Learning and Exploiting Camera Geometry for Computer Vision

This work explores the use of statistical methods in describing and estimating camera poses, as well as the information feedback loop between camera pose and object detection. Surging development in robotics and computer vision has pushed the need for algorithms that infer, understand, and utilize information about the position and orientation of the sensor platforms when observing and/or interacting with their environment.

The first contribution of this thesis is the development of a set of statistical tools for representing and estimating the uncertainty in object poses. A distribution for representing the joint uncertainty over multiple object positions and orientations is described, called the mirrored normal-Bingham distribution. This distribution generalizes both the normal distribution in Euclidean space, and the Bingham distribution on the unit hypersphere. It is shown to inherit many of the convenient properties of these special cases: it is the maximum-entropy distribution with fixed second moment, and there is a generalized Laplace approximation whose result is the mirrored normal-Bingham distribution. This distribution and approximation method are demonstrated by deriving the analytical approximation to the wrapped-normal distribution. Further, it is shown how these tools can be used to represent the uncertainty in the result of a bundle adjustment problem.

Another application of these methods is illustrated as part of a novel camera pose estimation algorithm based on object detections. The autocalibration task is formulated as a bundle adjustment problem using prior distributions over the 3D points to enforce the objects' structure and their relationship with the scene geometry. This framework is very flexible and enables the use of off-the-shelf computational tools to solve specialized autocalibration problems. Its performance is evaluated using a pedestrian detector to provide head and foot location observations, and it proves much faster and potentially more accurate than existing methods.

Finally, the information feedback loop between object detection and camera pose estimation is closed by utilizing camera pose information to improve object detection in scenarios with significant perspective warping. Methods are presented that allow the inverse perspective mapping traditionally applied to images to be applied instead to features computed from those images. For the special case of HOG-like features, which are used by many modern object detection systems, these methods are shown to provide substantial performance benefits over unadapted detectors while achieving real-time frame rates, orders of magnitude faster than comparable image warping methods.

The statistical tools and algorithms presented here are especially promising for mobile cameras, providing the ability to autocalibrate and adapt to the camera pose in real time. In addition, these methods have wide-ranging potential applications in diverse areas of computer vision, robotics, and imaging.

Improving the Accuracy of 3-D Reconstruction in Robotic Vision Applications

Thesis (Ph.D.)--University of Washington, 2016-08

On precise three-dimensional environment modeling via UAV-based photogrammetric systems

