摘要： 实时语义分割作为计算机视觉领域的核心任务之一,在无人驾驶、交通管控等诸多方面均发挥着极为关键的作用。现有基于编码器-解码器结构的实时语义分割算法通常通过牺牲分割精度来达到实时效果,然而,这类算法为了保证实时性,其感受野通常较小,从而导致对道路场景中的大尺度物体分割效果较差。为此,基于编码器-解码器结构,提出一种针对道路场景的实时语义分割算法。首先,在特征提取阶段设计一个多尺度特征融合(MFF)机制,对较大尺度内的感受野特征进行有效融合,提升对大尺度物体的分割效果;然后,在编码器末端融入一个极化自注意力(PSA)机制,增强大尺度感受野中的局部感知,进一步提升对大尺度物体的分割效果。在数据集Cityscapes与Camvid上进行测试,实验结果表明,采用单个NVIDIA RTX 3090 GPU时,该算法在43.5 帧/s和91.2 帧/s的帧率下分别取得了80.6%和81.1%的平均交并比(MIoU),相较对比算法获得了更高的分割精度。

关键词: 语义分割, 编码器-解码器结构, 多尺度特征融合, 自注意力机制, 大尺度物体

Abstract: Real-time semantic segmentation, one of the core tasks in computer vision, plays a crucial role in various applications such as autonomous driving and traffic control. Existing real-time semantic segmentation algorithms based on the encoder—decoder structure often sacrifice segmentation accuracy to achieve real-time performance. However, to ensure real-time performance, these algorithms typically have a small receptive field, resulting in poor segmentation performance for large-scale objects in road scenes. To address this issue, this paper proposes a real-time semantic segmentation algorithm tailored for road scenes based on the encoder—decoder structure. First, a Multi-scale Feature Fusion (MFF) mechanism is designed in the feature extraction stage to effectively fuse receptive field features on a larger scale, thereby enhancing the segmentation performance for large-scale objects. Second, a Polarized Self-Attention (PSA) mechanism is incorporated at the end of the encoder to enhance the local perception within the large-scale receptive field, further improving the segmentation performance for large-scale objects. Experimental results on the Cityscapes and Camvid datasets show that, when using a single NVIDIA RTX 3090 GPU, the algorithm achieves Mean Intersection over Union (MIoU) scores of 80.6% and 81.1% at frame rates of 43.5 frame/s and 91.2 frame/s, respectively. These results show that the proposed algorithm achieves higher segmentation accuracy than the comparative algorithm.

Key words: semantic segmentation, encoder—decoder structure, Multi-scale Feature Fusion (MFF), self-attention mechanism, large-scale objects

中图分类号: 

• TP391