Joint 2D and 3D cues for image segmentation towards robotic applications

This thesis investigates the fusion of 3D visual information with 2D image cues to provide 3D semantic maps of large-scale environments in which a robot traverses for robotic applications. A major theme of this thesis was to exploit the availability of 3D information acquired from robot sensors to improve upon 2D object classification alone. The proposed methods have been evaluated on several indoor and outdoor datasets collected from mobile robotic platforms including a quadcopter and ground vehicle covering several kilometres of urban roads.

Nutrition and physical activity policies and practices in family child care homes

Background Family child care homes (FCCHs) are the second-largest provider of nonrelative care in the U.S. However, despite providing care for nearly 1.9 million children aged <5 years, little is known about the nutrition and physical activity practices of FCCHs. Purpose To address this gap, this study aims to describe policies and practices related to nutrition and physical activity in a representative sample of FCCHs. Methods A stratified random sample of registered FCCHs operating in Kansas (N=297) completed the Nutrition and Physical Activity Self Assessment for Child Care (NAPSACC) instrument. Prevalence estimates and 95% CIs for meeting or exceeding accepted child care standards were calculated using SAS PROC SURVEYFREQ. Results Most providers either met or exceeded child care standards related to serving fruit and vegetables and provision of daily physical activity. Very few providers reported serving fried meats or vegetables or unhealthy snack foods on a regular basis. Areas of concern included infrequent servings of low-fat milk, frequent use of unhealthy foods for celebrations, widespread use of TV and video games throughout the day, restricting physical activity for children who misbehave, and lack of appropriate indoor spaces for physical activity. Only a small percentage of providers reported receiving regular training in nutrition or physical activity. Relatively few providers had written guidelines on nutrition or physical activity. Conclusions Some strengths were exhibited by FCCHs, but substantial weaknesses were shown with respect to meeting established child care standards for nutrition and physical activity. Interventions to promote healthy eating and regular physical activity in FCCHs are thus warranted.

Bluetooth and Wi-Fi MAC address based crowd data collection and monitoring : benefits, challenges and enhancement

This paper firstly presents the benefits and critical challenges on the use of Bluetooth and Wi-Fi for crowd data collection and monitoring. The major challenges include antenna characteristics, environment’s complexity and scanning features. Wi-Fi and Bluetooth are compared in this paper in terms of architecture, discovery time, popularity of use and signal strength. Type of antennas used and the environment’s complexity such as trees for outdoor and partitions for indoor spaces highly affect the scanning range. The aforementioned challenges are empirically evaluated by “real” experiments using Bluetooth and Wi-Fi Scanners. The issues related to the antenna characteristics are also highlighted by experimenting with different antenna types. Novel scanning approaches including Overlapped Zones and Single Point Multi-Range detection methods will be then presented and verified by real-world tests. These novel techniques will be applied for location identification of the MAC IDs captured that can extract more information about people movement dynamics.

Predictive validity of three ActiGraph energy expenditure equations for children

Purpose This Study evaluated the predictive validity of three previously published ActiGraph energy expenditure (EE) prediction equations developed for children and adolescents. Methods A total of 45 healthy children and adolescents (mean age: 13.7 +/- 2.6 yr) completed four 5-min activity trials (normal walking. brisk walking, easy running, and fast running) in ail indoor exercise facility. During each trial, participants were all ActiGraph accelerometer oil the right hip. EE was monitored breath by breath using the Cosmed K4b(2) portable indirect calorimetry system. Differences and associations between measured and predicted EE were assessed using dependent t-tests and Pearson correlations, respectively. Classification accuracy was assessed using percent agreement, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve. Results None of the equations accurately predicted mean energy expenditure during each of the four activity trials. Each equation, however, accurately predicted mean EE in at least one activity trial. The Puyau equation accurately predicted EE during slow walking. The Trost equation accurately predicted EE during slow running. The Freedson equation accurately predicted EE during fast running. None of the three equations accurately predicted EE during brisk walking. The equations exhibited fair to excellent classification accuracy with respect to activity intensity. with the Trost equation exhibiting the highest classification accuracy and the Puyau equation exhibiting the lowest. Conclusions These data suggest that the three accelerometer prediction equations do not accurately predict EE on a minute-by-minute basis in children and adolescents during overground walking and running. The equations maybe, however, for estimating participation in moderate and vigorous activity.

