Decoupled image-based visual servoing for cameras obeying the unified projection model

This paper proposes a generic decoupled imagebased control scheme for cameras obeying the unified projection model. The scheme is based on the spherical projection model. Invariants to rotational motion are computed from this projection and used to control the translational degrees of freedom. Importantly we form invariants which decrease the sensitivity of the interaction matrix to object depth variation. Finally, the proposed results are validated with experiments using a classical perspective camera as well as a fisheye camera mounted on a 6-DOF robotic platform.

Attitude observability of a loosely-coupled GPS/Visual Odometry Integrated Navigation Filter

We present a novel method for integrating GPS position estimates with position and attitude estimates derived from visual odometry using a scheme similar to a classic loosely-coupled GPS/INS integration. Under such an arrangement, we derive the error dynamics of the system and develop a Kalman Filter for estimating the errors in position and attitude. Using a control-based approach to observability, we show that the errors in both position and attitude (including yaw) are fully observable when there is a component of acceleration perpendicular to the velocity vector in the navigation frame. Numerical simulations are performed to confirm the observability analysis.

The dynamic processes of visual, corporate, and organisational identity : an exploratory study

The purpose of this study is to contribute to the cross-disciplinary body of literature of identity and organisational culture. This study empirically investigated the Hatch and Schultz (2002) Organisational Identity Dynamics (OID) model to look at linkages between identity, image, and organisational culture. This study used processes defined in the OID model as a theoretical frame by which to understand the relationships between actual and espoused identity manifestations across visual identity, corporate identity, and organisational identity. The linking processes of impressing, mirroring, reflecting, and expressing were discussed at three unique levels in the organisation. The overarching research question of How does the organisational identity dynamics process manifest itself in practice at different levels within an organisation? was used as a means of providing empirical understanding to the previously theoretical OID model. Case study analysis was utilised to provide exploratory data across the organisational groups of: Level A - Senior Marketing and Corporate Communications Management, Level B - Marketing and Corporate Communications Staff, and Level C - Non-Marketing Managers and Employees. Data was collected via 15 in-depth interviews with documentary analysis used as a supporting mechanism to provide triangulation in analysis. Data was analysed against the impressing, mirroring, reflecting, and expressing constructs with specific criteria developed from literature to provide a detailed analysis of each process. Conclusions revealed marked differences in the ways in which OID processes occurred across different levels with implications for the ways in which VI, CI, and OI interact to develop holistic identity across organisational levels. Implications for theory detail the need to understand and utilise cultural understanding in identity programs as well as the value in developing identity communications which represent an actual rather than an espoused position.

The Heavy Vehicle Study : a case-control study investigating risk factors for crash in long distance heavy vehicle drivers in Australia

Background Heavy vehicle transportation continues to grow internationally; yet crash rates are high, and the risk of injury and death extends to all road users. The work environment for the heavy vehicle driver poses many challenges; conditions such as scheduling and payment are proposed risk factors for crash, yet the precise measure of these needs quantifying. Other risk factors such as sleep disorders including obstructive sleep apnoea have been shown to increase crash risk in motor vehicle drivers however the risk of heavy vehicle crash from this and related health conditions needs detailed investigation. Methods and Design The proposed case control study will recruit 1034 long distance heavy vehicle drivers: 517 who have crashed and 517 who have not. All participants will be interviewed at length, regarding their driving and crash history, typical workloads, scheduling and payment, trip history over several days, sleep patterns, health, and substance use. All participants will have administered a nasal flow monitor for the detection of obstructive sleep apnoea. Discussion Significant attention has been paid to the enforcement of legislation aiming to deter problems such as excess loading, speeding and substance use; however, there is inconclusive evidence as to the direction and strength of associations of many other postulated risk factors for heavy vehicle crashes. The influence of factors such as remuneration and scheduling on crash risk is unclear; so too the association between sleep apnoea and the risk of heavy vehicle driver crash. Contributory factors such as sleep quality and quantity, body mass and health status will be investigated. Quantifying the measure of effect of these factors on the heavy vehicle driver will inform policy development that aims toward safer driving practices and reduction in heavy vehicle crash; protecting the lives of many on the road network.

