Spindle positioning method based on depth target detection

A positioning method and target detection technology, applied in image data processing, instruments, biological neural network models, etc., can solve the problems of high hardware cost, low precision and efficiency, and dependence on depth cameras, etc., and achieve the effect of efficient and accurate positioning methods

Pending Publication Date: 2020-04-03
BEIJING UNIV OF TECH
View PDF11 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] Aiming at the above-mentioned problems of high hardware cost, dependence on depth cameras, and low preci

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
  • Spindle positioning method based on depth target detection
  • Spindle positioning method based on depth target detection
  • Spindle positioning method based on depth target detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0094] When the neural network model of the present invention is used, a simplified model is selected to implement S2-S4, and the prediction results are randomly checked during the positioning process. If the prediction results are wrong, the model is rechecked and modified.

[0095] The present invention carries out re-examination and modification through the normal model, including:

[0096] Input the wrong RGB image into the normal model;

[0097] The normal model outputs the spatial position information of the wrong RGB image, the endpoints around the spindle, the first and last endpoints of the spindle, and the category;

[0098] Compare the results predicted by the model with the actual values ​​to find the wrong data;

[0099] Adjust the corresponding parameters based on the wrong data and retrain the neural network model.

[0100] The advantages of the present invention are:

[0101] The present invention proposes a neural network model for positioning for the spind...

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 spindle positioning method based on depth target detection. The spindle positioning method comprises the steps: obtaining an RGB image containing a spindle; acquiring spindledepth information of the RGB image by adopting a depth information estimation method; adopting a key point detection method to obtain spindle head and tail end points of the RGB image; and accordingto the spindle depth information and the coordinates of the head and tail end points of the spindle, calculating two-dimensional rotation angle and vertical angle information of the spindle, and thenobtaining spatial position information of the spindle. The spindle positioning method based on depth target detection detects the depth information of the spindle in the RGB image to get rid of dependence on a depth camera, performs key point and category detection on the spindle in the image to assist calculation of spindle spatial position information, meanwhile, adopts multi-result output, adjusts and trains a network structure according to results, can find problems conveniently and timely, and finally can obtain the efficient and accurate positioning method for the spindle based on the neural network.

Description

technical field [0001] The invention relates to the technical field of pose estimation, in particular to a spindle positioning method based on depth target detection. Background technique [0002] As the raw material of most clothes, yarn has been in our life for a long time, but we don’t pay attention to it, but its production actually requires a more complicated process, generally carding, dyeing, dehydration, drying, kneading, carding, spun yarn, winding. Barrel, doubling, two-for-one twisting, packaging. Most of the processes have been streamlined and automated, but human support is still inseparable. The high humidity in the yarn production workshop, coupled with the heat generated by the machine operation, creates a stuffy environment, which has a great impact on the physical and mental health of workers. Taking the spun yarn to the winding as an example, after the machine winds the spun yarn on the spindle, it is necessary to manually carry the framed spindles and p...

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
IPC IPC(8): G06T7/50G06T7/70G06N3/02
CPCG06T7/50G06T7/70G06N3/02G06T2207/30124
Inventor 沈琦李琛
Owner BEIJING 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