Target detection method based on a dense connection characteristic pyramid network

A feature pyramid and dense connection technology, which is applied in the fields of image processing and computer vision, can solve the problems of large size differences and insignificant differences in target appearance, and achieve the effects of improving performance, enhancing adaptability, and enhancing representation capabilities

Active Publication Date: 2019-04-12
SOUTH CHINA UNIV OF TECH
View PDF5 Cites 92 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problems of insignificant appearance differences and large size differences that may exist simultaneously during target 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
  • Target detection method based on a dense connection characteristic pyramid network
  • Target detection method based on a dense connection characteristic pyramid network
  • Target detection method based on a dense connection characteristic pyramid network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Below in conjunction with accompanying drawing and embodiment the method of the present invention is described in detail, present embodiment is carried out under the premise of technical scheme of the present invention, has provided embodiment and specific operation process, but protection scope of the present invention is not limited to following Example.

[0020] In this embodiment, the proposed object detection method based on a densely connected feature pyramid network can overcome the influence of insignificant differences in object appearance and large differences in object size during object detection to a certain extent.

[0021] In this embodiment, in the training phase, Figure 1a As shown, the specific implementation is as follows:

[0022] Step 1: Collect an image dataset labeled with target bounding boxes and category information, divide the dataset into a training set and a validation set, and perform certain data preprocessing. This step includes: making...

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 target detection method based on a dense connection characteristic pyramid network, and relates to the image processing and computer vision technology. The method comprises the steps of collecting an image data set labeled with a target bounding box and category information; constructing a dense connection feature pyramid network containing a Squeeze-Exciton structure capable of learning a dependency relationship between feature channels as a feature extraction backbone network; alternately training the RPN subnet and the R-FCN subnet to obtain a target detection model; and detecting a specific target in the image by using the model. The squeeze-Exciton structure and a dense connection structure are introduced into a feature extraction trunk network, characterization capability of the model is enhanced, adaptability of the model to targets of different sizes is enhanced through the feature pyramid structure, calculation sharing of the whole network model is achieved to the maximum degree through the R-FCN detection head, calculation resources are saved, and performance of the whole target detection model is improved. .

Description

technical field [0001] The invention relates to image processing and computer vision technology, in particular to a target detection method based on a densely connected feature pyramid network. Background technique [0002] The problem to be solved by vision can be summed up as "What is Where", that is, "what is where". Traditional image classification mainly solves the "What" problem, that is, to judge what kind of objects an image contains. But with the development of technology and the growth of application requirements, we not only pay attention to the simple classification of images, but also hope to accurately obtain the objects of interest and their positions in the images (generally given by the target bounding box), which is exactly the goal Detect the problem to be solved. Object detection has great practical value and application prospects. At the same time, object detection is also the cornerstone of computer vision research and the basis for solving other high...

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): G06K9/62G06K9/32G06N3/04
CPCG06V10/25G06N3/045G06F18/253G06F18/214
Inventor 秦华标杨光俊
Owner SOUTH CHINA 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap