Evaluation of spectral and texture features for object-based vegetation species classification using Support Vector Machines

The use of appropriate features to characterize an output class or object is critical for all classification problems. This paper evaluates the capability of several spectral and texture features for object-based vegetation classification at the species level using airborne high resolution multispectral imagery. Image-objects as the basic classification unit were generated through image segmentation. Statistical moments extracted from original spectral bands and vegetation index image are used as feature descriptors for image objects (i.e. tree crowns). Several state-of-art texture descriptors such as Gray-Level Co-Occurrence Matrix (GLCM), Local Binary Patterns (LBP) and its extensions are also extracted for comparison purpose. Support Vector Machine (SVM) is employed for classification in the object-feature space. The experimental results showed that incorporating spectral vegetation indices can improve the classification accuracy and obtained better results than in original spectral bands, and using moments of Ratio Vegetation Index obtained the highest average classification accuracy in our experiment. The experiments also indicate that the spectral moment features also outperform or can at least compare with the state-of-art texture descriptors in terms of classification accuracy.

Empirical comparison of machine learning algorithms for image texture classification with application to vegetation management in power line corridors

This paper reports on the empirical comparison of seven machine learning algorithms in texture classification with application to vegetation management in power line corridors. Aiming at classifying tree species in power line corridors, object-based method is employed. Individual tree crowns are segmented as the basic classification units and three classic texture features are extracted as the input to the classification algorithms. Several widely used performance metrics are used to evaluate the classification algorithms. The experimental results demonstrate that the classification performance depends on the performance matrix, the characteristics of datasets and the feature used.

Advances in vegetation management for power line corridor monitoring using aerial remote sensing techniques

This paper presents a comprehensive discussion of vegetation management approaches in power line corridors based on aerial remote sensing techniques. We address three issues 1) strategies for risk management in power line corridors, 2) selection of suitable platforms and sensor suite for data collection and 3) the progress in automated data processing techniques for vegetation management. We present initial results from a series of experiments and, challenges and lessons learnt from our project.

Color and texture feature fusion using kernel PCA with application to object-based vegetation species classification

A good object representation or object descriptor is one of the key issues in object based image analysis. To effectively fuse color and texture as a unified descriptor at object level, this paper presents a novel method for feature fusion. Color histogram and the uniform local binary patterns are extracted from arbitrary-shaped image-objects, and kernel principal component analysis (kernel PCA) is employed to find nonlinear relationships of the extracted color and texture features. The maximum likelihood approach is used to estimate the intrinsic dimensionality, which is then used as a criterion for automatic selection of optimal feature set from the fused feature. The proposed method is evaluated using SVM as the benchmark classifier and is applied to object-based vegetation species classification using high spatial resolution aerial imagery. Experimental results demonstrate that great improvement can be achieved by using proposed feature fusion method.

A biologically inspired object spectral-texture descriptor and its application to vegetation classification in power-line corridors

The use of appropriate features to represent an output class or object is critical for all classification problems. In this paper, we propose a biologically inspired object descriptor to represent the spectral-texture patterns of image-objects. The proposed feature descriptor is generated from the pulse spectral frequencies (PSF) of a pulse coupled neural network (PCNN), which is invariant to rotation, translation and small scale changes. The proposed method is first evaluated in a rotation and scale invariant texture classification using USC-SIPI texture database. It is further evaluated in an application of vegetation species classification in power line corridor monitoring using airborne multi-spectral aerial imagery. The results from the two experiments demonstrate that the PSF feature is effective to represent spectral-texture patterns of objects and it shows better results than classic color histogram and texture features.

The role of vegetation in enhancing radon concentration and ion production in the atmosphere

The role of ions in the production of atmospheric particles has gained wide interest due to their profound impact on climate. Away from anthropogenic sources, molecules are ionized by alpha radiation from radon exhaled from the ground and cosmic gamma radiation from space. These molecular ions quickly form into ‘cluster ions’, typically smaller than about 1.5 nm. Using our measurements and the published literature, we present evidence to show that cluster ion concentrations in forest areas are consistently higher than outside. Since alpha radiation cannot penetrate more than a few centimetres of soil, radon present deep in the ground cannot directly contribute to the measured cluster ion concentrations. We propose an additional mechanism whereby radon, which is water soluble, is brought up by trees and plants through the uptake of groundwater and released into the atmosphere by transpiration. We estimate that, in a forest comprising eucalyptus trees spaced 4m apart, approximately 28% of the radon in the air may be released by transpiration. Considering that 24% of the earth’s land area is still covered in forests; these findings have potentially important implications for atmospheric aerosol formation and climate.

