Elsevier

Remote Sensing of Environment

Volume 118, 15 March 2012, Pages 259-272
Remote Sensing of Environment

A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery

https://doi.org/10.1016/j.rse.2011.11.020Get rights and content

Abstract

Pixel-based and object-based image analysis approaches for classifying broad land cover classes over agricultural landscapes are compared using three supervised machine learning algorithms: decision tree (DT), random forest (RF), and the support vector machine (SVM). Overall classification accuracies between pixel-based and object-based classifications were not statistically significant (p > 0.05) when the same machine learning algorithms were applied. Using object-based image analysis, there was a statistically significant difference in classification accuracy between maps produced using the DT algorithm compared to maps produced using either RF (p = 0.0116) or SVM algorithms (p = 0.0067). Using pixel-based image analysis, there was no statistically significant difference (p > 0.05) between results produced using different classification algorithms. Classifications based on RF and SVM algorithms provided a more visually adequate depiction of wetland, riparian, and crop land cover types when compared to DT based classifications, using either object-based or pixel-based image analysis. In this study, pixel-based classifications utilized fewer variables (15 vs. 300), achieved similar classification accuracies, and required less time to produce than object-based classifications. Object-based classifications produced a visually appealing generalized appearance of land cover classes. Based exclusively on overall accuracy reports, there was no advantage to preferring one image analysis approach over another for the purposes of mapping broad land cover types in agricultural environments using medium spatial resolution earth observation imagery.

Highlights

► Pixel-based (PB) and object-based (OB) classifications are compared. ► Three machine learning algorithms (MLAs) are examined. ► No statistical difference between PB and OB classifications was found. ► For OB classifications, significant differences between MLAs were found.

Introduction

The classification of land use and land cover (LULC) from remotely sensed imagery can be divided into two general image analysis approaches: i) classifications based on pixels, and ii) classifications based on objects. While pixel-based analysis has long been the mainstay approach for classifying remotely sensed imagery, object-based image analysis has become increasingly commonplace over the last decade (Blaschke, 2010). Whether pixels or objects are used as underlying units for the purposes of classifying remotely derived imagery, the information contained within - and among - these units (e.g., spectral, textural, etc.) can be subjected to a variety of classification algorithms. Previous comparative studies have been conducted that examine the relative performance of different classification algorithms using pixel-based, and/or object-based image analysis. A brief summary of selected comparisons is provided below.

Using pixel-based based image analysis on Landsat Thematic Mapper (TM) data, Huang et al. (2002) compared thematic mapping accuracies produced using four different classification algorithms: support vector machines (SVMs), decision trees (DTs), a neural network classifier, and the maximum likelihood classifier (MLC). Their results suggested that the accuracy of SVM-based classifications generally outperformed the other three classification algorithms. Pal (2005) compared the accuracies of two supervised classification algorithms using Landsat Enhanced Thematic Mapper (ETM +) data: SVMs and Random Forests (RFs) (Breiman, 2001), and found that they performed equally well. Gislason et al. (2006) compared a RF approach to a variety of decision tree-like algorithms using pixel-based image analysis of Landsat MSS data. They found that the selected tree-like algorithms tested performed similarly, but that the RF algorithm outperformed the standard implementation of Breiman et al.'s (1984) DTs; however, their findings also showed that the RF algorithm performed slightly less well than a modified DT algorithm (boosted 1R). Carreiras et al. (2006) examined several classification algorithms, which included standard DTs, quadratic discriminant analysis, probability-bagging classification trees (PBCT), and k-nearest neighbors (K-NN) using pixel-based analysis of spatially coarse (1 km pixels) SPOT-4 VEGETATION imagery. Their results, verified by 10-fold cross-validation, showed that the PBCT algorithm produced the best overall classification accuracy. Brenning (2009) compared eleven classification algorithms using a pixel-based image analysis, and Landsat ETM + imagery, for the detection of rock glaciers. This extensive study found that penalized linear discriminant analysis (PLDA) yielded significantly better mapping results as compared to all other classifiers, including both SVMs and RFs. Using Landsat TM and ETM + data, Otukei and Blaschke (2010) compared the MLC, SVM, and DT algorithms in a pixel-based approach, and found DTs performed better than MLC and SVM. In an earlier study, Laliberte et al. (2006) used an object-based approach on Quickbird imagery to compare K-NN with DT algorithms. Their study found that DTs produced better overall classification accuracies than the K-NN algorithm, but that the former was more difficult to implement as compared to the latter.

