Object surface roughness identification method, system and equipment

An object surface and recognition method technology, applied in the field of object recognition, can solve the problems that it is difficult to ensure that the selected features contain enough information and affect the accuracy of roughness recognition, so as to achieve intuitive signal features, avoid the introduction of invalid features, and avoid The effect of feature loss

Pending Publication Date: 2022-03-11
BEIHANG UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the method of artificially selecting signal features is not only difficult to ensure that the selected features contain enough information, which affects the accuracy of roughness recognition due to feature loss, but also may introduce invalid features to affect the accuracy of roughness recognition.

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
  • Object surface roughness identification method, system and equipment
  • Object surface roughness identification method, system and equipment
  • Object surface roughness identification method, system and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045]figure 1 A flow chart of an object surface roughness identification method provided in Example 1 of the present invention. See figure 1 , The surface roughness identification method of the object of the present embodiment, including:

[0046] Step 101: Get the surface information of the target object.

[0047] Step 102: A method of feature the surface information by means of a wavelet transform to obtain a time spectrogram of the target object.

[0048] Step 103: In inputting the time spectrum of the target object, in the surface roughness recognition model of the object, the surface roughness of the target object is obtained; the surface roughness recognition model of the object is to train the residual learning network for the training set. owned.

[0049] In one example, step 101, including:

[0050] Touch the tactile sensor to contact the target object, collect and store the signal of the haptic sensor, i.e., surface information of the target object. Specifically, the ha...

Embodiment 2

[0082] This embodiment provides an object surface roughness recognition system, Figure 8 A structural diagram of an object surface roughness identification system provided in Example 2 of the present invention. See Figure 8 , The system, including:

[0083] The information acquisition module 201 is used to obtain surface information of the target object.

[0084] The feature extraction module 202 is used to extract the surface information by means of a wavelet transform to obtain a time spectrogram of the target object.

[0085] The roughness identification module 203 is configured to obtain a roughness of the surface roughness identification model of the target object to obtain a roughness of the surface roughness identification model of the target object; Poor learning networks are trained.

[0086] In one example, the feature extraction module 202 includes:

[0087] Time Frequency Domain Feature Extraction Unit, used to use discrete wavelet transform, and extract the time-frequ...

Embodiment 3

[0091] This embodiment provides a computer device. Figure 9 A structural diagram of a computer apparatus provided in Example 3 of the present invention. Figure 9 The displayed computer device 50 is merely an example and should not be restricted to the functions of the present embodiment. Such as Figure 9 As shown, the computer device 50 is manifested in the form of a general computing device. Components 50 can include, but are not limited to, one or more processors or processing units 500, memory 516, connected to a bus 501 of different system components (including memory 516 and processing unit 500). The memory 516 is configured to store a computer program that includes a program instruction; the processor is configured to call the program instruction to perform the object surface roughness identification method of Example 1.

[0092] Bus 501 represents one or more of several types of bus structures, including memory bus, memory controllers, peripheral bus, graphical acceleration...

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 an object surface roughness identification method and system. The method comprises the following steps: acquiring surface information of a target object; performing feature extraction on the surface information by adopting a wavelet transform method to obtain a time-frequency spectrogram of the target object; inputting the time-frequency spectrogram of the target object into an object surface roughness recognition model to obtain the surface roughness of the target object; the object surface roughness identification model is obtained by training a residual learning network by adopting a training set. According to the method, the introduction of invalid features can be avoided while feature loss is avoided, so that the roughness recognition precision is improved.

Description

Technical field [0001] The present invention relates to the field of object recognition, particularly to a surface roughness of the object recognition method, system and device. Background technique [0002] With the development of science and technology, we can achieve a variety of different functions of the robot mushroomed have emerged, and has made a wide range of applications in various fields, such as industrial production lines, such as picking agriculture. Currently single function manipulator or robot technology has been more mature. Then people began to focus on the robot to be able to complete more complex and sophisticated operations in more diverse environments, such as going into people's daily life for the service of humanity, or even to achieve direct contact and interaction with people. This requires that the robot includes a human-like touch, the contact object feature (such as hard and soft object, rough, temperature and humidity information) perceived to be mo...

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): G06K9/00G06K9/62G06F17/14G06N3/04G06N3/08
CPCG06F17/148G06F17/147G06N3/08G06N3/045G06F2218/06G06F2218/08G06F2218/12G06F18/241G06F18/214
Inventor 王少萍铁健石健罗雪松李少石
Owner BEIHANG UNIV
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