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

Small target detection method based on regional nomination

A small target detection and small target technology, which is applied in the field of image processing, can solve the problems of difficult detection of small target in the image, and achieve the effects of reducing the amount of calculation, comprehensive detection, and suppression of background noise

Active Publication Date: 2018-11-16
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is very difficult to detect small objects in images.

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
  • Small target detection method based on regional nomination
  • Small target detection method based on regional nomination
  • Small target detection method based on regional nomination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be further described below in conjunction with specific examples.

[0052] In the small target detection method based on region nomination provided in this embodiment, an RGB color standard image is input for detection. The complete process of the detection is as follows figure 1 , the complete neural network structure diagram used in the designed image small target detection is as follows figure 2 . When preprocessing the image file, use an algorithm to convert the image to be detected to a uniform size; next, use a 5-layer convolutional neural network to extract 5 layers of basic features from the image; then, the 4th and 5th layers of the image feature fusion; then use the region nomination network to generate small target region nominations on the fusion feature map; finally, map the nominated region generated by the region nomination network to the fusion feature map, and use the fully connected layer network on the nomination region f...

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 small target detection method based on regional nomination. The method comprises: step one, carrying out input image preprocessing and converting the input image into one with a unified size; step two, extracting an image base feature map and extracting five-layer feature maps; step three, carrying out feature fusion and carrying out fusion of the fourth-layer feature mapand the fifth-layer feature map; step four, carrying out small target area nomination and generating small target area nomination by using a regional nomination network; and step five, carrying out small target bounding frame refinement and small target area classification. The method has advantages of fast calculation speed, high small target recognition precision, good generalization performance, and good detection performance of common minimum target areas.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a small target detection method based on region nomination. Background technique [0002] Target detection refers to the process of accurately locating the objects contained in the image from the image and identifying the category of the object. Small target detection refers to locating and identifying objects that contain only a small number of pixels in the image. Small target detection has a very high application prospect in the fields of driverless road sign recognition and personal carry-on item recognition in the security field. [0003] Specifically, target detection is to find out the position, size and category of all objects contained in the image from the image. Existing target detection methods include region-based convolutional neural network RCNN, Fast-RCNN, Faster-RCNN series neural networks, end-to-end convolutional neural network SSD, and YOLO ...

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): G06K9/46G06K9/36G06N3/04
CPCG06V10/20G06V10/44G06N3/045
Inventor 张宇郑冬云郭炜强郑波关健创
Owner SOUTH CHINA UNIV OF TECH
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