Towards persistent localization and mapping with a continuous appearance-based topology

Appearance-based localization can provide loop closure detection at vast scales regardless of accumulated metric error. However, the computation time and memory requirements of current appearance-based methods scale not only with the size of the environment but also with the operation time of the platform. Additionally, repeated visits to locations will develop multiple competing representations, which will reduce recall performance over time. These properties impose severe restrictions on long-term autonomy for mobile robots, as loop closure performance will inevitably degrade with increased operation time. In this paper we present a graphical extension to CAT-SLAM, a particle filter-based algorithm for appearance-based localization and mapping, to provide constant computation and memory requirements over time and minimal degradation of recall performance during repeated visits to locations. We demonstrate loop closure detection in a large urban environment with capped computation time and memory requirements and performance exceeding previous appearance-based methods by a factor of 2. We discuss the limitations of the algorithm with respect to environment size, appearance change over time and applications in topological planning and navigation for long-term robot operation.

Relative entropy rate based model selection for linear hybrid system filters of uncertain nonlinear systems

Hybrid system representations have been exploited in a number of challenging modelling situations, including situations where the original nonlinear dynamics are too complex (or too imprecisely known) to be directly filtered. Unfortunately, the question of how to best design suitable hybrid system models has not yet been fully addressed, particularly in the situations involving model uncertainty. This paper proposes a novel joint state-measurement relative entropy rate based approach for design of hybrid system filters in the presence of (parameterised) model uncertainty. We also present a design approach suitable for suboptimal hybrid system filters. The benefits of our proposed approaches are illustrated through design examples and simulation studies.

SeqSLAM : visual route-based navigation for sunny summer days and stormy winter nights

Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.

Integrated vision-based attitude estimation

For many years, computer vision has lured researchers with promises of a low-cost, passive, lightweight and information-rich sensor suitable for navigation purposes. The prime difficulty in vision-based navigation is that the navigation solution will continually drift with time unless external information is available, whether it be cues from the appearance of the scene, a map of features (whether built online or known a priori), or from an externally-referenced sensor. It is not merely position that is of interest in the navigation problem. Attitude (i.e. the angular orientation of a body with respect to a reference frame) is integral to a visionbased navigation solution and is often of interest in its own right (e.g. flight control). This thesis examines vision-based attitude estimation in an aerospace environment, and two methods are proposed for constraining drift in the attitude solution; one through a novel integration of optical flow and the detection of the sky horizon, and the other through a loosely-coupled integration of Visual Odometry and GPS position measurements. In the first method, roll angle, pitch angle and the three aircraft body rates are recovered though a novel method of tracking the horizon over time and integrating the horizonderived attitude information with optical flow. An image processing front-end is used to select several candidate lines in a image that may or may not correspond to the true horizon, and the optical flow is calculated for each candidate line. Using an Extended Kalman Filter (EKF), the previously estimated aircraft state is propagated using a motion model and a candidate horizon line is associated using a statistical test based on the optical flow measurements and location of the horizon in the image. Once associated, the selected horizon line, along with the associated optical flow, is used as a measurement to the EKF. To evaluate the accuracy of the algorithm, two flights were conducted, one using a highly dynamic Uninhabited Airborne Vehicle (UAV) in clear flight conditions and the other in a human-piloted Cessna 172 in conditions where the horizon was partially obscured by terrain, haze and smoke. The UAV flight resulted in pitch and roll error standard deviations of 0.42° and 0.71° respectively when compared with a truth attitude source. The Cessna 172 flight resulted in pitch and roll error standard deviations of 1.79° and 1.75° respectively. In the second method for estimating attitude, a novel integrated GPS/Visual Odometry (GPS/VO) navigation filter is proposed, using a structure similar to a classic looselycoupled GPS/INS error-state navigation filter. Under such an arrangement, the error dynamics of the system are derived and a Kalman Filter is developed for estimating the errors in position and attitude. Through similar analysis to the GPS/INS problem, it is shown that the proposed filter is capable of recovering the complete attitude (i.e. pitch, roll and yaw) of the platform when subjected to acceleration not parallel to velocity for both the monocular and stereo variants of the filter. Furthermore, it is shown that under general straight line motion (e.g. constant velocity), only the component of attitude in the direction of motion is unobservable. Numerical simulations are performed to demonstrate the observability properties of the GPS/VO filter in both the monocular and stereo camera configurations. Furthermore, the proposed filter is tested on imagery collected using a Cessna 172 to demonstrate the observability properties on real-world data. The proposed GPS/VO filter does not require additional restrictions or assumptions such as platform-specific dynamics, map-matching, feature-tracking, visual loop-closing, gravity vector or additional sensors such as an IMU or magnetic compass. Since no platformspecific dynamics are required, the proposed filter is not limited to the aerospace domain and has the potential to be deployed in other platforms such as ground robots or mobile phones.

