大气与环境光学学报 ›› 2025, Vol. 20 ›› Issue (3): 410-422.doi: 10.3969/j.issn.1673-6141.2025.03.013

• “激光雷达新技术及其在大气环境中的应用”专辑 • 上一篇    

基于双向长短期记忆网络的机载海洋激光雷达海表位置提取方法

汤晨 1, 姜萍 1, 展文军 1, 郭子钰 1, 丁缪琦 1, 宋小全 1,2*   

  1. 1 中国海洋大学信息科学与工程学部海洋技术学院, 山东 青岛 266100; 2 青岛海洋科学与技术试点国家实验室, 山东 青岛 266237
  • 收稿日期:2025-03-31 修回日期:2025-04-30 出版日期:2025-05-28 发布日期:2025-05-26
  • 通讯作者: E-mail: songxq@ouc.edu.cn E-mail:songxq@ouc.edu.cn
  • 作者简介:汤 晨 (2000- ), 山东日照人, 硕士研究生, 主要从事机载激光雷达方面的研究。E-mail: 157165151@qq.com
  • 基金资助:
    国家重点研发计划资助 (2022YFB3901705, 2022YFC3700402)

A sea surface position extraction method for airborne marine lidar based on bidirectional long short-term memory network

TANG Chen 1, JIANG Ping 1, ZHAN Wenjun 1, GUO Ziyu 1, DING Miaoqi 1, SONG Xiaoquan 1,2*   

  1. 1 School of Ocean Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, China; 2 Qingdao Marine Science and Technology Pilot National Laboratory, Qingdao 266237, China
  • Received:2025-03-31 Revised:2025-04-30 Online:2025-05-28 Published:2025-05-26
  • Contact: Xiao-Quan SONG E-mail:songxq@ouc.edu.cn

摘要: 海表位置的准确定位和提取, 是影响机载海洋激光雷达测绘和测深精度的重要因素之一。使用532 nm激光 雷达测绘时, 海面波浪、激光穿透海气界面后近海表水体的散射和吸收会降低该波长下海表位置提取的精度。本文基 于双向长短期记忆网络 (Bi-LSTM) 开展海表位置提取研究, 利用1064 nm和532 nm双波长探测的完整海表回波波形 进行训练, 以1064 nm波长探测结果为真值来确定532 nm通道的海表位置。训练结果应用于532 nm波长探测数据, 发现基于Bi-LSTM算法提取海表位置其平均偏差为0.03 m, 而采用峰值算法提取时其平均偏差为 −0.21 m。进一步通 过Bi-LSTM算法定量评估海水漫衰减系数对偏差值的影响, 结果显示漫衰减系数在0.05~0.15 m-1范围时偏差最小值 为0.03 m。

关键词: 机载激光测深, 海洋激光雷达, 海表位置, 深度学习, 海水光学性质

Abstract: Accurate sea surface positioning and extraction are critical factors influencing the measurement precision and bathymetric accuracy of airborne oceanographic lidar. When 532 nm lidar is used for sea surveying and mapping, the scattering and absorption of sea surface waves and near-surface water after laser penetrating through the air-sea interface will degrade the accuracy of sea surface positioning at this wavelength. This study employed a Bidirectional Long Short-Term Memory (Bi-LSTM) network for sea surface positioning. According to Bi-LSTM method, the complete sea surface return waveforms from dualwavelength detection (1064 nm and 532 nm) were used for training, and then the 1064 nm detection results were used as ground truth to determine the sea surface positions of 532 nm channel. Application of the trained model to 532 nm detection data showed that the average positioning bias using Bi-LSTM algorithm was 0.03 m, while that of conventional peak detection algorithm was −0.21 m. Bi-LSTM algorithm was further used to quantitatively evaluate the influence of seawater diffuse attenuation coefficient on the bias, and the results showed that the minimum bias of 0.03 m occurred when the seawater diffuse attenuation coefficient was in the range of 0.05–0.15 m-1.

Key words: airborne laser bathymetry, marine lidar, sea surface position, deep learning, optical properties of seawater

中图分类号: