scholarly journals Nondestructive Testing of Lettuce Nitrogen Stress Based on Multidimensional Image

2021 ◽  
Vol 12 ◽  
pp. 44-60
Author(s):  
Bao Guo Shen ◽  
Jin Yue Dai ◽  
Xiao Dong Zhang ◽  
Zhao Hui Duan
Keyword(s):  
Reverse Engineering ◽  
Laser Scanning ◽  
Hyperspectral Image ◽  
Image Features ◽  
Hyperspectral Images ◽  
Quantitative Detection ◽  
3D Laser Scanning ◽  
Nitrogen Levels ◽  
Moisture Variation ◽  
Nitrogen Detection

Visible light near infrared (VS-NIR) hyperspectral combined with three-dimensional laser scanning was applied to extract the VS-NIR features of lettuce nitrogen between 400-1700 nm and 3D morphological features of the plants. Such combination realizes the rapid quantitative detection of lettuce nitrogen. This study is based on the hyperspectral image data cube achieved from lettuce leaves with different nitrogen levels. Stepwise regression sensitive area was used and adaptive band selection method was combined to extract the characteristic spectrum and feature image of lettuce nitrogen and characterize the average image intensity. Also; the error caused by moisture variation content in lettuce nitrogen image features was compensated. Then a model of lettuce nitrogen hyperspectral image diagnosis was built. The reverse engineering software Geomagic Qualify was used to repair and smooth interference noise and discontinuous range which are based on the 3D laser scanning data of lettuce. Accordingly, the stem diameter, plant height, leaf area, and biomass features of different nitrogen levels of lettuce are obtained and the model of nitrogen detection about lettuce growth features was built based on reverse engineering and integral method. Multi-scale fusion lettuce nitrogen detection model is built by using the acquired hyperspectral images with growing features of lettuce nitrogen and adopting genetic algorithm combined with partial least squares regression. Results show the correlation coefficient R of the built model is 0.95; the model precision is much better than single feature of hyperspectral images and 3D laser scanning model. The feature extraction algorithm and the eigenvectors provide the reference for development of facilities for online monitoring system of crop growth information.

scholarly journals Research on Tomato Nitrogen Content Nondestructive Testing Method Based on Multidimensional Image Processing Technology

2018 ◽  
Vol 8 ◽  
pp. 1374-1383
Author(s):  
Xue Wei Zhang ◽  
Xiao Dong Zhang ◽  
Hanping Mao ◽  
Hong Yan Gao ◽  
Zi Yu Zuo ◽  
...  
Keyword(s):  
Laser Scanning ◽  
Hyperspectral Image ◽  
Geometric Model ◽  
Three Dimensional ◽  
Partial Least Square ◽  
Least Square ◽  
Feature Model ◽  
Image Feature ◽  
Nitrogen Levels ◽  
Nitrogen Detection

This paper is aimed at greenhouse tomato nitrogen detection using hyperspectral imaging combined with three dimensional laser scanning technology. This technology extracts the nitrogen hyperspectral feature image and the plant three dimensional morphological characters, to achieve the rapid quantitative analysis of nitrogen in tomato. The characteristic spectrum of nitrogen was extracted, and the mean intensity characteristic of the image feature was obtained. Then based on the acquisition of the tomato hyperspectral image data cube at different nitrogen levels, the sensitive region stepwise regression combined with correlation analysis was performed. Based on the acquired three dimensional laser scanning data of tomatoes, the stem diameter, the plant height and other biomass characteristics of different nitrogen levels were obtained by establishing the spatial geometric model of tomato three dimensional point cloud. A multi-feature fusion model for tomato nitrogen detection was established by partial least square regression. The results showed that the R2 in the constructed model was 0.94, with the accuracy significantly better than that of the single feature model established by using hyperspectral image and three dimensional laser scanning.

scholarly journals Simultaneous Wood Defect and Species Detection with 3D Laser Scanning Scheme