A randomised controlled trial of a theory-based intervention to improve sun protective behaviour in adolescents ('you can still be HOT in the shade') : study protocol

Background: Most skin cancers are preventable by encouraging consistent use of sun protective behaviour. In Australia, adolescents have high levels of knowledge and awareness of the risks of skin cancer but exhibit significantly lower sun protection behaviours than adults. There is limited research aimed at understanding why people do or do not engage in sun protective behaviour, and an associated absence of theory-based interventions to improve sun safe behaviour. This paper presents the study protocol for a school-based intervention which aims to improve the sun safe behaviour of adolescents. Methods/design: Approximately 400 adolescents (aged 12-17 years) will be recruited through Queensland, Australia public and private schools and randomized to the intervention (n = 200) or 'wait-list' control group (n = 200). The intervention focuses on encouraging supportive sun protective attitudes and beliefs, fostering perceptions of normative support for sun protection behaviour, and increasing perceptions of control/self-efficacy over using sun protection. It will be delivered during three × one hour sessions over a three week period from a trained facilitator during class time. Data will be collected one week pre-intervention (Time 1), and at one week (Time 2) and four weeks (Time 3) post-intervention. Primary outcomes are intentions to sun protect and sun protection behaviour. Secondary outcomes include attitudes toward performing sun protective behaviours (i.e., attitudes), perceptions of normative support to sun protect (i.e., subjective norms, group norms, and image norms), and perceived control over performing sun protective behaviours (i.e., perceived behavioural control). Discussion: The study will provide valuable information about the effectiveness of the intervention in improving the sun protective behaviour of adolescents.

Multimodal and monomodal discourses of marketization in higher education : power, ideology, and the absence of the image

The ubiquity of multimodality in hypermedia environments is undeniable. Bezemer and Kress (2008) have argued that writing has been displaced by image as the central mode for representation. Given the current technical affordances of digital technology and user-friendly interfaces that enable the ease of multimodal design, the conspicuous absence of images in certain domains of cyberspace is deserving of critical analysis. In this presentation, I examine the politics of discourses implicit within hypertextual spaces, drawing textual examples from a higher education website. I critically examine the role of writing and other modes of production used in what Fairclough (1993) refers to as discourses of marketisation in higher education, tracing four pervasive discourses of teaching and learning in the current economy: i) materialization, ii) personalization, iii) technologisation, and iv) commodification (Fairclough, 1999). Each of these arguments is supported by the critical analysis of multimodal texts. The first is a podcast highlighting the new architectonic features of a university learning space. The second is a podcast and transcript of a university Open Day interview with prospective students. The third is a time-lapse video showing the construction of a new science and engineering precinct. These three multimodal texts contrast a final web-based text that exhibits a predominance of writing and the powerful absence or silencing of the image. I connect the weightiness of words and the function of monomodality in the commodification of discourses, and its resistance to the multimodal affordances of web-based technologies, and how this is used to establish particular sets of subject positions and ideologies through which readers are constrained to occupy. Applying principles of critical language study by theorists that include Fairclough, Kress, Lemke, and others whose semiotic analysis of texts focuses on the connections between language, power, and ideology, I demonstrate how the denial of image and the privileging of written words in the multimodality of cyberspace is an ideological effect to accentuate the dominance of the institution.

Quality based frame selection for video face recognition

Quality based frame selection is a crucial task in video face recognition, to both improve the recognition rate and to reduce the computational cost. In this paper we present a framework that uses a variety of cues (face symmetry, sharpness, contrast, closeness of mouth, brightness and openness of the eye) to select the highest quality facial images available in a video sequence for recognition. Normalized feature scores are fused using a neural network and frames with high quality scores are used in a Local Gabor Binary Pattern Histogram Sequence based face recognition system. Experiments on the Honda/UCSD database shows that the proposed method selects the best quality face images in the video sequence, resulting in improved recognition performance.

A simulation-based training system for surgical wound debridement

A simulation-based training system for surgical wound debridement was developed and comprises a multimedia introduction, a surgical simulator (tutorial component), and an assessment component. The simulator includes two PCs, a haptic device, and mirrored display. Debridement is performed on a virtual leg model with a shallow laceration wound superimposed. Trainees are instructed to remove debris with forceps, scrub with a brush, and rinse with saline solution to maintain sterility. Research and development issues currently under investigation include tissue deformation models using mass-spring system and finite element methods; tissue cutting using a high-resolution volumetric mesh and dynamic topology; and accurate collision detection, cutting, and soft-body haptic rendering for two devices within the same haptic space.

Improved foreground detection via block-based classifier cascade with probabilistic decision integration

Background subtraction is a fundamental low-level processing task in numerous computer vision applications. The vast majority of algorithms process images on a pixel-by-pixel basis, where an independent decision is made for each pixel. A general limitation of such processing is that rich contextual information is not taken into account. We propose a block-based method capable of dealing with noise, illumination variations, and dynamic backgrounds, while still obtaining smooth contours of foreground objects. Specifically, image sequences are analyzed on an overlapping block-by-block basis. A low-dimensional texture descriptor obtained from each block is passed through an adaptive classifier cascade, where each stage handles a distinct problem. A probabilistic foreground mask generation approach then exploits block overlaps to integrate interim block-level decisions into final pixel-level foreground segmentation. Unlike many pixel-based methods, ad-hoc postprocessing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed approach obtains on average better results (both qualitatively and quantitatively) than several prominent methods. We furthermore propose the use of tracking performance as an unbiased approach for assessing the practical usefulness of foreground segmentation methods, and show that the proposed approach leads to considerable improvements in tracking accuracy on the CAVIAR dataset.

