deletions | additions       diff --git a/Results.tex b/Results.tex  index e43a091..fb64e6f 100644  --- a/Results.tex  +++ b/Results.tex 
...
\subsection{Data Sizes}  In total, 600 hours of video data were collected, 50\% 50~\%  of which has been fully processed at this time. This represents driving data for over 50,000 unique drivers. At 30 frames per second, a data collection at an intersection over a period of 12 hours (e.g. 7 AM to 7 PM), over a driving distance of 50 metres and at an average driving speed of 30 km/h, and with an average hourly flowrate of 500 veh/h yields approximatly 1,080,000 instantaneous grouped observations. Additionally, each of these observations can have anywhere between 3 to 100 feature tracks associated with. The recommended number of features to aim for is roughly 15-20 per object: object over time:  this yields manageble manageable  data sizes (roughly 500 MB of storage per hour of video) while maintinging and adequate level of data richness and object representation. Video storage needs will vary greatly by camera choice, resolution, framerate, and video encoding settings. Figure~\ref{fig:interaction-sizes} shows the orders of magnitude of the interactions observed in the various sites.   \subsection{Processing Times}  Most of the analysis is conducted on a pair of dedicated consumer-grade high-performance machines, with some work offloaded to a computing cluster. Feature tracking performance depends on video resolution and special post-processing such as stabilisation or lens undistortion. A typical one hour 800*600 video is processed with current technology in about an hour. A typical one hour 1280*960 video with undistortion can be processed in about two hours. Basic analysis on one of these trajectory sequences takes between 5 minutes and 30 minutes, depending on traffic in the scene, while conflict analysis, particularly motion patterns, can typically take anywhere between 1 to 48 hours to complete. Conflict analysis processing times are very  sensitive to the interaction complexity of the scene.