Skip to main content
SpringerLink
Log in

Object-based crop classification in Hetao plain using random forest

  • Research Article
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

Crop classification based on object-based image analysis (OBIA) is increasingly reported. However, it is still challenging to produce high-quality crop type maps by using recent techniques. This article introduces a new object-based crop classification algorithm which contains 4 steps. First, a random forest (RF) classifier is trained by using the initial training set, which tends to have a relatively small size. Second, importance scores for each feature variable are derived by using the RF model. Third, by treating the importance scores as weighting factors, a weighted Euclidean distance criterion is designed and used for sample creation to enlarge training set. Fourth, RF is re-trained by using the enlarged training set, and then it is employed for final classification. To validate the proposed strategy, a Worldview-2 image covering a part of Hetao plain is experimented. Results indicate that the new method yields the best overall accuracy, which equals 90.52%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  • Baatz M, Schäpe M (2000) Multiresolution segmentation - an optimization approach for high quality multi-scale image segmentation. In: Strobl J, Blaschke T (eds) Angewandte Geographische InformationsVerarbeitung XII. Wichmann, Heidelberg, pp 12–23

    Google Scholar 

  • Belgiu M, Csillik O (2018) Sentinel-2 cropland mapping using pixel-based and object-based timeweighted dynamic time warping analysis. Remote Sens Environ 204:509–523

    Article  Google Scholar 

  • Belgiu M, Dragut L (2016) Random forest in remote sensing: a review of applications and future directions. ISPRS J Photogramm Remote Sens 114:24–31

    Article  Google Scholar 

  • Bhardwaj K, Patra S (2018) An unsupervised technique for optimal feature selection in attribute profifiles for spectral-spatial classifification of hyperspectral images. ISPRS J Photogramm Remote Sens 138:139–150

    Article  Google Scholar 

  • Boryan C, Yang Z, Mueller R, Craig M (2011) Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, cropland data layer program. Geocarto International 26(5):341–358

    Article  Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  • Castro AI, Torres-Sánchez J, Peña JM, Jiménez-Brenes FM, Csillik O, López-Granados F (2018) An automatic random forest-OBIA algorithm for early weed mapping between and within crop rows using UAV imagery. Remote Sens 10:285

    Article  Google Scholar 

  • Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357

    Article  Google Scholar 

  • Efron B, Tibshirani R (1994) An introduction to the bootstrap. Chapman and Hall/CRC, Boca Raton, p 436

    Book  Google Scholar 

  • Gaetano R, Masi G, Poggi G, Verdoliva L, Scarpa G (2015) Marker-controlled watershed-based segmentation of multi-resolution remote sensing images. IEEE Trans Geosci Remote Sens 53:2987–3004

    Article  Google Scholar 

  • Geiß C, Pelizari PA, Marconcini M, Sengara W, Edwards M, Lakes T, Taubenböck H (2015) Estimation of seismic building structural types using multi-sensor remote sensing and machine learning techniques. ISPRS J Photogramm Remote Sens 104:175–188

    Article  Google Scholar 

  • Hossain MD, Chen D (2019) Segmentation for object-based image analysis (OBIA): a review of algorithms and challenges from remote sensing perspective. ISPRS J Photogramm Remote Sens 150:115–134

    Article  Google Scholar 

  • Johnson B, Xie Z (2011) Unsupervised image segmentation evaluation and refinement using a multi-scale approach. ISPRS J Photogramm Remote Sens 66:473–483

    Article  Google Scholar 

  • Li X, Chen W, Cheng X, Liao Y, Chen G (2017) Comparison and integration of feature reduction methods for land cover classification with RapidEye imagery. Multimed Tools Appl 76:23041–23057

    Article  Google Scholar 

  • Liu W, Yang J, Li P, Han Y, Zhao J, Shi H (2018) A novel object-based supervised classification method with active learning and random forest for PolSAR imagery. Remote Sens 10:1092

    Article  Google Scholar 

  • Liu D, Cheng N, Zhang X, Wang C, Du W (2020) Annual large-scale urban land mapping based on Landsat time series in Google earth engine and OpenStreetMap data: a case study in the middle Yangtze River basin. ISPRS J Photogramm Remote Sens 159:337–351

    Article  Google Scholar 

  • Long JA, Lawrence RL, Greenwood MC, Marshall L, Miller PR (2013) Object-oriented crop classification using multitemporal ETM+ SLC-off imagery and random forest. GIScience & Remote Sensing 50(4):418–436

