Ship board number position positioning method and system based on deep learning

Abstract

The invention provides a ship board number position positioning method and system based on deep learning, and the method comprises the steps: S1, carrying out the data collection, and obtaining a picture with ship board number information; S2, marking the position of the ship board number in the ship board number picture through marking software; S3, establishing a deep learning neural network anda target identification model, training the target identification model by taking the marked ship board number picture as input, and identifying position coordinates of the ship board number in the picture; S4, based on port monitoring camera videos, processing low-brightness images with water mist and fuzzy images by utilizing image defogging and image enhancement technologies; S5, inputting theprocessed picture into a deep learning neural network, and carrying out ship board number position prediction and positioning identification to obtain ship board number position coordinates. According to the method, the multi-target ship board number can be identified and positioned, and the method has a good application scene in a complex port environment.

Description

technical field [0001] The present invention relates to the technical field of deep learning and target detection, in particular to a method and system for locating the position of ship's ship number based on deep learning. Background technique [0002] In recent years, with the development of world trade, maritime trade has flourished, and there are more and more ships, but with it, various smuggling, sand stealing, fish stealing and other activities are rampant. means of evading supervision. Traditional manual detection is slow, time-consuming and labor-intensive, and fails to achieve the purpose of effective supervision. Now large-scale ports and key river areas are equipped with high-definition cameras, which can monitor key areas through video. With the development of big data and artificial intelligence, fixed-size text recognition is developing rapidly, but how to obtain ship number location from video pictures Facilitating later text recognition has become a key bo...

AI Technical Summary

Problems solved by technology

Traditional manual detection is slow in efficiency, time-consuming and laborious, and fails to achieve the purpose of effective supervision

Now large ports and key river areas are equipped with high-definition cameras, which can monitor key areas through video. With the development of big data and artificial intelligence, fixed-size text recognition is developing rapidly, but how to obtain ship number location from video pictures Convenience of later text recognition becomes the key bottleneck of ship number recognition

Images