Relatively recent comparisons between the results of pixel-based and object-based image analysis have also been conducted. For example, Yan et al. (2006) compared pixel-based image analysis using MLC and object-based image analysis using K-NN on Terra Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) imagery. In their study, the authors claimed that the overall accuracy of the object-based K-NN classification drastically outperformed the pixel-based MLC classification (83.25% and 46.48%, respectively). Yu et al. (2006) used high spatial resolution digital airborne imagery and compared a pixel-based classification based on MLC with an object-based classification using K-NN, using a DT as a mechanism for feature selection in both cases. Their study showed that the 1-NN object-based classification outperformed the pixel-based MLC classification by 17%, although calculation of the average classification accuracy of each of the 48 vegetation classes listed was only 51% for the object-based K-NN classification, and 61.8% for the pixel-based classification using MLC. Platt and Rapoza (2008) compared K-NN and MLC for both pixel-based and object-based classifications, with and without the addition of expert-based knowledge, using multispectral IKONOS imagery. Their results revealed that the object-based NN classification using expert knowledge had the best overall classification (78%), while the best pixel-based classification using MLC (without expert knowledge) achieved an overall accuracy of 64%. Castillejo-González et al. (2009) compared pixel-based and object-based classifications in agricultural environments using multispectral Quickbird imagery and a variety of classification algorithms. The best pixel-based classification used non-pan-sharpened imagery and the MLC algorithm, while the best purely object-based classification used pan-sharpened imagery and MLC, with both approaches achieving high overall accuracies of 89.6% and 93.69%, respectively. Their study also revealed that the two best results, using non-pan-sharpened imagery and MLC, showed a small difference in classification accuracy between pixel-based and object-based image analysis (89.60% and 90.66%, respectively); however, the difference between these same approaches grew considerably when using pan-sharpened imagery (82.55% and 93.69%, respectively). Myint et al. (2011) used Quickbird imagery to classify urban land cover. They compared results from a MLC pixel-based classification with an object-based classifier using K-NN and a series of fuzzy membership functions. The object-based classification (90.4%) outperformed the pixel-based classification (67.6%) in overall accuracy for their original image; however, in their test image, the differences between the object-based and pixel-based approaches was reduced to less than 10% (95.2 and 87.8%, respectively). Finally, in a recent study, Dingle Robertson and King (2011) compared pixel-based and object-based image analysis for classifying broad agricultural land cover types for two time periods (1995 and 2005) using Landsat-5 TM imagery. They compared land cover maps produced using MLC (pixel-based) and K-NN (object-based) algorithms and found that the difference in overall accuracy between these classification approaches was not statistically significant. Despite these findings, an intensive visual analysis of their post-classification analysis revealed that the object-based classification using K-NN depicted areas of change more accurately than the pixel-based classification using MLC.

In general, the above comparisons between pixel-based and object-based classifications reveal that the latter typically outperform the former when comparing overall classification accuracy using a variety of remotely sensed imagery in settings ranging from agricultural to urban land cover classes. However, unlike the studies examining either pixel-based or object-based classifications in isolation, many comparison studies often rely on relatively simple classification algorithms (e.g., K-NN) for the object-based classification, and probabilistic based algorithms (e.g., MLC) for the pixel-based classification, the latter of which is less suited to datasets that are non-normally distributed, or that contain categorical data (Franklin & Wulder, 2002). The present study aims to bridge the gap between these previous comparisons by examining both pixel-based and object-based classification approaches, with a selection of relatively modern and robust supervised machine learning algorithms: decision trees (DTs), random forests (RFs), and support vector machines (SVMs). We conduct a visual and statistical assessment of the classification outputs using medium spatial resolution (10 m) multi-spectral imagery from the SPOT-5 HRG sensor. For the purposes of this study, six broad land cover classes were mapped in a riparian area undergoing intensive agricultural development in western Canada. We assessed each image analysis approach, and each of the selected machine learning algorithms, for their ability to accurately portray these selected land cover types. Recommendations are made in the context of operational mapping of agricultural landscapes for the purposes of general land cover mapping and monitoring in agricultural environments using medium spatial resolution earth observation imagery.

