Road marking extraction in UAV imagery using attentive capsule feature pyramid network
Road marking extraction in UAV imagery using attentive capsule feature pyramid network
复制标题
使用注意力胶囊特征金字塔网络提取无人机图像中的道路标记
DOI：
10.1016/j.jag.2022.102677
复制
发表时间：
2022-01-22
影响因子：
7.5
通讯作者：
Li, Jonathan
中科院分区：
文献类型：
--
作者：
Guan, Haiyan;Lei, Xiangda;Li, Jonathan
从极高空间分辨率的无人机 (UAV) 图像中准确、精确地描绘道路标记面临着许多挑战，例如复杂的场景、不同的道路标记尺寸和形状以及道路标记的缺失和遮挡。为了解决这些问题，我们通过将具有注意机制的胶囊表示集成到特征金字塔网络（FPN）中，制定了注意胶囊特征金字塔网络（ACapsFPN），旨在提高道路标记提取的准确性。与当前基于标量神经元表示的卷积神经网络（CNN）模型不同，胶囊网络利用矢量胶囊神经元来表征实体特征，其长度和实例化参数有助于特征及其变体的识别。通过构建胶囊 FPN，ACapsFPN 能够提取和集成多层次、多尺度的胶囊特征，以提供高质量且语义强的特征抽象。通过制定多尺度上下文特征描述符和三元特征注意模块，ACapsFPN 可以强调信息特征以生成特定于类的特征表示。定量和定性评估表明，ACapsFPN 为在不同类型的复杂条件下提取无人机图像中的道路标记提供了一种有价值的手段。此外，与现有替代方案的比较分析也证明了 ACapsFPN 在无人机道路标记提取方面的优越性和鲁棒性。
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.