deletions | additions       diff --git a/Introduction.tex b/Introduction.tex  index 6149f13..cc1f22e 100644  --- a/Introduction.tex  +++ b/Introduction.tex 
...
\section{Introduction}  Affordable computing and flexible and inexpensive sensor technology are transforming the current practice and methods for traffic data collection, monitoring and analysis: big data is changing how we interact with our environment and how we approach problem solving tasks in the field of transportation. This should come to no surprise as the complexity and pervasiveness in daily life of urban mobility lends itself naturally to large amounts of data. In this context, the use of mobile and/or fixed video sensors for traffic monitoring and data collection is becoming a common practice not only for freeways but also for urban streets. Early and notable examples include the NGSIM project which included a dataset of extracted trajectories from video data of a 1~km stretch of freeway \cite{Kim_2005} and the SAVEME project which fielded a small but early implementation of video tracking for surrogate safety analysis \cite{Ervin_2000} \cite{Gordon_2012}. The availability of such large data sets opens up possibilities for more dynamic traffic load balancing and congestion easing of road networks and in return provides researchers with participatory network usage data collection. This new situation in which traffic data is being collected intensively demands more intelligent and advanced automated  methods for traffic data analysis; it is then not surprising that computer vision techniques have gained popularity given the their  potential of for  transforming the existing CCTVmonitoring  infrastructure into a highly detailed traffic data collection tool to identify and study traffic behaviours. Furthermore, the CCTV infrastructure can be complimented with inexpensive consumer-grade video sensors \cite{Jackson_2013}.  One such behavioural study application is in proactive road safety diagnosis. This has been a long-standing goal in the field of transportation safety. Traditional statistical methods applied to accident data require long observation periods (years of crash data): one must wait for (enough) accidents to occur in this time. Beginning in the 1960s, attempts were made to predict collision rates based on observations without a collision rather than historical accident records \cite{Perkins_1968}: these methods are now termed surrogate safety methods. The Traffic Conflict Technique (TCT) was one of the earliest methods proposed which entailed the observation of quasi-collision events: situations in which road users were exposed to some recognizable risk (probability) of collision, e.g. a {\textquotedblleft}near-miss{\textquotedblright}. However, several problems limited their adoption: manual data collection is costly and may not be reliable, and the definition and objective measurement of these events are difficult were lacking  \cite{Chin_1997}. Today, with technological improvements in computing power, data storage, sensor technologies, and advances in artificial intelligence, these issues are quickly rapidly  being addressed. This research presents the application of a video-based automated trajectory analysis solution which combines the latest advances in high-resolution traffic data acquisition \cite{Saunier_2010} and machine learning methods to model and predict collision potential \cite{Mohamed_2013, St_Aubin_2014}  from relatively short, but extremely rich traffic data. This data is typically obtained from ordinary video data via computer vision from a camera situated at 5~metres or more above the roadway \cite{Jackson_2013}. This trajectory data consists of position and velocity measurements of road users captured 15 to 30 times per second to a relatively high degree of accuracy. This amounts to several million individual instantaneous measurements over the period of one day at a typical site. site (each camera).  This The capture of  high-resolution data permits the measurement of precisely defined instantaneous surrogate safety measures for the purpose of  identifying collision probability. potential for collision.  One such measure is time-to-collision Time-to-Collision  (TTC) which measures the time remaining, at any given instant and for any potential collision course with another road user or a stationary obstacle, before the collision occurs. This measure is useful as it provides a minimum reaction time required for drivers to react to and avoid a potential collisions. Higher TTCs are generally considered safer, though the precise link has yet to be validated in part because the potential for collision is poorly established and defined in the literature. In fact, this measure relies on motion prediction hypotheses to identify potential collision courses. The traditional approach is to use constant velocity projection \cite{Amundsen_1977} \cite{Laureshyn_2010} (situations in which road users fail to correct their course for some reason or another and are subject to Newton's first law of motion), which is the motion prediction method most frequently used, often without further justification. This approach does not natively provide a collision course probability, and it is not be suitable in situations where observed trajectories do no include constant velocity displacements: for example, turning lanes in an intersection and movements in a roundabout. More advanced collision course modelling efforts have being developed, including motion patterns which represent naturalistic (expected) driving behaviour learnt from all other road users of a particular scene with corresponding initial conditions. This probabilistic approach provides a continuum of potential collision points. Motion patterns may be described discretely over time and space \cite{St_Aubin_2014} or with prototype trajectories \cite{saunier07probabilistic}. Some disadvantages of motion patterns are that they are limited in time-horizon (maximum calculable TTC) and computationally intensive as they explore, for each pair of road users, at each point in time, all future positions in time and space subject to the time horizon. Furthermore, interaction complexity and exposure tend to increase exponentially as the number of simultaneous road users in a scene increases varying anywhere from hundreds to millions of interactions per hour.