Abstract : Images acquired from unmanned aerial vehicles (UAVs) can provide data with unprecedented spatial and temporal resolution for three-dimensional (3D) modeling. Solutions developed for this purpose are mainly operating based on photogrammetry concepts, namely UAV-Photogrammetry Systems (UAV-PS). Such systems are used in applications where both geospatial and visual information of the environment is required. These applications include, but are not limited to, natural resource management such as precision agriculture, military and police-related services such as traffic-law enforcement, precision engineering such as infrastructure inspection, and health services such as epidemic emergency management. UAV-photogrammetry systems can be differentiated based on their spatial characteristics in terms of accuracy and resolution. That is some applications, such as precision engineering, require high-resolution and high-accuracy information of the environment (e.g. 3D modeling with less than one centimeter accuracy and resolution). In other applications, lower levels of accuracy might be sufficient, (e.g. wildlife management needing few decimeters of resolution). However, even in those applications, the specific characteristics of UAV-PSs should be well considered in the steps of both system development and application in order to yield satisfying results. In this regard, this thesis presents a comprehensive review of the applications of unmanned aerial imagery, where the objective was to determine the challenges that remote-sensing applications of UAV systems currently face. This review also allowed recognizing the specific characteristics and requirements of UAV-PSs, which are mostly ignored or not thoroughly assessed in recent studies. Accordingly, the focus of the first part of this thesis is on exploring the methodological and experimental aspects of implementing a UAV-PS. The developed system was extensively evaluated for precise modeling of an open-pit gravel mine and performing volumetric-change measurements. This application was selected for two main reasons. Firstly, this case study provided a challenging environment for 3D modeling, in terms of scale changes, terrain relief variations as well as structure and texture diversities. Secondly, open-pit-mine monitoring demands high levels of accuracy, which justifies our efforts to improve the developed UAV-PS to its maximum capacities. The hardware of the system consisted of an electric-powered helicopter, a high-resolution digital camera, and an inertial navigation system. The software of the system included the in-house programs specifically designed for camera calibration, platform calibration, system integration, onboard data acquisition, flight planning and ground control point (GCP) detection. The detailed features of the system are discussed in the thesis, and solutions are proposed in order to enhance the system and its photogrammetric outputs. The accuracy of the results was evaluated under various mapping conditions, including direct georeferencing and indirect georeferencing with different numbers, distributions and types of ground control points. Additionally, the effects of imaging configuration and network stability on modeling accuracy were assessed. The second part of this thesis concentrates on improving the techniques of sparse and dense reconstruction. The proposed solutions are alternatives to traditional aerial photogrammetry techniques, properly adapted to specific characteristics of unmanned, low-altitude imagery. Firstly, a method was developed for robust sparse matching and epipolar-geometry estimation. The main achievement of this method was its capacity to handle a very high percentage of outliers (errors among corresponding points) with remarkable computational efficiency (compared to the state-of-the-art techniques). Secondly, a block bundle adjustment (BBA) strategy was proposed based on the integration of intrinsic camera calibration parameters as pseudo-observations to Gauss-Helmert model. The principal advantage of this strategy was controlling the adverse effect of unstable imaging networks and noisy image observations on the accuracy of self-calibration. The sparse implementation of this strategy was also performed, which allowed its application to data sets containing a lot of tie points. Finally, the concepts of intrinsic curves were revisited for dense stereo matching. The proposed technique could achieve a high level of accuracy and efficiency by searching only through a small fraction of the whole disparity search space as well as internally handling occlusions and matching ambiguities. These photogrammetric solutions were extensively tested using synthetic data, close-range images and the images acquired from the gravel-pit mine. Achieving absolute 3D mapping accuracy of 11±7 mm illustrated the success of this system for high-precision modeling of the environment.

Structural Connectivity Of The Default Mode Network And Cognition In Alzheimer׳s Disease.

Disconnectivity between the Default Mode Network (DMN) nodes can cause clinical symptoms and cognitive deficits in Alzheimer׳s disease (AD). We aimed to examine the structural connectivity between DMN nodes, to verify the extent in which white matter disconnection affects cognitive performance. MRI data of 76 subjects (25 mild AD, 21 amnestic Mild Cognitive Impairment subjects and 30 controls) were acquired on a 3.0T scanner. ExploreDTI software (fractional Anisotropy threshold=0.25 and the angular threshold=60°) calculated axial, radial, and mean diffusivities, fractional anisotropy and streamline count. AD patients showed lower fractional anisotropy (P=0.01) and streamline count (P=0.029), and higher radial diffusivity (P=0.014) than controls in the cingulum. After correction for white matter atrophy, only fractional anisotropy and radial diffusivity remained significantly lower in AD compared to controls (P=0.003 and P=0.05). In the parahippocampal bundle, AD patients had lower mean and radial diffusivities (P=0.048 and P=0.013) compared to controls, from which only radial diffusivity survived for white matter adjustment (P=0.05). Regression models revealed that cognitive performance is also accounted for by white matter microstructural values. Structural connectivity within the DMN is important to the execution of high-complexity tasks, probably due to its relevant role in the integration of the network.