Considering research enquiry into biophilic urbanism and office worker productivity

In cities, people spend a significant portion of their time indoors, much of which is in office buildings. The quality and nature of these spaces have the potential to be a strong determinant of people’s health and wellbeing. There is a body of evidence that suggests experiences of nature increase the rate of attention recovery, reduce stress, depression and anxiety, and increase cognitive abilities. Further, the presence of nature inside buildings (such as pot plants and internal green walls) can improve indoor air quality, potentially reducing illness and increasing cognitive function. Urban design that integrates nature into the built environment to provide these benefits, among others, is called ‘biophilic urbanism’ and is the subject of growing international interest and research. The potential for these benefits to increase worker productivity in office buildings is of particular interest, as this could significantly increase the financial performance of office building-based organisations. However, productivity is a complex concept that is difficult to define, and affected by a multitude of factors, which make it difficult to measure. This inability to quantify productivity increases from investments in nature- experiences in office buildings is currently a significant barrier to such investments. Within this context, this paper considers opportunities for research to explore the relationship between office-based nature experiences and productivity, by reviewing existing research in this field and reflecting on the authors’ own experiences. This review has a particular focus on the importance of quantifying this link in order to encourage private property owners to voluntarily integrate nature into buildings to provide city-wide ecosystem service benefits. The paper begins with a contextual overview of how biophilic urbanism can potentially increase worker productivity. Existing methods of measuring and evaluating the performance of biophilic urbanism within the context of office buildings are then explored, along with a discussion of issues with such methods that are currently limiting investment in biophilic urbanism to increase worker productivity and wellbeing. This includes a summary of a survey within a Perth office building to explore the impact of views of nature through a window. Drawing on these insights, the paper makes recommendations regarding opportunities for focusing future investigations to enhance understanding of how biophilic urbanism can contribute to increased wellbeing and productivity in office buildings. This paper builds on work conducted as part of the Sustainable Built Environment National Research Centre Project 1.5, Harnessing the Potential of Biophilic Urbanism in Australia, which considered the role of nature integrated into the built environment in responding to emerging challenges of climate change, resource shortages and population pressures, while providing a host of co- benefits to a range of stakeholders.

Considering research enquiry into biophilic urbanism and office worker productivity

In cities, people spend a significant portion of their time indoors, much of which is in office buildings. The quality and nature of these spaces have the potential to be a strong determinant of people’s health and wellbeing. There is a body of evidence that suggests experiences of nature increase the rate of attention recovery, reduce stress, depression and anxiety, and increase cognitive abilities. Further, the presence of nature inside buildings (such as pot plants and internal green walls) can improve indoor air quality, potentially reducing illness and increasing cognitive function. Urban design that integrates nature into the built environment to provide these benefits, among others, is called ‘biophilic urbanism’ and is the subject of growing international interest and research. The potential for these benefits to increase worker productivity in office buildings is of particular interest, as this could significantly increase the financial performance of office building-based organisations. However, productivity is a complex concept that is difficult to define, and affected by a multitude of factors, which make it difficult to measure. This inability to quantify productivity increases from investments in nature- experiences in office buildings is currently a significant barrier to such investments. Within this context, this paper considers opportunities for research to explore the relationship between office-based nature experiences and productivity, by reviewing existing research in this field and reflecting on the authors’ own experiences. This review has a particular focus on the importance of quantifying this link in order to encourage private property owners to voluntarily integrate nature into buildings to provide city-wide ecosystem service benefits. The paper begins with a contextual overview of how biophilic urbanism can potentially increase worker productivity. Existing methods of measuring and evaluating the performance of biophilic urbanism within the context of office buildings are then explored, along with a discussion of issues with such methods that are currently limiting investment in biophilic urbanism to increase worker productivity and wellbeing. This includes a summary of a survey within a Perth office building to explore the impact of views of nature through a window. Drawing on these insights, the paper makes recommendations regarding opportunities for focusing future investigations to enhance understanding of how biophilic urbanism can contribute to increased wellbeing and productivity in office buildings. This paper builds on work conducted as part of the Sustainable Built Environment National Research Centre Project 1.5, Harnessing the Potential of Biophilic Urbanism in Australia, which considered the role of nature integrated into the built environment in responding to emerging challenges of climate change, resource shortages and population pressures, while providing a host of co- benefits to a range of stakeholders.

