Geostatistical and texture analysis of airborne-acquired images used in forest classification

Airborne sensor image texture derived following a geostatistical analysis can increase the accuracy of forest classification because the resulting texture is insensitive to random variations in spectral response but related to the structural features of interest at the scale of a forest inventory (e.g. tree species). The combination of spectral and textural data derived from a kriging surface provided 86% classification accuracy in 36 pure and mixed-wood stands in seven forest classes in Alberta. This is an increase over the classification accuracy obtained when texture was derived from the original image data, and when the spectral response patterns were used alone.     

Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification

This study evaluated the synergistic use of high spatial resolution multispectral imagery (i.e., QuickBird, 2.4 m) and low-posting-density LIDAR data (3 m) for forest species classification using an object-based approach. The integration of QuickBird multispectral imagery and LIDAR data was considered during image segmentation and the subsequent object-based classification. Three segmentation schemes were examined: (1) segmentation based solely on the spectral image layers; (2) segmentation based solely on LIDAR-derived layers; and (3) segmentation based on both the spectral and LIDAR-derived layers. For each segmentation scheme, objects were generated at twelve different scales in order to determine optimal scale parameters. Six categories of classification metrics were generated for each object based on spectral data alone, LIDAR data alone and the combination of both data sources. Machine learning decision trees were used to build classification rule sets. Quantitative segmentation quality assessment and classification accuracy results showed the integration of spectral and LIDAR data, in both image segmentation and object-based classification, improved the forest classification compared to using either data source independently. Better segmentation quality led to higher classification accuracy. The highest classification accuracy (Kappa = 91.6%) was acquired when using both spectral- and LIDAR-derived metrics based on objects segmented from both spectral and LIDAR layers at scale parameter 250, where best segmentation quality was achieved. Optimal scales were analyzed for each segmentation-classification scheme. Statistical analysis of classification accuracies at different scales revealed that there was a range of optimal scales that provided statistically similar accuracy.     

Applications of image texture in forest classification

Texture is an important property of the images. Its inclusion in digital classification is known to improve the classification accuracy. In the present study, the texture features angular second moment, entropy and inverse difference moment were used to differentiate and classify forests affected by jhum (shifting cultivation) in north-eastern India. Large increases (11·1 per cent) in the classification accuracy were observed when texture and tone were used simultaneously. In general, the inverse difference moment was found to be more useful than the entropy. The angular second moment was not useful. The most accurate classification was achieved with a combination of the tone, the entropy and the inverse difference moment.     

Contribution of multispectral and multitemporal information from MODIS images to land cover classification

The goal of this study is to evaluate the relative usefulness of high spectral and temporal resolutions of MODIS imagery data for land cover classification. In particular, we highlight the individual and combinatorial influence of spectral and temporal components of MODIS reflectance data in land cover classification. Our study relies on an annual time series of twelve MODIS 8-days composited images (MOD09A1) monthly acquired during the year 2000, at a 500 m nominal resolution. As our aim is not to propose an operational classifier directed at thematic mapping based on the most efficient combination of reflectance inputs — which will probably change across geographical regions and with different land cover nomenclatures — we intentionally restrict our experimental framework to continental Portugal. Because our observation data stream contains highly correlated components, we need to rank the temporal and the spectral features according not only to their individual ability at separating the land cover classes, but also to their differential contribution to the existing information. To proceed, we resort to the median Mahalanobis distance as a statistical separability criterion. Once achieved this arrangement, we strive to evaluate, in a classification perspective, the gain obtained when the dimensionality of the input feature space grows. We then successively embedded the prior ranked measures into the multitemporal and multispectral training data set of a Support Vector Machines (SVM) classifier. In this way, we show that, only the inclusion of the approximately first three dates substantially increases the classification accuracy. Moreover, this multitemporal factor has a significant effect when coupled with combinations of few spectral bands, but it turns negligible as soon as the full spectral information is exploited. Regarding the multispectral factor, its beneficence on classification accuracy remains more constant, regardless of the number of dates being used.     

