wsq/polarrcnn-thesis
1
1
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
王老板 2024-09-28 10:49:55 +08:00
parent 7f069ea240
commit d8dc64042c
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
main.tex
View File

@ -246,7 +246,7 @@ where $\boldsymbol{c}^{l}_{j} \in \mathbb{R}^{2}$ and $\boldsymbol{c}^{g} \in \m
x_{i,j}&=-y_{i,j}\tan \theta_j +\frac{r^{g}_j}{\cos \theta_j},\label{positions}\\ x_{i,j}&=-y_{i,j}\tan \theta_j +\frac{r^{g}_j}{\cos \theta_j},\label{positions}\\
i&=1,2,\cdots,N_p,\notag i&=1,2,\cdots,N_p,\notag
\end{align} \end{align}
where the y-coordinates $\{y_{1,j}, y_{2,j},\cdots,y_{N,j}\}$ of the $j$-th lane anchor are uniformly sampled vertically from the image, as previously mentioned. where the y-coordinates $\{y_{1,j}, y_{2,j},\cdots,y_{N_p,j}\}$ of the $j$-th lane anchor are uniformly sampled vertically from the image, as previously mentioned.
\par \par
Given the feature maps $P_1, P_2, P_3$ from FPN, we can extract feature vectors corresponding to the positions of feature points $\{(x_{1,j},y_{1,j}),(x_{2,j},y_{2,j}),\cdots,(x_{N,j},y_{N,j})\}_{j=1}^{N^{lpm}_{pos}}$, respectively denoted as $\boldsymbol{F}_{1}, \boldsymbol{F}_{2}, \boldsymbol{F}_{3}\in \mathbb{R} ^{N^{lpm}_{pos}\times C_f}$. To enhance representation, similar to \cite{detr}, we employ a weighted sum strategy to combine features from different levels as Given the feature maps $P_1, P_2, P_3$ from FPN, we can extract feature vectors corresponding to the positions of feature points $\{(x_{1,j},y_{1,j}),(x_{2,j},y_{2,j}),\cdots,(x_{N,j},y_{N,j})\}_{j=1}^{N^{lpm}_{pos}}$, respectively denoted as $\boldsymbol{F}_{1}, \boldsymbol{F}_{2}, \boldsymbol{F}_{3}\in \mathbb{R} ^{N^{lpm}_{pos}\times C_f}$. To enhance representation, similar to \cite{detr}, we employ a weighted sum strategy to combine features from different levels as
\begin{equation} \begin{equation}