Comparative classification analysis of post-harvest growth detection from terrestrial LiDAR point clouds in precision agriculture
Comparative classification analysis of post-harvest growth detection from terrestrial LiDAR point clouds in precision agriculture
复制标题
DOI：
10.1016/j.isprsjprs.2015.03.003
复制
发表时间：
2015-06-01
影响因子：
12.7
通讯作者：
Lilienthal, Holger
中科院分区：
文献类型：
--
作者：
Koenig, Kristina;Hoefle, Bernhard;Lilienthal, Holger
在精准农业中，关于植物和土壤特性的详细地理信息发挥着重要作用，例如，在作物保护或施肥方面。本文提出了一种比较分类分析，收获后的生长检测使用的几何和辐射点云特征的地面激光扫描（TLS）数据，考虑到每个点的局部邻域。TLS数据的辐射校正进行了通过一个经验的范围校正功能来自现场实验。此后，校正的幅度和局部海拔特征进行了探讨，就其重要性的分类。为了比较，树诱导，朴素贝叶斯，和k-Means-派生的分类器进行了测试，不同的点密度，以区分地面和收获后的生长。对高度详细的RGB参考图像和红边归一化差异植被指数（NDVI 705），来自高光谱传感器的分类性能进行了验证。使用几何和辐射特征，我们实现了99%的精度与树感应。与参考图像分类相比，计算的收获后生长覆盖图达到80%的准确率。RGB和LiDAR衍生的覆盖率显示出与NDVI 705的二阶多项式相关性，R-2分别为0.8和0.7。较大的收获后生长斑块（>10 x 10 cm）已经可以通过2点的点密度检测到。0.01 m（2）。结果表明，高潜力的辐射和几何激光雷达点云特征识别收获后的生长，树木诱导分类。所提出的技术可以潜在地应用于更大的区域使用车载扫描仪。(c)2015年国际摄影测量与遥感学会（International Society for Photogrammetry and Remote Sensing，Inc.）（摄影测量和遥感学会）。Elsevier B. V.出版，保留所有权利。
In precision agriculture, detailed geoinformation on plant and soil properties plays an important role, e.g., in crop protection or the application of fertilizers. This paper presents a comparative classification analysis for post-harvest growth detection using geometric and radiometric point cloud features of terrestrial laser scanning (TLS) data, considering the local neighborhood of each point. Radiometric correction of the TLS data was performed via an empirical range-correction function derived from a field experiment. Thereafter, the corrected amplitude and local elevation features were explored regarding their importance for classification. For the comparison, tree induction, Naive Bayes, and k-Means-derived classifiers were tested for different point densities to distinguish between ground and post-harvest growth. The classification performance was validated against highly detailed RGB reference images and the red edge normalized difference vegetation index (NDVI705), derived from a hyperspectral sensor. Using both geometric and radiometric features, we achieved a precision of 99% with the tree induction. Compared to the reference image classification, the calculated post-harvest growth coverage map reached an accuracy of 80%. RGB and LiDAR-derived coverage showed a polynomial correlation to NDVI705 of degree two with R-2 of 0.8 and 0.7, respectively. Larger post-harvest growth patches (>10 x 10 cm) could already be detected by a point density of 2 pts./0.01 m(2). The results indicate a high potential of radiometric and geometric LiDAR point cloud features for the identification of post-harvest growth using tree induction classification. The proposed technique can potentially be applied over larger areas using vehicle-mounted scanners. (c) 2015 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.