Spectral–texture feature extraction using statistical moments with application to object-based vegetation species classification

The use of appropriate features to characterise an output class or object is critical for all classification problems. In order to find optimal feature descriptors for vegetation species classification in a power line corridor monitoring application, this article evaluates the capability of several spectral and texture features. A new idea of spectral–texture feature descriptor is proposed by incorporating spectral vegetation indices in statistical moment features. The proposed method is evaluated against several classic texture feature descriptors. Object-based classification method is used and a support vector machine is employed as the benchmark classifier. Individual tree crowns are first detected and segmented from aerial images and different feature vectors are extracted to represent each tree crown. The experimental results showed that the proposed spectral moment features outperform or can at least compare with the state-of-the-art texture descriptors in terms of classification accuracy. A comprehensive quantitative evaluation using receiver operating characteristic space analysis further demonstrates the strength of the proposed feature descriptors.

Boosting the margin: A new explanation for the effectiveness of voting methods

One of the surprising recurring phenomena observed in experiments with boosting is that the test error of the generated classifier usually does not increase as its size becomes very large, and often is observed to decrease even after the training error reaches zero. In this paper, we show that this phenomenon is related to the distribution of margins of the training examples with respect to the generated voting classification rule, where the margin of an example is simply the difference between the number of correct votes and the maximum number of votes received by any incorrect label. We show that techniques used in the analysis of Vapnik's support vector classifiers and of neural networks with small weights can be applied to voting methods to relate the margin distribution to the test error. We also show theoretically and experimentally that boosting is especially effective at increasing the margins of the training examples. Finally, we compare our explanation to those based on the bias-variance decomposition.

Exponentiated gradient algorithms for conditional random fields and max-margin Markov Networks

Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore an important problem, and becomes a key factor when learning from very large data sets. This paper describes exponentiated gradient (EG) algorithms for training such models, where EG updates are applied to the convex dual of either the log-linear or max-margin objective function; the dual in both the log-linear and max-margin cases corresponds to minimizing a convex function with simplex constraints. We study both batch and online variants of the algorithm, and provide rates of convergence for both cases. In the max-margin case, O(1/ε) EG updates are required to reach a given accuracy ε in the dual; in contrast, for log-linear models only O(log(1/ε)) updates are required. For both the max-margin and log-linear cases, our bounds suggest that the online EG algorithm requires a factor of n less computation to reach a desired accuracy than the batch EG algorithm, where n is the number of training examples. Our experiments confirm that the online algorithms are much faster than the batch algorithms in practice. We describe how the EG updates factor in a convenient way for structured prediction problems, allowing the algorithms to be efficiently applied to problems such as sequence learning or natural language parsing. We perform extensive evaluation of the algorithms, comparing them to L-BFGS and stochastic gradient descent for log-linear models, and to SVM-Struct for max-margin models. The algorithms are applied to a multi-class problem as well as to a more complex large-scale parsing task. In all these settings, the EG algorithms presented here outperform the other methods.

Exponentiated gradient algorithms for large-margin structured classification

We consider the problem of structured classification, where the task is to predict a label y from an input x, and y has meaningful internal structure. Our framework includes supervised training of Markov random fields and weighted context-free grammars as special cases. We describe an algorithm that solves the large-margin optimization problem defined in [12], using an exponential-family (Gibbs distribution) representation of structured objects. The algorithm is efficient—even in cases where the number of labels y is exponential in size—provided that certain expectations under Gibbs distributions can be calculated efficiently. The method for structured labels relies on a more general result, specifically the application of exponentiated gradient updates [7, 8] to quadratic programs.

Margin-adaptive model selection in statistical learning

A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one to take into account that learning within a small model can be much easier than within a large one. Requiring this “strong margin adaptivity” makes the model selection problem more challenging. We first prove, in a general framework, that some penalization procedures (including local Rademacher complexities) exhibit this adaptivity when the models are nested. Contrary to previous results, this holds with penalties that only depend on the data. Our second main result is that strong margin adaptivity is not always possible when the models are not nested: for every model selection procedure (even a randomized one), there is a problem for which it does not demonstrate strong margin adaptivity.

