CoChat

Recognition of Wheat Spike from Field Based Phenotype Platform Using Multi-Sensor Fusion and Improved Maximum Entropy Segmentation Algorithms

Open access

The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.

Abstract

To obtain an accurate count of wheat spikes, which is crucial for estimating yield, this paper proposes a new algorithm that uses computer vision to achieve this goal from an image. First, a home-built semi-autonomous multi-sensor field-based phenotype platform (FPP) is used to obtain orthographic images of wheat plots at the filling stage. The data acquisition system of the FPP provides high-definition RGB images and multispectral images of the corresponding quadrats. Then, the high-definition panchromatic images are obtained by fusion of three channels of RGB. The Gram–Schmidt fusion algorithm is then used to fuse these multispectral and panchromatic images, thereby improving the color identification degree of the targets. Next, the maximum entropy segmentation method is used to do the coarse-segmentation. The threshold of this method is determined by a firefly algorithm based on chaos theory (FACT), and then a morphological filter is used to de-noise the coarse-segmentation results. Finally, morphological reconstruction theory is applied to segment the adhesive part of the de-noised image and realize the fine-segmentation of the image. The computer-generated counting results for the wheat plots, using independent regional statistical function in Matlab R2017b software, are then compared with field measurements which indicate that the proposed method provides a more accurate count of wheat spikes when compared with other traditional fusion and segmentation methods mentioned in this paper.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/rs10020246

