基于深度学习的AUV水下视觉导引检测方法  

Underwater Visual Guidance Deep Learning Detection Method for AUV

作　　者：安平 王亭亭 赵渊 胡宁[1] AN Ping;WANG Tingting;ZHAO Yuan;HU Ning(China Academy of Aerospace Aerodynamics,Beijing 100074,China)

机构地区：[1]中国航天空气动力技术研究院,北京100074

出　　处：《水下无人系统学报》2023年第3期421-429,共9页Journal of Unmanned Undersea Systems

基　　金：国家自然科学基金项目(11872348)。

摘　　要：自主水下航行器(AUV)自主对接与回收技术主要通过导引定位的方式实现AUV与对接装置的自主归航、接近、对接及锁紧等动作。为满足AUV水下自主对接过程中实时性、高精确性和鲁棒性等要求,提出一种基于深度学习的水下视觉导引检测方法。针对复杂水下场景下传统图像处理方法检测效果不佳的问题,使用基于YOLOv5的深度学习视觉导引检测方法对导引光源以及对接装置进行检测。首先,将目标图像数据接入YOLOv5模型进行迭代训练,将训练得到的最优模型参数保存用于后续实时检测;然后,在水下自主对接过程中, AUV使用机器人操作系统平台实时读取水下数据并调用YOLO服务对水下图像进行检测,输出导引光源以及对接装置位置信息;同时通过位置解算,将检测得到的中心点坐标转化到AUV相机坐标系下;最后将解算得到的AUV与对接装置的相对位置与AUV的航行方向持续反馈给AUV,进行引导直至对接完成。在海试中对水下视觉导引的实际检测准确率为97.9%,检测单帧耗时为45 ms,试验结果表明该方法满足自主对接与回收技术中对水下对接精度及实时性要求,具有实际应用价值。The autonomous docking and recovery of autonomous undersea vehicle(AUV)technology mainly realizes theautonomous homing,approaching,docking,and locking of the AUV and the docking device by means of guidance andpositioning.To satisfy the requirements of real time,high accuracy,and robustness in the process of AUV underwaterautonomous docking,an underwater visual guidance detection method based on deep learning is proposed.To address the poordetection effect of traditional image processing methods in complex underwater scenes,the guiding light source and dockingdevice are detected by employing a deep learning visual guidance detection method based on the YOLO(you only lookonce)v5 model.First,the object images are sent to YOLOv5 model for iterative training,and the optimal model parametersobtained from the training are saved for subsequent real-time detection.Subsequently,in the underwater autonomous dockingprocess,the AUV utilizes the robot operating system(ROS)platform to read the underwater data and call the YOLO service todetect the underwater image in real-time,thereby outputting the location information of the guidance light source and thedocking device.Based on position calculation,the detected center coordinates are transformed into the AUV cameracoordinate system.Finally,the relative positions of the AUV with respect to the docking device and navigation directions ofthe AUV are calculated continuously and fed back into the AUV,which provides real-time guidance information until the docking progress is completed.In the sea trail,the actual accuracy of underwater visual guidance detection was 97.9%,and thedetection time of a single frame was 45 ms.The test results demonstrate that this method meets the requirements of real-timeunderwater docking accuracy for autonomous docking and recovery technology,and has practical application value.

关 键 词：自主水下航行器 水下自主对接 视觉导引 图像处理 深度学习 

分 类 号：U674.7[交通运输工程—船舶及航道工程] TP391.4[交通运输工程—船舶与海洋工程]