this is for holding javascript data
Paul St-Aubin edited Methodology Flow.tex
almost 10 years ago
Commit id: c2a6db6269ab815811a528ddba442370590806c0
deletions | additions
diff --git a/Methodology Flow.tex b/Methodology Flow.tex
index cf00627..c72481e 100644
--- a/Methodology Flow.tex
+++ b/Methodology Flow.tex
...
\subsection{Traffic Data}
Traffic flow data is
produced obtained from the
primary traffic data collection: automated analysis video data: vehicle trajectories extracted from video data using computer vision techniques built for traffic analysis applications. In this case, the computer vision tool used is the Traffic-Intelligence project, an open-source traffic-analysis software \cite{Jackson_2013}. See section \ref{data-size} for more details on the source
and size of
the data.
Trajectory data is formed from feature tracking of moving features within camera space. These feature tracks are a series of continuoisly
measures measured positions and velocity vectors mapped to real coordinates using a scene projection transformation by way of a homography matrix. These features are
continuous continuous, forming a path (trajectory) moving through space and time representing the movment of a vehicle
or other road user through the scene. Features are
clustered grouped together into objects using
algorithms specifically calibrated
algorithms for the task of identifying individual road users in
the a
scene. scene (though context-insentivive classification is still work in progress). Some
secondary-pass secondary filtering techniques were developped to automate validation and error correction
\cite{Jackson_2013}. \cite{Jackson_2013, St_Aubin_2014}.
Traffic flow
and flow ratios can be obtained by
counting performing counts on these objects according to the
traffic flow metric's context. context of the specific metric. In this case we collect per-lane per-hour counts over the time which the study is being conducted.
\subsubsection{Speed}
Speed is similarly obtained from trajectory data. It is derived from position observations between successive frames. It should be noted that a moving average filter of roughly 5 frames is applied to this data to correct for inaccuraies introduced by te pixels, but this still corresponds to speed measurements performed several times per second per object.
\subsubsection{Time-to-collision}
**Which TTC to use? Cross-reference the second TRB paper. There will be overlap on that content**