Methodology of wheat lodging annotation based on semi-automatic image segmentation algorithm

Gan Zhang, Fangming He, Haifeng Yan, Haifeng Xu, Zhenggao Pan, Xiaoying Yang, Dongyan Zhang, Weifeng Li

Abstract


Abstract: The existing identification of wheat lodging based on unmanned aerial vehicle (UAV) is significantly dependent on the artificial ground annotation method, which exhibits low annotation accuracy and strong subjectivity, thus resulting in a low degree of separation for the annotated lodging area and the non-lodging area.  To solve the problem of insufficient applicability of traditional annotation research to agricultural images, especially wheat field lodging images, a lodging annotation method in the study based on semi-automatic image segmentation algorithm was proposed.  Firstly, a total of 101 farmlands with lodging occurred during the flowering, filling and mature period of wheat in 2019 and 2021 were segmented as the research objects.  The above images were respectively changed into RGB and HSV color space and converted into four vegetation indexes, including excess-green (ExG), green leaf index (VEG), normalized green-red difference index (NGRDI), as well as red-green ratio index (GRRI).  Secondly, lodging regions were extracted and modified from the image in accordance with color features.  Lastly, the JM distance of lodging and non-lodging areas served as an index to examine the effect of image annotation for data analysis and evaluation of segmentation accuracy.  The result of the experiment indicated that there was a very significant difference between the JM distance based on the annotation method proposed in this study and the result based on manual annotation.  GRRI and ExG were the most suitable features for image annotation.  The method proposed in this study had high generalization performance for the images captured in the three fertility periods in 2019 and 2021, and the images with poor image annotation results took up a small proportion.  In brief, the lodging area annotation method proposed in this study increases the annotation accuracy by extracting lodging areas using a semi-automatic image segmentation algorithm.  The proposed method outperforms the manual annotation method.

Keywords: semi-automatic image annotation, wheat lodging, unmanned aerial vehicle, image processing, feature separability

DOI: 10.33440/j.ijpaa.20220501.193

 

Citation: Zhang G, He F M, Yan H F, Xu H F, Pan Z G, Yang X Y, Zhang D Y, Li W F.  Methodology of wheat lodging annotation based on semi-automatic image segmentation algorithm.  Int J Precis Agric Aviat, 2022; 5(1): 47–53.

Full Text:

PDF

References


Liu T X, Guan C Y, Lei D Y. The Research Progress on Evaluation Methods of Lodging Resistance in Crops. Chinese Agricultural Science Bulletin, 2007(5): 203–206. doi: none.

Fan X P, Zhou J P, Xu Y. Research Advances of Monitoring Agricultural Information Using UAV Low-Altitude Remote Sensing. Journal of Xinjiang University (Natural Science Edition in Chinese and English), 2021, 38: 623–31. doi: 10.13568/j.cnki.651094.651316.2020.09. 26.0002

Dong J H, Yang X D, G L, et al. Extraction of winter wheat lodging area information based on UAV remote sensing images. Heilongjiang Agriculture Sciences, 2016(10): 147–52. doi: 10.11942/ j.issn1002-2767.2016.10.0147

Yang M D, Huang K S, Kuo Y H, et al. Spatial and Spectral Hybrid Image Classification for Rice Lodging Assessment through UAV Imagery. Remote Sensing, 2017, 9(6). doi: 10.3390/rs9060583

Tian M L, Ban S t, Y T, et al. Monitoring of lodged rice using low-altitude UAV based multispectral image. Acta Agriculturae Shanghai, 2018, 34: 88–93. doi: 10.15955/j.issn1000-3924.2018.06.18

Li G, Zhang L Y, Song C Y, et al. Extraction Method of Wheat Lodging Information Based on Multi-temporal UAV remote sensing data.. Transactions of the Chinese Society of Agricultural Machinery, 2019, 50: 211–20. doi: 10.6041 /j.issn.1000-1298.2019.04.024

Ren Z Q, Ding L X, Liu L J, et al. Crop acreage monitoring based on UAV image. Bulletin of Surveying and Mapping, 2020, 76–81. doi: 10.13474/j.cnki.11-2246.2020.0218

Han L, Yang G, Yang X, et al. An explainable XGBoost model improved by SMOTE-ENN technique for maize lodging detection based on multi-source unmanned aerial vehicle images. Comput Electron Agr, 2022, 194: 106804. doi: 10.1016/j.compag.2022.106804

Wang J, Ge H, Dai Q, et al. Unsupervised discrimination between lodged and non-lodged winter wheat: a case study using a low-cost unmanned aerial vehicle. Int J Remote Sens, 2018, 39(8): 2079–2088. doi: 10.1080/01431161.2017.1422875

Li G, Han W, Huang S, et al. Extraction of Sunflower Lodging Information Based on UAV Multi-Spectral Remote Sensing and Deep Learning. Remote sensing, 2021, 13(14): 2721. doi: 10.3390/rs13142721

Tan S, Mortensen A K, Ma X, et al. Assessment of grass lodging using texture and canopy height distribution features derived from UAV visual-band images. Agr Forest Meteorol, 2021, 308–309: 108541. doi: 10.1016/j.agrformet.2021.108541. doi: 10.1016/j.imavis.2018.09.017

Bhagat P K, Choudhary P. Image annotation: Then and now. Image Vision Comput, 2018, 80: 1–23. doi: 10.1016/j.imavis.2018.09.017

D. Bratasanu, I. Nedelcu, M. Datcu, Bridging the semantic gap for satellite imageannotation and automatic mapping applications, IEEE J. Sel. Top. Appl. Earth Obs.Remote. Sens. 4 (1) (2011) 193–204. doi: none.

