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

YOLOv5-based side-scan sonar ocean sediment identification method and device

A side-scan sonar and identification method technology, applied in the field of computer vision, can solve problems such as easy omissions, low identification efficiency, and long time-consuming manual identification, so as to speed up the research process, improve objectivity, and improve detection efficiency.

Pending Publication Date: 2022-05-10
THIRD INST OF OCEANOGRAPHY MINIST OF NATURAL RESOURCES +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a side-scan sonar ocean bottom identification method and device based on YOLOv5, to solve the problem that manual identification takes a long time, is easy to miss, and has low identification efficiency in large areas including multiple types of ocean bottom. The problem

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
  • YOLOv5-based side-scan sonar ocean sediment identification method and device
  • YOLOv5-based side-scan sonar ocean sediment identification method and device
  • YOLOv5-based side-scan sonar ocean sediment identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0039] Embodiments of the present invention provide a side-scan sonar ocean bottom identification method based on YOLOv5, such as figure 1 As shown, the method includes the following steps:

[0040] S101. Obtain the raw data of the ocean bottom based on the side-scan sonar, and obtain an image of the ocean bottom based on the side-scan sonar after analysis and reconstruction.

[0041] In this step, the original file data of the side-scan sonar ocean bottom to be identified is obtai...

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 YOLOv5-based side-scan sonar ocean sediment identification method and device, and the method comprises the steps: obtaining ocean sediment original data based on side-scan sonar, and obtaining an ocean sediment image based on side-scan sonar after analysis and reconstruction; marking the data set according to the type of the ocean substrate; constructing an ocean sediment recognition model based on a YOLOv5 target recognition algorithm, and performing model training; a plurality of different network model variants are added into the ocean sediment recognition model; in the model training process, a multi-scale training method is added; adding a transfer learning method; replacing the SGD optimization function with an Adam optimization function; and identifying a to-be-detected ocean sediment image by using the trained model to obtain an identification result. According to the method, the effect of real-time target detection on the video file can be achieved, the detection efficiency is improved, and development of actual ocean exploration related work is facilitated.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a YOLOv5-based side-scan sonar ocean bottom identification method and device. Background technique [0002] In order to better understand the ocean, explore and develop marine resources more effectively, it is essential to have a comprehensive understanding of the seabed topography, and how to automatically and effectively obtain marine topography information and identify different types of ocean bottoms has become It clarifies the important issues of marine resource development and marine operation environment information guarantee. Obtaining marine topography and landform information is the basis for marine development, marine surveying and mapping, marine physical detection, underwater rescue, navigation safety research, and marine military engineering implementation. It is of great significance and value to national economic development and national security construct...

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): G06V20/05G06V10/25G06V10/32G06V10/774G06V10/82G06K9/62G06N3/04
CPCG06N3/045G06F18/214
Inventor 胡毅王紫薇时鹏陈欣杨晓芬
Owner THIRD INST OF OCEANOGRAPHY MINIST OF NATURAL RESOURCES
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