Cites

57 of 57 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Sketch map of experimental area . The image was taken on 1 May 2017 using Dajiang's S1000 unmanned aerial vehicle. The camera model is SONY QX-100, and the UAV flying height is 50 m. The green markings represent selected areas and red markings represent other areas. Figure 1. Sketch map of experimental area. The image was taken on 1 May 2017 using Dajiang's S1000 unmanned aerial vehicle. The camera model is SONY QX-100, and the UAV flying height is 50 m. The green markings represent selected areas and red markings represent other areas.
Figure 1 Sketch map of experimental area . The image was taken on 1 May 2017 using Dajiang's S1000 unmanned aerial vehicle. The camera model is SONY QX-100, and the UAV flying height is 50 m. The green markings represent selected areas and red markings represent other areas. Figure 1. Sketch map of experimental area. The image was taken on 1 May 2017 using Dajiang's S1000 unmanned aerial vehicle. The camera model is SONY QX-100, and the UAV flying height is 50 m. The green markings represent selected areas and red markings represent other areas.CC-BY · From the PDF
Image 2
CC-BY · From the PDF
Figure 3 Flow chart of recognition and counting method of wheat ear at filling stage. Figure 3. Flow chart of recognition and counting method of wheat ear at filling stage.
Figure 3 Flow chart of recognition and counting method of wheat ear at filling stage. Figure 3. Flow chart of recognition and counting method of wheat ear at filling stage.CC-BY · From the PDF
Figure 4 Image contrast before and after morphological filtering. ( a ) Before morphological filtering, ( b ) after morphological filtering. Figure 4. Image contrast before and after morphological filtering. ( a ) Before morphological filtering, ( b ) after morphological filtering.
Figure 4 Image contrast before and after morphological filtering. ( a ) Before morphological filtering, ( b ) after morphological filtering. Figure 4. Image contrast before and after morphological filtering. ( a ) Before morphological filtering, ( b ) after morphological filtering.CC-BY · From the PDF
Figure 5 Fusion results of original panchromatic and multispectral images after registration. (1) Image contrast before and after fusion in T1 plot: ( a ) Panchromatic image with T1 plot; ( b ) Fusion result in T1 plot; (2) Image contrast before and after fusion in T3 plot: ( c ) Panchromatic image with T3 plot; ( d ) Fusion result in T3 plot; (3) Image contrast before and after fusion in T4 plot: ( e ) Panchromatic image with T4 plot; ( f ) Fusion result in T4 plot Figure 5. Fusion results of original panchromatic and multispectral images after registration. ( 1 ) Image contrast before and after fusion in T1 plot: ( a ) Panchromatic image with T1 plot; ( b ) Fusion result in T1 plot; ( 2 ) Image contrast before and after fusion in T3 plot: ( c ) Panchromatic image with T3 plot; ( d ) Fusion result in T3 plot; ( 3 ) Image contrast before and after fusion in T4 plot: ( e ) Panchromatic image with T4 plot; ( f ) Fusion result in T4 plot.
Figure 5 Fusion results of original panchromatic and multispectral images after registration. (1) Image contrast before and after fusion in T1 plot: ( a ) Panchromatic image with T1 plot; ( b ) Fusion result in T1 plot; (2) Image contrast before and after fusion in T3 plot: ( c ) Panchromatic image with T3 plot; ( d ) Fusion result in T3 plot; (3) Image contrast before and after fusion in T4 plot: ( e ) Panchromatic image with T4 plot; ( f ) Fusion result in T4 plot Figure 5. Fusion results of original panchromatic and multispectral images after registration. ( 1 ) Image contrast before and after fusion in T1 plot: ( a ) Panchromatic image with T1 plot; ( b ) Fusion result in T1 plot; ( 2 ) Image contrast before and after fusion in T3 plot: ( c ) Panchromatic image with T3 plot; ( d ) Fusion result in T3 plot; ( 3 ) Image contrast before and after fusion in T4 plot: ( e ) Panchromatic image with T4 plot; ( f ) Fusion result in T4 plot.CC-BY · From the PDF
Figure 6 Cont.
Figure 6 Cont.CC-BY · From the PDF
Figure 6 Segmentation results in each plot. Red regions show where artificial and machine recognition agree, blue regions show where artificial recognition and machine recognition do not agree, green regions show where the machine gives erroneous recognition. (1) Segmentation results in T1 plot: ( a ) Proposed method; ( b ) Edge detection method; ( c ) fuzzy clustering method; ( d ) Snake model; ( e ) Minimum cut method; ( f ) region growth method; (2) Segmentation results in T2 plot: ( g ) Proposed method; ( h ) Edge detection method; ( i ) fuzzy clustering method; ( j ) Snake model; ( k ) Minimum cut method; ( l ) region growth method; (3) Segmentation results in T3 plot: ( m ) Proposed method; ( n ) Edge detection method; ( o ) fuzzy clustering method; ( p ) Snake model; ( q ) Minimum cut method; ( r ) region growth method; Figure 6. Segmentation results in each plot. Red regions show where artificial and machine recognition agree, blue regions show where artificial recognition and machine recognition do not agree, green regions show where the machine gives erroneous recognition. ( 1 ) Segmentation results in T1 plot: ( a ) Proposed method; ( b ) Edge detection method; ( c ) fuzzy clustering method; ( d ) Snake model; ( e ) Minimum cut method; ( f ) region growth method; ( 2 ) Segmentation results in T2 plot: ( g ) Proposed method; ( h ) Edge detection method; ( i ) fuzzy clustering method; ( j ) Snake model; ( k ) Minimum cut method; ( l ) region growth method; ( 3 ) Segmentation results in T3 plot: ( m ) Proposed method; ( n ) Edge detection method; ( o ) fuzzy clustering method; ( p ) Snake model; ( q ) Minimum cut method; ( r ) region growth method.
Figure 6 Segmentation results in each plot. Red regions show where artificial and machine recognition agree, blue regions show where artificial recognition and machine recognition do not agree, green regions show where the machine gives erroneous recognition. (1) Segmentation results in T1 plot: ( a ) Proposed method; ( b ) Edge detection method; ( c ) fuzzy clustering method; ( d ) Snake model; ( e ) Minimum cut method; ( f ) region growth method; (2) Segmentation results in T2 plot: ( g ) Proposed method; ( h ) Edge detection method; ( i ) fuzzy clustering method; ( j ) Snake model; ( k ) Minimum cut method; ( l ) region growth method; (3) Segmentation results in T3 plot: ( m ) Proposed method; ( n ) Edge detection method; ( o ) fuzzy clustering method; ( p ) Snake model; ( q ) Minimum cut method; ( r ) region growth method; Figure 6. Segmentation results in each plot. Red regions show where artificial and machine recognition agree, blue regions show where artificial recognition and machine recognition do not agree, green regions show where the machine gives erroneous recognition. ( 1 ) Segmentation results in T1 plot: ( a ) Proposed method; ( b ) Edge detection method; ( c ) fuzzy clustering method; ( d ) Snake model; ( e ) Minimum cut method; ( f ) region growth method; ( 2 ) Segmentation results in T2 plot: ( g ) Proposed method; ( h ) Edge detection method; ( i ) fuzzy clustering method; ( j ) Snake model; ( k ) Minimum cut method; ( l ) region growth method; ( 3 ) Segmentation results in T3 plot: ( m ) Proposed method; ( n ) Edge detection method; ( o ) fuzzy clustering method; ( p ) Snake model; ( q ) Minimum cut method; ( r ) region growth method.CC-BY · From the PDF
Figure 7 Image segmentation results compared with results of manual measurements. Figure 7. Image segmentation results compared with results of manual measurements.
Figure 7 Image segmentation results compared with results of manual measurements. Figure 7. Image segmentation results compared with results of manual measurements.CC-BY · From the PDF
Figure 8 Accuracy of wheat ear recognition with different image fusion methods and without image fusion. 5.3. Analysis of the Effect of Illumination Intensity on Recognition Accuracy Figure 8. Accuracy of wheat ear recognition with different image fusion methods and without image fusion.
Figure 8 Accuracy of wheat ear recognition with different image fusion methods and without image fusion. 5.3. Analysis of the Effect of Illumination Intensity on Recognition Accuracy Figure 8. Accuracy of wheat ear recognition with different image fusion methods and without image fusion.CC-BY · From the PDF
Figure 9 Segmentation accuracy as a function of illumination intensity. Figure 9. Segmentation accuracy as a function of illumination intensity.
Figure 9 Segmentation accuracy as a function of illumination intensity. Figure 9. Segmentation accuracy as a function of illumination intensity.CC-BY · From the PDF
Image 11
CC-BY · From the PDF
Figure 11 Segmentation accuracy as a function of observation radius.
Figure 11 Segmentation accuracy as a function of observation radius.CC-BY · From the PDF
Figure 12 Segmentation accuracy as a function of observation radius after two types of distortion.
Figure 12 Segmentation accuracy as a function of observation radius after two types of distortion.CC-BY · From the PDF
Figure 13 Comparison of running-times by using different coarse-segmentation methods. ( a ) Coarsesegmentation with Minimum cut; ( b ) Coarse-segmentation with Edge detection; ( c ) Coarsesegmentation with fuzzy clustering; ( d ) Coarse-segmentation with snake model; ( e ) Coarsesegmentation with region growth; ( f ) Coarse-segmentation with proposed method Figure 13. Comparison of running-times by using different coarse-segmentation methods. ( a ) Coarsesegmentation with Minimum cut; ( b ) Coarse-segmentation with Edge detection; ( c ) Coarse-segmentation with fuzzy clustering; ( d ) Coarse-segmentation with snake model; ( e ) Coarse-segmentation with region growth; ( f ) Coarse-segmentation with proposed method.
Figure 13 Comparison of running-times by using different coarse-segmentation methods. ( a ) Coarsesegmentation with Minimum cut; ( b ) Coarse-segmentation with Edge detection; ( c ) Coarsesegmentation with fuzzy clustering; ( d ) Coarse-segmentation with snake model; ( e ) Coarsesegmentation with region growth; ( f ) Coarse-segmentation with proposed method Figure 13. Comparison of running-times by using different coarse-segmentation methods. ( a ) Coarsesegmentation with Minimum cut; ( b ) Coarse-segmentation with Edge detection; ( c ) Coarse-segmentation with fuzzy clustering; ( d ) Coarse-segmentation with snake model; ( e ) Coarse-segmentation with region growth; ( f ) Coarse-segmentation with proposed method.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 57 references

