关键词: 语义分割, 轻量级, 实时性, 注意力机制, 感受野, 空洞卷积

Abstract: Semantic segmentation algorithms can classify images at the pixel level, and are widely used in fields such as unmanned driving, medical image processing, and industrial automation, and have important research value. The research of semantic segmentation algorithms focuses on three aspects: improving the accuracy of segmentation, reducing the amount of parameters and increasing the speed of inference. The lightweight semantic segmentation algorithm  ENet uses a multi-layer convolutional codec and a large number of dilated convolutions to avoid excessive downsampling and use of spatial information. Although it retains some spatial information integrity and large receptive field, the codec is bloated, the transmission of spatial information is poor, and the sensory field overflows and causes grid effect. Aiming at the above problems, this paper tailors the ENet algorithm structure, uses the attention mechanism and the pyramid dilated convolution to design spatial information transmission module, optimizes the algorithm structure, improves the algorithm receptive field, and completely transmits the spatial information transmission. The experimental results on public datasets Cityscapes and BDD100K show that the new module can improve the performance of the original algorithm with a smaller amount of parameters and calculations, which proves the redundancy of the original algorithm and the effectiveness of the designed module.

Key words: semantic segmentation, lightweight, real-time, attention mechanism, receptive field, dilated convolution