Song L Y, Luo M N, Liu L, et al. Sparse multi-modal topical coding for image annotation. Neurocomputing, 214(2016): 162–174. doi: 10.1016/j.neucom.2016.06.005

Ke X, Li S Z, Cao D L. A two-level model for automatic image annotation. Multimed Tools Appl, 2011, 61(1): 195–212. doi: 10.1007/ s11042-010-0706-9

Kong D G, Ding C, Huang H, et al. Multi-label ReliefF and F-statistic featureselections for image annotation, 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012. pp. 2352–2359. doi: 10.1109/CVPR.2012.6247947

Jia X, Sun F M, Li H J, et al. Image multi-label annotation based on supervised nonnegative matrix factorization with new matching measurement, Neurocomputing 219 (Supplement C) (2017) 518–525. doi: 10.1016/j.neucom.2016.09.052

Lin Y Q, Lv F J, Zhu S H, et al. Large-scaleimage classification: fast feature extraction and SVM training, CVPR 2011, 2011.pp. 1689–1696. doi: 10.1109/CVPR.2011.5995477

Yu N, Hua K A, Cheng H. A Multi-Directional Search technique for image annotation propagation. J Vis Commun Image R, 2012, 23(1): 237–244. doi: 10.1016/j.jvcir.2011.10.004

Zhu X F, W Nejdl, M Georgescu, An adaptive teleportation random walk model for learning social tag relevance, Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR ’14, ACM, New York, NY, USA, 2014, pp. 223–232. doi: 10.1145/2600428.2609556

Lei C Y, Liu D, Li W P, et al. Social diffusion analysis with common-interest model for image annotation. IEEE Trans. Multimedia 2016, 18(4): 687–701. doi: 10.1109/TMM.2015.2477277

Tang J H, Hong R, Qi G J, et al. Image annotation by kNN-sparse graph-based label propagation over noisily tagged web images, 14: 1–14: 15. ACM Trans. Intell. Syst. Technol, 2011, 2(2). doi: 10.1145/ 1899412.1899418

Xu X, A. Shimada, R.-i. Taniguchi, Image annotation by learning label-specific distance metrics. Image Analysis and Processing-ICIAP2013, Springer Berlin Heidelberg, Berlin, Heidelberg, 2013, pp. 101–110. doi: none

M.M. Kalayeh, H. Idrees, M. Shah, NMF-KNN: Image Annotation Using Weighted Multi-view Non-negative Matrix Factorization, 2014IEEEConferenceonComputer Vision and Pattern Recognition, 2014. pp. 184–191. doi: 10.1109/CVPR.2014.31

Lin Z J, Ding G G, Hu P P. Image auto-annotation via tag-dependent random search over range-constrained visual neighbours. Multimedia ToolsAppl. 2015, 74(11): 4091–4116. doi: 10.1007/s11042-013-1811-3

Wang L, Zhou T H, Lee Y K, et al. An efficient refinement algorithm for multi-label image annotation with correlation model. Telecommun Syst, 2015, 60(2): 285–301. doi: 10.1007/s11235-015-0030-9

Lin J, Yu T, Wang Z J. Rethinking Crowdsourcing Annotation: Partial Annotation With Salient Labels for Multilabel Aerial Image Classification. IEEE transactions on geoscience and remote sensing, 2022, 60: 1. doi: 10.1109/TGRS.2022.3191735

Theodosiou Z, Tsapatsoulis N. Image annotation: the effects of content, lexicon and annotation method. International Journal of Multimedia Information Retrieval, 2020, 9(3): 191–203. doi: 10.1007/ s13735-020-00193-z

Ke X, Li S, Cao D. A two-level model for automatic image annotation. Multimedia Tools and Applications, 2012, 61(1): 195–212. doi: 10.1007/s11042-010-0706-9

Wang Y J, Qi Q, Liu Y, et al. Unsupervised segmentation evaluation using area-weighted variance and Jeffries-Matusita distance for remote sensing images. Remote Sensing, 2018, 10: 1193. doi: 10.3390/ rs10081193

Qiu B W, Fan Z L, Zhong M, et al. A new approach for crop identification with wavelet variance and JM distance. Environmental Monitoring and Assessment, 2014, 186(11): 7929–7940. doi: 10.1007/ s10661-014-3977-1

Liu H L, Zhang F Z, Zhang L F, et al. UNVI-Based Time Series for Vegetation Discrimination Using Separability Analysis and Random Forest Classification. Remote Sensing, 2020, 12(3): 529. doi: 10.3390/ rs12030529

Du M, Noguchi N. Monitoring of Wheat Growth Status and Mapping of Wheat Yield’s within-Field Spatial Variations Using Color Images Acquired from UAV-camera System. Remote sensing (Basel, Switzerland), 2017, 9(3): 289. doi: 10.3390/rs9030289

Yang B H, Zhu Y, Zhou S J. Accurate Wheat Lodging Extraction from Multi-Channel UAV Images Using a Lightweight Network Model. Sensors (Basel, Switzerland), 2021, 21(20): 6826. doi: 10.3390/s21206826


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.