Modeling corneal surfaces with rational functions for high-speed videokeratoscopy data compression

High-speed videokeratoscopy is an emerging technique that enables study of the corneal surface and tear-film dynamics. Unlike its static predecessor, this new technique results in a very large amount of digital data for which storage needs become significant. We aimed to design a compression technique that would use mathematical functions to parsimoniously fit corneal surface data with a minimum number of coefficients. Since the Zernike polynomial functions that have been traditionally used for modeling corneal surfaces may not necessarily correctly represent given corneal surface data in terms of its optical performance, we introduced the concept of Zernike polynomial-based rational functions. Modeling optimality criteria were employed in terms of both the rms surface error as well as the point spread function cross-correlation. The parameters of approximations were estimated using a nonlinear least-squares procedure based on the Levenberg-Marquardt algorithm. A large number of retrospective videokeratoscopic measurements were used to evaluate the performance of the proposed rational-function-based modeling approach. The results indicate that the rational functions almost always outperform the traditional Zernike polynomial approximations with the same number of coefficients.

Modeling videokeratoscopic height data with spherical harmonics

Purpose: All currently considered parametric models used for decomposing videokeratoscopy height data are viewercentered and hence describe what the operator sees rather than what the surface is. The purpose of this study was to ascertain the applicability of an object-centered representation to modeling of corneal surfaces. Methods: A three-dimensional surface decomposition into a series of spherical harmonics is considered and compared with the traditional Zernike polynomial expansion for a range of videokeratoscopic height data. Results: Spherical harmonic decomposition led to significantly better fits to corneal surfaces (in terms of the root mean square error values) than the corresponding Zernike polynomial expansions with the same number of coefficients, for all considered corneal surfaces, corneal diameters, and model orders. Conclusions: Spherical harmonic decomposition is a viable alternative to Zernike polynomial decomposition. It achieves better fits to videokeratoscopic height data and has the advantage of an object-centered representation that could be particularly suited to the analysis of multiple corneal measurements.

Describing ocular aberrations with wavefront vergence maps

A common optometric problem is to specify the eye’s ocular aberrations in terms of Zernike coefficients and to reduce that specification to a prescription for the optimum sphero-cylindrical correcting lens. The typical approach is first to reconstruct wavefront phase errors from measurements of wavefront slopes obtained by a wavefront aberrometer. This paper applies a new method to this clinical problem that does not require wavefront reconstruction. Instead, we base our analysis of axial wavefront vergence as inferred directly from wavefront slopes. The result is a wavefront vergence map that is similar to the axial power maps in corneal topography and hence has a potential to be favoured by clinicians. We use our new set of orthogonal Zernike slope polynomials to systematically analyse details of the vergence map analogous to Zernike analysis of wavefront maps. The result is a vector of slope coefficients that describe fundamental aberration components. Three different methods for reducing slope coefficients to a spherocylindrical prescription in power vector forms are compared and contrasted. When the original wavefront contains only second order aberrations, the vergence map is a function of meridian only and the power vectors from all three methods are identical. The differences in the methods begin to appear as we include higher order aberrations, in which case the wavefront vergence map is more complicated. Finally, we discuss the advantages and limitations of vergence map representation of ocular aberrations.

Robust real time multi-layer foreground segmentation

Many surveillance applications (object tracking, abandoned object detection) rely on detecting changes in a scene. Foreground segmentation is an effective way to extract the foreground from the scene, but these techniques cannot discriminate between objects that have temporarily stopped and those that are moving. We propose a series of modifications to an existing foreground segmentation system\cite{Butler2003} so that the foreground is further segmented into two or more layers. This yields an active layer of objects currently in motion and a passive layer of objects that have temporarily ceased motion which can itself be decomposed into multiple static layers. We also propose a variable threshold to cope with variable illumination, a feedback mechanism that allows an external process (i.e. surveillance system) to alter the motion detectors state, and a lighting compensation process and a shadow detector to reduce errors caused by lighting inconsistencies. The technique is demonstrated using outdoor surveillance footage, and is shown to be able to effectively deal with real world lighting conditions and overlapping objects.

Abandoned object detection using multi-layer motion detection

Abandoned object detection (AOD) systems are required to run in high traffic situations, with high levels of occlusion. Systems rely on background segmentation techniques to locate abandoned objects, by detecting areas of motion that have stopped. This is often achieved by using a medium term motion detection routine to detect long term changes in the background. When AOD systems are integrated into person tracking system, this often results in two separate motion detectors being used to handle the different requirements. We propose a motion detection system that is capable of detecting medium term motion as well as regular motion. Multiple layers of medium term (static) motion can be detected and segmented. We demonstrate the performance of this motion detection system and as part of an abandoned object detection system.

