当前位置: X-MOL 学术Can. J. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model
Canadian Journal of Remote Sensing ( IF 2.0 ) Pub Date : 2020-12-20 , DOI: 10.1080/07038992.2020.1861541
Zhouxin Xi 1 , Chris Hopkinson 1
Affiliation  

Abstract

Detecting individual-tree crowns provides a fundamental analysis unit bridging macro ecological patterns and micro physiological functions. This study adapted an anchor-free deep learning model, CenterNet, to detect individual crown locations and regions from dense 3 D terrestrial laser scans. A total of 1181 crowns from twelve plots were manually delineated as reference, among which eight plots were used for training the CenterNet, and another four independent plots for testing model accuracies characterized as the F1-score of location detection and Intersection over Union (IoU) of bounding box area. The maximum training F1-score and IoU were 0.881 and 0.670 over 40k training iterations, respectively. The result testing F1-score and IoU were 0.754 and 0.583, respectively. Five morphological factors were quantified to investigate the causes of accuracy variation among different plots and species, including crown area, tree height, full-width-at-half-maximum, nearest neighbor crown distance, and overlapping ratio of neighboring crowns. Results show that tree height was most important trait for crown detection. A taller, larger, smoother, less crowded, and less overlapped tree was found easier to detect. Among six species, red pine, Scots pine, and silver birch were successfully detected, and Norway spruce, lodgepole pine, and trembling aspen were more difficult to detect.



中文翻译:

使用无锚深度学习模型从地面激光扫描中检测单个树冠区域

摘要

检测个体树冠提供了连接宏观生态模式和微观生理功能的基本分析单元。本研究采用无锚深度学习模型 CenterNet,从密集的 3D 地面激光扫描中检测单个冠的位置和区域。手动勾画了来自 12 个地块的 1181 个冠作为参考,其中 8 个地块用于训练 CenterNet,另外 4 个独立的地块用于测试模型精度,其特征是位置检测和交集 (IoU) 的 F1 分数边界框区域。在 40k 次训练迭代中,最大训练 F1-score 和 IoU 分别为 0.881 和 0.670。测试 F1-score 和 IoU 的结果分别为 0.754 和 0.583。量化了五个形态因素来研究不同地块和物种之间精度差异的原因,包括冠面积、树高、半峰全宽、最近邻树冠距离和相邻树冠重叠率。结果表明,树高是最重要的树冠检测性状。发现更高、更大、更平滑、不那么拥挤和更少重叠的树更容易被检测到。在6个树种中,红松、苏格兰松、银桦被成功检测到,挪威云杉、黑松和颤杨较难检测。结果表明,树高是最重要的树冠检测性状。发现更高、更大、更平滑、不那么拥挤且重叠更少的树更容易被检测到。在6个树种中,红松、苏格兰松、银桦被成功检测到,挪威云杉、黑松和颤杨较难检测。结果表明,树高是最重要的树冠检测性状。发现更高、更大、更平滑、不那么拥挤且重叠更少的树更容易被检测到。在6个树种中,红松、苏格兰松、银桦被成功检测到,挪威云杉、黑松和颤杨较难检测。

更新日期:2020-12-20
down
wechat
bug