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

Multi-class small target detection method based on metric learning

A technology of small target detection and metric learning, which is applied in the field of image processing, can solve problems such as classification of difficult and small targets, and achieve the effects of improving positioning performance, enhancing representation ability, and enhancing sensitivity

Inactive Publication Date: 2020-10-16
NORTHWESTERN POLYTECHNICAL UNIV
View PDF10 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, only considering the spatial information of the feature map and ignoring the relationship between various objects, it is difficult to accurately classify small objects in the context of multi-category detection.

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
  • Multi-class small target detection method based on metric learning
  • Multi-class small target detection method based on metric learning
  • Multi-class small target detection method based on metric learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0041] The object of the present invention is to provide a kind of multi-category small target detection method based on metric learning, is to realize by following technical scheme, and its specific steps are as follows:

[0042] Step 1. Construct a multi-category small target dataset. Taking the electronic components on the printed circuit board (PCB) as the research object, the PCB board data set is established. The specific process is as follows: use industrial cameras to capture various types of PCB boards, and save them in JPEG format; According to the different types of electronic components and packaging forms, the classification criteria of electronic components (that is, the category labels corresponding to electronic components of different types and packaging forms) are established, and Labelme software is used for image labeling to obtain labeling fi...

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 relates to a multi-class small target detection method based on metric learning, and designs a novel deep neural network structure by combining the feature expression capability of deeplearning with the similarity discrimination capability of metric learning according to the recognition characteristics of multi-class small targets. The method is characterized in that a Faster RCNN (Recurrent Convolutional Neural Network) network structure combined with a Feature Pyramid Network (FPN) is adopted to detect multiple types of small targets on the basis of data of a whole image; a graph network module is embedded into the network to carry out transmission calculation on similarity information among all regions in the image; a similarity measurement module based on triple loss isadopted at the rear end of the network to distinguish detail information among samples, feature information of small targets and similarity relations among the targets are fully extracted, and the accuracy of multi-class small target detection is improved.

Description

technical field [0001] The invention relates to a multi-category small target detection method based on metric learning, which belongs to the technical field of image processing. Background technique [0002] Target detection is a key research topic in the field of computer vision. At present, target detection technology has been widely used in the fields of automatic industrial inspection, medical imaging diagnosis and remote sensing image analysis (Khosravan N, Bagci U.S4ND: Single-shot single-scale lung nodule detection[C] / / International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, Cham, 2018:794-802.). Multi-category small target detection refers to a detection task in which there are more than two different target categories in the image, and the absolute size of each target is smaller than 32×32 pixels or the relative size is smaller than 0.1 times the original image (M.Kisantal, Z.Wojna, J.Murawski , et al.Augmentation ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06N3/045G06F18/241G06F18/214
Inventor 王靖宇王叶子张科吴虞霖王霰禹张国俊苏雨王震
Owner NORTHWESTERN POLYTECHNICAL 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