deletions | additions       diff --git a/Introduction.tex b/Introduction.tex  index 635fd2d..0684a72 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 urban mobility 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. This 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}. 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 methods for traffic data analysis; it is then not surprising that computer vision techniques have gained popularity given the potential of transforming the existing CCTV surveillance monitoring  infrastructure into a highly detailed traffic data collection tool to identify and study traffic behaviours. 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. 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 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:the  manual data collectionmethod  is costly and may not be reliable, and the definition and objective measurement of these events are difficult \cite{Chin_1997}. Today, with technological improvements in computing power, data storage, sensor technologies, and advances in artificial intelligence, these issues are quickly 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 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 10 m 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. This high-resolution data permits the measurement of precisely defined instantaneous surrogate safety measures identifying collision probability. One such measure is time-to-collision (TTC) which measures the time remaining remaining,  at any given instant to some collision point in the future defined by a and for any potential  collision course with another road user. user or a stationary obstacle, before the collision occurs.  This measure is useful as it provides the remaining a minimum reaction  time road users have 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. However, 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), 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 a further  justification. This approach does not natively provide a collision course probability, and it will 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 are have  being developed, including motion patterns which represent naturalistic (expected) driving behaviour learnt from the same data set. all other road users of a particular scene with corresponding initial conditions.  This procedure probabilistic approach  providesseveral potential collision points and their probability as  a function continuum  of both the characteristics of the specific site and the behaviour of the road users. The motion patterns, or the distribution of trajectories at a site and their probabilities, potential collision points. Motion patterns  may be described discretely over time and space \cite{St_Aubin_2014} or with prototype trajectories \cite{saunier07probabilistic}. The Some disadvantages of  motion and collision predictions 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(typically  subject to a the  time horizon). horizon.  Furthermore, interaction complexity and exposure tend to  increase exponentially as the number of simultaneous road users in a scene increases. For example, over the course of one day, a typical intersection can experience between 100 thousands and 100 increases varying anywhere from hundreds to  millions of these instantaneous interactions, depending on the intersection complexity. interactions per hour.  This paper presents presents, step-by-step,  a complete automated system for proactive road safety analysis that can deal with using  large amounts of video data. To the authors' knowledge, the presented system is the most comprehensive to be applied to such big a large amount of  data collected in the field for a real world traffic engineering study. A large video data set  wasdataset  collected at more than 20 roundabouts 40 roundabout weaving zones  in Queb{\'{e}}c across 20 different roundabouts  to study road user behaviour and their safety. Camera views record data at more than 40 roundabout corresponding safety using surrogate safety analysis. Roundabout  weaving zones, an zones are defined as the  area within the roundabout delimited by an entry approach  and the next following exit. Each camera records recorded  12 to 16 h hours  of video on a given typical  work day, which constitutes constituting  a dataset of over 600 470  hours of video data. Applying the proposed method to this large dataset yields yielded  considerable amounts of indicators, from individual road user measurements, e.g.\ e.g.  speed, to individual interaction measurements, e.g.\ e.g.  TTC, to aggregated indicators per road user or interaction, to aggregated indicators per site over time and space. Analysing such big data is a challenge of a magnitude that has never been undertaken before in driver behaviour and road safety research. It holds the key to understanding the processes that lead road users to collide, and to design and validate safety indicators that do not require accidents to occur. The approach will be demonstrated on this video dataset to identify roundabout characteristics that influence road safety. The paper is organized as follows: the next section presents the step-by-step  methodology, with practical examples drawn from the roundabout dataset, which is then applied to about half of the collected followed by video  data calibration results, safety indicator aggregation  and various system outputs are presented, before the conclusion prediction comparisons,  and discussion initial results  of future work. the complete roundabout study.