摘要
为了有效检测水下电缆,利用机器视觉技术处理采集的水下电缆图像,根据水下系统坐标模型和相机内参数获取电缆相对位置信息,通过Kalman定位融合算法减小航迹推算后产生的偏差值以达到修正水下机器人(ROV)跟踪路径的目的。实验表明,所提方法适用于成像质量较低的水下检测环境,可识别弯曲度较小的水下电缆轨迹并进行准确定位,检测成本低且易于实现,为水下电缆巡检工作提供技术支持。
An underwater cable positioning method based on machine vision and Kalman filtering was designed to effectively detect underwater cables.The machine vision technology was used to process the collected underwater cable images,and then the relative position information of the cable was obtained according to the underwater system coordinate model and the parameters in the camera.The Kalman positioning fusion algorithm was applied to reduce the deviation value generated after the track calculation to correct the underwater robot(Remote Operated Vehicle,ROV)tracking path.It was shown that the proposed method is suitable for underwater inspection environments with low imaging quality,and can identify and accurately locate underwater cable trajectory with smaller curvatures.The inspection cost is low and easy to implement.It provides technical support for underwater cable inspections.
作者
郭雨薇
刘俊
严允
GUO Yu-wei;LIU Jun;YAN Yun(School of Mechanical Engineering,Shanghai Dianji University,Shanghai 201306,China;CRRC SMD Shanghai Ltd.,Shanghai 201306,China)
出处
《船海工程》
北大核心
2022年第5期126-130,136,共6页
Ship & Ocean Engineering
基金
国家自然科学青年基金(12002198)。
