Object-based crop classification in Hetao plain using random forest

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%.

[1]  Jorge Torres-Sánchez,et al.  An Automatic Random Forest-OBIA Algorithm for Early Weed Mapping between and within Crop Rows Using UAV Imagery , 2018, Remote. Sens..

[2]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[3]  Gang Chen,et al.  Comparison and integration of feature reduction methods for land cover classification with RapidEye imagery , 2017, Multimedia Tools and Applications.

[4]  Jansle Vieira Rocha,et al.  A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[5]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[6]  Christopher Conrad,et al.  Analysis of uncertainty in multi-temporal object-based classification , 2015 .

[7]  Shengwei Zhang,et al.  Local and global evaluation for remote sensing image segmentation , 2017 .

[8]  Zhengwei Yang,et al.  Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer Program , 2011 .

[9]  Lucy Marshall,et al.  Object-oriented crop classification using multitemporal ETM+ SLC-off imagery and random forest , 2013 .

[10]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[11]  Chao Wang,et al.  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 , 2020 .

[12]  Lei Ma,et al.  Active learning for object-based image classification using predefined training objects , 2018 .

[13]  Swarnajyoti Patra,et al.  An unsupervised technique for optimal feature selection in attribute profiles for spectral-spatial classification of hyperspectral images , 2018 .

[14]  Mingquan Wu,et al.  Fine crop mapping by combining high spectral and high spatial resolution remote sensing data in complex heterogeneous areas , 2017, Comput. Electron. Agric..

[15]  Ping Zhong,et al.  Active Learning With Gaussian Process Classifier for Hyperspectral Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[16]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .

[17]  Clement Atzberger,et al.  Object Based Image Analysis and Data Mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas , 2012 .

[18]  Yue Han,et al.  A Novel Object-Based Supervised Classification Method with Active Learning and Random Forest for PolSAR Imagery , 2018, Remote. Sens..

[19]  Peerapon Vateekul,et al.  Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields , 2017, Remote. Sens..

[20]  Tengfei Su,et al.  Scale-variable region-merging for high resolution remote sensing image segmentation , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[21]  Hannes Taubenböck,et al.  Estimation of seismic building structural types using multi-sensor remote sensing and machine learning techniques , 2015 .

[22]  B. Wardlow,et al.  A comparison of MODIS 250-m EVI and NDVI data for crop mapping: a case study for southwest Kansas , 2010 .

[23]  Mariana Belgiu,et al.  Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis , 2018 .

[24]  Tengfei Su,et al.  Object-based feature selection using class-pair separability for high-resolution image classification , 2020, International Journal of Remote Sensing.

[25]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[26]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[27]  Dongmei Chen,et al.  Segmentation for Object-Based Image Analysis (OBIA): A review of algorithms and challenges from remote sensing perspective , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[28]  Brian Johnson,et al.  Unsupervised image segmentation evaluation and refinement using a multi-scale approach , 2011 .

[29]  Shengwei Zhang,et al.  Winter Wheat Mapping Using Landsat 8 Images and Geographic Object-Based Image Analysis , 2017 .

[30]  Luisa Verdoliva,et al.  Marker-Controlled Watershed-Based Segmentation of Multiresolution Remote Sensing Images , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Pedro Antonio Gutiérrez,et al.  Object-Based Image Classification of Summer Crops with Machine Learning Methods , 2014, Remote. Sens..

[32]  Lorenzo Bruzzone,et al.  Active and Semisupervised Learning for the Classification of Remote Sensing Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Lin Yan,et al.  Automated crop field extraction from multi-temporal Web Enabled Landsat Data , 2014 .