OpenRatSLAM : an open source brain-based SLAM system

RatSLAM is a navigation system based on the neural processes underlying navigation in the rodent brain, capable of operating with low resolution monocular image data. Seminal experiments using RatSLAM include mapping an entire suburb with a web camera and a long term robot delivery trial. This paper describes OpenRatSLAM, an open-source version of RatSLAM with bindings to the Robot Operating System framework to leverage advantages such as robot and sensor abstraction, networking, data playback, and visualization. OpenRatSLAM comprises connected ROS nodes to represent RatSLAM’s pose cells, experience map, and local view cells, as well as a fourth node that provides visual odometry estimates. The nodes are described with reference to the RatSLAM model and salient details of the ROS implementation such as topics, messages, parameters, class diagrams, sequence diagrams, and parameter tuning strategies. The performance of the system is demonstrated on three publicly available open-source datasets.

Airborne collision scenario flight tests : impact of angle measurement errors on reactive vision-based avoidance control

The future emergence of many types of airborne vehicles and unpiloted aircraft in the national airspace means collision avoidance is of primary concern in an uncooperative airspace environment. The ability to replicate a pilot’s see and avoid capability using cameras coupled with vision based avoidance control is an important part of an overall collision avoidance strategy. But unfortunately without range collision avoidance has no direct way to guarantee a level of safety. Collision scenario flight tests with two aircraft and a monocular camera threat detection and tracking system were used to study the accuracy of image-derived angle measurements. The effect of image-derived angle errors on reactive vision-based avoidance performance was then studied by simulation. The results show that whilst large angle measurement errors can significantly affect minimum ranging characteristics across a variety of initial conditions and closing speeds, the minimum range is always bounded and a collision never occurs.

Avoiding uninformed responses in destination image questionnaires

Since the first destination image studies were published in the early 1970s, the field has become one of the most popular in the tourism literature. While reviews of the destination image literature show no commonly agreed conceptualisation of the construct, researchers have predominantly used structured questionnaires for measurement. There has been criticism that the way some of these scales have been selected means a greater likelihood of attributes being irrelevant to participants. This opens up the risk of stimulating uninformed responses. The issue of uninformed response was first raised as a source of error 60 years ago. However, there has been little, if any, discussion in relation to destination image measurement, studies of which often require participants to provide opinion-driven rather than fact-based responses. This paper reports the trial of a ‘don’t know’ (DK) non-response option for participants in two destination image questionnaires. It is suggested the use of a DK option provides participants with an alternative to i) skipping the question, ii) using the scale midpoint to denote neutrality, or iii) providing an uninformed response. High levels of DK usage by participants can then alert the marketer of the need to improve awareness of destination performance for potential salient attributes.

Morphology-based model for predicting osteocyte-like cell line (MLO-Y4) growth process

This work has led to the development of empirical mathematical models to quantitatively predicate the changes of morphology in osteocyte-like cell lines (MLO-Y4) in culture. MLO-Y4 cells were cultured at low density and the changes in morphology recorded over 11 hours. Cell area and three dimensional shape features including aspect ratio, circularity and solidity were then determined using widely accepted image analysis software (ImageJTM). Based on the data obtained from the imaging analysis, mathematical models were developed using the non-linear regression method. The developed mathematical models accurately predict the morphology of MLO-Y4 cells for different culture times and can, therefore, be used as a reference model for analyzing MLO-Y4 cell morphology changes within various biological/mechanical studies, as necessary.

Measuring a destination’s brand equity between 2003 and 2012 using the consumer-based brand equity (CBBE) hierarchy

Given the increasing investments being made in brand development by destination marketing organisations (DMO) since the 1990s, including rebranding and repositioning, more research is needed to enhance understanding of how to effectively monitor destination brand performance over time. This paper reports the results of a study of brand performance of a competitive set of destinations, in their most important market, between 2003 and 2012. Brand performance was measured from the perspective of consumer perceptions, based on the concept of consumer-based brand equity (CBBE). A structured questionnaire was administered to different samples in 2003, 2007 and 2012. The results indicated minimal changes in perceptions of the five destinations over the 10 year period. Due to the commonality of challenges faced by DMOs worldwide, it is suggested the CBBE hierarchy provides destination marketers with a practical tool for evaluating brand performance over time; in terms of measures of effectiveness of past marketing communications, as well as indicators of future performance. In addition, and importantly, CBBE also provides transparent accountability measures for stakeholders. While the topic of destination image has been one of the most popular in the tourism literature, there has been a paucity of research published in relation to the temporal aspect of consumer perceptions. This is a rare investigation into the measurement of perceptions of destinations over a 10 year period.