Image-based intelligent ship identity recognition method

A technology for identification and ships, applied in ship traffic control, character and pattern recognition, instruments, etc., can solve the problems of large photo capture shake, unstable water background, unintuitive radar and AIS, etc., to ensure safety and reduce manpower Burden, consolidate and stabilize the effect

Inactive Publication Date: 2018-11-13
中船重工鹏力(南京)大气海洋信息系统有限公司 +1
View PDF10 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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 target

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
  • Image-based intelligent ship identity recognition method
  • Image-based intelligent ship identity recognition method
  • Image-based intelligent ship identity recognition method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0031] The present invention will be further described in detail below in conjunction with the drawings and specific preferred embodiments.

[0032] Such as figure 1 As shown, an image-based smart ship identification method includes the following steps.

[0033] Step 1. Establish a training data set: use a variety of different types of ship pictures and use a convolutional neural network-based method for training to obtain a training data set.

[0034] When the above training data set is established, it is preferable to use more than 1,000 different ships and no less than 5,000 photos for training.

[0035] Specific training network such as Image 6 As shown, the specific training method is the prior art, and will not be described in detail this time. For each picture in the training data set, pre-processing such as size adjustment is performed before entering the neural network, and the position of the ship of each picture in the training data set corresponds to the corresponding ho...

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 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...

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): G08G3/00G06K9/62G06K9/46
CPCG08G3/00G06V10/443G06F18/214
Inventor 田池唐吉徐坤夏金锋周晓安张金松张杰朱德理石志国陆月晴
Owner 中船重工鹏力(南京)大气海洋信息系统有限公司
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