2016 ◽  
Vol 2016 ◽  
pp. 1-6 ◽  
Author(s):  
Zhao Peng ◽  
Li Yue ◽  
Ning Xiao
Keyword(s):  
Wood Species ◽  
Wood Surface ◽  
Point Cloud ◽  
Laser Scanning ◽  
Species Recognition ◽  
Quantitative Detection ◽  
3D Laser Scanning ◽  
Color Information ◽  
Integration Algorithm ◽  
Detection Scheme

Wood grading and wood price are mainly connected with the wood defect and wood species. In this paper, a wood defect quantitative detection scheme and a wood species qualitative identification scheme are proposed simultaneously based on 3D laser scanning point cloud. First, an Artec 3D scanner is used to scan the wood surface to get the 3D point cloud. Each 3D point contains its X, Y, and Z coordinate and its RGB color information. After preprocessing, the Z coordinate value of current point is compared with the set threshold to judge whether it is a defect point (i.e., cavity, worm tunnel, and crack). Second, a deep preferred search algorithm is used to segment the retained defect points marked with different colors. The integration algorithm is used to calculate the surface area and volume of every defect. Finally, wood species identification is performed with the wood surface’s color information. The color moments of scanned points are used for classification, but the defect points are not used. Experiments indicate that our scheme can accurately measure the surface areas and volumes of cavity, worm tunnel, and crack on wood surface with measurement error less than 5% and it can also reach a wood species recognition accuracy of 95%.

scholarly journals Semi-automatic Low Cost 3D Laser Scanning Systems for Reverse Engineering

Procedia CIRP ◽  
2015 ◽  
Vol 28 ◽  
pp. 94-99 ◽  
Author(s):  
L.M. Galantucci ◽  
E. Piperi ◽  
F. Lavecchia ◽  
A. Zhavo
Keyword(s):  
Reverse Engineering ◽  
Laser Scanning ◽  
Low Cost ◽  
3D Laser Scanning ◽  
Scanning Systems

The Nitrogen Quantitative Model Based on Hyperspectral Image of Tomato Leaf

2012 ◽  
Vol 466-467 ◽  
pp. 191-195
Author(s):  
Jun Sun ◽  
Yan Wang ◽  
Xiao Hong Wu ◽  
Xiao Dong Zhang
Keyword(s):  
Nitrogen Content ◽  
Stepwise Regression ◽  
Hyperspectral Image ◽  
Quantitative Model ◽  
Leaf Nitrogen ◽  
Image Features ◽  
Tomato Leaf ◽  
Hyperspectral Images ◽  
Kjeldahl Method ◽  
Nitrogen Contents

Based on hyperspectral image which integrates spectrum and image information, the tomato leaf nitrogen model is built. Tomato samples were soillessly cultured with different nitrogen content. The hyperspectral images of tomato leaves are gathered at different stages of tomato. Kjeldahl method determines nitrogen content of the corresponding tomato leaves. According to the hyperspectral information of leaf, the characteristic wave bands of tomato nitrogen are obtained in the method of stepwise regression. The images in the characteristic bands are processed and analyzed, and image features which have high correlation with nitrogen contents of tomato leaves are picked up. The PLS algorithm is used in three growth periods to build tomato nitrogen prediction model, The result of the predicted test shows that the forecast average relative error of PLS model may achieve 10%, and can satisfy the forecast request.

Surface Reconstruction Based on the 3D Laser Scanner

2012 ◽  
Vol 215-216 ◽  
pp. 656-659
Author(s):  
Le Yang Chen
Keyword(s):  
Reverse Engineering ◽  
Surface Reconstruction ◽  
Point Cloud ◽  
Laser Scanning ◽  
Laser Scanner ◽  
3D Laser Scanning ◽  
Cloud Processing ◽  
Point Cloud Processing ◽  
Key Technologies ◽  
Rapid Scanning

3D laser scanning is one of the key technologies of reverse engineering. Digital point cloud is produced by the rapid scanning technology. Some technology about reverse engineering is introduced in this thesis. The curved surface can be generated by the point cloud processing, when the point cloud can be processed by the software called Geomagic Studio.

