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

Ship target recognition method based on transfer learning

A technology of transfer learning and ships, which is applied in the field of ship target recognition based on transfer learning, can solve the problems of high computational complexity and inability to guarantee fast operation, and achieve the effect of excellent classification performance

Pending Publication Date: 2019-05-24
SHANGHAI JIAO TONG UNIV
View PDF5 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these two different methods have achieved good test accuracy in multi-category recognition tasks, there is still a certain room for improvement, and the computational complexity is high, which cannot guarantee the speed of operation

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 target recognition method based on transfer learning
  • Ship target recognition method based on transfer learning
  • Ship target recognition method based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Such as figure 1 As shown, it is a method for ship target recognition based on transfer learning involved in this embodiment, which specifically includes the following steps:

[0023] Step 1. Perform preprocessing, data enhancement, and division of positive and negative samples of the training set and test set in sequence on the sample image, specifically:

[0024] 1.1) In order to meet the size requirements of the input layer of the network model and improve the efficiency of the training process, the data set is first preprocessed, that is, the pictures are uniformly processed into 64×64 and 229×229 sizes (similar Le-Net5 input is 64×64, the input of InceptionV3 is 229×229), and the image format is jpg.

[0025] 1.2) In order to avoid the problem of overfitting, expand the scale of the data set, and perform data enhancement on the preprocessed data set, the specific plan is to use XnView software to add noise disturbance and geometric transformation to the picture, w...

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 target identification method based on transfer learning. Firstly, a data set is generated through a data enhancement method; optimizing and dividing the data set based on the number of positive and negative samples to obtain a training set and a test set; In order to avoid overfitting caused by a small sample data set, adopting an Inception V3 model to train and testthe data set in a transfer learning mode; taking the quantitative evaluation index as a quantitative evaluation index, selecting a video frame shot in a real scene to carry out a comparison test, obtaining a series of coordinate points by setting a threshold value, drawing a qualitative evaluation index ROC curve, and generating classification information as a qualitative evaluation index. According to the method, high-precision classification and high-operation-efficiency identification of the ship target domain can be realized without manually extracting features, and the method has a higher classification recall rate and a higher operation speed.

Description

technical field [0001] The present invention relates to a technology in the field of image processing, in particular to a ship target recognition method based on migration learning. Background technique [0002] With the rapid development of water traffic, the water surface road conditions are becoming more and more complicated. The frequent occurrence of ship-bridge collision accidents has led to certain safety hazards in river navigation. Therefore, effective and accurate target recognition for ships is a necessary measure. Object recognition is an important research method in the field of computer vision. The traditional implementation algorithm is mainly based on artificial feature design. Since the features of the target are often affected by factors such as light intensity, shooting angle, and contour texture, there are defects in manual feature extraction, and the operator cannot effectively extract the target deep characterization. [0003] Aiming at the feature l...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
Inventor 肖刚张星辰乔丹赵俊豪冶平
Owner SHANGHAI JIAO TONG 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