Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Non-standard nameplate recognition system based on artificial intelligence and recognition method thereof

A technology of artificial intelligence and recognition system, applied in the field of artificial intelligence and computer vision, can solve the problems of missing ships, difficulty of ship name signs and rising costs, and achieve the effect of improving safety factor and low construction cost

Pending Publication Date: 2019-07-09
SUZHOU UNIV
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, due to the aging of the ship, obstacles, etc., it is not realistic to directly separate the complete character from the ship
For various reasons, the nameplate of the ship is a non-standard nameplate, which is quite different from the license plate. Therefore, it is difficult to apply the mature license plate recognition technology to the ship.
[0006] On the other hand, the innovative method based on the ship name signboard is difficult to put into a large number of applications, and it cannot achieve a sufficiently comprehensive ship name recognition, and there may be missing ships
At the same time, the system has a certain installation cost, and as the measurement accuracy increases, the cost will also increase a lot

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
  • Non-standard nameplate recognition system based on artificial intelligence and recognition method thereof
  • Non-standard nameplate recognition system based on artificial intelligence and recognition method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] Embodiment: A non-standard nameplate recognition system based on artificial intelligence, including an image acquisition module, a character recognition module and a ship name filling module.

[0027] The image acquisition module includes a plurality of network cameras erected on both sides of the waterway, monitors the information of ships in all directions of the whole waterway in real time, and simultaneously collects photos of ships and non-standard nameplates from multiple angles and makes sample pictures. The network cameras include No. 1 network Camera, No. 2 network camera, No. 3 network camera and No. 4 network camera, among which No. 1 network camera, No. 2 network camera and No. 4 network camera are small focal length cameras, and the cameras of the three network cameras pass through the left, forward and Installed to the right, it can obtain comprehensive ship information on the entire channel, and at the same time monitor the ships passing by in real time an...

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 non-standard nameplate recognition system based on artificial intelligence and a recognition method thereof. The recognition system comprises an image acquisition module anda character recognition module. The image acquisition module comprises a plurality of network cameras erected on the two sides of the channel, monitors ship information of all directions of the wholechannel in real time, collects ship and non-standard nameplate pictures from multiple angles and makes sample pictures; The character recognition module is used for making the collected sample pictures into a large sample data set through a target detection algorithm based on deep learning, and putting the large sample data set into a network for large sample training to realize recognition of ship nameplate characters; the system and the method have the advantages that the nameplate of a coming ship can be acquired and identified in real time, so that early warning and management can be timely and accurately performed on the ship under the conditions of ship overload, air route deviation and the like, and meanwhile, the identification system and the identification method thereof are alsosuitable for other non-standard nameplate application scenarios.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and computer vision, and in particular relates to an artificial intelligence-based non-standard nameplate recognition system and a recognition method thereof. Background technique [0002] Since ancient times, waterway shipping has been one of the most important modes of transportation in human society, and has played a vital role in promoting economic globalization. However, as the number of ships continues to rise, waterways are becoming more and more congested, and a series of incidents such as overloaded transportation and illegal escapes are also threatening the safety of human life and property. Therefore, the state achieves the purpose of mass management of ships through the registration management of ship name identification. At present, human beings are in the era of intelligence, and related technologies in the field of artificial intelligence and computer vision are con...

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): G06K9/32G06K9/62
CPCG06V20/63G06V30/10G06F18/241Y02A10/40
Inventor 羊箭锋祝啟瑞周怡袁传平温建新郑宾
Owner SUZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products