Semantic segmentation is applied extensively in autonomous driving and intelligent transportation with methods that highly demand spatial and semantic information. Here, an STDC-MA network is proposed to meet these demands. First, the STDC-Seg structure is employed in STDC-MA to ensure a lightweight and efficient structure. Subsequently, the feature alignment module (FAM) is applied to understand the offset between high-level and low-level features, solving the problem of pixel offset related to upsampling on the high-level feature map. Our approach implements the effective fusion between high-level features and low-level features. A hierarchical multiscale attention mechanism is adopted to reveal the relationship among attention regions from two different input sizes of one image. Through this relationship, regions receiving much attention are integrated into the segmentation results, thereby reducing the unfocused regions of the input image and improving the effective utilization of multiscale features. STDC- MA maintains the segmentation speed as an STDC-Seg network while improving the segmentation accuracy of small objects. STDC-MA was verified on the verification set of Cityscapes. The segmentation result of STDC-MA attained 76.81% mIOU with the input of 0.5x scale, 3.61% higher than STDC-Seg.
翻译:在自主驾驶和智能交通中广泛应用语义分解,使用的方法高度要求空间和语义信息。在这里,建议建立STDC-MA网络以满足这些需求。首先,在STCD-MA中采用STDC-Seg结构,以确保轻量和高效结构。随后,应用特征校正模块(FAM)来理解高层次和低层次特征之间的抵消,解决高层次和低层次特征图上抽取的像素相抵问题。我们的方法是将高层次特征和低层次特征有效地融合在一起。采用了一个分级的多尺度关注机制,以揭示一个图像两种不同输入大小的受关注区域之间的关系。通过这种关系,将受到极大关注的区域纳入分解结果,从而减少了投入图像中未集中的区域,并改进了多层次特征的有效利用。 STDC-MA保持了分解速度作为STDC-Setri网络的分解速度,同时提高了小物体的分解精度。 STDC-MA在城市的校准设置上进行了核实。STDC-MA的分解结果是SDS-MA的0.81,比SAMI的0.81。