    Article  Google Scholar 

  • Löw F, Knöfel P, Conrad C (2015) Analysis of uncertainty in multi-temporal object-based classification. ISPRS J Photogramm Remote Sens 105:91–106

    Article  Google Scholar 

  • Luciano AS, Picoli MCA, Rocha JV, Duft DG, Lamparelli RAC, Leal MRLV, Maire GL (2019) A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm. Int J Appl Earth Obs Geoinf 80:127–136

    Article  Google Scholar 

  • Ma L, Fu T, Li M (2018) Active learning for object-based image classification using predefined training objects. Int J Remote Sens 39:2746–2765

    Article  Google Scholar 

  • Panboonyuen T, Jitkajornwanich K, Lawawirojwong S, Srestasathiern P, Vateekul P (2017) Road segmentation of remotely-sensed images using deep convolutional neural networks with landscape metrics and conditional random fields. Remote Sens 9:680

    Article  Google Scholar 

  • Peña JM, Gutiérrez PA, Hervás-Martínez C, Six J, Plant RE, López-Granados F (2014) Object-based image classification of summer crops with machine learning methods. Remote Sens 6:5019–5041

    Article  Google Scholar 

  • Persello C, Bruzzone L (2014) Active and semisupervised learning for the classifification of remote sensing images. IEEE Trans Geosci Remote Sens 52:6937–6956

    Article  Google Scholar 

  • Su T (2019) Scale-variable region-merging for high resolution remote sensing image segmentation. ISPRS J Photogramm Remote Sens 147:319–334

    Article  Google Scholar 

  • Su T (2020) Object-based feature selection using classpair separability for high-resolution image classification. Int J Remote Sens 41:238–271

    Article  Google Scholar 

  • Su T, Zhang S (2017a) Winter wheat mapping method using Landsat 8 images and geographic object-based image analysis. Trans ASABE 60(3):625–633

    Article  Google Scholar 

  • Su T, Zhang S (2017b) Local and global evaluation for remote sensing image segmentation. ISPRS J Photogramm Remote Sens 130:256–276

    Article  Google Scholar 

  • Sun S, Zhong P, Xiao H, Wang R (2015) Active learning with Gaussian process classifier for hyperspectral image classification. IEEE Trans Geosci Remote Sens 53:1746–1760

    Article  Google Scholar 

  • Vieira MA, Formaggio AR, Rennó CD, Atzberger C, Aguiar DA, Mello MP (2012) Object based image analysis and data mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas. Remote Sens Environ 123:553–562

    Article  Google Scholar 

  • Wardlow BD, Egbert SL (2010) A comparison of MODIS 250-m EVI and NDVI data for crop mapping: a case study for Southwest Kansas. Int J Remote Sens 31(3):805–830

    Article  Google Scholar 

  • Wu M, Huang W, Ziu Z, Wang Y, Wang C, Li W, Hao P, Yu B (2017) Fine crop mapping by combining high spectral and high spatial resolution remote sensing data in complex heterogeneous areas. Comput Electron Agric 139:1–9

    Article  Google Scholar 

  • Yan L, Roy DP (2014) Automated crop field extraction from multi-temporal web enabled Landsat data. Remote Sens Environ 144:42–44

    Article  Google Scholar 

Download references

Acknowledgements

This study is jointly supported by the National Natural Science Foundation of China under grant number of 61701265, and the Inner Mongolia Science Fund for Distinguished Young Scholars, under grant number of 2019JQ06. The anonymous reviewers are thanked for their constructive and helpful comments.

Author information

Authors and Affiliations

  1. College of Water Conservancy and Civil Engineering, Inner Mongolia Agricultural University, No. 306, Zhaowuda Road, Hohhot, China

    Tengfei Su & Shengwei Zhang

  2. Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry, No. 306, Zhaowuda Road, Hohhot, China

    Shengwei Zhang

Authors
  1. Tengfei Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shengwei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shengwei Zhang.

Additional information

Communicated by: H. Babaie

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Su, T., Zhang, S. Object-based crop classification in Hetao plain using random forest. Earth Sci Inform 14, 119–131 (2021). https://doi.org/10.1007/s12145-020-00531-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-020-00531-z

Keywords

Search

Navigation