this is for holding javascript data
Paul St-Aubin edited Methodology.tex
over 9 years ago
Commit id: 406328ea8555a881019c3767011e3a83b23b48cf
deletions | additions
diff --git a/Methodology.tex b/Methodology.tex
index 333a056..9d08205 100644
--- a/Methodology.tex
+++ b/Methodology.tex
...
\subsection{Overview}
Figure~\ref{fig:1} outlines the general data collection and analysis
framework. For a given research mandate, factors are selected for testing and a set of video methodology. Video data is collected
for the study: for a cross-sectional study, at a
sample number of sites with adequate representation of
these factors, while controlling for as many other contributing factors
as possible. and controlled external factors; for a before-after study, at one or more sites before and after a change in contributing factors. With scene data and camera calibration parameters, feature tracking
can be is performed to extract
road user trajectories. The trajectories are
raw in the form of spatial-temporal position data of moving objects within the scene. This positional data is
then processed to obtain derived measures such as speed, heading and acceleration. Finally,
scene information can be added to obtain higher-level data, data is analysed and interpreted in a variety of ways: i) simple summaries such as average speed, counts; ii) generalised spatial relationship analysis, such as
movements referenced by lane, conflict
measures, and other analysis; iii) or high-level interpretation
behavioural measures (specific which attaches additional scene information (typically specific to the
study). study) to trajectories such as summaries by lane, at specific locations, gap times, motor vehicle infractions, etc. With a large amount of potential contributing factors (e.g. site characteristics), it may be beneficial to apply site clustering techniques before initiating behavioural measure correlation.