Superpixel segmentation method and system based on attention mechanism and convolutional neural network

A convolutional neural network and superpixel segmentation technology, applied in the field of image processing, can solve problems such as not considering the spatial relationship between pixels and seed points, and irregular superpixel shapes, so as to improve network performance, reduce dimensions, improve efficiency and The effect of accuracy

Pending Publication Date: 2021-10-26
山东澳万德信息科技有限责任公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the DB-SCAN clustering algorithm can find clusters of arbitrary shapes, it has good segmentation potential for objects with complex shapes and irregular shapes, but it does not consider the spatial relationship between pixels and seed points, resulting in superpixels irregular shape

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
  • Superpixel segmentation method and system based on attention mechanism and convolutional neural network
  • Superpixel segmentation method and system based on attention mechanism and convolutional neural network
  • Superpixel segmentation method and system based on attention mechanism and convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] The purpose of this embodiment is to provide a superpixel segmentation method based on attention mechanism and convolutional neural network.

[0039] A superpixel segmentation method based on attention mechanism and convolutional neural network, comprising:

[0040] Obtain an image to be subjected to superpixel segmentation;

[0041] The image is input into a pre-trained superpixel segmentation model to obtain a predicted superpixel correlation map, and based on the superpixel correlation map, determine the image superpixel segmentation result;

[0042] Wherein, the superpixel segmentation model adopts an encoder-decoder design, and the encoder includes several convolutional layers, and the image generates feature maps of different scales through convolutional layers of different levels in the encoder; the decoder Including several deconvolution layers, the feature maps generated by different levels of convolution layers in the encoder are passed to the corresponding l...

Embodiment 2

[0065] The purpose of this embodiment is to provide a superpixel segmentation system based on attention mechanism and convolutional neural network.

[0066] A superpixel segmentation system based on attention mechanism and convolutional neural network, including:

[0067] A data acquisition unit, which is used to acquire an image to be subjected to superpixel segmentation;

[0068] A superpixel segmentation unit, which is used to input the image into a pre-trained superpixel segmentation model to obtain a predicted superpixel correlation map, and determine an image superpixel segmentation result based on the superpixel correlation map;

[0069] Wherein, the superpixel segmentation model adopts an encoder-decoder design, and the encoder includes several convolutional layers, and the image generates feature maps of different scales through convolutional layers of different levels in the encoder; the decoder Including several deconvolution layers, the feature maps generated by d...

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 superpixel segmentation method and system based on an attention mechanism and a convolutional neural network. According to the scheme comprises the following steps of: embedding an attention module into a convolutional neural network; performing end-to-end training on an extrusion and excitation network generated thereby; learning superpixels of a particular task with a flexible loss function. carrying out a superpixel segmentation of an image through a trained network, so that the dimensionality is greatly reduced, and some abnormal pixels are eliminated. Through an algorithm of superpixel segmentation based on attention mechanism and convolutional neural network, a better segmentation result can be obtained, and a method with obvious advantages is provided for the image superpixel segmentation field.

Description

technical field [0001] The disclosure belongs to the technical field of image processing, and in particular relates to a superpixel segmentation method and system based on an attention mechanism and a convolutional neural network. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Superpixel segmentation is an important preprocessing step in computer image processing. In computer vision, a superpixel is to gather some pixels with similar characteristics to form a more representative large element. This new element will become the basic unit of other image processing algorithms. Not only does it greatly reduce the size, but it also eliminates some outlier pixels. Extensive experimental analysis shows that deep learning-based superpixel segmentation methods not only outperform existing superpixel algorithms on traditional segmentation bench...

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): G06T7/10G06N3/04G06N3/08
CPCG06T7/10G06N3/08G06N3/045
Inventor 王晶晶栾振业于子舒任金雯张立人
Owner 山东澳万德信息科技有限责任公司
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