Genetic feature selection for texture classification

This paper presents a novel approach to feature subset selection using genetic algorithms. This approach has the ability to accommodate multiple criteria such as the accuracy and cost of classification into the process of feature selection and finds the effective feature subset for texture classification. On the basis of the effective feature subset selected, a method is described to extract the objects which are higher than their surroundings, such as trees or forest, in the color aerial images. The methodology presented in this paper is illustrated by its application to the problem of trees extraction from aerial images.     

融和启发信息的蚁群特征选择方法

特征提取和选择是模式识别核心问题之一,它极大地影响着分类器的设计和性能,高维的特征选择更是一个NP难题。针对特征选择这一组合优化及多目标优化问题,本文提出了改进的融合启发信息ACO(Antcolony optimization)特征选择的新方法,该算法比不用启发信息的ACO方法能更好地找出代表问题空间的最优特征子集,降低分类系统的搜索空间,从而提高搜索效率。以航空纹理影像的特征选择和分类问题为例,利用原始蚂蚁算法和改进的蚂蚁算法选择的特征分别进行识别,结果证明该算法不仅能够比没有改进的蚂蚁找出有效特征集、降低图像特征空间维数、减少图像分类的工作量,而且提高了分类识别正确率。     

基于蚁群优化的特征选择新方法

利用蚁群优化算法解决特征选择问题，以获得能代表问题空间的较优特征子集，并能降低分类系统的搜索空间。以航空纹理影像的特征选择和分类问题为例，利用主分量变换和蚁群优化算法分别对原始纹理影像特征集合进行特征提取、选择和分类。结果表明，本文方法不仅能够降低图像特征空间维数，减少图像分类的工作量，而且还可以提高分类识别的正确率。     

单变量特征选择的苏北地区主要农作物遥感识别

遥感识别多源特征综合和特征优选是提高遥感影像分类精度的关键技术。农作物遥感识别中,识别特征的相对单一和数量过多均会导致作物识别精度不理想。随机森林(random forests)采用分类与回归树(CART)算法来生成分类树,结合了bagging和随机选择特征变量的优点,是一种有效的分类方法。单变量特征选择(univariate feature selection)能够对每一个待分类的特征进行测试,衡量该特征和响应变量之间的关系,根据得分舍弃不好的特征,优选得到的特征用于分类。本文基于随机森林和单变量特征选择,利用多时相光谱信息、植被指数信息、纹理信息及波段差值信息,设计多组分类实验方案,对江苏省泗洪县的高分一号(GF-1)和环境一号(HJ-1A)影像进行分类研究,旨在选择最佳的分类方案对实验区主要农作物进行识别和提取。实验结果表明:(1)多源信息综合的农作物分类精度明显高于单一的原始光谱特征分类,说明不同类型特征的引入能改善分类效果;(2)基于单变量特征选择算法的优选特征分类效果最佳,总体精度97.07%,Kappa系数0.96,表明了特征优选在降低维度的同时,也保证了较高的分类精度。随机森林和单变量特征选择结合的方法可以提高遥感影像的分类精度,为农作物的识别和提取研究提供了有效的方法。     

面向对象的无人机遥感影像岩溶湿地植被遥感识别

以广西桂林会仙喀斯特国家湿地公园为研究区，以无人机航摄影像为数据源，综合利用面向对象的影像分析技术、随机森林算法、阈值分类方法和Boruta全相关特征变量选择算法进行岩溶湿地植被的遥感识别。结果表明：针对不同特征变量对岩溶湿地遥感识别的贡献率而言，光谱特征（DOM > DSM） > 纹理特征（DOM > DSM） > 几何特征 > 上下文变量；两个航摄影像数据集的总体分类精度都在85%以上，Kappa系数也高于0.85。本文研究结果对基于高空间分辨率无人机可见光影像的岩溶湿地植被遥感识别在特征变量选择、分割参数选择及方法选择方面具有一定的借鉴意义。     

粗集属性划分的集成遥感分类

提出了一种基于粗集属性划分的遥感分类新方法, 构造了基于粗集的集成遥感分类器。该分类器利用粗集理论将输入的属性集合划分为多个约减, 利用这些约减构造多个训练子集。每个训练子集训练神经网分类器, 在决策时将多个单个分类器的结果进行投票选举。这种方法即减少了单个分类器的输入属性个数, 又避免了由于属性选取造成单一分类器在某些分类上的错误偏见。该分类器与神经网分类器方法, 以及属性选取与神经网结合方法进行了比较。结果表明RSEC无论在分类精度上, 还是在不同样本个数条件下的精度稳定程度上均有较好表现。     

