Ship water gauge automatic detection method and system

Abstract

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.

Description

technical field [0001] The invention relates to the field of ship safety management, in particular to a method and system for automatic detection of ship water gauges. Background technique [0002] As the globalization of the trade economy becomes more and more prosperous, sea transportation methods such as ocean freighters and cruise ships have always occupied a very important position in the development of global trade. Water gauge readings are an important basis for ship weight and ship stowage safety assessment, and the accuracy of water gauge readings will affect the safety and efficiency of shipping. In the process of water gauge reading, subjective and objective factors such as weather conditions, observation experience, presence or absence of obstacles, and heavy workload lead to large errors in reading results, which in turn cause a series of problems. [0003] At present, there are mainly two methods for ship draft detection, namely, manual visual inspection and a...

AI Technical Summary

Problems solved by technology

In addition, the inspectors will often encounter rain, snow or strong wind and waves. These conditions have brought many difficulties and changes to the observation of water gauge readings.

The method of automatic device detection mainly uses electronic components such as pressure sensors and ultrasonic sensors to measure the scale of the water gauge. This method has high requirements for the accuracy of the sensor. In addition, the sensor is placed in a humid environment, and the electronic circuit is not easy to arrange. The components are affected by the density of the medium, The influence of ambient temperature leads to excessive noise disturbances and large measurement errors. Therefore, the convenience and accuracy of this method in actual measurement applications are not ideal.

The detection process of the ship draft is seriously affected by external influences such as sea color, transparency, illumination level, and spray size. Traditional image processing methods are difficult to accurately monitor under complex and changeable conditions. Therefore, there is an urgent need for a Under such extreme environmental conditions, the high-precision automatic detection method can quickly and accurately measure the scale of the ship's waterline, and truly realize the automation and intelligence of the ship's water gauge detection

Images