利用样本生成方法进行机载多光谱LiDAR数据深度学习分类

doi:10.13474/j.cnki.11-2246.2021.365

测绘通报 ›› 2021, Vol. 0 ›› Issue (12): 16-21.doi: 10.13474/j.cnki.11-2246.2021.365

利用样本生成方法进行机载多光谱LiDAR数据深度学习分类

赵沛冉¹, 管海燕¹, 李迪龙², 景庄伟³, 于永涛⁴

1. 南京信息工程大学遥感与测绘工程学院, 江苏南京 210044;
2. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
3. 上海航天电子技术研究所, 上海 201109;
4. 淮阴工学院计算机与软件工程学院, 江苏淮安 223003

收稿日期:2020-12-02 发布日期:2021-12-30
通讯作者: 管海燕。E-mail:guanhy.nj@nuist.edu.cn
作者简介:赵沛冉(1997-),男,硕士生,主要研究方向为激光LiDAR点云数据。E-mail:1135269476@qq.com
基金资助:
国家自然科学基金（41971414；62076107）；福建省自然科学基金（2021J05059）

Deep learning classification of airborne multispectral LiDAR data using sample generation method

ZHAO Peiran¹, GUAN Haiyan¹, LI Dilong², JING Zhuangwei³, YU Yongtao⁴

1. School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China;
2. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
3. Shanghai Aerospace Electronic Institute, Shanghai 201109, China;
4. Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223003, China

Received:2020-12-02 Published:2021-12-30

摘要/Abstract

摘要： 机载多光谱LiDAR系统能够快速、准确地获取地物的空间几何和光谱信息,为地物覆盖分类和目标识别提供新的数据源。近年来,基于三维点云的深度学习算法取得了一系列突破性进展,然而直接将不规则的原始点云数据输入深度学习模型进行基于点的分类存在一定的困难。本文提出了一种基于FPS-KNN的样本生成方法,用于基于深度学习的机载多光谱LiDAR数据分类。该方法首先对输入数据进行归一化处理;然后利用最远点采样方法(FPS)和K近邻法(KNN)在输入数据中生成一系列规则大小的训练样本数据集。通过机载多光谱LiDAR数据的试验表明,该方法所生成的样本不仅符合卷积神经网络所要求的输入数据形式,而且能够确保对输入场景的完整覆盖。

关键词: 多光谱LiDAR, 点云样本, 深度学习, 地物分类, 样本尺度

Abstract: An airborne multispectral LiDAR system, which can quickly and accurately obtain the spatial geometry and spectral information of ground objects, provides a new data source for ground coverage classification and target recognition. In recent years, a series of breakthroughs have been achieved in deep learning algorithms based on 3D point cloud. However, it is difficult to directly input irregular original point cloud data into deep learning models for point-based classification. In this paper, a sample generation method based on PFS-KNN is proposed for deep learning based classification models using airborne multispectral LiDAR data. The method first normalizes the input data, and then farthest point sampling method and k-nearest neighbor method are used to generate a series of training sample data sets with regular size from the input data. Experiments with the airborne multi-spectral LiDAR data show that the samples generated by the proposed method not only meet the input data format required by the convolutional neural network, but also ensure the complete coverage of the input scene.

Key words: multispectral LiDAR, point cloud samples, deep learning, object classification, sample size

中图分类号:

P237

赵沛冉, 管海燕, 李迪龙, 景庄伟, 于永涛. 利用样本生成方法进行机载多光谱LiDAR数据深度学习分类[J]. 测绘通报, 2021, 0(12): 16-21.

ZHAO Peiran, GUAN Haiyan, LI Dilong, JING Zhuangwei, YU Yongtao. Deep learning classification of airborne multispectral LiDAR data using sample generation method[J]. Bulletin of Surveying and Mapping, 2021, 0(12): 16-21.