Research works printed but not linked: 3

  1. 2. Azzari, G.; Lobell, D.B. Satellite estimates of crop area and maize yield in Zambia's agricultural districts (Abstracts). In Proceedings of the AGU Fall Meeting, San Francisco, CA, USA, 14-18 December 2015.
  2. 37. Zhang, J.L.; Hu, X.T.; Wen, X.B. Remote sensing image fusion algorithm based on Shearlet transform and region segmentation. J. Optoelectron. Laser 2015, 26, 2393-2399.
  3. 46. Xu, S.; Xing, K.; Tian, Y.; Ma, G. Effect of light intensity on Epinephelus malabaricus's image segmentation processing. J. Tianjin Agric. Univ. 2016, 1, 34-37.

Cited by

See all 63

Metadata

Authors
Zhou, C., Liang, D., Yang, X., Xu, B., & Yang, G.
Affiliations
  • Anhui University (CN)
  • Ministry of Agriculture and Rural Affairs (CN)
  • National Engineering Research Center for Information Technology in Agriculture (CN)
Corresponding author
Yang, Guijun
Venue
Remote Sensing
Publisher
MDPI AG
Published
2018-02-06
Volume
10
Issue
2
Pages
246
ISSN
2072-4292 (ISSN-L)
OpenAlex
W2789573723
Cited by
62
References
57
Citations by year
2026: 3 · 2025: 3 · 2024: 6 · 2023: 10 · 2022: 12 · 2021: 9 · 2020: 8 · 2019: 8 · 2018: 3
FWCI
6.20
Type
journal article
Language
en
Open access
Locations
  • Remote Sensing (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Key Research and Development Program of China (2016YFD0300602, 2016YFD0800904)
  • the Natural Science Foundation of China (61661136003, 41471285, 41471351)
  • the Special Funds for Technology innovation capacity building sponsored by the Beijing Academy of Agriculture and Forestry Sciences (KJCX20170423, KYCXPT201703)
  • Beijing Municipal Science and Technology Project (Z161100004516009)
Topics
  • Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
  • Physical Sciences › Environmental Science › Ecology › Remote Sensing in Agriculture
  • Life Sciences › Agricultural and Biological Sciences › Plant Science › Leaf Properties and Growth Measurement
Keywords
multi-sensor image fusion, Gram-Schmidt fusion, firefly algorithm, chaos theory, morphological filtering, morphological reconstruction, multispectral imaging, wheat yield estimation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.