Providing real-time information services for public bus commuters

This paper investigates RTIS for public bus commuters; identifying their needs and proposing the architecture and design for this service. Considering that the service needs to be extensible, adaptable and interoperative, the new system is based on the use of XML Web Services. This gives the structure flexibility for further development and integration with other like services.

Measuring food access in Melbourne: access to healthy and fast foods by car, bus and foot in an urban municipality in Melbourne

Access to healthy food can be an important determinant of a healthy diet. This paper describes the assessment of access to healthy and unhealthy foods using a GIS accessibility programme in a large outer municipality of Melbourne. Access to a major supermarket was used as a proxy for access to a healthy diet and fast food outlet as proxy for access to unhealthy food. Our results indicated that most (>80%) residents lived within an 8–10 min car journey of a major supermarket i.e. have good access to a healthy diet. However, more advantaged areas had closer access to supermarkets, conversely less advantaged areas had closer access to fast food outlets. These findings have application for urban planners, public health practitioners and policy makers.

Risky driving habits and motor vehicle driver injury

Risky driving is an important cause of motor vehicle injury, but there is a lack of good epidemiological data in this field, particularly data comparing risky driving in younger drivers to those of other age groups. We examined the relationship between risky driving habits, prior traffic convictions and motor vehicle injury using cross-sectional data amongst 21,893 individuals in New Zealand, including 8029 who were aged 16–24 years. Those who reported frequently racing a motor vehicle for excitement or driving at 20 km/h or more over the speed limit, and those who had received traffic convictions over the past 12 months, were between two and four times more likely to have been injured while driving over the same time period. Driving unlicensed was a risk factor for older but not younger drivers, and driving at 20 km/h or more above the speed limits was a stronger risk factor for younger (<25 years) than older drivers. These results confirm the need for interventions targeting risky driving and suggest that different strategies may be required for different high-risk groups.

Cost-effectiveness of active transport for primary school children - Walking School Bus Program

Background : To assess from a societal perspective the incremental cost-effectiveness of the Walking School Bus (WSB) program for Australian primary school children as an obesity prevention measure. The intervention was modelled as part of the ACE-Obesity study, which evaluated, using consistent methods, thirteen interventions targeting unhealthy weight gain in Australian children and adolescents.

Methods : A logic pathway was used to model the effects on body mass index [BMI] and disability-adjusted life years [DALYs] of the Victorian WSB program if applied throughout Australia. Cost offsets and DALY benefits were modelled until the eligible cohort reached 100 years of age or death. The reference year was 2001. Second stage filter criteria ('equity', 'strength of evidence', 'acceptability', feasibility', sustainability' and 'side-effects') were assessed to incorporate additional factors that impact on resource allocation decisions.

Results : The modelled intervention reached 7,840 children aged 5 to 7 years and cost $AUD22.8M ($16.6M;$30.9M). This resulted in an incremental saving of 30 DALYs (7:104) and a net cost per DALY saved of $AUD0.76M ($0.23M; $3.32M). The evidence base was judged as 'weak' as there are no data available documenting the increase in the number of children walking due to the intervention. The high costs of the current approach may limit sustainability.

Conclusions : Under current modelling assumptions, the WSB program is not an effective or cost-effective measure to reduce childhood obesity. The attribution of some costs to non-obesity objectives (reduced traffic congestion and air pollution etc.) is justified to emphasise the other possible benefits. The program's cost-effectiveness would be improved by more comprehensive implementation within current infrastructure arrangements. The importance of active transport to school suggests that improvements in WSB or its variants need to be developed and fully evaluated.

The feasibility of a sustainable energy, driver-only electric commuter vehicle for New Zealand

This paper investigates whether low technology driver-only, battery electric commuter vehicles are feasible for New Zealand. Personal passenger transport faces several challenges in the coming decades: depletion of cheap oil reserves, increasing congestion, localised pollution, the need for reduced carbon emissions and the long term goal of sustainability. One way of solving some of these problems could be to introduce low cost, comfortable, energy efficient, driver-only electric vehicles. These would still give the driver a weatherproof, safe and comfortable means of commuting, but at a fraction of the energy and running costs of conventional petrol/diesel cars. To help assess their viability, the performance and energy use of the E-POD electric commuter vehicle is used as a benchmark. The work shows that such a vehicle could be made cheaply, using readily available technology with a range of 180km and a top speed of over 90km/h. The chassis could be made from natural fibre composite materials that might reduce significantly the embedded energy required for its manufacture. The electricity taken from the grid to charge the batteries could be replaced by electricity generated from grid connected photovoltaic panels mounted on the garage roof of the vehicle owner.

