The invention provides an unmanned ship underwater target detection and autonomous identification system and method based on deep learning. The system comprises an underwater target detection system, a shipborne distributed target autonomous identification system and an automatic laying and recovery system. The method comprises the following steps: sensing an underwater environment by using a foresight sonar and a synthetic aperture sonar to generate high-resolution image data; the detection data is uploaded to a shipborne distributed target autonomous identification module by using an optical fiber towing cable; performing target autonomous identification on the detected data by using a deep learning algorithm; displaying the detection data and the target identification result by using display control software; and the towed body is automatically released and recycled by using the automatic laying device. Through cooperation of the three system modules, the high-precision autonomous detection and identification function of the unmanned surface vehicle is realized, and a new solution is provided for underwater detection and identification of the unmanned surface vehicle.
本发明提出一种基于深度学习的无人艇水下目标探测与自主识别系统和方法,包括水下目标探测系统、船载分布式目标自主识别系统和自动布放回收系统;利用前视声纳和合成孔径声纳感知水下环境,生成高分辨率图像数据;利用光纤拖缆将探测数据上传至船载分布式目标自主识别模块;利用深度学习算法对探测的数据进行目标自主识别;利用显控软件对探测数据和目标识别结果进行显示;利用自动布放装置对拖体进行自动释放与回收。通过三个系统模块的协同配合,实现水面无人艇的高精度自主探测识别功能,为水面无人艇水下探测识别提供一种新的解决方案。
Unmanned ship target detection and autonomous identification system and method based on deep learning
基于深度学习的无人艇目标探测与自主识别系统和方法
2023-05-30
Patent
Electronic Resource
Chinese
Full-autonomous water quality detection unmanned ship system
European Patent Office | 2023
|Unmanned ship underwater target intelligent identification method based on imaging sonar
European Patent Office | 2023
|