Unmanned Aerial Vehicles UAVs attitude, height, motion estimation and control using visual systems

This paper presents an implementation of an aircraft pose and motion estimator using visual systems as the principal sensor for controlling an Unmanned Aerial Vehicle (UAV) or as a redundant system for an Inertial Measure Unit (IMU) and gyros sensors. First, we explore the applications of the unified theory for central catadioptric cameras for attitude and heading estimation, explaining how the skyline is projected on the catadioptric image and how it is segmented and used to calculate the UAV’s attitude. Then we use appearance images to obtain a visual compass, and we calculate the relative rotation and heading of the aerial vehicle. Additionally, we show the use of a stereo system to calculate the aircraft height and to measure the UAV’s motion. Finally, we present a visual tracking system based on Fuzzy controllers working in both a UAV and a camera pan and tilt platform. Every part is tested using the UAV COLIBRI platform to validate the different approaches, which include comparison of the estimated data with the inertial values measured onboard the helicopter platform and the validation of the tracking schemes on real flights.

Modeling corneal surfaces with three-dimensional basis functions

Purpose: To ascertain the effectiveness of object-centered three-dimensional representations for the modeling of corneal surfaces. Methods: Three-dimensional (3D) surface decomposition into series of basis functions including: (i) spherical harmonics, (ii) hemispherical harmonics, and (iii) 3D Zernike polynomials were considered and compared to the traditional viewer-centered representation of two-dimensional (2D) Zernike polynomial expansion for a range of retrospective videokeratoscopic height data from three clinical groups. The data were collected using the Medmont E300 videokeratoscope. The groups included 10 normal corneas with corneal astigmatism less than −0.75 D, 10 astigmatic corneas with corneal astigmatism between −1.07 D and 3.34 D (Mean = −1.83 D, SD = ±0.75 D), and 10 keratoconic corneas. Only data from the right eyes of the subjects were considered. Results: All object-centered decompositions led to significantly better fits to corneal surfaces (in terms of the RMS error values) than the corresponding 2D Zernike polynomial expansions with the same number of coefficients, for all considered corneal surfaces, corneal diameters (2, 4, 6, and 8 mm), and model orders (4th to 10th radial orders) The best results (smallest RMS fit error) were obtained with spherical harmonics decomposition which lead to about 22% reduction in the RMS fit error, as compared to the traditional 2D Zernike polynomials. Hemispherical harmonics and the 3D Zernike polynomials reduced the RMS fit error by about 15% and 12%, respectively. Larger reduction in RMS fit error was achieved for smaller corneral diameters and lower order fits. Conclusions: Object-centered 3D decompositions provide viable alternatives to traditional viewer-centered 2D Zernike polynomial expansion of a corneal surface. They achieve better fits to videokeratoscopic height data and could be particularly suited to the analysis of multiple corneal measurements, where there can be slight variations in the position of the cornea from one map acquisition to the next.

Accurate silhouettes for surveillance : improved motion segmentation using graph cuts

Silhouettes are common features used by many applications in computer vision. For many of these algorithms to perform optimally, accurately segmenting the objects of interest from the background to extract the silhouettes is essential. Motion segmentation is a popular technique to segment moving objects from the background, however such algorithms can be prone to poor segmentation, particularly in noisy or low contrast conditions. In this paper, the work of [3] combining motion detection with graph cuts, is extended into two novel implementations that aim to allow greater uncertainty in the output of the motion segmentation, providing a less restricted input to the graph cut algorithm. The proposed algorithms are evaluated on a portion of the ETISEO dataset using hand segmented ground truth data, and an improvement in performance over the motion segmentation alone and the baseline system of [3] is shown.

