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

A target detection method and device for a parallel robot vision system

A technology of robot vision and target detection, applied in the field of image processing

Inactive Publication Date: 2019-05-21
NORTH CHINA UNIV OF WATER RESOURCES & ELECTRIC POWER
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, the present invention provides a target detection method and device for a parallel robot vision system, which reduces the difficulty of data set production, improves the model generalization ability, further solves the problem of target object detection with similar colors and occlusion defects, and improves the running speed and target recognition positioning accuracy

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
  • A target detection method and device for a parallel robot vision system
  • A target detection method and device for a parallel robot vision system
  • A target detection method and device for a parallel robot vision system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the purpose, technical solution and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and technical solutions.

[0044] In the current image processing technology, supervised learning is used for data set training, and the early data set labeling and production will cost a lot of manpower and material resources; using unsupervised learning alone will easily cause problems such as inconvenient application to target detection and overfitting. For this reason, embodiment of the present invention, see figure 1 As shown, a target detection method for parallel robot vision system is provided, including the following content:

[0045] S101. Collect target images, and divide the collected target images into training data sets and test data sets;

[0046] S102. Building a hybrid autoencoder, sending the images in the training data set t...

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 belongs to the technical field of image processing, and particularly relates to a target detection method and device for a parallel robot vision system, and the method comprises the steps: collecting a target image, and dividing the target image into a training data set and a test data set; building a hybrid automatic encoder, feeding images in the training data set into the hybrid automatic encoder in batches for denoising and sparse processing, and obtaining image data with classification labels; Sending the image data into a Faster RCNN neural network to carry out model training; Sending the test data set image data into a trained Faster RCNN neural network to carry out model test; And embedding the tested Faster RCNN neural network model into a parallel robot vision system, and carrying out target identification and positioning on the to-be-detected image. According to the method, the model anti-interference capability and robustness are improved, the data set training difficulty is reduced, the model training speed and quality are improved, the neural network is easy to reuse for different to-be-identified targets, and the method has important guiding significance for the technical field of image processing and target identification.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a target detection method and device for a parallel robot vision system. Background technique [0002] In recent years, machine vision has developed rapidly. Machine vision will be more and more used in industry, life, transportation, aerospace, entertainment, construction and other industry scenarios, becoming the eyes of artificial intelligence. Therefore, faster and more accurate machine vision will be In the future development trend, at the technical level, faster and more accurate deep learning will be the focus of future research. Optimizing machine vision by reducing the difficulty of model training and increasing the speed of model training and recognition will be the development trend of machine vision. In machine vision, target detection technology is used in various industrial production, transportation and other fields, playing an indispensable ro...

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): G06T7/11G06T7/254G06T5/00G06K9/62G06N3/08
Inventor 王丽君温梦艳王欣欣高冠阳孔祥瑞谷宇希
Owner NORTH CHINA UNIV OF WATER RESOURCES & ELECTRIC POWER
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