Wives of pathological gamblers: personality traits, depressive symptoms and social adjustment

Objective: Wives of pathological gamblers tend to endure long marriages despite financial and emotional burden. Difficulties in social adjustment, personality psychopathology, and comorbidity with psychiatric disorders are pointed as reasons for remaining on such overwhelming relationships. The goal was to examine the social adjustment, personality and negative emotionality of wives of pathological gamblers. Method: The sample consisted of 25 wives of pathological gamblers, mean age 40.6, SD = 9.1 from a Gambling Outpatient Unit and at GAM-ANON, and 25 wives of non-gamblers, mean age 40.8, SD = 9.1, who answered advertisements placed at the Universidade de São Paulo hospital and medical school complex. They were selected in order to approximately match demographic characteristics of the wives of pathological gamblers. Subjects were assessed by the Social Adjustment Scale, Temperament and Character Inventory, Beck Depression Inventory and State-Trait Anxiety Inventory. Results: Three variables remained in the final Multiple Logistic Regression model, wives of pathological gamblers presented greater dissatisfaction with their marital bond, and higher scores on Reward Dependence and Persistence temperament factors. Both, Wives of pathological gamblers and wives of non-gamblers presented well-structured character factors excluding personality disorders. Conclusion: This personality profile may explain wives of pathological gamblers emotional resilience and their marriage longevity. Co-dependence and other labels previously used to describe them may work as a double edged sword, legitimating wives of pathological gamblers problems, while stigmatizing them as inapt and needy.

Computational adjustment technique for digital mammographic images based on the digitizer characteristic curve

We evaluated the performance of a novel procedure for segmenting mammograms and detecting clustered microcalcifications in two types of image sets obtained from digitization of mammograms using either a laser scanner, or a conventional ""optical"" scanner. Specific regions forming the digital mammograms were identified and selected, in which clustered microcalcifications appeared or not. A remarkable increase in image intensity was noticed in the images from the optical scanner compared with the original mammograms. A procedure based on a polynomial correction was developed to compensate the changes in the characteristic curves from the scanners, relative to the curves from the films. The processing scheme was applied to both sets, before and after the polynomial correction. The results indicated clearly the influence of the mammogram digitization on the performance of processing schemes intended to detect microcalcifications. The image processing techniques applied to mammograms digitized by both scanners, without the polynomial intensity correction, resulted in a better sensibility in detecting microcalcifications in the images from the laser scanner. However, when the polynomial correction was applied to the images from the optical scanner, no differences in performance were observed for both types of images. (C) 2008 SPIE and IS&T [DOI: 10.1117/1.3013544]

Adjustment of Mineral Elements in the Culture Medium for the Micropropagation of Three Vriesea Bromeliads from the Brazilian Atlantic Forest: The Importance of Calcium

Many different species of Bromeliaceae are endangered and their conservation requires specific knowledge of their growth habits and propagation. In vitro culture of bromeliads is an important method for efficient clonal propagation and ill vitro seed g,germination can be used to maintain genetic variability. The present work aims to evaluate the in vitro growth and nutrient concentration in leaves of the epiphyte bromeliads Vriesea friburguensis Mez, Vriesea hieroglyphica (Carriere) E. Morren, and Vriesea unilateralis Mez, which exhibit slow rates of growth in vivo and in vitro. Initially, we compared the endogenous mineral composition of bromeliad plantlets grown in half-strength Murashige and Skoog (MS) medium and the mineral composition considered adequate in the literature. This approach suggested that calcium (Ca) is a critical nutrient and this was considered for new media formulation. Three new culture media were defined in which the main changes to half-strength MS medium were an increase in Ca, magnesium, sulfur, copper, and chloride and a decrease in iron, maintaining the nitrate: ammonium rate at approximate to 2:1. The main difference among the three new media formulated was Ca concentration, which varied from 1.5 mm in half-strength MS to 3.0, 6.0, and 12 mm in M2, M3, and M4 media, respectively. Consistently, all three species exhibited significantly higher fresh and dry weight on M4, the newly defined medium with the highest level of Ca (12 mm). Leaf nitrogen, potassium, zinc, magnesium and boron concentrations increased as Ca concentration in the medium increased from 1.5 to 12 mm.