ANFIS Based Land Cover/Land Use Mapping of LISS IV Imagery Using Optimized Wavelet Packet Features

Digital image classification is the process of sorting all the pixels in an image into a finite number of individual classes. But, it is difficult to classify satellite images since they include both pure pixels and boundary pixels. The boundary pixels are ‘mixed’ pixels, representing an area occupied by more than one ground cover. That is, class boundaries represented by pixels, are not sharp but fuzzy. This paper discuses the application of Adaptive Neuro-Fuzzy inference system (ANFIS) for classification of remotely sensed images that contains mixed pixels. Decision making was performed in two stages: feature extraction using the Wavelet Packet Transforms (WPT) and the ANFIS trained with the back propagation gradient descent method in combination with the least squares method for classification. Genetic Algorithms (GA) based approach is analysed for the selection of a subset from the combination of Wavelet Packet Statistical Features (WPSF) and Wavelet Packet Co-occurrence (WPC) textural feature set, which are used to classify the LISS IV images. GA has been employed to reduce the complexity and increase the accuracy of classification. Four indices—user’s accuracy, producer’s accuracy, overall accuracy and kappa co-efficient are used to assess the accuracy of the classified data. Experiments show that the proposed approach produces better results compared to the results obtained when classical classifiers are used.     

适用于遥感分类的多邻域粗糙集加权特征提取方法

邻域粗糙集是一种有效的影像特征提取方法,邻域粗糙集模型存在稳定性不高和邻域半径需要反复调整的不足,难以实现地物特征的自动化提取。提出一种多邻域粗糙集加权特征提取方法用于高分辨率遥感影像特征提取。该方法首先利用不同半径的邻域粗糙集对影像的光谱和纹理特征进行提取,求得不同邻域半径下的有效特征子集;然后统计所有邻域半径下各个特征出现的概率,将概率作为权重与特征进行加权得到最终地物特征。QucikBird影像上分类试验表明本文算法优于传统邻域粗糙集特征提取方法,分类总精度平均提高3.88%,Kappa系数平均提高5.16%。在GeoEye-1影像上的分类试验同样证明了本文方法的有效性。     

Tree Detection in Urban Regions Using Aerial Lidar and Image Data

In this letter, we present an approach to detecting trees in registered aerial image and range data obtained via lidar. The motivation for this problem comes from automated 3-D city modeling, in which such data are used to generate the models. Representing the trees in these models is problematic because the data are usually too sparsely sampled in tree regions to create an accurate 3-D model of the trees. Furthermore, including the tree data points interferes with the polygonization step of the building roof top models. Therefore, it is advantageous to detect and remove points that represent trees in both lidar and aerial imagery. In this letter, we propose a two-step method for tree detection consisting of segmentation followed by classification. The segmentation is done using a simple region-growing algorithm using weighted features from aerial image and lidar, such as height, texture map, height variation, and normal vector estimates. The weights for the features are determined using a learning method on random walks. The classification is done using the weighted support vector machines, allowing us to control the misclassification rate. The overall problem is formulated as a binary detection problem, and the results presented as receiver operating characteristic curves are shown to validate our approach     

Genetic Algorithm Based Feature Subset Selection for Land Cover/ Land Use Mapping Using Wavelet Packet Transform

A genetic algorithm based approach is used in this paper for the selection of a subset from the combination of Wavelet Packet Statistical and Wavelet Packet Co-occurrence textural feature sets to classify the LISS IV satellite images using neural networks. Generally, adding a new feature increases the complexity of training and classification. Hence there is a need to differentiate between those features that contribute ample information and others. Many current feature reduction techniques such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) involve linear transformations of the original pattern vectors to new vectors of lower dimensions. Hence a multi-objective Genetic Algorithm has been employed to reduce the complexity and increase the accuracy of classification. Four indices - user’s accuracy, producer’s accuracy, overall accuracy and kappa co-efficient are used to assess the accuracy of the classified data. Experimental results show that the proposed Genetic Algorithm approach with lesser number of optimal features produces comparable results with that of our earlier approach using more features.     

Towards 3D map generation from digital aerial images

This paper describes the fusion of information extracted from multispectral digital aerial images for highly automatic 3D map generation. The proposed approach integrates spectral classification and 3D reconstruction techniques. The multispectral digital aerial images consist of a high resolution panchromatic channel as well as lower resolution RGB and near infrared (NIR) channels and form the basis for information extraction.Our land use classification is a 2-step approach that uses RGB and NIR images for an initial classification and the panchromatic images as well as a digital surface model (DSM) for a refined classification. The DSM is generated from the high resolution panchromatic images of a specific photo mission. Based on the aerial triangulation using area and feature-based points of interest the algorithms are able to generate a dense DSM by a dense image matching procedure. Afterwards a true ortho image for classification, panchromatic or color input images can be computed.In a last step specific layers for buildings and vegetation are generated and the classification is updated.     