Analysis of cardiac and epileptic signals using higher order spectra

The theory of nonlinear dyamic systems provides some new methods to handle complex systems. Chaos theory offers new concepts, algorithms and methods for processing, enhancing and analyzing the measured signals. In recent years, researchers are applying the concepts from this theory to bio-signal analysis. In this work, the complex dynamics of the bio-signals such as electrocardiogram (ECG) and electroencephalogram (EEG) are analyzed using the tools of nonlinear systems theory. In the modern industrialized countries every year several hundred thousands of people die due to sudden cardiac death. The Electrocardiogram (ECG) is an important biosignal representing the sum total of millions of cardiac cell depolarization potentials. It contains important insight into the state of health and nature of the disease afflicting the heart. Heart rate variability (HRV) refers to the regulation of the sinoatrial node, the natural pacemaker of the heart by the sympathetic and parasympathetic branches of the autonomic nervous system. Heart rate variability analysis is an important tool to observe the heart's ability to respond to normal regulatory impulses that affect its rhythm. A computerbased intelligent system for analysis of cardiac states is very useful in diagnostics and disease management. Like many bio-signals, HRV signals are non-linear in nature. Higher order spectral analysis (HOS) is known to be a good tool for the analysis of non-linear systems and provides good noise immunity. In this work, we studied the HOS of the HRV signals of normal heartbeat and four classes of arrhythmia. This thesis presents some general characteristics for each of these classes of HRV signals in the bispectrum and bicoherence plots. Several features were extracted from the HOS and subjected an Analysis of Variance (ANOVA) test. The results are very promising for cardiac arrhythmia classification with a number of features yielding a p-value < 0.02 in the ANOVA test. An automated intelligent system for the identification of cardiac health is very useful in healthcare technology. In this work, seven features were extracted from the heart rate signals using HOS and fed to a support vector machine (SVM) for classification. The performance evaluation protocol in this thesis uses 330 subjects consisting of five different kinds of cardiac disease conditions. The classifier achieved a sensitivity of 90% and a specificity of 89%. This system is ready to run on larger data sets. In EEG analysis, the search for hidden information for identification of seizures has a long history. Epilepsy is a pathological condition characterized by spontaneous and unforeseeable occurrence of seizures, during which the perception or behavior of patients is disturbed. An automatic early detection of the seizure onsets would help the patients and observers to take appropriate precautions. Various methods have been proposed to predict the onset of seizures based on EEG recordings. The use of nonlinear features motivated by the higher order spectra (HOS) has been reported to be a promising approach to differentiate between normal, background (pre-ictal) and epileptic EEG signals. In this work, these features are used to train both a Gaussian mixture model (GMM) classifier and a Support Vector Machine (SVM) classifier. Results show that the classifiers were able to achieve 93.11% and 92.67% classification accuracy, respectively, with selected HOS based features. About 2 hours of EEG recordings from 10 patients were used in this study. This thesis introduces unique bispectrum and bicoherence plots for various cardiac conditions and for normal, background and epileptic EEG signals. These plots reveal distinct patterns. The patterns are useful for visual interpretation by those without a deep understanding of spectral analysis such as medical practitioners. It includes original contributions in extracting features from HRV and EEG signals using HOS and entropy, in analyzing the statistical properties of such features on real data and in automated classification using these features with GMM and SVM classifiers.

Effect of simulated visual impairment on nighttime driving performance

PURPOSE: This study investigated the effects of simulated visual impairment on nighttime driving performance and pedestrian recognition under real-road conditions. METHODS: Closed road nighttime driving performance was measured for 20 young visually normal participants (M = 27.5 +/- 6.1 years) under three visual conditions: normal vision, simulated cataracts, and refractive blur that were incorporated in modified goggles. The visual acuity levels for the cataract and blur conditions were matched for each participant. Driving measures included sign recognition, avoidance of low contrast road hazards, time to complete the course, and lane keeping. Pedestrian recognition was measured for pedestrians wearing either black clothing or black clothing with retroreflective markings on the moveable joints to create the perception of biological motion ("biomotion"). RESULTS: Simulated visual impairment significantly reduced participants' ability to recognize road signs, avoid road hazards, and increased the time taken to complete the driving course (p < 0.05); the effect was greatest for the cataract condition, even though the cataract and blur conditions were matched for visual acuity. Although visual impairment also significantly reduced the ability to recognize the pedestrian wearing black clothing, the pedestrian wearing "biomotion" was seen 80% of the time. CONCLUSIONS: Driving performance under nighttime conditions was significantly degraded by modest visual impairment; these effects were greatest for the cataract condition. Pedestrian recognition was greatly enhanced by marking limb joints in the pattern of "biomotion," which was relatively robust to the effects of visual impairment.

