A ship name recognition system and method based on deep learning framework

A deep learning and ship technology, applied in the field of deep learning, can solve the problems of different character lengths, limited ship name recognition ability, poor classifier fitting ability, etc., to achieve the effect of eliminating the blind spot of management

Active Publication Date: 2022-05-06
WUHAN UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The fitting ability of the classifier selected in the traditional character recognition method is poor, and the recognition accuracy is very dependent on the preprocessing work before recognition (such as character correction, character segmentation, etc.). limited ability to recognize

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A ship name recognition system and method based on deep learning framework
  • A ship name recognition system and method based on deep learning framework
  • A ship name recognition system and method based on deep learning framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] as Figure 1 Shown is the structural diagram of a ship name recognition system based on deep learning provided by the embodiment of the invention, including: maritime supervision UAV, airborne image processing module, airborne communication module and maritime monitoring center;

[0042] The maritime supervision UAV is equipped with airborne image processing module and airborne communication module, and the airborne communication module is connected with the maritime monitoring center;

[0043] The maritime supervision UAV collects the target ship image and transmits the target ship image to the airborne image processing module, in which the target ship image includes the ship name information;

[0044] The airborne image processing module uses the deep learning artificial intelligence algorithm to determine the position of the ship name information, then recognizes the character information contained in the ship name position area, obtains the ship name information in the t...

Embodiment 2

[0055] as Figure 2 and Figure 3 Shown is the flow diagram of a ship name recognition method based on deep learning provided by the embodiment of the invention, including the following steps:

[0056] S1: capture the image of the target ship containing the ship name through the maritime supervision UAV;

[0057] S2: take the target ship image as the input of the trained deep learning recognition model, extract the image features of the suspected ship name in the target ship image, and form the target object;

[0058] S3: detect the target threshold, label the target, form a label box containing the ship name information in the target ship image, locate the position of the ship name information based on the trained deep learning recognition model, and obtain the confidence of the target combined with the label box;

[0059] In the embodiment of the invention, the target threshold represents the threshold of the target ship image.

[0060] In the embodiment of the invention, labeling...

Embodiment 3

[0076] The application also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card type memory (such as SD or DX memory), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disc, server, APP application mall, etc, The computer program is stored on it. When the program is executed by the processor, the ship name recognition method based on deep learning framework in the embodiment of the method is realized.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a ship name recognition system and method based on a deep learning framework, which belongs to the field of deep learning. The system is mainly composed of a maritime supervision drone, an airborne image processing module, an airborne communication module and a maritime supervision center. The UAV patrols the maritime supervision area, collects image information of illegal ships in the supervision area and transmits it to the image processing module; the image processing module uses deep learning artificial intelligence algorithm to determine the location of the ship name information, and then calculates the ship name location area The contained character information is identified, and the ship name information in the target ship image is obtained, and the ship name information is transmitted to the maritime monitoring center through the airborne communication module, and the maritime violations are controlled according to law. The invention can effectively identify the illegal ship name information, and provides an effective solution to the problem of ship name identification in maritime supervision.

Description

technical field [0001] The invention belongs to the field of deep learning, and more specifically relates to a ship name recognition system and method based on a deep learning framework. Background technology [0002] In maritime supervision, ship identification has always been a very important topic, in which ship name is one of the most important identity information, which identifies the basic identity information of the ship. According to the regulations of the International Maritime Organization (IMO), non international navigation ships with a gross tonnage of more than 300 tons and international navigation ships with a gross tonnage of more than 500 tons must be mandatory to install automatic identification system (AIS) equipment. The above provisions have not made provisions on the compulsory installation of AIS for ships below 300 gross tons. At the same time, some operating ships shut down AIS equipment without authorization for reasons such as saving fuel cost, evading ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06V30/194G06V20/00G06T7/73G06N3/04G06N3/08
CPCG06T7/73G06N3/08G06T2207/20081G06T2207/20084G06T2207/30232G06V20/13G06V20/63G06N3/045
Inventor 马勇王京徐扬严新平
Owner WUHAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap