David R. Stockwell

A novel texture feature based multiple classifier technique for roadside vegetation classification

Proposed technique use LBP based GLCM feature vector and multiple classifiers.We achieve over 92% accuracy for vegetation classification.Extensive experiments use 5-fold cross validation.The experiments were conducted on dense and sparse grasses.In future, extension will be done by introducing large dataset of grasses. This paper presents a novel texture feature based multiple classifier technique and applies it to roadside vegetation classification. It is well-known that automation of roadside vegetation classification is one of the important issues emerging strongly in improving the fire risk and road safety. Hence, the application presented in this paper is significantly important for identifying fire risks and road safety. The images collected from outdoor environments such as roadside, are affected for a high variability of illumination conditions because of different weather conditions. This paper proposes a novel texture feature based robust expert system for vegetation identification. It consists of five steps, namely image pre-processing, feature extraction, training with multiple classifiers, classification, validation and statistical analysis. In the initial stage, Co-occurrence of Binary Pattern (CBP) technique is applied in order to obtain the texture feature relevant to vegetation in the roadside images. In the training and classification stages, three classifiers have been fused to combine the multiple decisions. The first classifier is based on Support Vector Machine, the second classifier is based on feed forward back-propagation neural network (FF-BPNN) and the third classifier is based on -Nearest Neighbor (k-NN). The proposed technique has been applied and evaluated on two types of vegetation images i.e. dense and sparse grasses. The classification accuracy with a success of 92.72% has been obtained using 5-fold cross validation approach. An (Analysis of Variance) test has also been conducted to show the statistical significance of results.

An hierarchical approach towards road image segmentation

The segmentation of road images from vehicle mounted video is a challenging and difficult problem. One of the problems is the presence of different types of objects and not all objects are present in the same frame. For example, road sign is not visible in all frames. In this paper, we propose a novel framework for segmenting road images in a hierarchical manner that can separate the following objects: sky, road, road signs, and vegetation from the video data. Each frame in the video is analysed separately. The hierarchical approach does not assume the presence of a certain number of objects in a single frame. We have also developed a segmentation framework based on SVM learning. The proposed framework has been tested on the Transport and Main Roads Queenslands video data. The experimental results indicate that the proposed framework can detect different objects with an accuracy of 95.65%.

Class-Semantic Color-Texture Textons for Vegetation Classification

This paper proposes a new color-texture texton based approach for roadside vegetation classification in natural images. Two individual sets of class-semantic textons are first generated from color and filter bank texture features for each class. The color and texture features of testing pixels are then mapped into one of the generated textons using the nearest distance, resulting in two texton occurrence matrices – one for color and one for texture. The classification is achieved by aggregating color-texture texton occurrences over all pixels in each over-segmented superpixel using a majority voting strategy. Our approach outperforms previous benchmarking approaches and achieves 81% and 74.5% accuracies of classifying seven objects on a cropped region dataset and six objects on an image dataset collected by the Department of Transport and Main Roads, Queensland, Australia.

Biases in the Australian High Quality Temperature Network

Various reports identify global warming over the last century as around 0.7°C, but warming in Australia at around 0.9°C, suggesting Australia may be warming faster than the rest of the world. This study evaluates potential biases in the High Quality Network (HQN) compiled from 100 rural surface temperature series from 1910 due to: (1) homogeneity adjustments used to correct for changes in location and instrumentation, and (2) the discrimination of urban and rural sites. The approach was to compare the HQN with a new network compiled from raw data using the minimal adjustments necessary to produce contiguous series, called the Minimal Adjustment Network (MAN). The average temperature trend of the MAN stations was 31% lower than the HQN, and by a number of measures, the trend of the Australian MAN is consistent with the global trend. This suggests that biases from these sources have exaggerated apparent Australian warming. Additional problems with the HQN include failure of homogenization procedures to properly identify errors, individual sites adjusted more than the magnitude of putative warming last century, and some sites of such poor quality they should not be used, especially under a “High Quality” banner.

