Architecture, Building and Planning - Research Publications
Permanent URI for this collection
Search Results
1 - 8 of 8
-
ItemThe "Paris-end" of Town?: Deriving Urban Typologies Using Three Imagery Types(MDPI, 2020)Urban typologies allow areas to be categorised according to form and the social, demographic, and political uses of the areas. The use of these typologies and finding similarities and dissimilarities between cities enables better targeted interventions for improved health, transport, and environmental outcomes in urban areas. A better understanding of local contexts can also assist in applying lessons learned from other cities. Constructing urban typologies at a global scale through traditional methods, such as functional or network analysis, requires the collection of data across multiple political districts, which can be inconsistent and then require a level of subjective classification. To overcome these limitations, we use neural networks to analyse millions of images of urban form (consisting of street view, satellite imagery, and street maps) to find shared characteristics between the largest 1692 cities in the world. The comparison city of Paris is used as an exemplar and we perform a case study using two Australian cities, Melbourne and Sydney, to determine if a "Paris-end" of town exists or can be found in these cities using these three big data imagery sets. The results show specific advantages and disadvantages of each type of imagery in constructing urban typologies. Neural networks trained with map imagery will be highly influenced by the structural mix of roads, public transport, and green and blue space. Satellite imagery captures a combination of both urban form and decorative and natural details. The use of street view imagery emphasises the features of a human-scaled visual geography of streetscapes. However, for both satellite and street view imagery to be highly effective, a reduction in scale and more aggressive pre-processing might be required in order to reduce detail and create greater abstraction in the imagery.
-
ItemNo Preview AvailableA global analysis of urban design types and road transport injury: an image processing study.(Elsevier, 2020-01-01)BACKGROUND: Death and injury due to motor vehicle crashes is the world's fifth leading cause of mortality and morbidity. City and urban designs might play a role in mitigating the global burden of road transport injury to an extent that has not been captured by traditional safe system approaches. We aimed to determine the relationship between urban design and road trauma across the globe. METHODS: Applying a combined convolutional neural network and graph-based approach, 1692 cities capturing one third of the world's population were classified into types based on urban design characteristics represented in sample maps. Associations between identified city types, characteristics contained within sample maps, and the burden of road transport injury as measured by disability adjusted life-years were estimated through univariate and multivariate analyses, controlling for the influence of economic activity. FINDINGS: Between Mar 1, 2017, and Dec 24, 2018, nine global city types based on a final sample of 1632 cities were identified. Burden of road transport injury was an estimated two-times higher (risk ratio 2·05, 95% CI 1·84-2·27) for the poorest performing city type compared with the best performing city type, culminating in an estimated loss of 8·71 (8·08-9·25) million disability-adjusted life-years per year attributable to suboptimal urban design. City types that featured a greater proportion of railed public transport networks combined with dense road networks characterised by smaller blocks showed the lowest rates of road traffic injury. INTERPRETATION: This study highlights the important role that city and urban design plays in mitigating road transport injury burden at a global scale. It is recommended that road and transport safety efforts promote urban design that features characteristics inherent in identified high-performance city types including higher density road infrastructure and high rates of public transit. FUNDING: See acknowledgments.
-
ItemSky pixel detection in outdoor imagery using an adaptive algorithm and machine learning(Elsevier, 2019)Computer vision techniques enable automated detection of sky pixels in outdoor imagery. In urban climate, sky detection is an important first step in gathering information about urban morphology and sky view factors. However, obtaining accurate results remains challenging and becomes even more complex using imagery captured under a variety of lighting and weather conditions. To address this problem, we present a new sky pixel detection system demonstrated to produce accurate results using a wide range of outdoor imagery types. Images are processed using a selection of mean-shift segmentation, K-means clustering, and Sobel filters to mark sky pixels in the scene. The algorithm for a specific image is chosen by a convolutional neural network, trained with 25,000 images from the Skyfinder data set, reaching 82% accuracy for the top three classes. This selection step allows the sky marking to follow an adaptive process and to use different techniques and parameters to best suit a particular image. An evaluation of fourteen different techniques and parameter sets shows that no single technique can perform with high accuracy across varied Skyfinder and Google Street View data sets. However, by using our adaptive process, large increases in accuracy are observed. The resulting system is shown to perform better than other published techniques.
