Multisensor Data Fusion for Improved Segmentation of Individual Tree Crowns in Dense Tropical Forests
Multisensor Data Fusion for Improved Segmentation of Individual Tree Crowns in Dense Tropical Forests
复制标题
DOI：
10.1109/jstars.2021.3069159
复制
发表时间：
2021-01-01
影响因子：
5.5
通讯作者：
Vincent, Gregoire
中科院分区：
文献类型：
--
作者：
Aubry-Kientz, Melaine;Laybros, Anthony;Vincent, Gregoire
从遥感数据的树冠自动分割是特别具有挑战性的，在密集的，多样的，多层的热带森林冠层，并跟踪死亡率，这种方法是更加困难的。在这里，我们研究的潜力相结合的机载激光扫描（ALS）与多光谱和高光谱数据，以提高树冠分割的准确性在法属圭亚那的一个研究地点。我们将ALS点云聚类方法与光谱深度学习模型相结合，在识别手动分割的参考牙冠时实现了83%的准确率（一致性>0.5）。该方法优于两步过程，该过程涉及对ALS点云进行聚类，然后使用高光谱距离的逻辑回归来校正过度分割。我们使用这种方法来映射重复调查的树木死亡率，并表明，在第一次确定的树冠高度损失集群是一个很好的估计，在这些地区的死树的数量。我们的研究结果表明，多传感器数据融合提高了自动分割的个别树冠，并提出了一个很有前途的途径，研究森林人口与重复遥感收购。
Automatic tree crown segmentation from remote sensing data is especially challenging in dense, diverse, and multilayered tropical forest canopies, and tracking mortality by this approach is even more difficult. Here, we examine the potential for combining airborne laser scanning (ALS) with multispectral and hyperspectral data to improve the accuracy of tree crown segmentation at a study site in French Guiana. We combined an ALS point cloud clustering method with a spectral deep learning model to achieve 83% accuracy at recognizing manually segmented reference crowns (with congruence >0.5). This method outperformed a two-step process that involved clustering the ALS point cloud and then using the logistic regression of hyperspectral distances to correct oversegmentation. We used this approach to map tree mortality from repeat surveys and show that the number of crowns identified in the first that intersected with height loss clusters was a good estimator of the number of dead trees in these areas. Our results demonstrate that multisensor data fusion improves the automatic segmentation of individual tree crowns and presents a promising avenue to study forest demography with repeated remote sensing acquisitions.