参考文献

[1] LAWIN F J, DANELLJAN M, TOSTEBERG P, et al. Deep projective 3D semantic segmentation[M]//Computer Analysis of Images and Patterns. Cham:Springer International Publishing, 2017:95-107.
[2] MATIKAINEN L, KARILA K, LITKEY P, et al. Combining single photon and multispectral airborne laser scanning for land cover classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 164:200-216.
[3] 李含伦, 张爱武, 刘诏, 等. 基于LiDAR波形分解的点云SVM分类方法研究[J]. 测绘通报, 2014(1):28-32.
[4] 赵中阳, 程英蕾, 释小松, 等.基于多尺度特征和PointNet的LiDAR点云地物分类方法[J]. 激光与光电子学进展, 2019, 56(5):251-258.
[5] LI W Z, WANG F D, XIA G S. A geometry-attentional network for ALS point cloud classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 164:26-40.
[6] LI X, WANG L, WANG M, et al. DANCE-NET:density-aware convolution networks with context encoding for airborne LiDAR point cloud classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166:128-139.
[7] WANG Z, ZHANG L, ZHANG L, et al. A deep neural network with spatial pooling (DNNSP) for 3D point cloud classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(8):4594-4604.
[8] 释小松, 程英蕾, 赵中阳. 利用神经网络的城区机载激光雷达点云分类算法[J]. 计算机应用研究, 2020, 37(4):1256-1260.
[9] 王旭娇, 马杰, 王楠楠, 等.基于图卷积网络的深度学习点云分类模型[J].激光与光电子学进展, 2019, 56(21):56-60.
[10] KLOKOV R, LEMPITSKY V. Escape from cells:deep kd-networks for the recognition of 3D point cloud models[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice:IEEE, 2017:863-872.
[11] YOUSEFHUSSIEN M, KELBE D J, IENTILUCCI E J, et al. A multi-scale fully convolutional network for semantic labeling of 3D point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 143:191-204.
[12] 王宏涛, 雷相达, 赵宗泽. 融合光谱信息的机载LiDAR点云三维深度学习分类方法[J]. 激光与光电子学进展, 2020, 57(12):122802.
[13] WEN C, YANG L, LI X, et al. Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 162:50-62.
[14] WEN C, LI X, YAO X, et al. Airborne LiDAR point cloud classification with global-local graph attention convolution neural network[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 173:181-194.
[15] MOENNING C, DODGSON N A. Fast marching farthest point sampling for implicit surfaces and point clouds[J]. Computer Laboratory Technical Report, 2003(565):1-12.
[16] QI C R, SU H, MO K, et al. Pointnet:deep learning on point sets for 3d classification and segmentation[C]//Proceedings of 2017 IEEE conference on computer vision and pattern recognition. Honolulu:IEEE, 2017:652-660.
[17] QI C R, YI L, SU H, et al. Pointnet++:deep hierarchical feature learning on point sets in a metric space[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York:Curran Associates Inc., 2017:5105-5114.
[18] WANG Y, SUN Y, LIU Z, et al. Dynamic graph cnn for learning on point clouds[J]. Acm Transactions On Graphics (tog), 2019, 38(5):1-12.
[19] LIU Y, FAN B, XIANG S, et al. Relation-shape convolu-tional neural network for point cloud analysis[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach:Institute of Electrical and Electronic Engineers, 2019:8895-8904.
[20] WANG L, HUANG Y, HOU Y, et al. Graph attention convolution for point cloud semantic segmentation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach:Institute of Electrical and Electronic Engineers, 2019:10296-10305.

利用样本生成方法进行机载多光谱LiDAR数据深度学习分类

Deep learning classification of airborne multispectral LiDAR data using sample generation method

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘立, 董先敏, 刘娟, 文学虎. 人机融合智能的遥感解译生产新方法[J]. 测绘通报, 2022, 0(7): 118-123,137.
[2]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[3]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[4]	张晋赫, 秦育罗, 张在岩, 宋伟东, 朱洪波. 复杂场景下农村道路裂缝分割方法[J]. 测绘通报, 2022, 0(5): 74-78,88.
[5]	师芸, 石龙龙, 牛敏杰, 赵侃. 基于单阶段实例分割网络的黄土滑坡多任务自动识别[J]. 测绘通报, 2022, 0(4): 26-31.
[6]	王雪, 梁珂, 隋立春, 钟棉卿, 朱剑锋. 膨胀卷积与金字塔表达的深度学习模型用于农村建筑物提取[J]. 测绘通报, 2022, 0(4): 61-65.
[7]	高鸣, 周鑫鑫, 刘琦, 杨光迪, 吴长彬. 深度学习网络支持下的农房侵占耕地自动化监测[J]. 测绘通报, 2022, 0(3): 47-53.
[8]	孙琴琴, 蔡国印, 杨柳忠, 张宁, 杜明义. 城市尺度典型地表要素综合提取方法研究[J]. 测绘通报, 2022, 0(2): 62-66.
[9]	张自强, 刘涛, 杜萍, 锁旭宏, 杨国林. 图残差神经网络支持下的建筑物群组模式分类[J]. 测绘通报, 2022, 0(1): 1-7.
[10]	车子杰, 高飞, 吴兆福, 李振轩. 基于改进U-Net网络的多源遥感影像洪涝灾害信息提取与变化分析[J]. 测绘通报, 2022, 0(1): 26-32.
[11]	程瑞, 高建, 邢强, 孙中昶. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021, 0(9): 21-27.
[12]	淳锦, 张新长, 郭海京, 张建国, 金诗程. 基于多源信息与深度学习特征提取的人口空间抽样方法[J]. 测绘通报, 2021, 0(8): 42-47.
[13]	李梓豪, 唐超. 基于高清工业相机的盾构隧道裂缝智能识别算法分析[J]. 测绘通报, 2021, 0(8): 83-87,101.
[14]	吴永静, 吴锦超, 林超, 窦宝成, 黎珂. 基于深度学习的高分辨率遥感影像光伏用地提取[J]. 测绘通报, 2021, 0(5): 96-101.
[15]	梁哲恒, 邓鹏, 姜福泉, 盛森, 魏汝兰, 谢刚生. 基于卷积神经网络的无人机影像违章建筑检测应用[J]. 测绘通报, 2021, 0(4): 111-115.