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

A deep learning laser underwater target recognition instrument with improved target clustering characteristics

A deep learning and underwater target technology, which is applied in the field of deep learning laser underwater target recognition, can solve the problems of image resolution enlargement or reduction, large combination space, and human inability to exhaustively.

Active Publication Date: 2022-06-24
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is very difficult to manually adjust the network depth, width, and image resolution to enlarge or reduce. When the amount of calculation is limited, it is difficult to determine which one is enlarged or reduced. In other words, such a combination Too much space, manpower cannot exhaustively

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
  • A deep learning laser underwater target recognition instrument with improved target clustering characteristics
  • A deep learning laser underwater target recognition instrument with improved target clustering characteristics
  • A deep learning laser underwater target recognition instrument with improved target clustering characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be specifically described below with reference to the accompanying drawings.

[0024] figure 1 It is the workflow of the deep learning laser underwater target recognition instrument to improve the target clustering characteristics. The specific implementation process is as follows:

[0025] 1) The underwater laser scanning device performs laser scanning in the working area, forms point cloud data and transmits it back to the computing device through the cable.

[0026] 2) The EfficientNet convolutional neural network model sum combined with the improved metric learning loss function is integrated in the computing device, and the identification process is as follows:

[0027] 2.1) Process the laser point cloud data into three-channel image data, and input the EfficientNet convolutional neural network model combined with the improved metric learning loss function stored in the data storage device.

[0028] 2.2) Calculate the triple loss of har...

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 deep learning laser underwater target recognition instrument for improving target clustering characteristics. It consists of an underwater laser scanning device connected in sequence, a computing device, a storage device, and a display device. The underwater laser scanning device scans the underwater area to be detected, and transmits the obtained laser point cloud data to the computing device, converting it into It is two-dimensional image data, which is then transmitted into the storage device for storage and displayed by the display device. By adding the metric learning loss, the present invention can guide the network to reduce the metric distance of the extracted feature vectors of the same category of targets, and increase the metric distance of feature vectors between different targets, thereby improving the clustering effect of the network on laser underwater target data , to improve the recognition accuracy.

Description

technical field [0001] The invention relates to a laser underwater target recognition technology, in particular, to a deep learning laser underwater target recognition device for improving target clustering characteristics. Background technique [0002] Laser underwater target recognition technology is an advanced detection technology currently under development. It integrates laser technology, communication technology, signal processing, target recognition and electronic technology, and has broad application prospects. The research and development of this technology is of great value both in theory and in practical application. Since the early 1990s, the outstanding performance of the American "Magic Lantern" system in the Gulf War has made laser underwater target recognition technology a hot research topic in various countries. It is one of the key technologies in ocean exploration and development in the past two decades. First, in my country, it is still in the stage of 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 Patents(China)
IPC IPC(8): G06V20/05G06V10/82G06V10/774G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/00G06N3/045G06F18/214
Inventor 吕以豪王文海高洁卢建刚陈金水刘兴高
Owner ZHEJIANG 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