摘要
为提取空间特征更细节和语义信息更全面的道路信息,提高道路信息提取的推理速度,在端到端的卷积神经网络(convolutional neural network,CNN)基础上,提出一种结合空间注意力机制、全局信息感知和特征融合模块的道路提取模型.首先利用空间注意力机制和全局信息感知模块获取道路特征的上下文信息,提高浅层特征的空间信息表达能力;然后构建顾及通道和语义信息的特征融合模块,消除基于端到端的CNN中浅层和深层特征之间的语义差距,完成跨层特征的有效融合;最后使用多层次知识蒸馏学习策略,减少并降低所提模型的网络参数和计算复杂度,快速、准确地获取遥感影像中的道路信息.在公开的Deep Globe和马萨诸塞州2个卫星遥感影像道路数据集,以及京津新城无人机遥感影像道路数据集上进行训练、验证和评估的实验结果表明,所提模型是一种精度高、效果好的道路提取模型,无论是卫星遥感数据源还是无人机遥感数据源均具有较好的道路信息提取能力,其F1分别达到79.36%,78.42%和84.27%,均优于对比的道路提取模型;同时,多层次知识蒸馏学习策略能显著地提高模型的精度、提升泛化能力,其IOU值分别提高0.29,0.77和0.46个百分点,在模型精度和网络参数方面都取得了较优的效果,具有广阔的应用前景.
Based on an end-to-end convolutional neural network(CNN),the paper proposed a road extraction model combining spatial attention mechanism,global information perception,and feature fusion module.It can extract road information with detailed spatial features and comprehensive semantic information and improve the inference speed of road information extraction.Firstly,the spatial attention mechanism and global information awareness module were used to obtain road contextual information and improve the spatial information representation of low-level features.Secondly,the feature fusion module was built to consider the channel and semantic information to eliminate the semantic gap between low-and high-level features.Finally,the multilevel knowledge distillation learning strategy was used to reduce network parameters and computational complexity to obtain road information quickly and accurately.The training,validation,and evaluation were conducted on the Deep Globe,Massachusetts,and Beijing-Tianjin New Town remote sensing image road datasets.The results show that the proposed model provides high accuracy and a suitable extraction effect.It achieves excellent road information extraction ability both in satellite remote sensing data sources and UAV remote sensing data sources.The F1 scores reach 79.36%,78.42%,and 84.27%,respectively,outperforming other road extraction models.Meanwhile,the multilevel knowledge distillation learning strategy significantly improves the accuracy and generalization ability of the model.The index IOU values were improved by 0.29,0.77,and 0.46 percentage points,respectively.It achieves better results regarding model accuracy and network parameters and has broad application prospects.
作者
王勇
曾祥强
曾俊铖
黄开青
叶虎平
甘宏
陈宇焜
Wang Yong;Zeng Xiangqiang;Zeng Juncheng;Huang Kaiqing;Ye Huping;Gan Hong;Chen Yukun(State Key Laboratory of Resources and Environmental Information System,Institute of Geographic Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101;College of Resources and Environment,University of Chinese Academy of Sciences,Beijing 100049;Fujian Expressway Science&Technology Innovation Research Institute Co.,Ltd.,Fuzhou 350001;Fujian Luoning Expressway Co.,Ltd.,Fuzhou 350600)
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2023年第10期1541-1553,共13页
Journal of Computer-Aided Design & Computer Graphics
基金
福建省高速公路科技计划(2022HZ022002)
国家重点研发计划(2022YFC3800700)
中国科学院战略性先导科技专项(XDA28050200)
第三次新疆综合科学考察项目(2021xjkk1402).
关键词
深度学习
遥感影像
道路提取
特征感知融合
知识蒸馏
deep learning
remote sensing
road extraction
feature awareness fusion
knowledge distillation