基于分形理论的航空图像分类方法

提出一种基于分形理论和BP神经网络的航空遥感图像有监督分类方法。该方法尝试将航空图像的光谱信息和纹理特征相结合。它首先将彩色航空图像由RGB格式转化为HSI格式，然后，根据亮度计算分数维、多重分形广义维数谱q-D(q)和“空隙”等基于分形的纹理特征，同时加入归一化的色度和饱和度作为光谱特征，采用BP神经网络作为分类器。通过对彩色航空图像的分类实验，结果证实该方法行之有效。     

基于分形理论的航空图像分类方法

提出一种基于分形理论和BP神经网络的航空遥感图像有监督分类方法。该方法尝试将航空图像的光谱信息和纹理特征相结合。它首先将彩色航空图像由RGB格式转化为HSI格式，然后，根据亮度计算分数维、多重分形广义维数谱q-D(q)和“空隙”等基于分形的纹理特征，同时加入归一化的色度和饱和度作为光谱特征，采用BP神经网络作为分类器。通过对彩色航空图像的分类实验，结果证实该方法行之有效。     

无人机高空间分辨率影像分类研究

本文利用无人机影像进行土地利用类型研究,面向对象方法对影像分割,获取了最佳分割尺度;根据各土地类别的特征信息建立分类定义,提出了快速、准确获取土地利用类型的方法。研究结果表明,运用面向对象方法能很好地解决无人机高分辨率影像分类问题,其中关键是影像分割尺度的选择和影像对象特征信息的提取。     

基于人工免疫系统的遥感图像分类

提出了一种基于人工免疫系统(ArtificialImmuneSystem)的分类方法。该方法首先应用人工免疫系统的克隆选择算法对样本进行自学习,得到全局最优的聚类中心,然后利用学习得到的聚类中心对整幅影像进行分类。由于人工免疫系统继承了生物免疫系统的自组织、自学习、自识别、自记忆的能力,从而使得人工免疫系统具有非线性的分类能力,并能够快速准确地得到全局最优解,克服了传统分类方法约束条件多,容易陷入局部最优的缺点。实验结果证明,该算法分类精度上优于传统的分类方法,总精度和Kappa系数分别达到了89.80%和0.8725,因而具有实用价值。     

Band Selection and Dimension Estimation for Hyperspectral Imagery—a New Approach Based on Invasive Weed Optimization

Currently, hyperspectral images have potential applications in many scientific areas due to the high spectral resolution. Extracting suitable and adequate bands/features from high dimensional data is a crucial task to classify such data. To overcome this issue, dimension reduction techniques have direct effects to improve the efficiency of classifiers on hyperspectral images. One common approach for decreasing the dimensionality is the feature/band selection by considering the optimum dimensionality of the hyperspectral imagery. In this paper, a new method was proposed to select optimal band for classification application, based on a metaheuristic Invasive Weed Optimization (IWO) algorithm. In this regard, the K-nearest neighbour (K-NN) technique was used as the classifier. Moreover, as a by-product of our band selection method, a new method was proposed to estimate an optimum dimension of the reduced hyperspectral images for better classification. Experimental results over three real-world hyperspectral datasets clearly showed that the proposed IWO-based band selection algorithm of this study led to the significant progress in selecting suitable bands for classification applications and estimation of optimum dimensionality of these datasets. In this regard, the overall accuracy (OA) of classification of the proposed IWO-based band selection algorithm was 92.02, 93.57, and 89.72 % for each dataset, respectively. Moreover, results reveal the superiority of the proposed IWO-based band selection algorithm against the other algorithms including GA, SA, ACO, and PSO for band selection purpose.     

An effective ensemble classification framework using random forests and a correlation based feature selection technique

Accurate classification of heterogeneous land surfaces with homogeneous land cover classes is a challenging task as satellite images are characterized by a large number of features in the spectral and spatial domains. The identifying relevance of a feature or feature set is an important task for designing an effective classification scheme. Here, an ensemble of random forests (RF) classifiers is realized on the basis of relevance of features. Correlation‐based Feature Selection (CFS) was utilized to assess the relevance of a subset of features by studying the individual predictive ability of each feature along with the degree of redundancy between them. Predictability of RF was greatly improved by random selection of the relevant features in each of the splits. An investigation was carried out on different types of images from the Landsat Enhanced Thematic Mapper Plus (Landsat ETM+) and QuickBird sensors. It has been observed that the performance of the RF classifier was significantly improved while using the optimal set of relevant features compared with a few of the most advanced supervised classifiers such as maximum likelihood classifier (MLC), Navie Bayes, multi‐layer perception (MLP), support vector machine (SVM) and bagging.     