Driver recognition based on dynamic handgrip pattern on steeling wheel

This paper proposes a novel biometric authentication method based on the recognition of drivers' dynamic handgrip on steering wheel. A pressure sensitive mat mounted on a steering wheel is employed to collect handgrip data exerted by the hands of drivers who intend to start the vehicle. Then, the likelihood-ratio-based classifier is designed to distinguish rightful driver of a car after analyzing their inherent dynamic features of grasping. The experimental results obtained in this study show that mean acceptance rates of 85.4% for the trained subjects and mean rejection rates of 82.65% for the un-trained ones are achieved by the classifier in the two batches of testing. It can be concluded that the driver verification approach based on dynamic handgrip recognition on steering wheel is a promising biometric technology and will be further explored in the near future in smart car design.

Driver verification based on handgrip recognition on steering wheel

This paper presents a novel driver verification algorithm based on the recognition of handgrip patterns on steering wheel. A pressure sensitive mat mounted on a steering wheel is employed to collect a series of pressure images exerted by the hands of the drivers who intend to start the vehicle. Then, feature extraction from those images is carried out through two major steps: Quad-Tree-based multi-resolution decomposition on the images and Principle Component Analysis (PCA)-based dimension reduction, followed by implementing a likelihood-ratio classifier to distinguish drivers into known or unknown ones. The experimental results obtained in this study show that the mean acceptance rates of 78.15% and 78.22% for the trained subjects and the mean rejection rates of 93.92% and 90.93% to the un-trained ones are achieved in two trials, respectively. It can be concluded that the driver verification approach based on the handgrip recognition on steering wheel is promising and will be further explored in the near future.

Comparative evaluation of pedestrian detection methods for mobile bus surveillance

We present a comparative evaluation of the state-of-art algorithms for detecting pedestrians in low frame rate and low resolution footage acquired by mobile sensors. Four approaches are compared: a) The Histogram of Oriented Gradient (HoG) approach [1]; b) A new histogram feature that is formed by the weighted sum of both the gradient magnitude and the filter responses from a set of elongated Gaussian filters [2] corresponding to the quantised orientation, called Histogram of Oriented Gradient Banks (HoGB) approach; c) The codebook based HoG feature with branch-and-bound (efficient subwindow search) algorithm [3] and; d) The codebook based HoGB approach. Results show that the HoG based detector achieves the highest performance in terms of the true positive detection, the HoGB approach has the lowest false positives whilst maintaining a comparable true positive rate to the HoG, and the codebook approaches allow computationally efficient detection.

Passenger monitoring in moving bus video

In this paper, we present a novel person detection system for public transport buses tackling the problem of changing illumination conditions. Our approach integrates a stable SIFT (Scale Invariant Feature Transform) background seat modeling mechanism with a human shape model into a weighted Bayesian framework to detect passengers on-board buses. SIFT background modeling extracts local stable features on the pre-annotated background seat areas and tracks these features over time to build a global statistical background model for each seat. Since SIFT features are partially invariant to lighting, this background model can be used robustly to detect the seat occupancy status even under severe lighting changes. The human shape model further confirms the existence of a passenger when a seat is occupied. This constructs a robust passenger monitoring system which is resilient to illumination changes. We evaluate the performance of our proposed system on a number of challenging video datasets obtained from bus cameras and the experimental results show that it is superior to state-of-art people detection systems.

Pedestrian detection for mobile bus surveillance

In this paper, we present a system for pedestrian detection involving scenes captured by mobile bus surveillance cameras in busy city streets. Our approach integrates scene localization, foreground and background separation, and pedestrian detection modules into a unified detection framework. The scene localization module performs a two stage clustering of the video data. In the first stage, SIFT Homography is applied to cluster frames in terms of their structural similarities and second stage further clusters these aligned frames in terms of lighting. This produces clusters of images which are differential in viewpoint and lighting. A kernel density estimation (KDE) method for colour and gradient foreground-background separation are then used to construct background model for each image cluster which is subsequently used to detect all foreground pixels. Finally, using a hierarchical template matching approach, pedestrians can be identified. We have tested our system on a set of real bus video datasets and the experimental results verify that our system works well in practice.

Climate as a driver of population variability in breeding Gentoo Penguins (Pygoscelis papua) at the Falkland Islands

Detecting and predicting how populations respond to environmental variability are eminent challenges in conservation research and management. This is particularly true for wildlife populations at high latitudes, many of which demonstrate changes in popula