﻿ 船舶电子海图目标信息快速检索方法
 舰船科学技术  2022, Vol. 44 Issue (24): 137-140    DOI: 10.3404/j.issn.1672-7649.2022.24.028 PDF

Design of fast retrieval method for ship electronic chart target information
ZHANG Sheng, LIU Chun-bao
Jilin University, Changchun 130021, China
Abstract: In order to help ships avoid obstacles quickly, a fast retrieval method for target information of ship electronic chart is proposed. First, the Mercator projection method is used to transform the projection of the ship's electronic chart, from which the geographic longitude and latitude of the electronic chart are obtained, and the index data structure table is constructed. The complete information of the electronic chart is obtained according to the first three elements in the table, so as to determine the target information retrieval area. Then, after the target information data is collected, the semantic association oriented feature is extracted and used for the directional index path, so that the target information can be quickly retrieved. The experimental results show that this method has the advantages of strong real-time and high effectiveness.
Key words: electronic chart     target information     information retrieval     dynamic data pickup
0 引　言

1 电子海图空间数据索引结构并确立检索区域 1.1 建立电子海图空间数据索引结构

 $\left( {w,j} \right) = \phi _{org}^{ - 1}\left( {\frac{{{X_{org}}}}{{K \times s \times f}}} \right) + \left( {{w_0},{j_0}} \right) 。$ (1)

 图 1 船舶数据索引结构与海图格式关系图 Fig. 1 Relationship between ship data index structure and chart format

1.2 确定电子海图目标信息检索区域

 图 2 船舶电子海图检索区域 Fig. 2 Retrieval area of ship electronic chart

 $A = V\left( {\frac{t}{2} + \frac{{56.2}}{{K\delta }} + \tan \frac{\theta }{2}} \right) + \frac{{RL}}{2}\cos \theta + P。$ (2)

 $NE = \tan \frac{\theta }{2} \cdot \frac{V}{{K\delta }} \cdot \sin \theta + \frac{L}{2}\sin \theta + \frac{B}{2} + P 。$ (3)

2 电子海图目标信息检索 2.1 电子海图目标信息语义关联指向特征提取

 ${C_x}\left( j \right) = \frac{1}{N}\sum\limits_{i = 0}^{N = 1} {{x_i}}。$ (4)

 $E\left\{ {{h_1}\left( {{y_1}} \right) + {h_2}\left( {{y_2}} \right)} \right\} = E\left\{ {{h_1}\left( {{y_1}} \right)} \right\}E\left\{ {{h_2}\left( {{y_2}} \right)} \right\}，$ (5)

 $C\left( \tau \right) = \mathop {\lim }\limits_{T \to \infty } \frac{1}{T}\int_{ - \frac{T}{2}}^{\frac{T}{2}} {x\left( t \right) + x\left( {t + \tau } \right) + {\rm{d}}} \tau。$ (6)

 $W\left( {X,Y} \right) = \frac{{P\left( {X \cap Y} \right)}}{{P\left( X \right) + P\left( Y \right) - P\left( {X \cap Y} \right)}}。$ (7)

2.2 动态拾取海图数据法

 图 3 电子海图目标信息检索流程 Fig. 3 Ship electronic chart target information retrieval process
3 实验与分析

 ${Pr}ecision=\frac{检索出的目标信息数量}{检索的目标信息总量}。$ (8)

 ${Re}call=\frac{检索出的目标信息数量}{船舶电子海图全部目标信息}。$ (9)

 $F-测试值=\frac{2\times {Re}call\times {Pr}ecision}{{Re}call+{Pr}ecision}。$ (10)

 图 4 3种方法的查准率对比测试 Fig. 4 Comparison test of the three methods

 图 5 3种方法的调和平均数对比测试 Fig. 5 Harmonic mean comparison test of three methods

4 结　语

 [1] 王百勇, 张艳华, 贾俊乾. 基于深度学习理论下电子海图与雷达图像船舶感知信息融合[J]. 现代雷达, 2021, 43(5): 44-50. [2] 谭凯中, 秦勃, 何亚文. 面向过程的海洋时空数据分布式存储与并行检索[J]. 中国海洋大学学报(自然科学版), 2021, 51(11): 94-101+134. [3] 张大恒, 张英俊, 张闯. 基于Faster R-CNN的电子海图和雷达图像的数据融合[J]. 系统工程与电子技术, 2020, 42(6): 1267-1273. DOI:10.3969/j.issn.1001-506X.2020.06.09 [4] 董江, 王昭, 胡海. 基于全球多源海图目录的海图检索服务研究[J]. 海洋测绘, 2021, 41(5): 78-82. DOI:10.3969/j.issn.1671-3044.2021.05.017