Employee adjustment to large-scale organisational change

The present study was designed to test the utility of a stress-coping model of employee adjustment to organisational change. Specifically, it was proposed that employee adjustment to this type of work stress would be influenced by the characteristics of the change situation, employees' appraisals of the situation, their coping strategies, and the extent of their personal resources. Data were collected from 140 middle managers and supervisors involved in a large-scale public sector integration. The results of the research provided some support for the proposed model: high levels of psychological distress were related to a reliance on informal sources of information, high appraised stress, low appraised certainty, and the use of avoidant rather than problem-focused strategies, whereas poor social functioning was associated with low self-esteem, high levels or disruption across the period of change, a reliance on informal sources of information, and the use of avoidant coping strategies. There was no evidence that coping strategies mediated the effects of the event characteristics, situational appraisals, and personal resources on adjustment; however, there was some evidence linking these variables to coping strategies, in particular, problem-focused coping. There was also some evidence to indicate that the experience of organisational change was different for managers and supervisors: levels of threat were higher for the managers than the supervisors, but there was no difference between the groups of employees in terms of adjustment.

Adjustment to a low-control situation: Reexamining the role of coping responses

The aim of the study was to test a revised conceptualization of the role of coping in adjustment to a low-control stressor-women's adjustment to a failed in vitro fertilization (NF) attempt. Data were collected prior to the IVF treatment (Time I) and twice after the failed NF attempt (1 to 2 weeks after finding out the results, n = 171, and fi weeks later, n = 139). Initial adjustment was assessed at Time I, whereas measures of coping and both self-report and partner ratings of adjustment were obtained at Times ? and 3. As predicted, escapist strategies and problem-management strategies (mainly at Time ?) were associated with poor adjustment, whereas problem-appraisal coping was associated with better adjustment., There was also support for the proposed positive relationship between adjustment and emotional approach coping (on self-report adjustment).

An experimental study of the effects of work stress, work control, and task information on adjustment

The present study was designed to examine the main and interactive effects of task demands, work control, and task information on levels of adjustment. Task demands, work control, and task information were manipulated in an experimental setting where participants completed a letter-sorting activity (N = 128). Indicators of adjustment included measures of positive mood, participants' perceptions of task performance, and task satisfaction. Results of the present study provided some support for the main effects of objective task demands, work control, and task information on levels of adjustment. At the subjective level of analysis, there was some evidence to suggest that work control and task information interacted in their effects on levels of adjustment. There was minimal support for the proposal that work control and task information would buffer the negative effects of task demands on adjustment. There was, however, some evidence to suggest that the stress-buffering role of subjective work control was more marked at high, rather than low, levels of subjective task information.

The effects of work control and job demands on employee adjustment and work performance

The present study examined the effects of work control and job demands on employee adjustment and work performance using a multidimensional measure of work control (assessing levels of task control, decision control and work scheduling control). It was proposed that the negative effects of job demands and employee adjustment would be moderated by high levels of task control. It was also proposed that there would be evidence of main effects of both job demands and work control (particularly task-related levels of control) on employee adjustment. To test these predictions, a study of 135 university employees holding administrative positions was undertaken. Methodological improvements over previous research included the use of both self-reported adjustment measures and supervisor ratings of work performance as outcome variables, and the assessment of the predictor and outcome measures at different points in time (self-reported adjustment was assessed at both Times 1 and 2). The results revealed some support for the proposal that the effects of job demands would be buffered by high levels of task control, but not more peripheral aspects of work control. There were also significant main effects of task control on job satisfaction.

Modelling the Distribution of Ischaemic Stroke-Specific Survival Time Using an EM-based Mixture Approach with Random Effects Adjustment

A two-component survival mixture model is proposed to analyse a set of ischaemic stroke-specific mortality data. The survival experience of stroke patients after index stroke may be described by a subpopulation of patients in the acute condition and another subpopulation of patients in the chronic phase. To adjust for the inherent correlation of observations due to random hospital effects, a mixture model of two survival functions with random effects is formulated. Assuming a Weibull hazard in both components, an EM algorithm is developed for the estimation of fixed effect parameters and variance components. A simulation study is conducted to assess the performance of the two-component survival mixture model estimators. Simulation results confirm the applicability of the proposed model in a small sample setting. Copyright (C) 2004 John Wiley Sons, Ltd.

