AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Plant Phenomics Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

In Situ Root Dataset Expansion Strategy Based on an Improved CycleGAN Generator

Qiushi Yu1,†, Nan Wang1,†, Hui Tang1, JiaXi Zhang1, Rui Xu2, Liantao Liu3( )
College of Mechanical and Electrical Engineering, Hebei Agricultural University, 071000 Baoding, China
College of Foreign Languages, Hebei Agricultural University, 071000 Baoding, China
College of Agronomy, Hebei Agricultural University, 071000 Baoding, China

†These authors contributed equally to this work.

Show Author Information

Abstract

The root system plays a vital role in plants' ability to absorb water and nutrients. In situ root research offers an intuitive approach to exploring root phenotypes and their dynamics. Deep-learning-based root segmentation methods have gained popularity, but they require large labeled datasets for training. This paper presents an expansion method for in situ root datasets using an improved CycleGAN generator. In addition, spatial-coordinate-based target background separation method is proposed, which solves the issue of background pixel variations caused by generator errors. Compared to traditional threshold segmentation methods, this approach demonstrates superior speed, accuracy, and stability. Moreover, through time-division soil image acquisition, diverse culture medium can be replaced in in situ root images, thereby enhancing dataset versatility. After validating the performance of the Improved_UNet network on the augmented dataset, the optimal results show a 0.63% increase in mean intersection over union, 0.41% in F1, and 0.04% in accuracy. In terms of generalization performance, the optimal results show a 33.6% increase in mean intersection over union, 28.11% in F1, and 2.62% in accuracy. The experimental results confirm the feasibility and practicality of the proposed dataset augmentation strategy. In the future, we plan to combine normal mapping with rendering software to achieve more accurate shading simulations of in situ roots. In addition, we aim to create a broader range of images that encompass various crop varieties and soil types.

References

1

Hinsinger P, Brauman A, Devau N, Gérard F, Jourdan C, Laclau J-P, Le Cadre E, Jaillard B, Plassard C. Acquisition of phosphorus and other poorly mobile nutrients by roots. Where do plant nutrition models fail? Plant Soil. 2011;348:29–61.
Crossref Google Scholar
2

Lynch JP, Wojciechowski T. Opportunities and challenges in the subsoil: Pathways to deeper rooted crops. J Exp Bot. 2015;66(8):2199–2210.
Crossref Google Scholar
3

Zhu H, Zhang LM, Garg A. Investigating plant transpiration-induced soil suction affected by root morphology and root depth. Comput Geotech. 2018;103:26–31.
Crossref Google Scholar
4

Dlamini NE, Zhou M. Soils and seasons effect on sugarcane ratoon yield. Field Crop Res. 2022;284:Article 108588.
Crossref Google Scholar
5

Chen Y, Zheng J, Yang Z, Xu C, Liao P, Pu S, El-Kassaby YA, Feng J. Role of soil nutrient elements transport on Camellia oleifera yield under different soil types. BMC Plant Biol. 2023;23(1):378.
Crossref Google Scholar
6

Liu S, Begum N, An T, Zhao T, Xu B, Zhang S, Deng X, Lam H-M, Nguyen HT, Siddique KH, et al. Characterization of root system architecture traits in diverse soybean genotypes using a semi-hydroponic system. Plants. 2021;10(12):2781.
Crossref Google Scholar
7

Aziz AA, Lim KB, Rahman EKA, Nurmawati MH, Zuruzi AS. Agar with embedded channels to study root growth. Sci Rep. 2020;10(1):14231.
Crossref Google Scholar
8

Ingram PA, Zhu J, Shariff A, Davis IW, Benfey PN, Elich T. High-throughput imaging and analysis of root system architecture in Brachypodium distachyon under differential nutrient availability. Philos Trans R Soc Lond B Biol Sci. 2012;367(1595):1559–1569.
Crossref Google Scholar
9

Bates GH. A device for the observation of root growth in the soil. Nature. 1937;139:966–967.
Crossref Google Scholar
10

Koenig C, Wey H, Binkley T. Precision of the XCT 3000 and comparison of densitometric measurements in distal radius scans between XCT 3000 and XCT 2000 peripheral quantitative computed tomography scanners. J Clin Densitom. 2008;11(4):575–580.
Crossref Google Scholar
11

