地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (11): 2086-2095.doi: 10.12082/dqxxkx.2021.210103

• 遥感科学与应用技术 • 上一篇    

基于卷积神经网络的ICESat-2光子点云去噪分类

陆大进1(), 黎东1,2,*(), 朱笑笑2, 聂胜2, 周国清3, 张兴忆1, 杨超1   

  1. 1. 昆明理工大学 国土资源工程学院,昆明 650093
    2. 中国科学院空天信息创新研究院数字地球重点实验室,北京 100094
    3. 桂林理工大学 测绘地理信息学院,桂林 541006
  • 收稿日期:2021-03-03 修回日期:2021-05-31 出版日期:2021-11-25 发布日期:2022-01-25
  • 通讯作者: *黎东(1981— ),男,湖北宜昌人,博士,高级工程师,主要从事激光雷达数据处理与应用研究。 E-mail: lidong@aircas.ac.cn
    *黎东(1981— ),男,湖北宜昌人,博士,高级工程师,主要从事激光雷达数据处理与应用研究。 E-mail: lidong@aircas.ac.cn
    *黎东(1981— ),男,湖北宜昌人,博士,高级工程师,主要从事激光雷达数据处理与应用研究。 E-mail: lidong@aircas.ac.cn
    *黎东(1981— ),男,湖北宜昌人,博士,高级工程师,主要从事激光雷达数据处理与应用研究。 E-mail: lidong@aircas.ac.cn
    *黎东(1981— ),男,湖北宜昌人,博士,高级工程师,主要从事激光雷达数据处理与应用研究。 E-mail: lidong@aircas.ac.cn
  • 作者简介:陆大进(1997— ),男,云南宣威人,硕士生,主要从事激光雷达数据处理与林业应用。E-mail: 2650571428@qq.com
  • 基金资助:
    广西自然科学基金—创新研究团队项目(2019GXNSFGA245001);国家自然科学基金项目(42071405);中国科学院青年创新促进会(2019130)

Denoising and Classification of ICESat-2 Photon Point Cloud based on Convolutional Neural Network

LU Dajin1(), LI Dong1,2,*(), ZHU Xiaoxiao2, NIE Sheng2, ZHOU Guoqing3, ZHANG Xingyi1, YANG Chao1   

  1. 1. Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, China
    2. Key Lab of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
    3. College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China
  • Received:2021-03-03 Revised:2021-05-31 Online:2021-11-25 Published:2022-01-25
  • Contact: *LI Dong, E-mail: lidong@aircas.ac.cn
    *LI Dong, E-mail: lidong@aircas.ac.cn
    *LI Dong, E-mail: lidong@aircas.ac.cn
    *LI Dong, E-mail: lidong@aircas.ac.cn
    *LI Dong, E-mail: lidong@aircas.ac.cn
  • Supported by:
    Guangxi Natural Science Fund for Innovation Research Team, No(2019GXNSFGA245001);National Natural Science Foundation of C-hina, No(42071405);The Youth Innovation Promotion Association Chinese Academy of Sciences, No(2019130)

摘要:

ICESat-2(Ice, Cloud, and land Elevation Satellite-2)是美国NASA(National Aeronautics and Space Administration)在2018年发射的激光测高卫星,其上搭载的激光测高系统ATLAS(Advanced Topographic Laser Altimeter System)采用微脉冲多波束光子计数激光雷达系统,因其低能耗、高探测灵敏度、高重复频率的特性极大改善了沿轨采样密度,但也使获取的数据中包含大量的噪声,如何有效实现光子点云去噪分类成为后续应用的关键,也是当前研究的热点和难点,为此本文提出一种基于卷积神经网络的光子点云去噪和分类算法。首先将光子点云按照沿轨和高程方向划分格网,去除明显的噪声光子,并将每个粗信号光子点栅格化为影像;然后基于少量样本构建的卷积神经网络分类模型实现光子点云精去噪和分类;最后利用机载激光雷达数据进行验证,并与ATL08产品的去噪分类结果进行对比。结果表明,对于裸地和森林区域,卷积神经网络算法均能有效去除噪声光子,特别对于森林区域,可同时实现去噪和分类;其中,裸地区域地表计算的R2RMSE分别为1.0和0.72 m,森林区域地表和树冠计算的R2分别为1.0和0.70, RMSE分别为1.11 m和4.99 m。本文利用深度学习算法实现光子点云去噪分类,在裸地和森林区域均取得了较好的结果,为后续光子点云数据处理提供了参考。

关键词: ICESat-2, 监督学习, 光子计数, 光子点云, 栅格化, 去噪与分类, 卷积神经网络, 深度学习

Abstract:

ICESat-2 (Ice, Cloud, and land Elevation Satellite-2) launched by NASA (National Aeronautics and Space Administration) in 2018 is a laser altitude measurement satellite. The advanced topographic laser altimeter system (ATLAS) instrument on-board ICESat-2 employs a micro-pulse and multi-beam photon counting laser altimeter system with low energy consumption, high detection sensitivity, and high repetition rates, and thus greatly improves the sampling density in the along-track distance. However, it introduces a significant number of solar noise photons in the raw data. How to effectively remove the noise photons and classify the signal photons into ground photons and canopy photons is critical for subsequent applications such as the estimation of terrain elevation and forest height, and it has been a hot and challenging topic in the current research. In this paper, a denoising and classification algorithm based on convolutional neural network was proposed. The convolutional neural network has made a series of breakthrough research results in the fields of image classification, object detection, semantic segmentation, and so on. To remove obvious noise photons, the photons were first divided into grids in the along-track distance and elevation direction, and the rough signal photons were gridded into pictures. Then, the convolutional neural network was employed to perform the final denoising and classification. Finally, the proposed algorithm was tested with the airborne LiDAR datasets, including DSM (Digital Surface Model) and DTM (Digital Terrain Model), and was further compared with ATL08 (land and vegetation height) products. Experimental results show that our proposed algorithm can remove noise photons effectively in bare land and forest areas. Moreover, this algorithm can simultaneously remove noise photons and classify signal photons into ground photons and canopy photons in forest areas. The R 2 and RMSE values of the retrieved ground surface in the bare land areas were 1.0 and 0.72 m, respectively. In the forest areas, the R 2 of the estimated ground surface and canopy surface were 1.0 and 0.70 with the RMSE values of 1.11 m and 4.99 m, respectively. The reason for this result may be that it is difficult for photons to penetrate the forest canopy and reach the ground surface in forest areas, which causes the RMSE value of the forest area to be larger than that of the bare land area. In this paper, the deep learning algorithm was used to realize the denoising and classification of photon counting data, and good results were achieved in bare land and forest areas, which provides a reference for subsequent photon counting LiDAR data processing.

Key words: ICESat-2, supervised learning, photon-counting, photon point cloud, rasterized, denoising and classification, convolutional neural network, deep learning