Ship behavior identification method based on deep learning

A technology of deep learning and behavior, applied in the field of ship behavior recognition based on deep learning, can solve the problems of clustering method distribution interference, time-consuming, easy to ignore effective information, etc.

Active Publication Date: 2019-09-13
HANGZHOU DIANZI UNIV
View PDF2 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1. Need to manually design features, it is easy to ignore a lot of effective information;
[0005] 2. The calculation overhead depends on the established model, wh

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 behavior identification method based on deep learning
  • Ship behavior identification method based on deep learning
  • Ship behavior identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The technical solutions provided by the present invention will be further described below in conjunction with the accompanying drawings.

[0060] see figure 1 , the present invention provides a ship behavior recognition method based on deep learning, figure 1 Shown is the overall architecture diagram of the deep learning-based ship behavior recognition method of the present invention. On the whole, the present invention includes two major steps, step S1: self-built ship behavior recognition data set through data preprocessing and track segmentation method; step S2 : Design a ship behavior recognition network, use the data set training in step S1 to realize the recognition of ship behavior;

[0061] Step S1 is based on the AIS data of the ship automatic identification system, and uses the abnormal position processing method and the abnormal speed processing method to process the abnormal data in the data, which reduces the influence of data noise on the network results;...

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 behavior identification method based on deep learning, and belongs to the field of mode identification. The ship behavior identification method can be applied to the fields of intelligent marine monitoring, ship intelligent supervision and the like. The ship behavior identification method specifically comprises the steps: S1, acquiring original ship track data, and building a ship behavior identification data set through a data preprocessing and track segmentation method; and S2, designing a ship behavior identification network in which the multi-scale convolution module and the long-short-term memory network are cascaded, and realizing behavior identification of the ship track data by using the ship behavior identification network trained by the self-built ship behavior identification data set. By the adoption of the technical scheme, the ship behavior identification technology is applied to the field of ship supervision, and ship behaviors are automatically analyzed from mass ship track data, and effective evidence obtaining and supervision can be conducted on ship behavior activities of offshore oceans, and a low-efficiency manual inspection mode is replaced. The whole scheme has the characteristics of low dependence on equipment, high identification accuracy, high identification speed and the like.

Description

technical field [0001] The invention relates to the technical field of ship behavior pattern recognition, in particular to a method for ship behavior recognition based on deep learning. Background technique [0002] my country has abundant marine resources and port resources. With the further development and utilization of marine resources, the number of ships of various types is increasing day by day, and maritime traffic activities are becoming more and more frequent. There are various acts of using ships to carry out illegal activities, including smuggling, Illegal immigration, illegal fishing, etc. The automatic identification system (Automatic Identification System, AIS) is a new type of navigation aid system, which can help relevant departments coordinate marine traffic and supervise marine activities. For example, during the fishing ban period of marine pastures, AIS data can be used to analyze whether there is illegal fishing. At present, most ships with a displacem...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/049G06N3/082G06V40/20G06V20/00G06N3/045G06F18/2414
Inventor 刘俊王立林田胜徐小康姜涛
Owner HANGZHOU DIANZI UNIV
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