Differential adjustment in gill Na(+)/K(+)- and V-ATPase activities and transporter mRNA expression during osmoregulatory acclimation in the cinnamon shrimp Macrobrachium amazonicum (Decapoda, Palaemonidae)

We evaluate osmotic and chloride (Cl(-)) regulatory capability in the diadromous shrimp Macrobrachium amazonicum, and the accompanying alterations in hemolymph osmolality and [Cl(-)], gill Na(+)/K(+)-ATPase activity, and expression of gill Na(+)/K(+)-ATPase alpha-subunit and V-ATPase B subunit mRNA during salinity (S) acclimation. We also characterize V-ATPase kinetics and the organization of transport-related membrane systems in the gill epithelium. Macrobrachium amazonicum strongly hyper-regulates hemolymph osmolality and [Cl(-)] in freshwater and in salinities up to 25 parts per thousand S. During a 10-day acclimation period to 25 parts per thousand S, hemolymph became isosmotic and hypo-chloremic after 5 days, [Cl(-)] alone remaining hyporegulated thereafter. Gill Na(+)/K(+)-ATPase alpha-subunit mRNA expression increased 6.5 times initial values after 1 h, then decreased to 3 to 4 times initial values by 24 h and to 1.5 times initial values after 10 days at 25 parts per thousand S. This increased expression was accompanied by a sharp decrease at 5 h then recovery of initial Na(+)/K(+)-ATPase activity within 24 h, declining again after 5 days, which suggests transient Cl(-) secretion. V-ATPase B-subunit mRNA expression increased 1.5-fold within 1 h, then reduced sharply to 0.3 times initial values by 5 h, and remained unchanged for the remainder of the 10-day period. V-ATPase activity dropped sharply and was negligible after a 10-day acclimation period to 21 parts per thousand S, revealing a marked downregulation of ion uptake mechanisms. The gill epithelium consists of thick, apical pillar cell flanges, the perikarya of which are coupled to an intralamellar septum. These two cell types respectively exhibit extensive apical evaginations and deep membrane invaginations, both of which are associated with numerous mitochondria, characterizing an ion transporting epithelium. These changes in Na(+)/K(+)- and V-ATPase activities and in mRNA expression during salinity acclimation appear to underpin ion uptake and Cl(-) secretion by the palaemonid shrimp gill.

Electrophysiological characteristics of the Marshall bundle in humans

BACKGROUND Marshall bundles (MBs) are the muscle bundles within the ligament of Marshall. OBJECTIVE This trial sought to the electrophysiological characteristics of the MB and the anatomical connections between MB and left atrium (LA) in patients with persistent atrial fibrillation (AF). METHODS We enrolled 72 patients (male: female 59: 13, age 59.9 +/- 9.4 years) who underwent MB mapping and ablation for AF. MB mapping was done via an endocardial or epicardial approach during sinus rhythm and AF. RESULTS Recordings were successful in 64 of 72 patients (89%). A single connection was noted in 11 of 64 patients between the MB and the coronary sinus (CS) muscle sleeves. The MB recordings showed distinct MB potentials with a proximal-to-distal activation pattern during sinus rhythm. During AF, organized passive activations and dissociated slow MB ectopic activities were commonly observed in this type of connection. Double connections to both CS and LA around left pulmonary veins were noted in 23 of 64 patients (36%). After the ablation of the distal connection, MB recording showed typical double potentials as in single connection. Multiple connections were noted in 30 of 64 patients (47%). During sinus rhythm, the earliest activation was in the middle of the MB. The activation patterns were irregular and variable in each patient. During AF, rapid and fractionated complex activations were noted in all patients of this group. CONCLUSION We documented 3 different types of MB-LA connections. Rapid and fractionated activations were most commonly observed in the MB that had multiple LA connections.