Red channel and full convolutional neural network-based underwater optical intelligent sensing method

A convolutional neural network and intelligent perception technology, which is applied in the field of underwater optical intelligent perception, can solve problems such as difficult to achieve real-time, image semantic level area division, poor image segmentation algorithm effect, etc., and achieve high contrast effect

Active Publication Date: 2018-06-15
NORTHWESTERN POLYTECHNICAL UNIV
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The image segmentation algorithm based on shallow features is poor, and it cannot divide the image into semantic-level regions
The image segmentation algorithm based on the convolutional neural network has a goo

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
  • Red channel and full convolutional neural network-based underwater optical intelligent sensing method
  • Red channel and full convolutional neural network-based underwater optical intelligent sensing method
  • Red channel and full convolutional neural network-based underwater optical intelligent sensing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings and embodiments, and the present invention includes but not limited to the following embodiments.

[0035] The present invention provides an underwater optical intelligent perception method based on red channel and fully convolutional neural network, such as figure 1 As shown, firstly, the high-contrast underwater optical image is collected by the gating imaging device, and then the red channel algorithm is used to restore the color of the image to obtain the enhanced underwater image, and finally the image is intelligently processed by the improved fully convolutional neural network Semantic segmentation, quickly obtain high-precision underwater perception images. The specific process is as follows:

[0036] 1. Use the pulsed laser and the strobe camera to perform image imaging to obtain the image of the underwater scene.

[0037] Such as figure 2 As shown, two worki...

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 provides a red channel and full convolutional neural network-based underwater optical intelligent sensing method. The method is used for intelligently sensing underwater scenes by utilizing optical information, and comprises the following steps of: firstly acquiring an underwater optical image which has a high contrast ratio and restraining an atomization phenomenon through gated imaging equipment; carrying out color recovery on the image through a red channel algorithm so as to effectively carry out visual effect enhancement on the image and ensure that the image is closer to animaging effect under natural illumination; and finally carrying out intelligent semantic segmentation on the image by using an improved full convolutional neural network so as to rapidly obtain a high-precision underwater sensing image.

Description

technical field [0001] The invention belongs to the technical field of computer vision and graphics processing, and specifically proposes an underwater optical intelligent perception method based on a red channel and a fully convolutional neural network. Background technique [0002] In recent years, with the increasing shortage of land resources and the continuous development of the international situation, the ocean has increasingly become the focus of competition among countries around the world. On the one hand, the ocean, as the largest ecosystem on the earth, is a huge treasure house of resources, which can provide the material basis for the sustainable development of society; important military strategy. With the continuous advancement of science and technology, ocean perception technology is becoming more and more mature. The research of ocean sensing technology is of great significance to the exploration and development of marine resources, marine military applica...

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): G06T5/00G06K9/32G06K9/34G06N3/04
CPCG06T5/001G06T2207/10024G06T2207/20084G06T2207/20081G06V10/25G06V10/26G06N3/045
Inventor 李学龙王琦李昊鹏
Owner NORTHWESTERN POLYTECHNICAL 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