Semantic segmentation of road elements in 2D images is a crucial task in the recognition of some static objects such as lane lines and free space. In this paper, we propose DHSNet,which extracts the objects features with a end-to-end architecture along with a heatmap proposal. Deformable convolutions are also utilized in the proposed network. The DHSNet finely combines low-level feature maps with high-level ones by using upsampling operators as well as downsampling operators in a U-shape manner. Besides, DHSNet also aims to capture static objects of various shapes and scales. We also predict a proposal heatmap to detect the proposal points for more accurate target aiming in the network.

翻译：二维图像中道路元素的语义分割是识别车道线和自由空间等静态物体的关键任务。本文提出DHSNet，该网络通过端到端架构结合热图建议来提取目标特征。所提出的网络还采用了可变形卷积。DHSNet通过U形结构中的上采样和下采样算子，将低层特征图与高层特征图精细融合。此外，DHSNet还旨在捕捉各种形状和尺度的静态物体。我们还预测了建议热图以检测建议点，从而在网络中实现更精确的目标定位。