm in comparison with other traditional image classification algorithms: Parallelepiped, Minimum Distance, Maximum Likelihood, and Back-Propagation Neural Network. The results evince that the proposed algorithm consistently outperforms the traditional algorithms in all the experiments and, hence, provides an effective option for processing remote-sensing imagery.