From the margin to the centre : towards an art strategy for the ethnic enclaves in the city

Sunnybank represents a distinctly Australian take on the classic ‘Chinatown’ – or indeed other ethic community enclaves such as ‘little Italy’, ‘little Bombay’, ‘little Athens’ and so on. In the Northern Hemisphere these tended to grow up in the dense working class neighbourhoods of industrial cities, especially in port cities like Liverpool, London, New York and San Francisco. The existing Chinatowns of Sydney and Melbourne, and to some extent Brisbane’s Fortitude Valley, are of this variety. In the late 1970s, with the growth of suburbanisation and the de-industrialisation and consequent dereliction of the ‘inner city’, these ethnic communities were one of the few signs of life in the city. Apart from the daily commute into the CBD, business with the city council or a trip to the big shopping streets these areas were one of the few reasons for visiting city centres stigmatised by urban decay and petty crime.

Importance of soil ecology in vegetation rehabilitation on a North Stradbroke Island sand mine

Sibelco Australia Limited (SAL), a mineral sand mining operation on North Stradbroke Island, undertakes progressive rehabilitation of mined areas. Initial investigations have found that some areas at SAL’s Yarraman Mine have failed to redevelop towards approved criteria. This study, undertaken in 2010, examined ground cover rehabilitation of different aged plots at the Yarraman Mine to determine if there was a relationship between key soil and vegetation attributes. Vegetation and soil data were collected from five plots rehabilitated in 2003, 2006, 2008, 2009 and 2010, and one unmined plot. Cluster (PATN) analysis revealed that vegetation species composition, species richness and ground cover differed between plots. Principal component analysis (PCA) extracted ten soil attributes that were then correlated with vegetation data. The attributes extracted by PCA, in order of most common variance, were: water content, pH, terrolas depth, elevation, slope angle, leaf litter depth, total organic carbon, and counts of macrofauna, fungi and bacteria. All extracted attributes differed between plots, and all except bacteria correlated with at least one vegetation attribute. Water content and pH correlated most strongly with vegetation cover suggesting an increase in soil moisture and a reduction in pH are required in order to improve vegetation rehabilitation at Yarraman Mine. Further study is recommended to confirm these results using controlled experiments and to test potential solutions, such as organic amendments.

The influence of vegetation and soil type on the speciation of iron in soil water

Soluble organic matter derived from exotic Pinus species has been shown to form stronger complexes with iron (Fe) than that derived from most native Australian species. It has also been proposed that the establishment of exotic Pinus plantations in coastal southeast Queensland may have enhanced the solubility of Fe in soils by increasing the amount of organically complexed Fe, but this remains inconclusive. In this study we test whether the concentration and speciation of Fe in soil water from Pinus plantations differs significantly from soil water from native vegetation areas. Both Fe redox speciation and the interaction between Fe and dissolved organic matter (DOM) were considered; Fe - DOM interaction was assessed using the Stockholm Humic Model. Iron concentrations (mainly Fe 2+) were greatest in the soil waters with the greatest DOM content collected from sandy podosols (Podzols), where they are largely controlled by redox potential. Iron concentrations were small in soil waters from clay and iron oxide-rich soils, in spite of similar redox potentials. This condition is related to stronger sorption on to the reactive clay and iron oxide mineral surfaces in these soils, which reduces the amount of DOM available for electron shuttling and microbial metabolism, restricting reductive dissolution of Fe. Vegetation type had no significant influence on the concentration and speciation of iron in soil waters, although DOM from Pinus sites had greater acidic functional group site densities than DOM from native vegetation sites. This is because Fe is mainly in the ferrous form, even in samples from the relatively well-drained podosols. However, modelling suggests that Pinus DOM can significantly increase the amount of truly dissolved ferric iron remaining in solution in oxic conditions. Therefore, the input of ferrous iron together with Pinus DOM to surface waters may reduce precipitation of hydrous ferric oxides (ferrihydrite) and increase the flux of dissolved Fe out of the catchment. Such inputs of iron are most probably derived from podosols planted with Pinus.