The invention provides a ship water gauge automatic detection method and system. Video images of different ships are acquired by using unmanned aerial vehicle equipment and are converted into trainingwater gauge scale pictures, actual water gauge scales of the training water gauge scale pictures are read by using ship water gauge reading experience, and a training data set is established; the deep learning VGG network model is trained by using the training data set to obtain a trained deep learning VGG network model; finally, a video image of a ship to be detected is acquired by the unmannedaerial vehicle, the video image is converted into a test water gauge scale picture, and the test water gauge scale picture is input into the trained deep learning VGG network model to obtain a prediction result, thereby achieving the purpose of ship water gauge identification automatic detection. Calculation speed is improved. According to the invention, high-precision automatic detection of the ship waterline scale can be realized rapidly and accurately under various extreme environment conditions.
本发明提出了一种船舶水尺自动检测方法及系统。本发明利用无人机设备获取不同船舶的视频影像,并将其转化成训练水尺刻度图片,利用船舶水尺读数经验读取训练水尺刻度图片的实际水尺刻度,建立训练数据集;利用训练数据集对深度学习VGG网络模型进行训练,得到训练后的深度学习VGG网络模型;最后,通过无人机获取待检测船舶的视频影像并转化为测试水尺刻度图片,输入训练后的深度学习VGG网络模型,得到预测结果,从而实现船舶水尺识自动检测的目的,而且本发明基于结合了批量标准化处理的深度学习神经网络,提高了计算的速度。本发明实现了在各种极端环境状况下,快速、准确地对船舶水线刻度进行高精度自动检测。
Ship water gauge automatic detection method and system
一种船舶水尺自动检测方法及系统
2021-02-09
Patent
Electronic Resource
Chinese