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.

Availability of advance visual information constrains association-football goalkeeping performance during penalty kicks

A pressing concern within the literature on anticipatory perceptual-motor behaviour is the lack of clarity on the applicability of data, observed under video-simulation task constraints, to actual performance in which actions are coupled to perception, as captured during in-situ experimental conditions. We developed an in-situ experimental paradigm which manipulated the duration of anticipatory visual information from a penalty taker’s actions to examine experienced goalkeepers’ vulnerability to deception for the penalty kick in association football. Irrespective of the penalty taker’s kick strategy, goalkeepers initiated movement responses earlier across consecutively earlier presentation points. Overall goalkeeping performance was better in non-deception trials than in deception conditions. In deception trials, the kinematic information presented up until the penalty taker initiated his/her kicking action had a negative effect on goalkeepers’ performance. It is concluded that goalkeepers are likely to benefit from not anticipating a penalty taker’s performance outcome based on information from the run-up, in preference to later information that emerges just before the initiation of the penalty taker’s kicking action.

Visual field size criteria for mobility rehabilitation referral

Purpose. To investigate evidence-based visual field size criteria for referral of low-vision (LV) patients for mobility rehabilitation. Methods. One hundred and nine participants with LV and 41 age-matched participants with normal sight (NS) were recruited. The LV group was heterogeneous with diverse causes of visual impairment. We measured binocular kinetic visual fields with the Humphrey Field Analyzer and mobility performance on an obstacle-rich, indoor course. Mobility was assessed as percent preferred walking speed (PPWS) and number of obstacle-contact errors. The weighted kappa coefficient of association (κr) was used to discriminate LV participants with both unsafe and inefficient mobility from those with adequate mobility on the basis of their visual field size for the full sample and for subgroups according to type of visual field loss and whether or not the participants had previously received orientation and mobility training. Results. LV participants with both PPWS <38% and errors >6 on our course were classified as having inadequate (inefficient and unsafe) mobility compared with NS participants. Mobility appeared to be first compromised when the visual field was less than about 1.2 steradians (sr; solid angle of a circular visual field of about 70° diameter). Visual fields <0.23 and 0.63 sr (31 to 52° diameter) discriminated patients with at-risk mobility for the full sample and across the two subgroups. A visual field of 0.05 sr (15° diameter) discriminated those with critical mobility. Conclusions. Our study suggests that: practitioners should be alert to potential mobility difficulties when the visual field is less than about 1.2 sr (70° diameter); assessment for mobility rehabilitation may be warranted when the visual field is constricted to about 0.23 to 0.63 sr (31 to 52° diameter) depending on the nature of their visual field loss and previous history (at risk); and mobility rehabilitation should be conducted before the visual field is constricted to 0.05 sr (15° diameter; critical).

Modest visual impairments and headlamp glare reduce pedestrian visability at night

Background: This study investigated the effects of experimentally induced visual impairment, headlamp glare and clothing on pedestrian visibility. Methods: 28 young adults (M=27.6±4.7 yrs) drove around a closed road circuit at night while pedestrians walked in place at the roadside. Pedestrians wore either black clothing, black clothing with a rectangular vest consisting of 1325 cm2 of retroreflective tape, or the same amount of tape positioned on the extremities in a configuration that conveyed biological motion (“biomotion”). Visual impairment was induced by goggles containing either blurring lenses, simulated cataracts, or clear lenses; visual acuity for the cataract and blurred lens conditions was matched. Drivers pressed a response pad when they first recognized that a pedestrian was present. Sixteen participants drove around the circuit in the presence of headlamp glare while twelve drove without glare. Results: Visual impairment, headlamp glare and pedestrian clothing all significantly affected drivers’ ability to recognize pedestrians (p<0.05). The simulated cataracts were more disruptive than blur, even though acuity was matched across the two manipulations. Pedestrians were recognized more often and at longer distances when they wore “biomotion” clothing than either the vest or black clothing, even in the presence of visual impairment and glare. Conclusions: Drivers’ ability to see and respond to pedestrians at night is degraded by modest visual impairments even when vision meets driver licensing requirements; glare further exacerbates these effects. Clothing that includes retroreflective tape in a biological motion configuration is relatively robust to visual impairment and glare.

