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

Classifier construction method for target detection and target detection method

A technology of target detection and construction method, which is applied in the field of computer vision, can solve the problems of high data uniformity, achieve the effect of solving low target detection rate, accurate target detection result, and improving detection rate

Active Publication Date: 2015-07-15
SICHUAN JIUZHOU ELECTRIC GROUP
View PDF8 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the existing target detection methods based on static images have high requirements for the uniformity of data, which makes it often necessary to screen the sample data multiple times to exclude samples that may have interference.

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
  • Classifier construction method for target detection and target detection method
  • Classifier construction method for target detection and target detection method
  • Classifier construction method for target detection and target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The implementation of the present invention will be described in detail below in conjunction with the accompanying drawings and examples, so as to fully understand and implement the process of how to apply technical means to solve technical problems and achieve technical effects in the present invention. It should be noted that, as long as there is no conflict, each embodiment and each feature in each embodiment of the present invention can be combined with each other, and the formed technical solutions are all within the protection scope of the present invention.

[0033] Also, in the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced without the specific details or in the particular manner described.

[0034] In addition, the steps shown in the flow dia...

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 classifier construction method for target detection and a target detection method. The classifier construction method comprises a negative sample generation process, a positive sample generation process and a classifier conformation process, wherein the negative sample generation process comprises the steps of processing an obtained scene original image set to obtain a background set not containing a target and generating a negative sample according to the background set; the positive sample generation process comprises the steps of processing a positive sample original image set containing the target to obtain a positive sample set which comprises a plurality of positive samples; the classifier conformation process comprises the steps of obtaining sub-classifiers corresponding to all the positive samples through combining negative samples and misrecognition samples, and further obtaining required classifiers according to sets of all classifiers. Compared with the prior art, the method has the advantages of higher detection rate and higher capture rate.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for constructing a classifier for object detection and an object detection method. Background technique [0002] Target detection has always been a popular research direction in the field of computer vision. It is the most basic component of computer vision tasks. Its scientific research value lies in providing more advanced tasks in computer vision (such as target recognition, content analysis, artificial intelligence, etc. ) to provide basic research and technical support. In addition, target detection itself has good commercial application value, for example, most digital cameras are equipped with face detection systems. [0003] The detection method based on static images is one of the most commonly used methods in target detection methods. However, the existing object detection methods based on static images need to collect a large amount of training sampl...

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): G06K9/62
Inventor 孙文超侯林利
Owner SICHUAN JIUZHOU ELECTRIC GROUP
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