Measurement of erosion state and refractory lining thickness of blast furnace hearth by using three-dimensional laser scanning method

2020 ◽  
Vol 118 (1) ◽  
pp. 106
Author(s):  
Lei Zhang ◽  
Jianliang Zhang ◽  
Kexin Jiao ◽  
Guoli Jia ◽  
Jian Gong ◽  
...  
Keyword(s):  
Blast Furnace ◽  
Laser Scanning ◽  
Refractory Lining ◽  
Three Dimensional ◽  
3D Laser Scanning ◽  
Scanning Method ◽  
Blast Furnace Production ◽  
Severe Erosion ◽  
Residual Thickness ◽  
Minimum Depth

The three-dimensional (3D) model of erosion state of blast furnace (BF) hearth was obtained by using 3D laser scanning method. The thickness of refractory lining can be measured anywhere and the erosion curves were extracted both in the circumferential and height directions to analyze the erosion characteristics. The results show that the most eroded positions located below 20# tuyere with an elevation of 7700 mm and below 24#–25# tuyere with an elevation of 8100 mm, the residual thickness here is only 295 mm. In the circumferential directions, the serious eroded areas located between every two tapholes while the taphole areas were protected well by the bonding material. In the height directions, the severe erosion areas located between the elevation of 7600 mm to 8200 mm. According to the calculation, the minimum depth to ensure the deadman floats in the hearth is 2581 mm, corresponding to the elevation of 7619 mm. It can be considered that during the blast furnace production process, the deadman has been sinking to the bottom of BF hearth and the erosion areas gradually formed at the root of deadman.

scholarly journals Cluster-Wise Weighted NMF for Hyperspectral Images Unmixing with Imbalanced Data

2021 ◽  
Vol 13 (2) ◽  
pp. 268
Author(s):  
Xiaochen Lv ◽  
Wenhong Wang ◽  
Hongfu Liu
Keyword(s):  
Spatial Information ◽  
Hyperspectral Image ◽  
Imbalanced Data ◽  
Reconstruction Error ◽  
Hyperspectral Data ◽  
Weight Matrix ◽  
Hyperspectral Images ◽  
Mixed Data ◽  
Sparsity Constraints ◽  
Additional Constraints

Hyperspectral unmixing is an important technique for analyzing remote sensing images which aims to obtain a collection of endmembers and their corresponding abundances. In recent years, non-negative matrix factorization (NMF) has received extensive attention due to its good adaptability for mixed data with different degrees. The majority of existing NMF-based unmixing methods are developed by incorporating additional constraints into the standard NMF based on the spectral and spatial information of hyperspectral images. However, they neglect to exploit the nature of imbalanced pixels included in the data, which may cause the pixels mixed with imbalanced endmembers to be ignored, and thus the imbalanced endmembers generally cannot be accurately estimated due to the statistical property of NMF. To exploit the information of imbalanced samples in hyperspectral data during the unmixing procedure, in this paper, a cluster-wise weighted NMF (CW-NMF) method for the unmixing of hyperspectral images with imbalanced data is proposed. Specifically, based on the result of clustering conducted on the hyperspectral image, we construct a weight matrix and introduce it into the model of standard NMF. The proposed weight matrix can provide an appropriate weight value to the reconstruction error between each original pixel and the reconstructed pixel in the unmixing procedure. In this way, the adverse effect of imbalanced samples on the statistical accuracy of NMF is expected to be reduced by assigning larger weight values to the pixels concerning imbalanced endmembers and giving smaller weight values to the pixels mixed by majority endmembers. Besides, we extend the proposed CW-NMF by introducing the sparsity constraints of abundance and graph-based regularization, respectively. The experimental results on both synthetic and real hyperspectral data have been reported, and the effectiveness of our proposed methods has been demonstrated by comparing them with several state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document