Simulated visual impairment leads to cognitive slowing in older adults

PURPOSE: To investigate the impact of different levels of simulated visual impairment on the cognitive test performance of older adults and to compare this with previous findings in younger adults. METHODS.: Cognitive performance was assessed in 30 visually normal, community-dwelling older adults (mean = 70.2 ± 3.9 years). Four standard cognitive tests were used including the Digit Symbol Substitution Test, Trail Making Tests A and B, and the Stroop Color Word Test under three visual conditions: normal baseline vision and two levels of cataract simulating filters (Vistech), which were administered in a random order. Distance high-contrast visual acuity and Pelli-Robson letter contrast sensitivity were also assessed for all three visual conditions. RESULTS.: Simulated cataract significantly impaired performance across all cognitive test performance measures. In addition, the impact of simulated cataract was significantly greater in this older cohort than in a younger cohort previously investigated. Individual differences in contrast sensitivity better predicted cognitive test performance than did visual acuity. CONCLUSIONS.: Visual impairment can lead to slowing of cognitive performance in older adults; these effects are greater than those observed in younger participants. This has important implications for neuropsychological testing of older populations who have a high prevalence of cataract.

Recognising audio-visual speech in vehicles using the AVICAR database

Interacting with technology within a vehicle environment using a voice interface can greatly reduce the effects of driver distraction. Most current approaches to this problem only utilise the audio signal, making them susceptible to acoustic noise. An obvious approach to circumvent this is to use the visual modality in addition. However, capturing, storing and distributing audio-visual data in a vehicle environment is very costly and difficult. One current dataset available for such research is the AVICAR [1] database. Unfortunately this database is largely unusable due to timing mismatch between the two streams and in addition, no protocol is available. We have overcome this problem by re-synchronising the streams on the phone-number portion of the dataset and established a protocol for further research. This paper presents the first audio-visual results on this dataset for speaker-independent speech recognition. We hope this will serve as a catalyst for future research in this area.

Estimates of crowding in long-term care: Comparing two approaches

Objective: Because studies of crowding in long-term care settings are lacking, the authors sought to: (1) generate initial estimates of crowding in nursing homes and assisted living facilities; and (2) evaluate two operational approaches to its measurement. ----- ----- Background: Reactions to density and proximity are complex. Greater density intensifies people's reaction to a situation in the direction (positive or negative) that they would react if the situation were to occur under less dense conditions. People with dementia are especially reactive to the environment. ----- ----- Methods: Using a cross-sectional correlational design in nursing homes and assisted living facilities involving 185 participants, multiple observations (N = 6,455) of crowding and other environmental variables were made. Crowding, location, and sound were measured three times per observation; ambiance was measured once. Data analyses consisted of descriptive statistics, t-tests, and one-way analysis of variance. ----- ----- Results: Crowding estimates were higher for nursing homes and in dining and activity rooms. Crowding also varied across settings and locations by time of day. Overall, the interaction of location and time affected crowding significantly (N = 5,559, df [47, 511], F = 105.69, p < .0001); effects were greater within location-by-hour than between location-by-hour, but the effect explained slightly less variance in Long-Term Care Crowding Index (LTC-CI) estimates (47.41%) than location alone. Crowding had small, direct, and highly significant correlations with sound and with the engaging subscale for ambiance; a similar, though inverse, correlation was seen with the soothing subscale for ambiance. ----- ----- Conclusions: Crowding fluctuates consistent with routine activities such as meals in long-term care settings. Furthermore, a relationship between crowding and other physical characteristics of the environment was found. The LTC-CI is likely to be more sensitive than simple people counts when seeking to evaluate the effects of crowding on the behavior of elders-particularly those with dementia-in long-term care settings. aging in place.

