diff options
| -rw-r--r-- | experimental.tex | 6 | ||||
| -rw-r--r-- | uniqueness.tex | 16 |
2 files changed, 11 insertions, 11 deletions
diff --git a/experimental.tex b/experimental.tex index d03763b..8085321 100644 --- a/experimental.tex +++ b/experimental.tex @@ -47,7 +47,7 @@ outputs a set of joints in real world coordinates. The view of the Kinect is seen in \fref{fig:hallway}, showing the color image, the depth image with figures, and the fitted skeleton of a person in a single frame. Skeletons are fit from roughly 1-5 meters away from the Kinect. For each frame with a -skelton we record color image and the positions of the joints. +skeleton we record color image and the positions of the joints. \begin{figure}[t] \begin{center} @@ -232,14 +232,14 @@ building. %run. We only evaluate SHT in this setting since it already takes consecutive frames into account and because it performed better than MoG in the offline setting -(\ref{sec:experiment:offline}). We partition the dataset into 10 time +(\xref{sec:experiment:offline}). We partition the dataset into 10 time sequences of equal size. For a given threshold, the algorithm is trained and tested incrementally: train on the first $k$ sequences (in the chronological order) and test on the $(k+1)$-th sequence. \fref{fig:online} shows the prediction-recall curve when averaging the prediction rate over the 10 incremental experiments. Overall performance is worse than in \fref{fig:offline:sht} since the system trains on less data than in -\ref{sec:experiment:offline} in all but the last step. We still see +\xref{sec:experiment:offline} in all but the last step. We still see recognition rates mostly above 90\% for group sizes of 3 and 5. \begin{figure}[t] diff --git a/uniqueness.tex b/uniqueness.tex index 8f0b369..6c90310 100644 --- a/uniqueness.tex +++ b/uniqueness.tex @@ -52,7 +52,7 @@ each measurement of the pairs. \subsection{Results} We evaluate the performance of the pair-matching problem on the -dataset by using a proximity threshold algorithm: for a given +dataset by using a nearest neighbor algorithm: for a given threshold, a pair will be classified as \emph{matched} if the Euclidean distance between the two skeletons is lower than the threshold, and \emph{unmatched} otherwise. Formally, let @@ -77,18 +77,18 @@ output of the algorithm for the threshold $\delta$ is defined as: \label{fig:roc} \end{figure} -Figure \ref{fig:roc} shows the ROC curve of the proximity threshold +Figure \ref{fig:roc} shows the ROC curve of the nearest neighbor algorithm for different values of the standard deviation of the noise, as well as the ROC of the best performing face detection algorithm in the image-restricted LFW benchmark: \emph{Associate-Predict} \cite{associate}. -The results show that with a standard deviation of 3mm, skeleton -proximity thresholding performs quite similarly to face detection at -low false-positive rate. At this noise level, the error is smaller -than 1cm with 99.9\% probability. Even with a standard deviation of -5mm, it is still possible to detect 90\% of the matched pairs with a -false positive rate of 6\%. +The results show that with a standard deviation of 3mm, nearest +neighbor performs quite similarly to face detection at low +false-positive rate. At this noise level, the error is smaller than +1cm with 99.9\% probability. Even with a standard deviation of 5mm, it +is still possible to detect 90\% of the matched pairs with a false +positive rate of 6\%. This experiment gives an idea of the noise variance level above which it is not possible to consistently distinguish skeletons. If the noise |