地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (6): 1106-1117.doi: 10.12082/dqxxkx.2021.200532

• 遥感科学与应用技术 • 上一篇    下一篇

基于离散粒子群算法的2种新型水体提取方法的对比与验证

李志红1,2(), 李旺平1,2,*(), 王玉1,2, 陈璐1,2, 郁林1,2, 周兆叶1,2, 郝君明1,2, 吴晓东3, 李传华4   

  1. 1.兰州理工大学土木工程学院,兰州 730050
    2.兰州理工大学甘肃省应急测绘工程研究中心,兰州 730050
    3.中国科学院西北生态环境资源研究院冰冻圈国家重点实验室青藏高原冰冻圈观测研究站,兰州 730000
    4.西北师范大学地理与环境科学学院,兰州 730070
  • 收稿日期:2020-09-16 修回日期:2021-01-06 出版日期:2021-06-25 发布日期:2021-08-25
  • 通讯作者: 李旺平
  • 作者简介:李志红(1996— ),女,甘肃白银人,硕士生,主要从事3S技术及应用研究。E-mail: 1824316193@qq.com
  • 基金资助:
    国家自然科学基金项目(41601066);甘肃省自然科学基金项目(20JR5RA444)

Comparison and Verification of Two New Lake Water Extraction Methods based on Discrete Particle Swarms Optimization Algorithm

LI Zhihong1,2(), LI Wangping1,2,*(), WANG Yu1,2, CHEN Lu1,2, YU Lin1,2, ZHOU Zhaoye1,2, HAO Junming1,2, WU Xiaodong3, LI Chuanhua4   

  1. 1. Lanzhou University of Technology, Lanzhou 730050, China
    2. Emergency mapping engineering research center of Gansu, Lanzhou 730050, China
    3. Cryosphere Research Station on Qinghai-Xizang Plateau, Chinese Academy of Sciences, State Key Laboratory of Cryospheric Sciences, Lanzhou, northwest academy of ecological environment and resources, Chinese Academy of Sciences, Lanzhou 730000, China
    4. School of Geography and Environmental Science, Northwest Normal University, Lanzhou 730070, China
  • Received:2020-09-16 Revised:2021-01-06 Online:2021-06-25 Published:2021-08-25
  • Contact: LI Wangping
  • Supported by:
    National Natural Science Foundation of China(41601066);Natural Science Foundation of Gansu province, China(20JR5RA444)

摘要:

随着遥感技术在水体提取与监测方面的广泛应用,更多的研究者致力于提高遥感水体提取的精度。离散粒子群算法在遥感图像分类研究中获得了较高的精度和更稳健的分类效果,已经被应用到遥感水体提取领域,但其在水体提取中的适用性和精度还有待对比与验证。本文采用最新提出的2种基于离散粒子群算法的水体提取方法,即光谱匹配耦合离散粒子群算法(SMDPSO)与最大熵耦合离散粒子群算法(MEDPSO),基于Landsat8_OLI遥感影像,分别选择了有冰雪、有云、有山体阴影和有建筑物的4种环境复杂,常规方法提取精度较低的区域进行水体提取,并与2种常用的水体指数法(NDWI、MNDWI)进行了对比与验证。结果表明:① SMDPSO和MEDPSO方法在4个实验区都能快速地寻找出最佳的水体分布,具有一定的通用性;NDWI和MNDWI方法对有冰雪、有云、有山体阴影和有建筑物影响的区域表现出水体信息的错分现象,提取精度较低;② SMDPSO方法能够识别细小河流和离散水体,水体提取精度较高,但在有冰雪、云、山体阴影和建筑物的复杂环境下提取精度较低、误判率高;MEDPSO方法不仅可以识别细小水体,而且也解决了其他3种方法在提取过程中无法抑制背景信息干扰的问题,在4个实验区的总体精度均在97.8%以上,高于其他3种方法;③ 将离散粒子群算法引入到水体提取方法之中,可增强方法的区域整体性,也可提高其水体提取的精度和自动化程度;④ 运用最大熵模型等机器学习方法,可以结合光谱、形状和纹理等影像信息以及地形信息来进行水体识别,使得水体信息提取精度更高。本文的研究可为离散粒子群算法的推广以及遥感水体提取方法的选择提供参考。

关键词: 水体提取, 离散粒子群算法, 光谱匹配, 最大熵, NDWI, MNDWI, Landsat8_OLI, 精度评定

Abstract:

The remote sensing technology has been widely used in water body extraction and monitoring. Nowadays, many researchers are committed to improving the accuracy of water body extraction. Discrete particle swarm optimization algorithms can obtain high accuracy and robust classification results in remote sensing image classification, which has been widely used to extract the water bodies. However, the applicability and accuracy in water body extraction using discrete particle swarm still need to be assessed and verified. Here we proposed two new methods for water body extraction based on the discrete particle swarm optimization algorithm, namely, Spectral Matching Coupled Discrete Particle Swarm Optimization method (SMDPSO) and Maximum Entropy coupled Discrete Particle Swarm Optimization method (MEDPSO). Based on Landsat8_OLI remote sensing data, we selected the imageries with four environmental elements, i.e., ice and snow, clouds, mountain shadows, and buildings. The conventional method was used to extract the water body, and the results were compared and verified with two commonly used water index methods (NDWI, MNDWI). The results show that: (1) SMDPSO and MEDPSO methods can quickly find the best water bodies in the four experimental areas, and the two methods were all applicable for the study areas. Using the NDWI and MNDWI methods, water bodies can be misclassified with ice, snow, clouds, shadows, and buildings, and the extraction accuracy was low; (2) The SMDPSO method can identify small rivers and discrete water bodies. The overall water body extraction accuracy was high, but the extraction accuracy was low in complex environment. The MEDPSO method can not only identify small water bodies, but also suppress background information interference in the extraction process which cannot be realized by the other three methods. The overall accuracy of the four experimental areas was above 97.8%, which was higher than the other three methods; (3) By introducing the discrete particle swarm optimization algorithm into the water body extraction methods, the regional integrity of each method can be enhanced, and the accuracy and automation of the water body extraction can also be improved; (4) The machine learning methods such as the maximum entropy model, and image information such as spectrum, shape, and texture, as well as terrain information can be used to identify water bodies. These methods can achieve higher accuracy in the water body extraction. These results provide scientific references for the application of discrete particle swarm optimization algorithms, as well as the selection of water body extraction methods using remote sensing data.

Key words: water body extraction, discrete particle swarm optimization, spectral matching, maximum entropy model, NDWI, MNDWI, Landsat8_OLI, accuracy evaluation