Ship name recognition system and method based on deep learning framework

A deep learning and recognition system technology, applied in neural learning methods, scene recognition, character and pattern recognition, etc., can solve the problems of different character lengths, poor fitting ability of classifiers, and limited recognition ability of ship names, etc., to eliminate The effect of management blind spots

Active Publication Date: 2020-11-24
WUHAN UNIV OF TECH
View PDF8 Cites 1 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
  • Ship name recognition system and method based on deep learning framework
  • Ship name recognition system and method based on deep learning framework
  • Ship name recognition system and method based on deep learning framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

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

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

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

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

Embodiment 2

[0055] Such as figure 2 and image 3 Shown is a schematic flow chart of a deep learning-based ship name recognition method provided by an embodiment of the present invention, including the following steps:

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

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

[0058] S3: Detect the threshold of the target object, mark the target object, form a label frame 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 combine the label frame Get the confidence of the target;

[0059] In the embodiment of the present invention, the target object threshold represents the threshold of t...

Embodiment 3

[0076] The present application also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card memory (for example, SD or DX memory, etc.), 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 Storage, Magnetic Disk, Optical Disk, Server, App Store, etc., on which computer programs, program When executed by a processor, the ship name recognition method based on the deep learning framework in the method embodiment 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, and belongs to the field of deep learning, and the system mainly consists of a maritime supervision unmanned plane, an airborne image processing module, an airborne communication module, and a maritime supervision center. The unmanned aerial vehicle cruises a maritime supervision area, collects illegal ship image information of the supervision area and transmits the illegal ship image information to the image processing module. The image processing module judges the position of the ship name information by adopting a deep learning artificial intelligence algorithm, and then identifies character information contained in the ship name position area to obtain ship name information in the target ship image, and transmits the ship name information to a maritime affair monitoring center through an airborne communication module to perform law-dependent management and control on maritime affair illegal behaviors. According to the invention, illegal ship name information can be effectively identified, and an effective solution is provided for a ship name identification problem in maritime affair 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 technique [0002] In maritime supervision, the identification of ships has always been a very important topic, and the name of the ship is one of its most important identity information, marking the basic identity information of the ship. According to the regulations of the International Maritime Organization (IMO), non-international voyage ships over 300 gross tonnage and international voyage ships over 500 gross tonnage must be equipped with automatic identification system (Automatic Identification System, AIS) equipment. The above regulations have not made mandatory installation of AIS for ships below 300 gross tonnage. At the same time, for reasons such as saving fuel costs, evading the supervision of the competent authority, and AIS equipment failure, some operating ships ...

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
IPC IPC(8): G06K9/00G06K9/32G06T7/73G06N3/04G06N3/08
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