基于轻量级Transformer的城市路网提取方法

Urban road network extraction method based on lightweight Transformer

针对现有方法存在道路区域提取不精准和实时性不足的限制,提出基于轻量级Transformer的路网提取方法RoadViT.利用卷积神经网络与Transformer混合的MobileViT架构进行编码特征,有效地提取高级上下文信息.提出金字塔解码器实现多尺度特征的提取和融合,生成像素类别的概率分布.结合Mosaic与多尺度缩放和随机裁剪策略实现数据增强,构建精细多样的遥感图像.针对城市遥感图像中道路类别和背景类别的不平衡问题,提出动态加权损失函数.实验结果表明,RoadViT的参数量仅为1.25×10^(6),在Jetson TX2上的推理速度可达10帧/s,在CHN6-CUG数据集上的精度可达57.0%.所提方法是轻量级Transformer在城市遥感图像中的有效探索,在保证推理实时性的同时,实现道路提取精度的提升.

A road network extraction method based on a lightweight Transformer was proposed,named RoadViT aiming at some limitations of the existing methods,such as imprecise road region extraction and limited real-time performance.The MobileViT architecture which could mix convolutional neural networks and the Transformer was used to encode features in order to efficiently extract high-level context information.Then a pyramid decoder was proposed to implement the extraction and fusion of multi-scale features,and the probability distribution of pixel categories was generated.The Mosaic method was combined with multi-scale scaling and random cropping strategies to implement data enhancement,which could construct fine and various remote sensing images.A dynamic weighting loss function was proposed to mitigate the problem according to the imbalance between the road category and background category in urban remote sensing images.The experimental results show that RoadViT,with a number of parameters of only 1.25×10^(6),can achieve an inference speed of up to 10 frames in a second on the Jetson TX2,and an accuracy of up to 57.0%on the CHN6-CUG dataset.The proposed method is an effective exploration of the lightweight Transformer in urban remote sensing images,which can achieve improved road extraction accuracy while maintaining the real-time performance of inference.