Borisjuk L, Rolletschek H, Neuberger T. Surveying the plant’s world by magnetic resonance imaging. Plant J. 2012;70(1):129–146.
Crossref Google Scholar
12

Liang Q, Liao H, Yan X. Quantitative analysis of plant root architecture. Chin J Bot. 2007;24(06):695.
Google Scholar
13

Mohamed A, Monnier Y, Mao Z, Lobet G, Maeght J-L, Ramel M, Stokes A. An evaluation of inexpensive methods for root image acquisition when using rhizotrons. Plant Methods. 2017;13:11.
Crossref Google Scholar
14

Zhao H, Wang N, Sun H, Zhu L, Zhang K, Zhang Y, Zhu J, Li A, Bai Z, Liu X, et al. RhizoPot platform: A high-throughput in situ root phenotyping platform with integrated hardware and software. Front Plant Sci. 2022;13:Article 1004304.
Crossref Google Scholar
15

Abràmoff MD, Magalhães PJ, Ram SJ. Image processing with ImageJ. Biophotonics Int. 2004;11:36–42.
Google Scholar
16

Le Bot J, Serra V, Fabre J, Draye X, Adamowicz S, Pagès L. DART: A software to analyse root system architecture and development from captured images. Plant Soil. 2010;326(1):261–273.
Crossref Google Scholar
17

Lobet G, Draye X, Périlleux C. An online database for plant image analysis software tools. Plant Methods. 2013;9(1):38.
Crossref Google Scholar
18

Wang T, Rostamza M, Song Z, Wang L, Mcnickle G, Iyer-Pascuzzi AS, Qiu Z, Jin J. SegRoot: A high throughput segmentation method for root image analysis. Comput Electron Agric. 2019;162:845–854.
Crossref Google Scholar
19

Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39(12):2481–2495.
Crossref Google Scholar
20

Jubery TZ, Carley CN, Singh A, Sarkar S, Ganapathysubramanian B, Singh AK. Using machine learning to develop a fully automated soybean nodule acquisition pipeline (SNAP). Plant Phenomics. 2021;2021:Article 9834746.
Crossref Google Scholar
21
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, editors. Medical image computing and computer-assisted intervention – MICCAI 2015. Cham: Springer International Publishing; 2015. p. 234–241.
Crossref
22
Lin T-Y, Goyal P, Girshick R, He K, Dollár P. Focal loss for dense object detection. Paper presented at: Proceedings of the IEEE international conference on computer vision; 2017 Oct 22–29; Venice, Italy.
Crossref
23
Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision. Cham: Springer International Publishing; 2018. p. 801-818.
Crossref
24

Gaggion N, Ariel F, Daric V, Lambert E, Legendre S, Roulé T, Camoirano A, Milone DH, Crespi M, Blein T, et al. ChronoRoot: High-throughput phenotyping by deep segmentation networks reveals novel temporal parameters of plant root system architecture. GigaScience. 2021;10(7):giab052.
Crossref Google Scholar
25

Smith AG, Han E, Petersen J, Olsen N, Giese C, Athmann M, Dresbøll DB, Thorup-Kristensen K. RootPainter: Deep learning segmentation of biological images with corrective annotation. New Phytol. 2022;236(2):774–791.
Crossref Google Scholar
26
Zhu J-Y, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. Paper presented at: Proceedings of the IEEE international conference on computer vision; 2017 Oct 22–29; Venice, Italy.
Crossref
27

Chen R, Zhao J, Yao X, Jiang S, He Y, Bao B, Luo X, Xu S, Wang C. Generative design of outdoor green spaces based on generative adversarial networks. Buildings. 2023;13(4):1083.
Crossref Google Scholar
28

Zhang W, Chen K, Wang J, Shi Y, Guo W. Easy domain adaptation method for filling the species gap in deep learning-based fruit detection. Hortic Res. 2021;119.
Crossref Google Scholar
29

Mi J, Gao W, Yang S, Hao X, Li M, Wang M, Zheng L. A method of plant root image restoration based on GAN. IFAC-PapersOnLine. 2019;52(30):219–224.
Crossref Google Scholar
30

Zhu L, Liu L, Sun H, Zhang K, Zhang Y, Li A, Bai Z, Wang G, Liu X, Dong H, et al. Low nitrogen supply inhibits root growth but prolongs lateral root lifespan in cotton. Ind Crop Prod. 2022;189:Article 115733.
Crossref Google Scholar
31

