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

Rapid acquisition and calibration method of image data set in deep learning

An image data set and calibration method technology, which is applied in the field of rapid acquisition and rapid calibration of image data sets in deep learning, and can solve problems such as high cost, small amount of labeled data, and difficulty in labeled data.

Active Publication Date: 2018-04-13
SOUTHEAST UNIV
View PDF11 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Technical problem: In order to solve the problem that the number of labeled data in deep learning is small and it is difficult and expensive to obtain new labeled data, the present invention provides a method for fast acquisition and fast calibration of image data sets in deep learning, which can be used for specific categories Provides great convenience for training and recognition of image data

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
  • Rapid acquisition and calibration method of image data set in deep learning
  • Rapid acquisition and calibration method of image data set in deep learning
  • Rapid acquisition and calibration method of image data set in deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Below in conjunction with embodiment and accompanying drawing, the technical scheme of the present invention will be described in further detail; It should be understood that this embodiment is only used to illustrate the present invention and is not intended to limit the scope of the present invention. Modifications in various equivalent forms all fall within the scope defined by the appended claims of this application. like figure 1 As shown, a method for fast acquisition and fast calibration of image data sets based on video frame foreground extraction includes the following steps:

[0060] S1. Carry out video acquisition. If jitter occurs during the video acquisition process, electronic image stabilization technology is used to remove the jitter of the surveillance video. If there is no jitter during video capture, proceed to the next step.

[0061] like Figure 2(a)-2(b) As shown, in step S1, the specific video frame processing includes the following steps:

[...

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 rapid acquisition and calibration method of an image data set in deep learning. After electronic image stabilization processing is carried out on a collected video, denoisingand smoothening are carried out by median filtering, and foreground extraction is performed by using a Gaussian mixture model; according to the position of an outer profile of the extracted foreground, corresponding position information in an original video frame is located to obtain a minimum bounding box of a specific target automatically; foreground target classification of the video frame iscarried out by using a hog-feature-based local template matching algorithm; with an inter-frame matching algorithm, same-class marking is carried out on a corresponding connection region between adjacent frames; and the position information and type information of the foreground are obtained to realize rapid calibration of an image data set. Therefore, problems that only a few of data carry tags in deep learning and new data with tags are obtained difficulty with high cost are solved; and the great convenience is provided for training and identification of the specific type of image data.

Description

technical field [0001] The invention relates to image processing technology, in particular to a method for fast acquisition and fast calibration of image data sets in deep learning. Background technique [0002] Vision is a very important perception for human beings to understand the world. For humans, it is a very simple task to recognize handwritten numbers through vision, recognize objects in pictures, or find out some specific objects and their outlines in pictures. However, for a computer, it is not a simple and easy task for the computer to recognize the content in the picture. The image recognition problem hopes to process, analyze and understand the content in the picture with the help of computer programs, so that the computer can automatically recognize various targets and objects in different patterns from the picture. The field of image recognition is an important field of artificial intelligence, and many breakthroughs have been made in recent years. [0003]...

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): G06K9/46G06K9/40G06K9/62
CPCG06V10/30G06V10/507G06F18/22
Inventor 张小国叶绯王宇王庆
Owner SOUTHEAST UNIV
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