diff --git a/Article/Expe_auto/compTable.tex b/Article/Expe_auto/compTable.tex new file mode 100644 index 0000000000000000000000000000000000000000..58ec5511eaf2b901189f3e477b53d1435c5a5676 --- /dev/null +++ b/Article/Expe_auto/compTable.tex @@ -0,0 +1,20 @@ +\begin{tabular}{|l||r@{$\pm$}r|r@{$\pm$}r|r@{$\pm$}r|r@{$\pm$}r|r@{$\pm$}r|} +\hline +Measure $M$ & \multicolumn{2}{c|}{$T$ (ms)} & \multicolumn{2}{c|}{$C$ (\%)} +& \multicolumn{2}{c|}{$N$} +& \multicolumn{2}{c|}{$L$ (pixels)} & \multicolumn{2}{c|}{$L/N$ (pixels)} \\ +\hline +LSD +& 63.5 & 13.1 & 61.3 & 11.2 +& 536 & 194 & 17745 & 5364 & 34.6 & 8.0 \\ +ED-Lines +& & & 64.6 & 11.1 +& 568 & 210 & 19331 & 5694 & 35.9 & 8.9 \\ +CannyLines +& 75.5 & 11.7 & 60.6 & 10.6 +& 467 & 139 & 17678 & 4419 & 39.5 & 10.2 \\ +Our detector +& 66.6 & 14.8 & 65.8 & 9.3 +& 524 & 119 & 19210 & 3797 & 37.4 & 5.9 \\ +\hline +\end{tabular} diff --git a/Article/expeV2.tex b/Article/expeV2.tex index ae5503d4014f0c19513156f4405d4adf95c43153..ef100da8505b586fe97910a3d70a8728ae5f08f0 100755 --- a/Article/expeV2.tex +++ b/Article/expeV2.tex @@ -143,7 +143,6 @@ on the York Urban Database \cite{DenisAl08}.} \end{table} Globally the performance of the new detector are pretty similar to those -of the other ones, with seemingly a small advantage for the ground truth -cover. CannyLines provides longer lines and LSD is faster. +of the other ones. CannyLines provides longer lines and LSD is faster. But additionnaly, our detector provides an indication on the detected lines quality through the additional width parameter.