Estimation of Abundance and Distribution of Salt Marsh Plants from Images Using Deep Learning
Estimation of Abundance and Distribution of Salt Marsh Plants from Images Using Deep Learning
复制标题
DOI：
10.1109/icpr48806.2021.9412264
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
J. Parashar;S. Bhandarkar;J. Simon;B. Hopkinson;S. Pennings
中科院分区：
文献类型：
--
作者：
J. Parashar;S. Bhandarkar;J. Simon;B. Hopkinson;S. Pennings
计算机视觉和机器学习领域的最新进展，尤其是深度卷积神经网络（CNN），被用来识别和定位盐沼图像中的各种植物物种。三种不同的方法进行了探讨，提供了不同层次的粒度定义的空间分辨率的丰度和空间分布的估计。在粗粒度的方法中，CNN的任务是识别盐沼图像中的六种植物物种中的哪一种存在/不存在。具有不同拓扑特性和注意力机制的CNN能够为更丰富的植物物种提供> 90%的精确度和召回率的准确估计，并降低不太常见的植物物种的性能。每个植物物种的覆盖百分比的估计是以更精细的空间分辨率进行的，其中提取较小的图像块，并且CNN的任务是识别图像块中心的植物物种或基质。对于覆盖率估计任务，观察到CNN表现出与存在/不存在估计任务类似的性能特征，但精度和召回率降低了10%-10%。最后，细粒度的估计的各种植物物种的空间分布进行通过语义分割。据观察，DeepLab-V3语义分割架构可以为丰富的植物物种提供非常准确的估计，但对于不太丰富的植物物种，性能会显着下降;在极端情况下，稀有植物类别被完全忽略。总体而言，CNN估计质量和基本估计的空间分辨率之间观察到一个明确的权衡，从而为基于CNN的方法在盐沼图像中自动植物识别和定位的生态应用提供指导。
Recent advances in computer vision and machine learning, most notably deep convolutional neural networks (CNNs), are exploited to identify and localize various plant species in salt marsh images. Three different approaches are explored that provide estimations of abundance and spatial distribution at varying levels of granularity defined by spatial resolution. In the coarsest-grained approach, CNNs are tasked with identifying which of six plant species are present/absent in large patches within the salt marsh images. CNNs with diverse topological properties and attention mechanisms are shown capable of providing accurate estimations with > 90 % precision and recall for the more abundant plant species and reduced performance for less common plant species. Estimation of percent cover of each plant species is performed at a finer spatial resolution, where smaller image patches are extracted and the CNNs tasked with identifying the plant species or substrate at the center of the image patch. For the percent cover estimation task, the CNNs are observed to exhibit a performance profile similar to that for the presence/absence estimation task, but with an ≈ 5%-10% reduction in precision and recall. Finally, fine-grained estimation of the spatial distribution of the various plant species is performed via semantic segmentation. The DeepLab-V3 semantic segmentation architecture is observed to provide very accurate estimations for abundant plant species, but with significant performance degradation for less abundant plant species; in extreme cases, rare plant classes are seen to be ignored entirely. Overall, a clear trade-off is observed between the CNN estimation quality and the spatial resolution of the underlying estimation thereby offering guidance for ecological applications of CNN-based approaches to automated plant identification and localization in salt marsh images.