The increasing development of urban centers brings serious challenges for traffic management. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project’s aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to track in real-time multi-modal transportation while ensuring citizens’ privacy. The performance of the sensor was evaluated on a town center dataset. We also introduce the interoperable Agnosticity framework designed to collect, store and access data from multiple sensors, with results from two real-world experiments.

No abstract

Traffic emissions are a complex and variable cocktail of toxic chemicals. They are the major source of atmospheric pollution in the parts of cities where people live, commute and work. Reducing exposure requires information about the distribution and nature of emissions. Spatially and temporally detailed data are required, because both the rate of production and the composition of emissions vary significantly with time of day and with local changes in wind, traffic composition and flow. Increasing computer processing power means that models can accept highly detailed inputs of fleet, fuels and road networks. The state of the science models can simulate the behaviour and emissions of all the individual vehicles on a road network, with resolution of a second and tens of metres. The chemistry of the simulated emissions is also highly resolved, due to consideration of multiple engine processes, fuel evaporation and tyre wear. Good results can be achieved with both commercially available and open source models. The extent of a simulation is usually limited by processing capacity; the accuracy by the quality of traffic data. Recent studies have generated real time, detailed emissions data by using inputs from novel traffic sensing technologies and data from intelligent traffic systems (ITS). Increasingly, detailed pollution data is being combined with spatially resolved demographic or epidemiological data for targeted risk analyses.

No abstract

No abstract