Application of data mining techniques in the prediction of coronary artery disease : use of anaesthesia time-series and patient risk factor data

The high morbidity and mortality associated with atherosclerotic coronary vascular disease (CVD) and its complications are being lessened by the increased knowledge of risk factors, effective preventative measures and proven therapeutic interventions. However, significant CVD morbidity remains and sudden cardiac death continues to be a presenting feature for some subsequently diagnosed with CVD. Coronary vascular disease is also the leading cause of anaesthesia related complications. Stress electrocardiography/exercise testing is predictive of 10 year risk of CVD events and the cardiovascular variables used to score this test are monitored peri-operatively. Similar physiological time-series datasets are being subjected to data mining methods for the prediction of medical diagnoses and outcomes. This study aims to find predictors of CVD using anaesthesia time-series data and patient risk factor data. Several pre-processing and predictive data mining methods are applied to this data. Physiological time-series data related to anaesthetic procedures are subjected to pre-processing methods for removal of outliers, calculation of moving averages as well as data summarisation and data abstraction methods. Feature selection methods of both wrapper and filter types are applied to derived physiological time-series variable sets alone and to the same variables combined with risk factor variables. The ability of these methods to identify subsets of highly correlated but non-redundant variables is assessed. The major dataset is derived from the entire anaesthesia population and subsets of this population are considered to be at increased anaesthesia risk based on their need for more intensive monitoring (invasive haemodynamic monitoring and additional ECG leads). Because of the unbalanced class distribution in the data, majority class under-sampling and Kappa statistic together with misclassification rate and area under the ROC curve (AUC) are used for evaluation of models generated using different prediction algorithms. The performance based on models derived from feature reduced datasets reveal the filter method, Cfs subset evaluation, to be most consistently effective although Consistency derived subsets tended to slightly increased accuracy but markedly increased complexity. The use of misclassification rate (MR) for model performance evaluation is influenced by class distribution. This could be eliminated by consideration of the AUC or Kappa statistic as well by evaluation of subsets with under-sampled majority class. The noise and outlier removal pre-processing methods produced models with MR ranging from 10.69 to 12.62 with the lowest value being for data from which both outliers and noise were removed (MR 10.69). For the raw time-series dataset, MR is 12.34. Feature selection results in reduction in MR to 9.8 to 10.16 with time segmented summary data (dataset F) MR being 9.8 and raw time-series summary data (dataset A) being 9.92. However, for all time-series only based datasets, the complexity is high. For most pre-processing methods, Cfs could identify a subset of correlated and non-redundant variables from the time-series alone datasets but models derived from these subsets are of one leaf only. MR values are consistent with class distribution in the subset folds evaluated in the n-cross validation method. For models based on Cfs selected time-series derived and risk factor (RF) variables, the MR ranges from 8.83 to 10.36 with dataset RF_A (raw time-series data and RF) being 8.85 and dataset RF_F (time segmented time-series variables and RF) being 9.09. The models based on counts of outliers and counts of data points outside normal range (Dataset RF_E) and derived variables based on time series transformed using Symbolic Aggregate Approximation (SAX) with associated time-series pattern cluster membership (Dataset RF_ G) perform the least well with MR of 10.25 and 10.36 respectively. For coronary vascular disease prediction, nearest neighbour (NNge) and the support vector machine based method, SMO, have the highest MR of 10.1 and 10.28 while logistic regression (LR) and the decision tree (DT) method, J48, have MR of 8.85 and 9.0 respectively. DT rules are most comprehensible and clinically relevant. The predictive accuracy increase achieved by addition of risk factor variables to time-series variable based models is significant. The addition of time-series derived variables to models based on risk factor variables alone is associated with a trend to improved performance. Data mining of feature reduced, anaesthesia time-series variables together with risk factor variables can produce compact and moderately accurate models able to predict coronary vascular disease. Decision tree analysis of time-series data combined with risk factor variables yields rules which are more accurate than models based on time-series data alone. The limited additional value provided by electrocardiographic variables when compared to use of risk factors alone is similar to recent suggestions that exercise electrocardiography (exECG) under standardised conditions has limited additional diagnostic value over risk factor analysis and symptom pattern. The effect of the pre-processing used in this study had limited effect when time-series variables and risk factor variables are used as model input. In the absence of risk factor input, the use of time-series variables after outlier removal and time series variables based on physiological variable values’ being outside the accepted normal range is associated with some improvement in model performance.