Affine invariant classification and retrieval of texture images

In this paper, we propose a new method of extracting affine invariant texture signatures for content-based affine invariant image retrieval (CBAIR). The algorithm discussed in this paper exploits the spectral signatures of texture images. Based on spectral representation of affine transform, anisotropic scale invariant signatures of orientation spectrum distributions are extracted. Peaks distribution vector (PDV) obtained from signature distributions captures texture properties invariant to affine transform. The PDV is used to measure the similarity between textures. Extensive experimental results are included to demonstrate the performance of the method in texture classification and CBAIR.     

Parallel supervised land-cover classification system for hyperspectral and multispectral images

Hyperspectral and multispectral imagery allows remote-sensing applications such as the land-cover mapping, which is a significant baseline to understand and to monitor the Earth. Furthermore, it is a relevant process for socio-economic activities. For that reason, high land-classification accuracies are imperative, and minor image processing time is essential. In addition, the process of gathering classes’ documented samples is complicated. This implies that the classification system is required to perform with a limited number of training observations. Another point worth mentioning is that there are hardly any methods that can be used analogously for hyperspectral or multispectral images. This paper aims to propose a novel classification system that can be used for both types of images. The designed classification system is composed of a novel parallel feature extraction algorithm, which utilises a cluster of two graphics processing units in combination with a multicore central processing unit (CPU), and an artificial neural network (ANN) particularly devised for the classification of the features ensued by the implemented feature extraction method. To prove the performance of the proposed classification system, it is compared with non-parallel and CPU-only-parallel implementations employing multispectral and hyperspectral databases. Moreover, experiments with different number of samples for training the classifier are performed. Finally, the proposed ANN is compared with a state-of-the-art support vector machine in classification and processing time results.     

Unsupervised classification of multispectral Landsat images with multidimensional particle swarm optimization

This article proposes a novel unsupervised classification approach for automatic analysis of multispectral Landsat images. The automatic classification of the information in multidimensional (MD) Landsat data space by dynamic clustering is addressed as an optimization problem and two recently proposed heuristic techniques based on Particle Swarm Optimization (PSO) are applied to determine the optimal (number of) clusters in a given input data space: distance metric and a proper validity index function. The first technique, the so-called MD-PSO, re-forms the native structure of swarm particles (agents) in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Fractional global best formation (FGBF) basically collects all promising dimensional components and fractionally creates an artificial global best (aGB) agent that has the potential to be a better ‘guide’ than the swarm’s native global best position (gbest) agent. In this study, the proposed dynamic clustering approach based on MD-PSO and FGBF techniques is applied to automatically classify the colour-coded representations of the multispectral (MD) Landsat data. The approach has been applied to real-world multispectral data and it provided quite encouraging results compared to the traditional K-means and ISODATA (iterative self-organizing data analysis) clustering methods. The proposed unsupervised technique determines the true number of classes within Landsat data for optimal classification performance while preserving spatial resolution and textural information in the classification map.     

Sparse representation with multi-manifold analysis for texture classification from few training images

Texture classification is one of the most important tasks in computer vision field and it has been extensively investigated in the last several decades. Previous texture classification methods mainly used the template matching based methods such as Support Vector Machine and k-Nearest-Neighbour for classification. Given enough training images the state-of-the-art texture classification methods could achieve very high classification accuracies on some benchmark databases. However, when the number of training images is limited, which usually happens in real-world applications because of the high cost of obtaining labelled data, the classification accuracies of those state-of-the-art methods would deteriorate due to the overfitting effect. In this paper we aim to develop a novel framework that could correctly classify textural images with only a small number of training images. By taking into account the repetition and sparsity property of textures we propose a sparse representation based multi-manifold analysis framework for texture classification from few training images. A set of new training samples are generated from each training image by a scale and spatial pyramid, and then the training samples belonging to each class are modelled by a manifold based on sparse representation. We learn a dictionary of sparse representation and a projection matrix for each class and classify the test images based on the projected reconstruction errors. The framework provides a more compact model than the template matching based texture classification methods, and mitigates the overfitting effect. Experimental results show that the proposed method could achieve reasonably high generalization capability even with as few as 3 training images, and significantly outperforms the state-of-the-art texture classification approaches on three benchmark datasets.     

