Image-based intelligent ship identity recognition method

Abstract

The invention discloses an image-based intelligent ship identity recognition method. The image-based intelligent ship identity recognition method mainly includes the following steps: 1) establishing an image-based ship information database for ships passing through a navigation channel for the first time; 2) capturing a navigation channel area and judging whether ships exist in the navigation channel area; 3) positioning and dividing a ship area; 4) extracting image features of ships; and 5) matching the features of the ships in the capture area with the ship information of the ship database to determine the identity of the ships. The image-based intelligent ship identity recognition method positions the ships and recognizes the identity of the ships by means of a deep learning method, andadopts a parallel acceleration processing method for processing large-scale ship information data, thus having the advantages of high recognition rate, high response speed, and very wide applicationprospects.

Description

technical field [0001] The invention relates to the field of maritime intelligent transportation, in particular to an image-based intelligent ship identification method. Background technique [0002] In recent years, the development of intelligent transportation has been very rapid, but it is basically based on the vehicle detection and recognition of land transportation with a fixed background. For water transportation, there are the following difficulties: 1. The background on the water is not fixed, and it is affected by weather such as light, rain and fog 2. The river surface is generally very wide, and the distance detection results of ship targets are quite different; 3. The camera built on the riverside is affected by the wind, and the photo capture shakes a lot. Therefore, the ship supervision on the river has always been based on Radar and AIS complement each other for supervision. [0003] However, both radar and AIS have a disadvantage that they are not intuitive...

AI Technical Summary

Problems solved by technology

[0002] In recent years, the development of intelligent transportation has been very rapid, but it is basically based on the vehicle detection and recognition of land transportation with a fixed background. For water transportation, there are the following difficulties: 1. The background on the water is not fixed, and it is affected by weather such as light, rain and fog 2. The river surface is generally very wide, and the distance detection results of ship targets are quite different; 3. The camera built on the riverside is affected by the wind, and the photo capture shakes a lot. Therefore, the ship supervision on the river has always been based on Radar and AIS complement each other to monitor

[0003] However, both radar and AIS have a disadvantage that they are not intuitive, and they cannot directly see the scene of ship traffic like video, which is especially important in the process of accidents and search and rescue.

Images