Laser sensor depth data reconstruction method based on compressed sampling matching pursuit

A laser sensor, depth data technology, applied in electrical components, code conversion, etc., can solve problems such as large amount of data, periodic and effective statistics and analysis of the growth status of unfavorable crops, and long plant growth cycle.

Inactive Publication Date: 2016-11-16
JIANGSU UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional crop morphological feature detection is mainly through the technology of real-time shooting video or photos. However, due to the long growth cycle of plants, the video effect is greatly affected by the weather and the change of day and night. This method has a huge impact on the transmission and storage of plant feature data. It is also not conducive to the periodic and effective statistics and analysis of the growth status of the same crop in the future
[0004] The amount of data obtained by laser sensor data collection is generally relatively large, which will bring huge pressure to the process of storage and transmission

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
  • Laser sensor depth data reconstruction method based on compressed sampling matching pursuit
  • Laser sensor depth data reconstruction method based on compressed sampling matching pursuit
  • Laser sensor depth data reconstruction method based on compressed sampling matching pursuit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In the compressed sensing theory, the measurement matrix Φ is used to realize the compressed sampling of the sensor depth data, and the wavelet transform is used to realize the sparse representation of the original signal. The sparse representation of the signal f is f=Ψθ, Ψ is a sparse matrix, and θ is K sparse Sparse vector, then the sampled values ​​obtained:

[0031] y=Φf=ΦΨθ=Aθ

[0032] In the formula, y is the data sampling value of M×1 dimension, f is the N×1 signal composed of sensor depth data, Φ is the measurement matrix of M×N dimension, Ψ is the sparse matrix of N×N dimension, and θ is the N×1 dimension sparse vector.

[0033] The dimension M of the compressed sampling value y is much smaller than the dimension N of the original sensor depth data signal f, which realizes the projection from high dimension to low dimension, which is the compression process. When y contains enough original signal information, in Under certain conditions, the reconstruction o...

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 laser sensor depth data reconstruction method based on compressed sampling matching pursuit. Data quantity obtained through collection of a laser sensor is high, the collected data is compressed based on screening of massive redundant data carried out by a measurement matrix; and through decompression of the data, plant images can be reconstructed. According to the method, the compressed sampling matching pursuit algorithm is employed. According to the algorithm, atoms iterated at each time may be discarded in a next iteration process; residual errors will be correspondingly updated; and the reconstruction precision is improved. According to the method, the sensor data storage and transmission pressure is greatly reduced by starting with the data collected by the sensor; and the compressed depth data has great significance in stage growth analysis and data query of crops.

Description

technical field [0001] The invention relates to the reconstruction technology of laser sensor depth data, in particular, it is a laser sensor depth data reconstruction method based on compressed sampling matching pursuit. Background technique [0002] With the increasing application of mechanization in agriculture, in the modern production process, the instant grasp of crop growth information and the statistical analysis of crop growth status data are used to control plant diseases and insect pests to achieve high yields of agricultural crops A bumper harvest is of great significance to the development of agricultural economy in my country's national economy. [0003] Traditional crop morphological feature detection is mainly through the technology of real-time shooting video or photos. However, due to the long growth cycle of plants, the video effect is greatly affected by the weather and the change of day and night. This method has a huge impact on the transmission and stor...

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): H03M7/30
CPCH03M7/3062
Inventor 刘慧李光武沈跃
Owner JIANGSU 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