Feature image extraction method based on deformable convolutional layer and feature image extraction device thereof

A feature image and convolutional layer technology, applied in the field of artificial intelligence, can solve problems such as limited recognition accuracy, inconvenient storage, and large data volume, and achieve the effect of increasing recognition accuracy and increasing adaptability

Inactive Publication Date: 2017-10-24
GUANGDONG UNIV OF TECH
View PDF3 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the prior art, for a deformed object, a large number of feature images related to the object need to be stored, which will make the amount of data very large, which is inconvenient to store, and it will take a lot of time to compare t

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
  • Feature image extraction method based on deformable convolutional layer and feature image extraction device thereof
  • Feature image extraction method based on deformable convolutional layer and feature image extraction device thereof
  • Feature image extraction method based on deformable convolutional layer and feature image extraction device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The core of the present invention is to provide a method for extracting feature images based on deformable convolutional layers. The network architecture used in the prior art is usually the basic network architecture that has been used for twenty years. After the target image is acquired, the target image will be sampled based on the regular grid position, and then the sampled image value Do the convolution and use the resulting pixel value as the output for that location in the icon image.

[0034] Express convolution operations using mathematical expressions:

[0035] the y l =W l x l +b l

[0036] Among them, l is the convolutional layer index, that is, it is represented as the lth convolutional layer; x is the convolutional area in the target image, and its size is usually set to the pixels of the c channel of k×k. Of course, the length of the convolutional area The width and width can also be inconsistent, depending on the specific situation; W is the convol...

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 feature image extraction method based on a deformable convolutional layer. The method comprises the steps that a target image is acquired; and pixel values are extracted from the target image through the sampling points of the convolutional kernel in the convolutional layer so as to obtain a feature image, wherein the actual coordinate values of the sampling points are the actual coordinate values calculated according to the preset initial coordinate values and the deviation variable trained in advance. According to the method, one deviation variable can be additionally arranged for each sampling point in the convolutional kernel so that a convolutional neural network is enabled to realize the capacity of learning image space geometric deformation, the convolutional kernel is enabled to randomly sample near the present position, the adaptability of the convolutional layer for the deformed image in extracting the feature image can be increased and the identification accuracy for the deformed object can be increased. The invention also discloses a feature image extraction device based on a deformable convolutional neural network. The feature image extraction device also has the beneficial effects.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a method and device for extracting feature images based on deformable convolution layers. Background technique [0002] With the continuous advancement of science and technology, deep learning has achieved long-term development in recent years. At present, the most popular technology is convolutional neural network, and image detection based on convolutional neural network has become a basic research topic in various fields such as national defense and military, social security, public transportation, and commercial applications. The best image detection techniques to date have been implemented using convolutional neural networks. [0003] In the process of image detection, the same object may present different sizes, postures, perspective changes or even rigid deformation in the image, and the acquired image will be deformed for the same object. When the image is...

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): G06K9/46G06N3/04G06N3/08
CPCG06N3/084G06V10/40G06N3/045
Inventor 刘治李家兴章云
Owner GUANGDONG UNIV OF TECH
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