Faculty of Agriculture, Yamagata University, Tsuruoka 997-8555, Japan.
Faculty of Natural Sciences, Leibniz Universität, 30167 Hannover, Germany.
Sensors (Basel). 2021 Jan 11;21(2):471. doi: 10.3390/s21020471.
Invasive blueberry species endanger the sensitive environment of wetlands and protection laws call for management measures. Therefore, methods are needed to identify blueberry bushes, locate them, and characterise their distribution and properties with a minimum of disturbance. UAVs (Unmanned Aerial Vehicles) and image analysis have become important tools for classification and detection approaches. In this study, techniques, such as GIS (Geographical Information Systems) and deep learning, were combined in order to detect invasive blueberry species in wetland environments. Images that were collected by UAV were used to produce orthomosaics, which were analysed to produce maps of blueberry location, distribution, and spread in each study site, as well as bush height and area information. Deep learning networks were used with transfer learning and unfrozen weights in order to automatically detect blueberry bushes reaching True Positive Values (TPV) of 93.83% and an Overall Accuracy (OA) of 98.83%. A refinement of the result masks reached a Dice of 0.624. This study provides an efficient and effective methodology to study wetlands while using different techniques.
入侵性的越橘属物种危及湿地的敏感环境，保护法呼吁采取管理措施。因此，需要采用一些方法来识别越橘灌丛，定位它们，并在最小干扰的情况下描述它们的分布和特性。无人机 (Unmanned Aerial Vehicles) 和图像分析已成为分类和检测方法的重要工具。在这项研究中，地理信息系统 (GIS) 和深度学习等技术被结合起来，以便在湿地环境中检测入侵性的越橘属物种。利用无人机采集的图像制作正射镶嵌图，然后对其进行分析，以生成每个研究地点的越橘属位置、分布和扩散图，以及灌丛高度和面积信息。使用迁移学习和解冻权重的深度学习网络，自动检测越橘属灌丛的 True Positive Values (TPV) 达到 93.83%，Overall Accuracy (OA) 达到 98.83%。对结果掩模进行细化，得到了 Dice 为 0.624。本研究提供了一种高效、有效的方法来研究湿地，同时使用了不同的技术。
