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

Target identification method based on adaptive color fast point feature histogram

A point feature histogram and target recognition technology, which is applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of low efficiency and low precision of neighborhood radius, and achieve real-time detection, reduced time required, and high The effect of precision target recognition

Pending Publication Date: 2021-10-01
ZHEJIANG UNIV OF TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the problem of inefficient and low-precision manual multiple debugging of the neighborhood radius in the existing target recognition technology, the present invention proposes a target recognition method based on the adaptive color fast point feature histogram, using the neighborhood covariance matrix decomposition Calculate the feature entropy of the obtained eigenvalues, determine the adaptive optimal neighborhood radius for feature extraction, and improve the accuracy and efficiency of target 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
  • Target identification method based on adaptive color fast point feature histogram
  • Target identification method based on adaptive color fast point feature histogram
  • Target identification method based on adaptive color fast point feature histogram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] A target recognition method based on adaptive color fast point feature histogram, said method comprises the following steps

[0057] (1) Read point cloud data: read the pallet template point cloud and the scene point cloud collected by Kinect V2. The data is in ply format, including 3D coordinate information and color information. The template point cloud has 14554 points, and the scene point cloud has 109794 points, the reading result is as follows Figure 7 shown;

[0058] (2) Point cloud preprocessing: set the ground normal vector to [0,1,0] and the wall normal vector to [0,0,1], use the pcfitplane function to extract the ground and wall and remove them;

[0059] (3) Obtain adaptive neighborhood: minimum neighborhood radius r_min=0.0085, maximum neighborhood radius r_max=0.018, radius interval 0.0005, calculate the feature entropy corresponding to different neighborhood radii, and take the radius corresponding to the minimum feature entropy as the feature extraction...

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 relates to the technical field of three-dimensional point cloud processing, and discloses a target identification method based on an adaptive color fast point feature histogram for solving the problem of low efficiency and low precision of manual multiple debugging of a neighborhood radius in the existing target identification technology. The method comprises the steps of reading point cloud data; preprocessing the data; obtaining an adaptive optimal neighborhood radius; calculating a normal vector; performing key point detection; extracting features; performing feature matching; and eliminating mismatching point pairs. Compared with an existing fast point feature histogram (FPFH) feature descriptor and a feature extraction algorithm, the adaptive color fast point feature histogram (ACFPFH) feature descriptor comprises color information of an object, and a selection standard of a neighborhood radius is given by an adaptive neighborhood feature extraction algorithm based on feature entropy. The optimal neighborhood radius of each point can be obtained, the randomness of obtaining the neighborhood radius by manually debugging parameters for multiple times is overcome, and the target recognition precision and efficiency are effectively improved.

Description

technical field [0001] The invention relates to the technical field of three-dimensional point cloud processing, in particular to an object recognition method based on an adaptive color fast point feature histogram. Background technique [0002] In recent years, object recognition has been widely used in important fields such as robot 3D scene perception and navigation, unmanned driving, and augmented reality. In the field of logistics, the introduction of unmanned driving technology into industrial vehicles can greatly reduce labor costs, improve operating efficiency, and shorten the logistics cycle. Due to the influence of factors such as many obstacles, uneven lighting, cumulative errors in handling, and manual intervention, unmanned industrial vehicles have problems such as inefficiency and repeated handling in the actual cargo handling process. Target recognition is one of the key technologies for unmanned industrial vehicles. Accurate and efficient recognition of pall...

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): G06K9/46
Inventor 邵益平陈志慧
Owner ZHEJIANG 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