Open Journal of Fisheries Research 水产研究, 2019, 6(4), 179-188
Published Online December 2019 in Hans. http://www.hanspub.org/journal/ojfr
https://doi.org/10.12677/ojfr.2019.64024
文章引用: 连鹏, 刘阳, 何晓晴, 景有甫, 黄聪颖, 董浙燚, 宋旭辉, 徐安康. 基于无人机遥感的海洋养殖区识别研究
[J]. 水产研究, 2019, 6(4): 179-188. DOI: 10.12677/ojfr.2019.64024
Mariculture Areas Recognition Based on
UAV Remote Sensing
Peng Lian, Yang Liu
*
, Xiaoqing He, Youfu Jing, Congying Huang, Zheyi Dong,
Xuhui Song, Ankang Xu
Department of Fisheries, College of Fisheries, Ocean University of China, Qingdao Shandong
Received: Nov. 20
th
, 2019; accepted: Dec. 4
th
, 2019; published: Dec. 11
th
, 2019
Abstract
UAV remote sensing technology has become an increasingly important tool for GIS to obtain data.
It is widely applied in various fields such as planning and design, risk assessment and overall op-
timization, with high accuracy, strong flexibility and rapid extraction of multi-dimensional fea-
tures. In this paper, UAV remote sensing and image recognition technology based on machine
learning are used to model mariculture areas along the coast of Lingshan Island in Qingdao,
Shandong and to identify the marine aquaculture areas and coastal residents. In addition, the me-
thod based on support vector machine is used to process spatial information of each functional
area along the coast and consequently get the parameters of each feature element of the area. In
this paper, based on the supervised classification, 35% of sample pixels are used as training set to
test the robustness of the model simulation effect under different spectral details and spatial de-
tails. The results show that: for small sample size and the requirement of fast ground object iden-
tification and analysis, SVM shows a high accuracy (up to 76.56%), but for small samples, the
model effect is greatly affected by the training set. In the future, about field investigation and veri-
fication of results, combination of big data could improve the object identification accuracy.
Keywords
UAV Remote Sensing, Machine Learning, Mariculture Areas, SVM, Supervised Classification
基于无人机遥感的海洋养殖区识别研究
连 鹏,刘 阳
*
,何晓晴,景有甫,黄聪颖,董浙
燚
,宋旭辉,徐安康
中国海洋大学水产学院渔业系,山东 青岛
收稿日期:2019年11月20日;录用日期:2019年12月4日;发布日期:2019年12月11日
*
通讯作者。