Zhu L, Liu L, Sun H, Zhang Y, Liu X, Wang N, Chen J, Zhang K, Bai Z, Wang G, et al. The responses of lateral roots and root hairs to nitrogen stress in cotton based on daily root measurements. J Agron Crop Sci. 2022;208(1):89–105.
Crossref Google Scholar
32

Xiao S, Liu L, Zhang Y, Sun H, Zhang K, Bai Z, Dong H, Li C. Fine root and root hair morphology of cotton under drought stress revealed with RhizoPot. J Agron Crop Sci. 2020;206(6):679–693.
Crossref Google Scholar
33

Zhu L, Li A, Sun H, Li P, Liu X, Guo C, Zhang Y, Zhang K, Bai Z, Dong H, et al. The effect of exogenous melatonin on root growth and lifespan and seed cotton yield under drought stress. Ind Crop Prod. 2023;204:117344.
Crossref Google Scholar
34
Woo S, Park J, Lee J-Y, Kweon IS. CBAM: Convolutional block attention module. In: Lecture notes in computer science. Cham: Springer International Publishing; 2018. p. 3–19.
Crossref
35

Yu Q, Wang J, Tang H, Zhang J, Zhang W, Liu L, Wang N. Application of improved UNet and EnglightenGAN for segmentation and reconstruction of in situ roots. Plant Phenomics. 2023;5:0066.
Crossref Google Scholar
36
Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S. GANs trained by a two time-scale update rule converge to a local nash equilibrium. Paper presented at: The Proceedings of the 31st International Conference on Neural Information Processing Systems; 2017; Long Beach, CA, USA.
37
Bińkowski M, Sutherland D J, Arbel M, Gretton A. Demystifying mmd gans. ArXiv. 2018. https://doi.org/10.48550/arXiv.1801.01401.
38

Shen C, Liu L, Zhu L, Kang J, Shao L. High-throughput in situ root image segmentation based on the improved DeepLabv3+ method. Front Plant Sci. 2020;11:Article 576791.
Crossref Google Scholar
39

Jia KA, Llbc D, Fz E, Chen SA, Nan W, Ls A. Semantic segmentation model of cotton roots in-situ image based on attention mechanism. Comput Electron Agric. 2021;189:Article 106370.
Crossref Google Scholar
40
Jiang J, Chen B, Pan J, Wang X, Dapeng L, Jiang J, Long M. ForkMerge: Overcoming negative transfer in multi-task learning. ArXiv. 2023. https://doi.org/10.48550/arXiv.2301.12618.
41

Gao Y, Li Y, Jiang R, Zhan X, Lu H, Guo W, Yang W, Ding Y, Liu S. Enhancing green fraction estimation in Rice and wheat crops: A self-supervised deep learning semantic segmentation approach. Plant Phenomics. 2023;5:0064.
Crossref Google Scholar
42

Li Y, Zhan X, Liu S, Lu H, Jiang R, Guo W, Chapman S, Ge Y, Solan B, Ding Y, et al. Self-supervised plant phenotyping by combining domain adaptation with 3D plant model simulations: Application to wheat leaf counting at seedling stage. Plant Phenomics. 2023;5:0041.
Crossref Google Scholar
43

Sahin HM, Miftahushudur T, Grieve B, Yin H. Segmentation of weeds and crops using multispectral imaging and CRF-enhanced U-Net. Comput Electron Agric. 2023;211:Article 107956.
Crossref Google Scholar
44
Li C, Wand M. Combining markov random fields and convolutional neural networks for image synthesis. Paper presented at: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27–30; Las Vegas, NV, USA.
Crossref
Plant Phenomics
Volume 6,
2024
Article number: 0148
DOI: 10.34133/plantphenomics.0148
Cite this article:
Yu Q, Wang N, Tang H, et al. In Situ Root Dataset Expansion Strategy Based on an Improved CycleGAN Generator. Plant Phenomics, 2024, 6: 0148. https://doi.org/10.34133/plantphenomics.0148

158

Views

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 23 August 2023
Accepted: 12 January 2024
Published: 12 February 2024
© 2024 Qiushi Yu et al. Exclusive licensee Nanjing Agricultural University. No claim to original U.S. Government Works.

Distributed under a Creative Commons Attribution License 4.0 (CC BY 4.0).
Return