On the classification of multispectral satellite images using the multilayer perceptron

For classifying multispectral satellite images, a multilayer perceptron (MLP) is trained using either (i) ground truth data or (ii) the output of a K-means clustering program or (iii) both, as applied to certain representative parts of the given data set. In the second case, different sets of clustered image outputs, which have been checked against actual ground truth data wherever available, are used for testing the MLP. The cover classes are, typically, different types of (a) vegetation (including forests and agriculture); (b) soil (including mountains, highways and rocky terrain); and (c) water bodies (including lakes). Since the extent of ground truth may not be sufficient for training neural networks, the proposed procedure (of using clustered output images) is believed to be novel and advantageous. Moreover, it is found that the MLP offers an accuracy of more than 99% when applied to the multispectral satellite images in our library. As importantly, comparison with some recent results shows that the proposed application of the MLP leads to a more accurate and faster classification of multispectral image data.     

瓷砖图像的纹理特征分类研究

在已有的瓷砖图像分类系统中,仅靠颜色特征和简单的纹理边缘信息只能对无花纹的单色砖或简单花纹的瓷砖进行有效分类,对复杂图案的瓷砖存在识别率低的问题。针对此种情况,结合瓷砖图像的灰度共生矩阵和统计几何特征,将这些特征输入支持向量机进行特征分层分类。采用基于径向基核函数和[K]交叉验证法所得到的最优参数构造支持向量机,解决瓷砖纹理特征具有非线性的分类问题。用瓷砖生产线上采集的大量图像进行实验表明,该方法准确率高,分类效果好。     

Statistical cloud detection from SEVIRI multispectral images

Cloud detection from geostationary satellite multispectral images through statistical methodologies is investigated. Discriminant analysis methods are considered to this purpose, endowed with a nonparametric density estimation and a linear transform into principal and independent components. The whole methodology is applied to the MSG-SEVIRI sensor through a set of test images covering the central and southern part of Europe. “Truth” data for the learning phase of discriminant analysis are taken from the cloud mask product MOD35 in correspondence of passages of MODIS close to the SEVIRI images. Performance of the discriminant analysis methods is estimated over sea/land, daytime/nighttime both when training and test datasets coincide and when they are different. Discriminant analysis shows very good performance in detecting clouds, especially over land. PCA and ICA are effective in improving detection.     

Land‐use classification of multispectral aerial images using artificial neural networks

During the past decade, there have been significant improvements in remote sensing technologies, which have provided high‐resolution data at shorter time intervals. Considerable effort has been directed towards developing new classification strategies for analysing this imagery, but the use of artificial intelligence‐based analysis techniques has been somewhat limited. The aim of this study was to develop an artificial neural network (ANN)‐based technique for the classification of multispectral aerial images for land use in agricultural and environmental applications. The specific land‐use classes included water, forest, and several types of agricultural fields. Multispectral images at a 1‐m resolution were obtained for the state of Georgia, USA from a Geographic Information Systems (GIS) data clearinghouse. These false‐colour images contained green, red and infrared true‐colour information. Three approaches were used for the preparation of the inputs to the ANN. These included histograms of the pixel intensities, textural parameters extracted from the image, and matrices of the pixels for spatial information. A probabilistic neural network was used. Seven hundred images were used for model development and 175 for independent model evaluation. The overall accuracy for the evaluation data set was 74% for the histogram approach, 71% for the spatial approach and 89% for the textural approach. The evaluation of ANNs based on various combinations of all three approaches did not show an improvement in accuracy. We also found that some approaches could be used selectively for certain classes. For example, the textural approach worked best for forest classes. For future studies, edge detection prior to classification, with more careful selection of each class, should be included for land‐use classification of multispectral images.     

基于形状与纹理特征的显微图像识别

为了实现对空气中的致敏花粉信息进行自动化统计,针对上海地区典型气传致敏花粉的光学显微镜图像,提出了基于形状和纹理特征的识别方法。对图像中分割得到的花粉区域,使用全局形状描述和傅里叶描述子提取形状信息,灰度共生矩阵提取纹理特征,并且构建k近邻分类器进行识别。选用桑科56例、禾本科25例和松科60例共141例实验样本,分别可以实现91%、88%和98%分类准确率。实验结果表明,该方法可以初步实现对花粉显微图像的分割和识别,为花粉的自动识别系统打下基础。     

Incorporating statistical information into expert classification systems to reduce classification costs

