update

main.tex

@@ -68,8 +68,6 @@ In recent years, fueled by advancements in deep learning and the availability of
                 \includegraphics[width=0.9\linewidth]{thsis_figure/anchor_demo/anchor_fix_learned.jpg}
                 \caption{}
         \end{subfigure}
-        %\qquad
-        %让图片换行，
 
         \begin{subfigure}{0.49\linewidth}
                 \centering
@@ -85,6 +83,160 @@ In recent years, fueled by advancements in deep learning and the availability of
         \label{anchor setting}
 \end{figure}
 
+
+
+\begin{figure}[t]
+        \centering
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/nms_demo/less_gt.jpg}
+                \caption{}
+        \end{subfigure}
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/nms_demo/less_pred.jpg}
+                \caption{}
+        \end{subfigure}
+
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/nms_demo/redun_gt.jpg}
+                \caption{}
+        \end{subfigure}
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/nms_demo/redun_pred.jpg}
+                \caption{}
+        \end{subfigure}
+        \caption{Comparision between different anchor thresholds in different scenarios. (a) Ground truth in dense scenario. (b) Predictions with large nms thresholds in dense scenario. (c) Ground truth in sparse scenario. (d) Predictions with small nms threshol in sparse scenario.}
+        \label{nms setting}
+\end{figure}
+
+
+
+\begin{figure}[t]
+        \centering
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/heatmap/cam1.jpg}
+                \caption{}
+        \end{subfigure}
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/heatmap/anchor1.jpg}
+                \caption{}
+        \end{subfigure}
+
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/heatmap/cam2.jpg}
+                \caption{}
+        \end{subfigure}
+        \begin{subfigure}{0.49\linewidth}
+                \centering
+                \includegraphics[width=0.9\linewidth]{thsis_figure/heatmap/anchor2.jpg}
+                \caption{}
+        \end{subfigure}
+        \caption{Comparision between different anchor thresholds in different scenarios. (a) Ground truth in dense scenario. (b) Predictions with large nms thresholds in dense scenario. (c) Ground truth in sparse scenario. (d) Predictions with small nms threshol in sparse scenario.}
+        \label{cam}
+\end{figure}
+
+
+\begin{figure*}[htbp]
+        \centering
+        \def\imgwidth{0.24\textwidth}
+
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun_gt.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun_pred50.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun_pred15.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun_nmsfree.jpg}
+        \end{minipage}\hfill
+        \vspace{0.5em}
+
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun2_gt.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun2_pred50.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun2_pred15.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/redun2_nmsfree.jpg}
+        \end{minipage}\hfill
+        \vspace{0.5em}
+
+
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less_gt.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less_pred50.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less_pred15.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less_nmsfree.jpg}
+        \end{minipage}\hfill
+        \vspace{0.5em}
+
+
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less2_gt.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less2_pred50.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less2_pred15.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/less2_nmsfree.jpg}
+        \end{minipage}\hfill
+        \vspace{0.5em}
+
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all_gt.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all_pred50.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all_pred15.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all_nmsfree.jpg}
+        \end{minipage}\hfill
+        \vspace{0.5em}
+
+
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all2_gt.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all2_pred50.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all2_pred15.jpg}
+        \end{minipage}\hfill
+        \begin{minipage}{0.24\textwidth}
+        \includegraphics[width=\linewidth]{thsis_figure/view_nms/all2_nmsfree.jpg}
+        \end{minipage}\hfill
+        \vspace{0.5em}
+
+    
+        \caption{hhh}
+    \end{figure*}
+
 Drawing inspiration from object detection methods such as Yolos and Fast RCNN, several anchor-based approaches have been introduced for lane detection, the representative work including LanesATT and CLRNet. These methods have demonstrated superior performance by leveraging anchor priors and enabling larger receptive fields for feature extraction. However, anchor-based methods encounter similar drawbacks as anchor-based general object detection method as follows:
 
 \begin{itemize} (1) A large amount of dense anchors should be configured to ensure the recall of detection result since the lane  distributions are complex in real scenarios (i.e the direction and the localtion), as the Fig. \ref{anchor setting}(a) shows.