diff options
| -rw-r--r-- | experimental.tex | 51 |
1 files changed, 45 insertions, 6 deletions
diff --git a/experimental.tex b/experimental.tex index 2f4d6d4..127cd78 100644 --- a/experimental.tex +++ b/experimental.tex @@ -36,14 +36,13 @@ a skeleton was detected by the Microsoft SDK. For each frames the following data is available: \begin{itemize} \item the 3D coordinates of 20 body joints -\item the z-value: this is the distance from the detected skeleton to - the camera +\item a picture recored by the video camera \end{itemize} -For some of frames, one or several joints were occluded by another -part of the body. In those cases, the coordinates of these joints are +For some of frames, one or several joints are occluded by another part +of the body. In those cases, the coordinates of these joints are either absent from the frame or present but tagged as \emph{Inferred} -by the Microsoft SDK. It means that even though the joint was not -present on the frame, the skeleton-fitting algorithm was able to guess +by the Microsoft SDK. It means that even though the joint is not +present on the frame, the skeleton-fitting algorithm is able to guess its location. Each frame also has a skeleton ID number. If this numbers stays the @@ -52,6 +51,46 @@ algorithm was able to detect the skeleton in a contiguous way. This allows us to define the concept of a \emph{run}: a sequence of frames with the same skeleton ID. +Ground truth person recognition is obtained by manually labelling each +run based on the images captured by the video camera of the +Kinect. For ease of labelling, only the runs with people walking +toward the camera are kept. These are the runs where the average +distance from the skeleton joints to the camera is increasing. + +Several reductions are then applied to the data set to extract +\emph{features} from the raw data: +\begin{itemize} +\item from the joints coordinates, the lengths of 15 body parts are + computed. These are distances between two contiguous joints in the + human body. If one of the two joints of a body part is not present + or inferred in a frame, the corresponding body part is reported as + absent for that frame. +\item the number of features is then reduced to 9 by using the + vertical symmetry of the human body: if two body parts are symmetric + about the vertical axis, we bundle them into one feature by + averaging their lengths. If only one of them is present, we take the + value of its counterpart. If none of them are present, the feature + is reported as missing for this frame. The resulting nine features + are: Head-ShoulderCenter, ShoulderCenter-Shoulder, Shoulder-Elbow, + Elbow-Wrist, ShoulderCenter-Spine, Spine-HipCenter, + HipCenter-HipSide, HipSide-Knee, Knee-Ankle. +\item finally, all the frames where one of the 9 features is missing + are filtered out. +\end{itemize} + +Table \ref{tab:dataset} summarizes some statistics about the resulting +dataset. + +\begin{table} +\begin{tabular}{cc} + +\end{tabular} +\caption{} +\label{tab:dataset} +\end{table} + + + %%% Local Variables: |