-
ItemRoad traffic injury in urban areas: understanding the complex city.(ICoRSI, 2019)Over the past 4 decades considerable efforts have been taken to mitigate the growing burden of road injury. With increasing urbanisation along with global mobility that demands not only safety but equitable, efficient and clean (reduced carbon footprint) transport, the responses to dealing with the burgeoning road traffic injury in low- and middle-income countries has become increasingly complex. In this paper, we apply unique methods to identify important strategies that could be implemented to reduce road traffic injury in the Asia and Pacific region; a region comprising large middle-income countries (China and India) that are currently in the throes of rapid motorization. Using a convolutional neural network approach, we classified cities around the world based on urban characteristics related to private motor vehicles and public transport networks. We then identified 689 cities situated within the Asia-Pacific region and assessed the global burden of disease attributed to road traffic injury for urban design clusters. The modelling identified 9 urban cluster types. The majority (64%) of cities in the Asia-Pacific region fall within Clusters 1 and 2 namely, urban form that is sparse with low capacity road infrastructure and limited public transport. Clusters 1 and 2 comprises cities predominantly from China and South Asia with many low- to middle-income cities that are in the throes of considerable urban development. Urban cluster types with both dense road networks (e.g., Clusters Intense and Cul de sac) and public transport (e.g., Clusters High Transit and Motor City) demonstrated lower rates of DALYs lost per 100,000 population for road traffic injury. This study demonstrates the utility of employing image recognition methods to discover new insights to better understand the complex city and how it relates to road traffic injury.
-
ItemReal-time monitoring of driver drowsiness on mobile platforms using 3D neural networks(SPRINGER LONDON LTD, 2020-07)Abstract Driver drowsiness increases crash risk, leading to substantial road trauma each year. Drowsiness detection methods have received considerable attention, but few studies have investigated the implementation of a detection approach on a mobile phone. Phone applications reduce the need for specialised hardware and hence, enable a cost-effective roll-out of the technology across the driving population. While it has been shown that three-dimensional (3D) operations are more suitable for spatiotemporal feature learning, current methods for drowsiness detection commonly use frame-based, multi-step approaches. However, computationally expensive techniques that achieve superior results on action recognition benchmarks (e.g. 3D convolutions, optical flow extraction) create bottlenecks for real-time, safety-critical applications on mobile devices. Here, we show how depthwise separable 3D convolutions, combined with an early fusion of spatial and temporal information, can achieve a balance between high prediction accuracy and real-time inference requirements. In particular, increased accuracy is achieved when assessment requires motion information, for example, when sunglasses conceal the eyes. Further, a custom TensorFlow-based smartphone application shows the true impact of various approaches on inference times and demonstrates the effectiveness of real-time monitoring based on out-of-sample data to alert a drowsy driver. Our model is pre-trained on ImageNet and Kinetics and fine-tuned on a publicly available Driver Drowsiness Detection dataset. Fine-tuning on large naturalistic driving datasets could further improve accuracy to obtain robust in-vehicle performance. Overall, our research is a step towards practical deep learning applications, potentially preventing micro-sleeps and reducing road trauma.
-
Item
-
ItemNo Preview AvailableThe Paris end of town? Urban typology through machine learning.(American Association of Geographers, 2018)
-
ItemIdentifying behavioural change among drivers using Long Short-Term Memory recurrent neural networks(Elsevier, 2018)Globally, motor vehicle crashes account for over 1.2 million fatalities per year and are the leading cause of death for people aged 15–29 years. The majority of road crashes are caused by human error, with risk heightened among young and novice drivers learning to negotiate the complexities of the road environment. Direct feedback has been shown to have a positive impact on driving behaviour. Methods that could detect behavioural changes and therefore, positively reinforce safer driving during the early stages of driver licensing could have considerable road safety benefit. A new methodology is presented combining in-vehicle telematics technology, providing measurements forming a personalised driver profile, with neural networks to identify changes in driving behaviour. Using Long Short-Term Memory (LSTM) recurrent neural networks, individual drivers are identified based on their pattern of acceleration, deceleration and exceeding the speed limit. After model calibration, new, real-time data of the driver is supplied to the LSTM and, by monitoring prediction performance, one can assess whether a (positive or negative) change in driving behaviour is occurring over time. The paper highlights that the approach is robust to different neural network structures, data selections, calibration settings, and methodologies to select benchmarks for safe and unsafe driving. Presented case studies show additional model applications for investigating changes in driving behaviour among individuals following or during specific events (e.g., receipt of insurance renewal letters) and time periods (e.g., driving during holiday periods). The application of the presented methodology shows potential to form the basis of timely provision of direct feedback to drivers by telematics-based insurers. Such feedback may prevent internalisation of new, risky driving habits contributing to crash risk, potentially reducing deaths and injuries among young drivers as a result.