A ship waterline area identification method based on machine vision

Abstract

The invention discloses a ship draft area identification method based on machine vision. The method comprises acquiring a ship water gauge image through an unmanned aerial vehicle; detecting a water gauge scale outline contained in the image by adopting a machine vision algorithm; calculating prediction intervals of the horizontal direction and the vertical direction of the draft line through statistical screening and a clustering algorithm; according to the ship waterline area identification method, installation of equipment such as a pressure sensor and laser water level detection can be avoided, the equipment cost for identifying the waterline is remarkably reduced, and the ship waterline area identification method has good operability; the recognition method based on machine vision canrealize accurate positioning of the waterline according to ship water gauge characters and the waterline as markers, effectively overcomes the influence of port complex scenes on waterline positioning, is low in calculation complexity, and can meet the requirements of port waterline recognition on rapidity and accuracy.

Description

technical field [0001] The invention relates to a computer vision-based recognition method for a waterline area of ​​a ship, belonging to the technical field of image processing. Background technique [0002] The identification of the weight of import and export cargo is one of the important tasks of the port. At present, the main identification method is the weight of the water gauge. The test results of the waterline directly affect the accuracy of cargo weighing, and are related to the transfer and settlement of goods, dispute claims, port pricing fees and tariff calculations. Therefore, how to quickly and accurately measure the waterline has received more and more attention. [0003] At present, pressure sensor detection, laser water level detection and image detection are usually used instead of manual measurement methods to realize the estimation of the ship's waterline and improve the real-time performance and weighing accuracy of port management. Among them, the pre...

AI Technical Summary

Problems solved by technology

At the same time, it solves the problem that the pressure sensor detection is not accurate enough to identify the waterline of the ship due to the wear and tear of the instrument, the floating objects in the laser water level detection have an impact on the measurement accuracy, and the traditional image processing technology lacks the waterline and waterline in the ship pictures taken under complex conditions. The problem of corresponding character area recognition

Images