Assessment of commercial network RTK user positioning performance over long inter-station distances

The paper provides an assessment of the performance of commercial Real Time Kinematic (RTK) systems over longer than recommended inter-station distances. The experiments were set up to test and analyse solutions from the i-MAX, MAX and VRS systems being operated with three triangle shaped network cells, each having an average inter-station distance of 69km, 118km and 166km. The performance characteristics appraised included initialization success rate, initialization time, RTK position accuracy and availability, ambiguity resolution risk and RTK integrity risk in order to provide a wider perspective of the performance of the testing systems. ----- ----- The results showed that the performances of all network RTK solutions assessed were affected by the increase in the inter-station distances to similar degrees. The MAX solution achieved the highest initialization success rate of 96.6% on average, albeit with a longer initialisation time. Two VRS approaches achieved lower initialization success rate of 80% over the large triangle. In terms of RTK positioning accuracy after successful initialisation, the results indicated a good agreement between the actual error growth in both horizontal and vertical components and the accuracy specified in the RMS and part per million (ppm) values by the manufacturers. ----- ----- Additionally, the VRS approaches performed better than the MAX and i-MAX when being tested under the standard triangle network with a mean inter-station distance of 69km. However as the inter-station distance increases, the network RTK software may fail to generate VRS correction and then may turn to operate in the nearest single-base RTK (or RAW) mode. The position uncertainty reached beyond 2 meters occasionally, showing that the RTK rover software was using an incorrect ambiguity fixed solution to estimate the rover position rather than automatically dropping back to using an ambiguity float solution. Results identified that the risk of incorrectly resolving ambiguities reached 18%, 20%, 13% and 25% for i-MAX, MAX, Leica VRS and Trimble VRS respectively when operating over the large triangle network. Additionally, the Coordinate Quality indicator values given by the Leica GX1230 GG rover receiver tended to be over-optimistic and not functioning well with the identification of incorrectly fixed integer ambiguity solutions. In summary, this independent assessment has identified some problems and failures that can occur in all of the systems tested, especially when being pushed beyond the recommended limits. While such failures are expected, they can offer useful insights into where users should be wary and how manufacturers might improve their products. The results also demonstrate that integrity monitoring of RTK solutions is indeed necessary for precision applications, thus deserving serious attention from researchers and system providers.

Geometry‐specified troposphere decorrelation for subcentimeter real‐time kinematic solutions over long baselines

Real‐time kinematic (RTK) GPS techniques have been extensively developed for applications including surveying, structural monitoring, and machine automation. Limitations of the existing RTK techniques that hinder their applications for geodynamics purposes are twofold: (1) the achievable RTK accuracy is on the level of a few centimeters and the uncertainty of vertical component is 1.5–2 times worse than those of horizontal components and (2) the RTK position uncertainty grows in proportional to the base‐torover distances. The key limiting factor behind the problems is the significant effect of residual tropospheric errors on the positioning solutions, especially on the highly correlated height component. This paper develops the geometry‐specified troposphere decorrelation strategy to achieve the subcentimeter kinematic positioning accuracy in all three components. The key is to set up a relative zenith tropospheric delay (RZTD) parameter to absorb the residual tropospheric effects and to solve the established model as an ill‐posed problem using the regularization method. In order to compute a reasonable regularization parameter to obtain an optimal regularized solution, the covariance matrix of positional parameters estimated without the RZTD parameter, which is characterized by observation geometry, is used to replace the quadratic matrix of their “true” values. As a result, the regularization parameter is adaptively computed with variation of observation geometry. The experiment results show that new method can efficiently alleviate the model’s ill condition and stabilize the solution from a single data epoch. Compared to the results from the conventional least squares method, the new method can improve the longrange RTK solution precision from several centimeters to the subcentimeter in all components. More significantly, the precision of the height component is even higher. Several geosciences applications that require subcentimeter real‐time solutions can largely benefit from the proposed approach, such as monitoring of earthquakes and large dams in real‐time, high‐precision GPS leveling and refinement of the vertical datum. In addition, the high‐resolution RZTD solutions can contribute to effective recovery of tropospheric slant path delays in order to establish a 4‐D troposphere tomography.