跳到主要导航 跳到搜索 跳到主要内容

Road marking extraction in UAV imagery using attentive capsule feature pyramid network

  • Haiyan Guan*
  • , Xiangda Lei
  • , Yongtao Yu
  • , Haohao Zhao
  • , Daifeng Peng
  • , José Marcato Junior
  • , Jonathan Li
  • *此作品的通讯作者
  • Nanjing University of Information Science & Technology
  • Huaiyin Institute of Technology
  • Universidade Federal de Mato Grosso do Sul
  • University of Waterloo

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Accurately and precisely delineating road-markings from very high spatial resolution unmanned aerial vehicle (UAV) images face many challenges, such as complex scenarios, diverse road marking sizes and shapes, and absent and occluded road markings. To address these issues, we formulate an attentive capsule feature pyramid network (ACapsFPN) by integrating capsule representations with attention mechanisms into the feature pyramid network (FPN), aiming at improving road marking extraction accuracy. Different from the current convolutional neural network (CNN) models based on scalar neuron representations, capsule networks characterize entity features by leveraging vectorial capsule neurons, whose lengths and instantiation parameters contribute to the identification of features and their variants. By constructing a capsule FPN, the ACapsFPN is capable of extracting and integrating multi-level and multi-scale capsule features to provide high-quality and semantically-strong feature abstractions. By formulating a multi-scale context feature descriptor and the ternary feature attention modules, the ACapsFPN can emphasize informative features to generate a class-specific feature representation. Quantitative and qualitative evaluations show the ACapsFPN provides a valuable means for extracting road markings in UAV images under different kinds of complex conditions. In addition, comparative analyses with existing alternatives also demonstrate the superiority and robustness of the ACapsFPN in UAV road marking extraction.

源语言英语
期刊论文编号102677
期刊International Journal of Applied Earth Observation and Geoinformation
卷107
DOI
出版状态已出版 - 3月 2022
已对外发布是

学术指纹

探究 'Road marking extraction in UAV imagery using attentive capsule feature pyramid network' 的科研主题。它们共同构成独一无二的学术指纹。

引用此