基于视觉图像处理的特征提取和图像识别方案是对雷达和AIS的有效补充，有效识别其他船舶、礁石等可以有效保障舰船航行安全。本文提出一种基于CNN和拉普拉斯金字塔图像融合的视觉图像特征深度提取系统，设计了系统的基本结构，并分析了系统中各模块的基本功能，提出了基于CNN的特征深度提取方案，对船舶和浮标目标特征进行提取，使用拉普拉斯金字塔融合将不同舰船上获取的图像进行深度融合。本文建立的多方位视觉图像特征深度提取系统可以有效获取多种目标特征，并可以有效提高特征表示的丰富性和准确性。
Feature extraction and image recognition schemes based on visual image processing are effective complements to radar and AIS, effectively identifying other ship targets, reefs, and so on, which can effectively ensure the safety of ship navigation. This paper proposes a visual image feature deep extraction system based on CNN and Laplacian pyramid image fusion, designs the basic structure of the system, and analyzes the basic functions of each module within the system. A feature deep extraction scheme based on CNN is proposed, and features of ship and buoy targets are extracted. The Laplacian pyramid fusion is used to deeply integrate images obtained from different ships. The multi-directional visual image feature deep extraction system established in this paper can effectively acquire various target features and can significantly enhance the richness and accuracy of feature representation.
2024,46(10): 157-160 收稿日期：2023-12-26
DOI：10.3404/j.issn.1672-7649.2024.10.027
分类号：U667.65
作者简介：王晓橹(1975-),女,硕士,讲师,研究方向为视觉传达设计
参考文献：
[1] 郝亚楠. 双目视觉物体测距和识别的管理系统设计与实现[J]. 山西大同大学学报(自然科学版), 2024, 40(2): 25-28.
HAO Ya-nan. Design and implementation of management system for binocular vision object distance measurement and recognition[J]. Journal of Shanxi Datong University (Natural Science Edition), 2024, 40(2): 25-28.
[2] 王行洲, 秦立宇, 陈亮宏, 等. 多目视觉系统在电芯自动上料设备中的应用[J]. 机械研究与应用, 2024, 37(1): 150-152+156.
WANG Xing-zhou, QIN Li-yu, CHEN Liang-hong, et al. Application of multi-vision system in automatic battery loading equipment[J]. Mechanical Research & Application, 2024, 37(1): 150-152+156.
[3] 雷洁, 徐文华, 许国冬, 等. 基于双目视觉定位技术的无人船航迹跟踪控制室内模型实验[J]. 无人系统技术, 2022, 5(1): 43-50.
LEI Jie, XU Wen-hua, XU Guo-dong, et al. Indoor model experiment of unmanned boat trajectory tracking control based on binocular vision localization technology[J]. Unmanned System Technology, 2022, 5(1): 43-50.
[4] 张啸尘, 赵建森, 王胜正, 等. 基于YOLOv3算法的船舶双目视觉检测与定位方法[J]. 上海海事大学学报, 2021, 42(1): 26-32.
ZHANG Xiao-chen, ZHAO Jian-sen, WANG Sheng-zheng, et al. Ship binocular vision detection and positioning method based on YOLOv3 algorithm[J]. Journal of Shanghai Maritime University, 2021, 42(1): 26-32.
[5] 刘东辉, 柳飞, 刘奇. 基于激光与视觉融合的船舶扫描和吊具防撞系统及方法[J]. 起重运输机械, 2024(3): 33-37.
LIU Dong-hui, LIU Fei, LIU Qi. Ship scanning and gantry anti-collision system and method based on laser and vision fusion[J]. Lifting and Transporting Machinery, 2024(3): 33-37.
[6] 刘小飞, 李明杰, 喻佳. 无人机立体视觉识别船舶航行风险仿真[J]. 计算机仿真, 2024, 41(2): 29-33.
LIU Xiao-fei, LI Ming-jie, YU Jia. Unmanned aerial vehicle stereo vision recognition of ship navigation risk simulation[J]. Computer Simulation, 2024, 41(2): 29-33.