Spatial contextual superpixel model for natural roadside vegetation classification

In this paper, we present a novel Spatial Contextual Superpixel Model (SCSM) for vegetation classification in natural roadside images. The SCSM accomplishes the goal by transforming the classification task from a pixel into a superpixel domain for more effective adoption of both local and global spatial contextual information between superpixels in an image. First, the image is segmented into a set of superpixels with strong homogeneous texture, from which Pixel Patch Selective (PPS) features are extracted to train class-specific binary classifiers for obtaining Contextual Superpixel Probability Maps (CSPMs) for all classes, coupled with spatial constraints. A set of superpixel candidates with the highest probabilities is then determined to represent global characteristics of a testing image. A superpixel merging strategy is further proposed to progressively merge superpixels with low probabilities into the most similar neighbors by performing a double-check on whether a superpixel and its neighour accept each other, as well as enhancing a global contextual constraint. We demonstrate high performance by the proposed model on two challenging natural roadside image datasets from the Department of Transport and Main Roads and on the Stanford background benchmark dataset. A novel Spatial Contextual Superpixel Model (SCSM) for natural vegetation classification.A new reverse superpixel merging strategy to progressively merge superpixels.High performance on challenging natural datasets and Stanford background data.

Roadside vegetation classification using color intensity and moments

Roadside vegetation classification plays a significant role in many applications, such as grass fire risk assessment and vegetation growth condition monitoring. Most existing approaches focus on the use of vegetation indices from the invisible spectrum, and only limited attention has been given to using visual features, such as color and texture. This paper presents a new approach for vegetation classification using a fusion of color and texture features. The color intensity features are extracted in the opponent color space, while the texture comprises of three color moments. We demonstrate 79% accuracy of the approach on a dataset created from real world video data collected by the Department of Transport and Main Roads (DTMR), Queensland, Australia, and promising results on a set of natural images. We also highlight some typical challenges for roadside vegetation classification in natural conditions.

Recent Climate Observations: Disagreement with Projections

The non-linear trend in Rahmstorf et al. [2007] is updated with recent global temperature data. The evidence does not support the basis for their claim that the sensitivity of the climate system has been underestimated.

Spatially Constrained Location Prior for scene parsing

Semantic context is an important and useful cue for scene parsing in complicated natural images with a substantial amount of variations in objects and the environment. This paper proposes Spatially Constrained Location Prior (SCLP) for effective modelling of global and local semantic context in the scene in terms of inter-class spatial relationships. Unlike existing studies focusing on either relative or absolute location prior of objects, the SCLP effectively incorporates both relative and absolute location priors by calculating object co-occurrence frequencies in spatially constrained image blocks. The SCLP is general and can be used in conjunction with various visual feature-based prediction models, such as Artificial Neural Networks and Support Vector Machine (SVM), to enforce spatial contextual constraints on class labels. Using SVM classifiers and a linear regression model, we demonstrate that the incorporation of SCLP achieves superior performance compared to the state-of-the-art methods on the Stanford background and SIFT Flow datasets.

Critique of Drought Models in the Australian Drought Exceptional Circumstances Report (DECR)

This paper1 evaluates the reliability of modeling in the Drought Exceptional Circumstances Report (DECR) where global circulation (or climate) simulations were used to forecast future extremes of temperatures, rainfall and soil moisture. The DECR provided the Australian government with an assessment of the likely future change in the extent and frequency of drought resulting from anthropogenic global warming. Three specific and different statistical techniques show that the simulation of the occurrence of extreme high temperatures last century was adequate, but the simulation of the occurrence of extreme low rainfall was unacceptably poor. In particular, the simulations indicate that the measure of hydrological drought increased significantly last century, while the observations indicate a significant decrease. The main conclusion and purpose of the paper is to provide a case study showing the need for more rigorous and explicit validation of climate models if they are to advise government policy.

Aggregating pixel-level prediction and cluster-level texton occurrence within superpixel voting for roadside vegetation classification.

Roadside vegetation classification has recently attracted increasing attention, due to its significance in applications such as vegetation growth management and fire hazard identification. Existing studies primarily focus on learning visible feature based classifiers or invisible feature based thresholds, which often suffer from a generalization problem to new data. This paper proposes an approach that aggregates pixel-level supervised classification and cluster-level texton occurrence within a voting strategy over superpixels for vegetation classification, which takes into account both generic features in the training data and local characteristics in the testing data. Class-specific artificial neural networks are trained to predict class probabilities for all pixels, while a texton based adaptive K-means clustering process is introduced to group pixels into clusters and obtain texton occurrence. The pixel-level class probabilities and cluster-level texton occurrence are further integrated in superpixel-level voting to assign each superpixel to a class category. The proposed approach outperforms previous approaches on a roadside image dataset collected by the Department of Transport and Main Roads, Queensland, Australia, and achieves state-of-the-art performance using low-resolution images from the Croatia roadside grass dataset.