Optimal Segmentation Scale Parameter, Feature Subset and Classification Algorithm for Geographic Object-Based Crop Recognition Using Multisource Satellite Imagery

Lingbo Yang,Lamin Mansaray,Jingfeng Huang,Limin Wang

doi:10.3390/rs11050514

Abstract

Geographic object-based image analysis (GEOBIA) has been widely used in the remote sensing of agricultural crops. However, issues related to image segmentation, data redundancy and performance of different classification algorithms with GEOBIA have not been properly addressed in previous studies, thereby compromising the accuracy of subsequent thematic products. It is in this regard that the current study investigates the optimal scale parameter (SP) in multi-resolution segmentation, feature subset, and classification algorithm for use in GEOBIA based on multisource satellite imagery. For this purpose, a novel supervised optimal SP selection method was proposed based on information gain ratio, and was then compared with a preexisting unsupervised optimal SP selection method. Additionally, the recursive feature elimination (RFE) and enhanced RFE (EnRFE) algorithms were modified to generate an improved EnRFE (iEnRFE) algorithm, which was then compared with its precursors in the selection of optimal classification features. Based on the above, random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM) were applied to segmented objects for crop classification. The results indicated that the supervised optimal SP selection method is more suitable for application in heterogeneous land cover, whereas the unsupervised method proved more efficient as it does not require reference segmentation objects. The proposed iEnRFE method outperformed the preexisting EnRFE and RFE methods in optimal feature subset selection as it recorded the highest accuracy and less processing time. The RF, GBDT, and SVM algorithms achieved overall classification accuracies of 91.8%, 92.4%, and 90.5%, respectively. GBDT and RF recorded higher classification accuracies and utilized much less computational time than SVM and are, therefore, considered more suitable for crop classification requiring large numbers of image features. These results have shown that the proposed object-based crop classification scheme could provide a valuable reference for relevant applications of GEOBIA in crop recognition using multisource satellite imagery.

Highlights

The acquisition of reliable crop distribution maps is becoming increasingly important for agricultural land management amidst growing food demands in response to an ever-increasing human population globally [1]
CTohnisclpuaspioenr presents a complete object-based crop recognition scheme that includes the selection of the oTphtiismpaalpSePr pofremseunlttis-raecsoomluptiloentesoebgjmecetn-btaatsieodnc, rfeoapturerceosgunbistieotnanscdhcelmasesitfihcaat tiinocnlumdeetshtohde sfoelreuctsieon inoGf EthOeBoIpAt.imal scale parameter (SP) of multi-resolution segmentation, feature subset and classification method for use in GAEcOoBmIApa. rison of two optimal SP selection algorithms, unsupervised and supervised, indicated that theAscuopmerpvairsiesdonmoefthtwodoporpotpimosaeldSiPnstehliescptiaopnearlcgoouriltdhbmest,teurnasduappetrvtoisdediffaenrednstusiptueravtiiosends,tihnadnictahteed that the supervised method proposed in this paper could better adapt to different situations than the unsupervised method
Three feature selection methods including recursive feature elimination (RFE), enhanced RFE (EnRFE) and improved EnRFE (iEnRFE) were evaluated to arrive at the optimal subset

Summary

Introduction

The acquisition of reliable crop distribution maps is becoming increasingly important for agricultural land management amidst growing food demands in response to an ever-increasing human population globally [1]. Geographic object-based image analysis (GEOBIA) is an important approach to the use of multisource satellite imagery in crop classification [5,6]. Despite its advantages over traditional classifiers, the use of GEOBIA is constrained by uncertainties associated with image segmentation [14], feature selection [15,16] and classification algorithms [17,18]. In order to exploit the full potential of GEOBIA in crop recognition with multisource satellite imagery, the optimal combination of segmentation, feature selection and classification algorithms needs to be identified, the current study

Methods

Results

Conclusion