摘要
针对仿生机器鱼水下作业时面临的水下图像质量偏低、水下自主定位难的问题,提出一种颜色均衡与G-B通道先验融合的水下图像增强式算法。将该算法和视觉同时定位与地图构建(SLAM)方法结合,实现了水下图像增强式的视觉三维重建。在不同水域环境下进行了水下图像处理实验、水下环境视觉三维重建实验和运动轨迹跟踪实验,结果表明该方法有效提高了水下图像综合质量,特征匹配效率提高了16.03%,真实轨迹与估计轨迹的误差平均约为7.99 mm。
Regarding with problems of low quality of underwater images and difficulty of underwater autonomous localization faced by bionic robotic fish in underwater operations,an enhanced underwater image algorithm with color equalization and a priori fusion of G-B channels was proposed.The algorithm was combined with visual SLAM construction methods to enhance visual 3D reconstruction of underwater images.Underwater image processing experiments,underwater environment visual 3D reconstruction experiments,and motion trajectory tracking experiments were carried out in different water environments.The results show that the method effectively improves the comprehensive quality of underwater images.The feature matching efficiency is improved by 16.03%,and the error between the real trajectory and the estimated trajectory is about 7.99 mm on average.
作者
梅杰
覃嘉锐
陈定方
陈昆
MEI Jie;QIN Jiarui;CHEN Dingfang;CHEN Kun(School of Transportation and Logistics Engineering,Wuhan University of Technology,Wuhan,430063;Institute of Intelligent Manufacturing and Control,Wuhan University of Technology,Wuhan,430063;Key Laboratory of Port Cargo Handling Technology of Wuhan University of Technology,Wuhan,43006)
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2024年第2期268-279,共12页
China Mechanical Engineering
基金
国家自然科学基金(5180051287)。