Interactive expert systems seek relevant information from a user in order to answer a query or to solve a problem that the user has posed. A fundamental design issue for such a system is therefore itsinformation-seeking strategy, which determines the order in which it asks questions or performs experiments to gain the information that it needs to respond to the user. This paper examines the problem of optimal knowledge acquisition through questioning in contexts where it is expensive or time-consuming to obtain the answers to questions. An abstract model of an expert classification system — considered as a set of logical classification rules supplemented by some statistical knowledge about attribute frequencies — is developed and applied to analyze the complexity and to present constructive algorithms for doing probabilistic question-based classification. New heuristics are presented that generalize previous results for optimal identification keys and questionnaires. For an important class of discrete discriminant analysis problems, these heuristics find optimal or near-optimal questioning strategies in a small fraction of the time required by an exact solution algorithm.     

Evaluation of speckle filtering and texture analysis methods for land cover classification from SAR images

This paper describes a comparative evaluation of several speckle reduction and texture analysis techniques, with particular emphasis on their applicability to supervised land cover classification from SAR images. Issues related to suppression of speckle in a uniform area, preservation of edges, and texture preservation are pursued in these filters. Quality of texture features is measured by the relevancy, discriminative power and ease of computation of the features. The discriminative power of texture features is measured using the Jeffreys-Matusita distance and classification performance measured on a validation set independent from the classifier's training set. Classifiers investigated are maximum-likelihood, multi-layer perceptron (MLP) and radial basis function (RBF) neural networks. Classification accuracy is measured by KHAT statistic calculated from confusion matrices. Two SAR images of ERS-1 and E-SAR programme showing different land cover categories within the regions of Douala and Ngaoundere (Cameroon), and a bi-polarized Synthetic Aperture Radar (SAR) image from an agricultural station near the city of Altona (Canada) are used for analysis. Speckle suppression techniques based on the wavelet transform performs the best, followed by the modified K-nearest neighbours and the Lee's local statistic filters. Depending on the nature of the land cover types being classified, texture features derived from second- and third-order histogram performed the best, followed by first-order statistics and features derived using the grey-level difference vector method. Among all classifiers considered, the MLP and the RBF neural networks performed the best, achieving up to 94% overall accuracy for the E-SAR image of Douala, for example.     

Bryophyte cover estimation in a boreal black spruce forest using airborne lidar and multispectral sensors

Bryophytes are the dominant ground cover vegetation layer in many boreal forests and in some of these forests the net primary production of bryophytes exceeds the overstory. Therefore it is necessary to quantify their spatial coverage and species composition in boreal forests to improve boreal forest carbon budget estimates. We present results from a small exploratory test using airborne lidar and multispectral remote sensing data to estimate the percentage of ground cover for mosses in a boreal black spruce forest in Manitoba, Canada. Multiple linear regression was used to fit models that combined spectral reflectance data from CASI and indices computed from the SLICER canopy height profile. Three models explained 63-79% of the measured variation of feathermoss cover while three models explained 69-92% of the measured variation of sphagnum cover. Root mean square errors ranged from 3-15% when predicting feathermoss, sphagnum, and total moss ground cover. The results from this case study warrant further testing for a wider range of boreal forest types and geographic regions.     

A multiscale texture analysis procedure for improved forest stand classification

Image texture is a complex visual perception. With the ever-increasing spatial resolution of remotely sensed data, the role of image texture in image classification has increased. Current approaches to image texture analysis rely on a single band of spatial information to characterize texture. This paper presents a multiscale approach to image texture where first and second-order statistical measures were derived from different sizes of processing windows and were used as additional information in a supervised classification. By using several bands of textural information processed with different window sizes (from 5×5 to 15×15) the main forest stands in the image were improved up to a maximum of 40%. A geostatistical analysis indicated that there was no single window size that would adequately characterize the range of textural conditions present in this image. A number of different statistical texture measures were compared for this image. While all of the different texture measures provided a degree of improvement (from 4 to 13% overall), the multiscale approach achieved a higher degree of classification accuracy regardless of which statistical procedure was used. When compared with single band texture measures, the level of overall improvement varied between 4 and 8%. The results indicate that this multiscale approach is an improvement over the current single band approach to analysing image texture.