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

Military ship and civilian ship automatic identification method based on deep learning

A deep learning and automatic identification technology, applied in the automatic identification of civilian ships and the field of military ships based on deep learning, can solve the problems of non-reuse of features and suboptimal feature extraction.

Inactive Publication Date: 2018-10-02
HANGZHOU DIANZI UNIV
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The features of each layer of the traditional deep learning target recognition network are not reused, including fully connected layers with excessive weight parameters, resulting in suboptimal feature extraction

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
  • Military ship and civilian ship automatic identification method based on deep learning
  • Military ship and civilian ship automatic identification method based on deep learning
  • Military ship and civilian ship automatic identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The method for automatic identification of military ships and civilian ships based on deep learning provided by the present invention will be further described below in conjunction with the accompanying drawings.

[0059] Aiming at the relevant technical problems existing in the prior art, this invention starts from the concept of intelligent recognition of military ships and civilian ships, and combines the most advanced technical means of deep learning in target detection, and proposes a target recognition method based on dense full convolutional neural network. This method can accurately detect military ships and civilian ships.

[0060] In order to solve the technical problems existing in the prior art, the present invention proposes an automatic recognition method for military ships and civilian ships based on deep learning——DRFCN2, specifically as figure 1 , including the following step (1): Generate as few high-quality sampling regions as possible through a regio...

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 military ship and civilian ship automatic identification method based on deep learning, and belongs to the field of automatic target identification based on the image. The method can be applied to the field of coast defence, weapon and equipment intellectualization and situation assessment. According to the method, an algorithm model of densely connected convolution layers is redesigned for the problems that all the layers of the conventional target identification network based on deep learning are unidirectionally connected and the feature expression capacity is insufficient. The algorithm model reuses the features of each layer by using the dense connection mode so that the target identification average accuracy of the algorithm model can be enhanced; the full connection layer of excessively high weight parameter is eliminated by the algorithm model by using the full convolution feature extraction mode, and the algorithm model trained by the mode is smaller;besides, the problems of gradient diffusion and gradient expansion can be solved by the algorithm model.

Description

technical field [0001] The invention belongs to the field of image-based automatic target recognition, and in particular relates to an automatic recognition method for military ships and civilian ships based on deep learning. Background technique [0002] Under the new situation, networked joint operations present the characteristics of land, sea, air, space, electromagnetic, and cyber multi-dimensional battlefield integration operations. Carrier, surface, underwater, ship mount, database system), multi-source sensors (SAR / ISAR, infrared camera, hyperspectral / multispectral / low light / EO / visible light, sonar, laser, millimeter wave) and other ways can obtain Massive image and video data, the data source has the characteristics of "5V+1C", namely: Volume (large capacity), Variety (diversity), Velocity (timeliness) and Veracity (accuracy), Value (value) and Complexity (Complexity). Therefore, it is particularly important how to find out the required military ships, civilian sh...

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
CPCG06N3/08G06V20/46G06N3/045G06F18/241
Inventor 刘俊孟伟秀黄亮潘浩谷雨
Owner HANGZHOU DIANZI 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com