Factors associated with physical activity in children attending family child care homes

Objective To determine the relationship between family child care home (FCCH) practices and characteristics, and objectively measured physical activity (PA) among children attending FCCHs. Methods FCCH practices and characteristics were assessed in 45 FCCHs in Oregon (USA) in 2010-2011 using the Nutrition and Physical Activity Self-Assessment for Child Care Instrument. Within the 45 FCCHs, 136 children between ages 2 and 5. years wore an accelerometer during child care attendance over a one-week period. Time spent in light, moderate, and vigorous PA per hour was calculated using intensity-related cut-points (Pate et al., 2006). Results FCCH characteristics and practices associated with higher levels of PA (min/h; p < 0.05) included provision of sufficient outdoor active play [32.2 (1.0) vs. 28.6 (1.3)], active play using portable play equipment [31.7 (1.0) vs. 29.3 (1.4)], the presence of a variety of fixed play equipment [32.2 (1.0) vs. 28.9 (1.3)], and suitable indoor play space [32.2 (1.0) vs. 28.6 (1.3)], engaging in active play with children [32.1 (1.1) vs. 29.6 (1.2)], and receiving activity-related training [33.1 (1.2) vs. 30.3 (1.1)]. Conclusions This is the first study to identify practices and characteristics of FCCHs that influence children's PA. These data should be considered when developing programs and policies to promote PA in FCCHs.

An investigation of Staphylococcus aureus and related species from flood affected and other environmental sources

This research investigated the microbial air quality of flooded houses in Brisbane suburbs following the January 2011 flood event. Flood waters can carry and spread human pathogenic bacteria, and these organisms can be dispersed into residential air by aerosolisation. This study found that the bacterial load was significantly different for indoor and outdoor areas of flood affected houses, but no significant differences were observed between flooded and non-flooded houses. This could be due to the rapid clean-up of flooded houses following the event. Molecular methods were used to identify and characterise staphylococcal species in residential air of flooded and non-flooded houses. A major finding was the diverse population of airborne staphylococci as well as the high rate of methicillin-resistance in these strains. By determining the genetic relatedness of residential air sourced staphylococci, a potential source for pathogenic strains can be identified.

The impact of flood and post-flood cleaning on airborne microbiological and particle contamination in residential houses

In January 2011, Brisbane, Australia, experienced a major river flooding event. We aimed to investigate its effects on air quality and assess the role of prompt cleaning activities in reducing the airborne exposure risk. A comprehensive, multi-parameter indoor and outdoor measurement campaign was conducted in 41 residential houses, 2 and 6 months after the flood. The median indoor air concentrations of supermicrometer particle number (PN), PM10, fungi and bacteria 2 months after the flood were comparable to those previously measured in Brisbane. These were 2.88 p cm-3, 15 µg m-3, 804 cfu m-3 and 177 cfu m-3 for flood-affected houses (AFH), and 2.74 p cm-3, 15 µg m-3, 547 cfu m-3 and 167 cfu m-3 for non-affected houses (NFH), respectively. The I/O (indoor/outdoor) ratios of these pollutants were 1.08, 1.38, 0.74 and 1.76 for AFH and 1.03, 1.32, 0.83 and 2.17 for NFH, respectively. The average of total elements (together with transition metals) in indoor dust was 2296 ± 1328 µg m-2 for AFH and 1454 ± 678 µg m-2 for NFH, respectively. In general, the differences between AFH and NFH were not statistically significant, implying the absence of a measureable effect on air quality from the flood. We postulate that this was due to the very swift and effective cleaning of the flooded houses by 60,000 volunteers. Among the various cleaning methods, the use of both detergent and bleach was the most efficient at controlling indoor bacteria. All cleaning methods were equally effective for indoor fungi. This study provides quantitative evidence of the significant impact of immediate post-flood cleaning on mitigating the effects of flooding on indoor bioaerosol contamination and other pollutants.