The nonconceptual gateway to early word learning

My research investigates why nouns are learned disproportionately more frequently than other kinds of words during early language acquisition (Gentner, 1982; Gleitman, et al., 2004). This question must be considered in the context of cognitive development in general. Infants have two major streams of environmental information to make meaningful: perceptual and linguistic. Perceptual information flows in from the senses and is processed into symbolic representations by the primitive language of thought (Fodor, 1975). These symbolic representations are then linked to linguistic input to enable language comprehension and ultimately production. Yet, how exactly does perceptual information become conceptualized? Although this question is difficult, there has been progress. One way that children might have an easier job is if they have structures that simplify the data. Thus, if particular sorts of perceptual information could be separated from the mass of input, then it would be easier for children to refer to those specific things when learning words (Spelke, 1990; Pylyshyn, 2003). It would be easier still, if linguistic input was segmented in predictable ways (Gentner, 1982; Gleitman, et al., 2004) Unfortunately the frequency of patterns in lexical or grammatical input cannot explain the cross-cultural and cross-linguistic tendency to favor nouns over verbs and predicates. There are three examples of this failure: 1) a wide variety of nouns are uttered less frequently than a smaller number of verbs and yet are learnt far more easily (Gentner, 1982); 2) word order and morphological transparency offer no insight when you contrast the sentence structures and word inflections of different languages (Slobin, 1973) and 3) particular language teaching behaviors (e.g. pointing at objects and repeating names for them) have little impact on children's tendency to prefer concrete nouns in their first fifty words (Newport, et al., 1977). Although the linguistic solution appears problematic, there has been increasing evidence that the early visual system does indeed segment perceptual information in specific ways before the conscious mind begins to intervene (Pylyshyn, 2003). I argue that nouns are easier to learn because their referents directly connect with innate features of the perceptual faculty. This hypothesis stems from work done on visual indexes by Zenon Pylyshyn (2001, 2003). Pylyshyn argues that the early visual system (the architecture of the "vision module") segments perceptual data into pre-conceptual proto-objects called FINSTs. FINSTs typically correspond to physical things such as Spelke objects (Spelke, 1990). Hence, before conceptualization, visual objects are picked out by the perceptual system demonstratively, like a finger pointing indicating ‘this’ or ‘that’. I suggest that this primitive system of demonstration elaborates on Gareth Evan's (1982) theory of nonconceptual content. Nouns are learnt first because their referents attract demonstrative visual indexes. This theory also explains why infants less often name stationary objects such as plate or table, but do name things that attract the focal attention of the early visual system, i.e., small objects that move, such as ‘dog’ or ‘ball’. This view leaves open the question how blind children learn words for visible objects and why children learn category nouns (e.g. 'dog'), rather than proper nouns (e.g. 'Fido') or higher taxonomic distinctions (e.g. 'animal').

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.

Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

Model-order selection in Zernike polynomial expansion of corneal surfaces using the efficient detection criterion

Corneal-height data are typically measured with videokeratoscopes and modeled using a set of orthogonal Zernike polynomials. We address the estimation of the number of Zernike polynomials, which is formalized as a model-order selection problem in linear regression. Classical information-theoretic criteria tend to overestimate the corneal surface due to the weakness of their penalty functions, while bootstrap-based techniques tend to underestimate the surface or require extensive processing. In this paper, we propose to use the efficient detection criterion (EDC), which has the same general form of information-theoretic-based criteria, as an alternative to estimating the optimal number of Zernike polynomials. We first show, via simulations, that the EDC outperforms a large number of information-theoretic criteria and resampling-based techniques. We then illustrate that using the EDC for real corneas results in models that are in closer agreement with clinical expectations and provides means for distinguishing normal corneal surfaces from astigmatic and keratoconic surfaces.

Automatic in-bucket volume estimation for dragline operations

This paper presents a method for calculating the in-bucket payload volume on a dragline for the purpose of estimating the material’s bulk density in real-time. Knowledge of the bulk density can provide instant feedback to mine planning and scheduling to improve blasting and in turn provide a more uniform bulk density across the excavation site. Furthermore costs and emissions in dragline operation, maintenance and downstream material processing can be reduced. The main challenge is to determine an accurate position and orientation of the bucket with the constraint of real-time performance. The proposed solution uses a range bearing and tilt sensor to locate and scan the bucket between the lift and dump stages of the dragline cycle. Various scanning strategies are investigated for their benefits in this real-time application. The bucket is segmented from the scene using cluster analysis while the pose of the bucket is calculated using the iterative closest point (ICP) algorithm. Payload points are segmented from the bucket by a fixed distance neighbour clustering method to preserve boundary points and exclude low density clusters introduced by overhead chains and the spreader bar. A height grid is then used to represent the payload from which the volume can be calculated by summing over the grid cells. We show volume calculated on a scaled system with an accuracy of greater than 95 per cent.