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

A method for semantic segmentation of surface panoramic image

A panoramic image and semantic segmentation technology, applied in the field of computer vision recognition, can solve the problems of poor target segmentation effect and slow speed in small areas, and achieve the effect of real-time semantic segmentation, avoiding gradient decay, and fast segmentation.

Active Publication Date: 2019-01-04
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method for semantic segmentation of panoramic water surface images, thereby solving the technical problems existing in the prior art that the speed is slow and the segmentation effect on small area objects is not good

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 method for semantic segmentation of surface panoramic image
  • A method for semantic segmentation of surface panoramic image
  • A method for semantic segmentation of surface panoramic image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A method for semantic segmentation of water surface panoramic images, comprising:

[0039]Input the panoramic image of the water surface to be tested into the convolutional neural network for real-time semantic segmentation, and obtain the segmentation result of the panoramic image of the water surface;

[0040] Such as figure 2 As shown in (a), the traditional convolutional neural network uses a convolution with a length and a width of 3, and the size of the traditional convolution kernel is 3*3. The present invention uses two sizes of 3*1 and 1*3 respectively. The convolution kernel, such as figure 2 As shown in (b), the convolutional neural network sets skip connections every 4 convolutional layers.

[0041] When the number of input convolutional layer channels is c1 and the number of output volume base layer channels is c2, the calculation amount of traditional convolution is:

[0042] 3*3*c1*c2=9*c1*c2

[0043] The convolution calculation amount of the presen...

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 method for semantic segmentation of water surface panoramic image, which includes steps: a convolution neural network is designed, pixel-level marking is carried out on eachtarget class in the water surface panoramic image in the training set to obtain a real marking image, The training set is used to train the convolution neural network, and the output result of the convolution neural network is compared with the real label image to obtain the training error; the training error is back propagated in the convolution neural network, the parameters of the convolution neural network are updated, and the trained convolution neural network is obtained after many iterative training; the water surface panoramic image to be measured is input into a convolution neural network for real-time semantic segmentation, and the segmentation result of the water surface panoramic image is obtained. The invention has the advantages of high segmentation speed and good segmentation effect on small area targets, and provides comprehensive, fast and accurate environmental sensing information for surface intelligent equipment such as unmanned ship.

Description

technical field [0001] The invention belongs to the technical field of computer vision recognition, and more specifically relates to a method for semantic segmentation of water surface panoramic images. Background technique [0002] With the proposal of the ocean power strategy, my country has begun to vigorously develop marine equipment. As an unmanned surface mobile platform, unmanned boats can not only enter some harsh environments to complete tasks, but also improve the efficiency of tasks that require long-term operations. They play a very important role in many practical applications, such as Customs patrols, shallow sea mine clearance and water quality monitoring, etc. For unmanned boats, environmental perception technology is an indispensable part of autonomous navigation and autonomous obstacle avoidance. In particular, in the process of actual operation, it is far from enough to only be able to detect targets or obstacles in the direction of advancement, and dang...

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): G06K9/00G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V20/00G06V10/267G06V2201/07G06N3/045G06F18/254G06F18/214
Inventor 曹治国李德辉肖阳朱昂帆赵晨杨健宫凯程
Owner HUAZHONG UNIV OF SCI & TECH
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