Evaluation of semivariogram features for object-based image classification

Inclusion of textures in image classification has been shown beneficial. This paper studies an efficient use of semivariogram features for object-based high-resolution image classification. First, an input image is divided into segments, for each of which a semivariogram is then calculated. Second, candidate features are extracted as a number of key locations of the semivariogram functions. Then we use an improved Relief algorithm and the principal component analysis to select independent and significant features. Then the selected prominent semivariogram features and the conventional spectral features are combined to constitute a feature vector for a support vector machine classifier. The effect of such selected semivariogram features is compared with those of the gray-level co-occurrence matrix (GLCM) features and window-based semivariogram texture features (STFs). Tests with aerial and satellite images show that such selected semivariogram features are of a more beneficial supplement to spectral features. The described method in this paper yields a higher classification accuracy than the combination of spectral and GLCM features or STFs.     

Utility of image point cloud data towards generating enhanced multitemporal multisensor land cover maps

Multitemporal land cover classification over urban areas is challenging, especially when using heterogeneous data sources with variable quality attributes. A prominent challenge is that classes with similar spectral signatures (such as trees and grass) tend to be confused with one another. In this paper, we evaluate the efficacy of image point cloud (IPC) data combined with suitable Bayesian analysis based time-series rectification techniques to improve the classification accuracy in a multitemporal context. The proposed method uses hidden Markov models (HMMs) to rectify land covers that are initially classified by a random forest (RF) algorithm. This land cover classification method is tested using time series of remote sensing data from a heterogeneous and rapidly changing urban landscape (Kuopio city, Finland) observed from 2006 to 2014. The data consisted of aerial images (5 years), Landsat data (all 9 years) and airborne laser scanning data (1 year). The results of the study demonstrate that the addition of three-dimensional image point cloud data derived from aerial stereo images as predictor variables improved overall classification accuracy, around three percentage points. Additionally, HMM-based post processing reduces significantly the number of spurious year-to-year changes. Using a set of 240 validation points, we estimated that this step improved overall classification accuracy by around 3.0 percentage points, and up to 6 to 10 percentage points for some classes. The overall accuracy of the final product was 91% (kappa = 0.88). Our analysis shows that around 1.9% of the area around Kuopio city, representing a total area of approximately 0.61 km², experienced changes in land cover over the nine years considered.     

Tree Crown Detection,Delineation and Counting in UAV Remote Sensed Images: A Neural Network Based Spectral–Spatial Method

UAVs are fast emerging as a remote sensing platform to complement satellite based remote sensing. Agriculture and ecology is one of the important applications of UAV remote sensing, also known as low altitude remote sensing (LARS). This work demonstrates the use and potential of LARS in agriculture, particularly small holder open field agriculture. Two UAVs are used for remote sensing. The first UAV is a fixed wing aircraft with a high spatial resolution visible spectrum also known as RGB camera as a payload. The second UAV is a quadrotor UAV with an RGB camera interfaced to an on-board single board computer as the payload. LARS was carried out to acquire aerial high spatial resolution RGB images of different farms. Spectral–spatial classification of high spatial resolution RGB images for detection, delineation and counting of tree crowns in the image is presented. Supervised classification is carried out using extreme learning machine (ELM), a single hidden layer feed forward network neural network classifier. ELM was modelled for RGB values as input feature vectors and binary (tree and non-tree pixels) output class. Due to similarities in spectral intensities, some of the non-tree pixels were classified as tree pixels and in order to remove them, spatial classification was performed on the image. Spatial classification was carried out using thresholded geometrical property filtering techniques. Threshold values chosen for carrying out spatial classification were analysed to obtain optimal values. Finally in the delineation and counting, the connected tree crowns were segmented using Watershed algorithm performed on the image after marking individual tree crowns using Distance Transform method. Five representative UAV images captured at different altitudes with different crowns of banana plant, mango trees and coconut trees were used to demonstrate the performance of the proposed method. The performance was compared with the traditional KMeans spectral–spatial method of clustering. Results and comparison of performance parameters of KMeans spectral–spatial and ELM spectral–spatial classification methods are presented. Results indicate that ELM performed better than KMeans.