Characteristics of ultrafine particle sources and deposition rates in primary school classrooms

The aim of this work was to investigate changes in particle number concentration (PNC) within naturally ventilated primary school classrooms arising from local sources either within or adjacent to the classrooms. We quantify the rate at which ultrafine particles were emitted either from printing, grilling, heating or cleaning activities and the rate at which the particles were removed by both deposition and air exchange processes. At each of 25 schools in Brisbane, Australia, two weeks of measurements of PNC and CO2 were taken both outdoors and in the two classrooms. Bayesian regression modelling was employed in order to estimate the relevant rates and analyse the relationship between air exchange rate (AER), particle infiltration and the deposition rates of particle generated from indoor activities in the classrooms. During schooling hours, grilling events at the school tuckshop as well as heating and printing in the classrooms led to indoor PNCs being elevated by a factor of more than four, with emission rates of (2.51 ± 0.25) x 1011 p min-1, (8.99 ± 6.70) x 1011 p min-1 and (5.17 ± 2.00) x 1011 p min-1, respectively. During non-school hours, cleaning events elevated indoor PNC by a factor of above five, with an average emission rate of (2.09 ± 6.30) x 1011 p min-1. Particles were removed by both air exchange and deposition; chiefly by ventilation when AER > 0.7 h-1 and by deposition when AER < 0.7 h-1.

The impact of fuser roller temperature on laser printer particle emission

The emission of particles in the ultrafine range (<100 nm) from laser printers has not been reported until recently (Uhde et al., 2006; He et al., 2007; Morawska et al., 2009). The research reported to date has provided a body of information about printer emissions and shed light on particle formation mechanisms. However, until now, the effect of fuser roller temperature on particle emissions had not been comprehensively investigated...

A hierarchical model of goal directed navigation selects trajectories in a visual environment

We have developed a Hierarchical Look-Ahead Trajectory Model (HiLAM) that incorporates the firing pattern of medial entorhinal grid cells in a planning circuit that includes interactions with hippocampus and prefrontal cortex. We show the model’s flexibility in representing large real world environments using odometry information obtained from challenging video sequences. We acquire the visual data from a camera mounted on a small tele-operated vehicle. The camera has a panoramic field of view with its focal point approximately 5 cm above the ground level, similar to what would be expected from a rat’s point of view. Using established algorithms for calculating perceptual speed from the apparent rate of visual change over time, we generate raw dead reckoning information which loses spatial fidelity over time due to error accumulation. We rectify the loss of fidelity by exploiting the loop-closure detection ability of a biologically inspired, robot navigation model termed RatSLAM. The rectified motion information serves as a velocity input to the HiLAM to encode the environment in the form of grid cell and place cell maps. Finally, we show goal directed path planning results of HiLAM in two different environments, an indoor square maze used in rodent experiments and an outdoor arena more than two orders of magnitude larger than the indoor maze. Together these results bridge for the first time the gap between higher fidelity bio-inspired navigation models (HiLAM) and more abstracted but highly functional bio-inspired robotic mapping systems (RatSLAM), and move from simulated environments into real-world studies in rodent-sized arenas and beyond.

Topological localization using optical flow descriptors

We propose a topological localization method based on optical flow information. We analyse the statistical characteristics of the optical flow signal and demonstrate that the flow vectors can be used to identify and describe key locations in the environment. The key locations (nodes) correspond to significant scene changes and depth discontinuities. Since optical flow vectors contain position, magnitude and angle information, for each node, we extract low and high order statistical moments of the vectors and use them as descriptors for that node. Once a database of nodes and their corresponding optical flow features is created, the robot can perform topological localization by using the Mahalanobis distance between the current frame and the database. This is supported by field trials, which illustrate the repeatability of the proposed method for detecting and describing key locations in indoor and outdoor environments in challenging and diverse lighting conditions.

A Study of feature extraction algorithms for optical flow tracking

Sparse optical flow algorithms, such as the Lucas-Kanade approach, provide more robustness to noise than dense optical flow algorithms and are the preferred approach in many scenarios. Sparse optical flow algorithms estimate the displacement for a selected number of pixels in the image. These pixels can be chosen randomly. However, pixels in regions with more variance between the neighbours will produce more reliable displacement estimates. The selected pixel locations should therefore be chosen wisely. In this study, the suitability of Harris corners, Shi-Tomasi's “Good features to track", SIFT and SURF interest point extractors, Canny edges, and random pixel selection for the purpose of frame-by-frame tracking using a pyramidical Lucas-Kanade algorithm is investigated. The evaluation considers the important factors of processing time, feature count, and feature trackability in indoor and outdoor scenarios using ground vehicles and unmanned aerial vehicles, and for the purpose of visual odometry estimation.