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

Deep learning target detection method based on central point regression

A technology of deep learning and target detection, which is applied to instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of small target detection difficulties and high false detection of remote sensing images, and achieve the effect of maintaining speed advantages and high detection accuracy

Pending Publication Date: 2021-11-23
HUBEI UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a deep learning target detection method based on center point regression, to solve the problems of high false detection and small target detection difficulty when the original CenterNet algorithm detects remote sensing 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
  • Deep learning target detection method based on central point regression
  • Deep learning target detection method based on central point regression
  • Deep learning target detection method based on central point regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0029] As a new Anchor-free end-to-end target detection algorithm, CenterNet uses a point to represent the center of the object's bounding box, and then directly returns other attributes from the image features around the center position, such as object size, orientation, and attitude. etc., turning the object detection problem into a standard keypoint estimation problem. The specific steps are as follows: input an I∈R W×H×3 An image with width W and height H...

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 provides a deep learning target detection method based on central point regression, wherein the method comprises the following specific steps: introducing a horizontal connection module on an original Center Net network structure, enabling the features of different layers to be correlated, and fusing the deep features and shallow features, so as to improve the detection performance of a small target; introducing a channel attention module into a horizontal connection module, carrying out adaptive calibration on feature responses among different channels, and improving the feature extraction capability of the network; and finally, carrying out a contrast experiment on the UCAS-AOD and RSOD public remote sensing data sets. The method not only has high detection precision in remote sensing image aircraft target detection, but also keeps the speed advantage of a single-stage detection model, and has certain practical value.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a center point regression-based deep learning target detection method. Background technique [0002] Remote sensing images are taken by satellites, including spatial resolution, time resolution, spectral resolution, etc. Target detection in remote sensing images has important significance and application value in civil and military applications, especially aircraft target detection in remote sensing images, which can provide more valuable information for more efficient management of civil aviation and military operations. Different from traditional aircraft images, aircraft target detection in remote sensing images faces difficulties such as multi-scale, complex background, and large image memory usage. [0003] With the rapid development of deep learning, object detection methods based on Convolutional Neural Networks (CNN) have become a trend for processing and recogn...

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): G06K9/32G06K9/62G06N3/04
CPCG06N3/045G06F18/253G06F18/214
Inventor 李婕周顺王恩果李毅巩朋成张正文朱鑫潮
Owner HUBEI 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