Section snippets

Study area

The study area is located along the South Saskatchewan River approximately 90 km east of the provincial borders of Alberta and Saskatchewan (Fig. 1). Approximately 80 sq. km, the study area is a subset of a much larger drainage basin selected for a long-term study of land cover change and land use practices typical of the southern half of the western Prairie Provinces of Canada. Similar large drainage areas have been previously selected by others to assess potential impacts caused by development

Ancillary datasets

Several tiles of the Canadian Digital Elevation Data (CDED) digital elevation model (DEM) were downloaded from the GeoBase online spatial data portal (www.geobase.ca). At latitudes of less than 68° N, the CDED DEM has a horizontal post spacing of approximately 23 m (North–south) × 16–11 m (East–west). After projection into Albers Equal Area Conic and nearest-neighbor resampling, the CDED DEM was converted to square 16 × 16 m pixels. An Albers-Equal Area Conic was selected as the final projection for

Tuning of machine learning algorithm parameters

For DT-based classifications, values ranging from 1 to 8 were examined for the “maximum depth” tuning parameter. Based on the highest overall classification accuracy (i.e., the percentage of correctly classified samples) achieved by pixel-based and object-based models (85.4% and 83.3%, respectively) a maximum depth value of 8 was selected for both pixel-based and object-based classifications models. Several values for the mtry tuning parameter (2–4, 6–8, 10–12, 14) were examined for the

Discussion

In general, classifications produced using either pixel-based or object-based image analysis created similar and visually acceptable depictions of the broad land cover classes present within the study area. As expected, compared to the pixel-based classifications, the object-based classifications offered a more generalized visual appearance and more contiguous depiction of land cover, which perhaps better represents how land cover interpreters and analysts actually perceive the landscape (

Conclusions

Classification of EO imagery using pixel-based and object-based image analysis was performed using three machine learning algorithms. No statistical difference between object-based and pixel-based classifications was found when the same machine learning algorithms were compared. When conducting object-based image analysis, RF or SVM algorithms produced classification accuracies that were statistically different compared to DT based algorithms. No statistical significant between pixel-based

Funding

This research was supported by the Government of Saskatchewan's Go Green Fund awarded to Dr. Monique Dubé, and by Dr. Steven Franklin's Natural Science and Engineering Research Council of Canada Discovery Grant.

Acknowledgments

The authors gratefully acknowledge the assistance of Gyanesh Chander (SGT Inc.) for calculating the Thuillier solar spectrum calculations for SPOT-5 HRG-1 and HRG-2 sensors; Claire Tinel (CNES, France) for advice concerning the derivation of radiometric calibration coefficients for the SPOT-5 HRG sensors; researchers at Agriculture and Agri-Food Canada (AAFC), the Saskatchewan Ministry of the Environment (MoE), and the Saskatchewan Research Council (Flysask.ca) for providing various data sets

References (80)

  • L.K.A. Dorren et al.

    Improved Landsat-based forest mapping in steep mountainous terrain using object-based classification

    Forest Ecology and Management

    (2003)
  • M.G. Dubé

    Cumulative effect assessment in Canada: a regional framework for aquatic ecosystems

    Environmental Impact Assessment Review

    (2003)
  • M.A. Friedl et al.

    Decision tree classification of land cover from remotely sensed data

    Remote Sensing of Environment

    (1997)
  • P.O. Gislason et al.

    Random Forests for land cover classification

    Pattern Recognition Letters

    (2006)
  • L.J. Gordon et al.

    Agricultural modifications of hydrological flows create ecological surprises

    Trends in Ecology & Evolution

    (2008)
  • D.P. McKenzie et al.

    Comparing correlated kappas by resampling: Is one level of agreement significantly different from another?

    Journal of Psychiatric Research

    (1996)
  • S.W. Myint et al.

    Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery

    Remote Sensing of Environment

    (2011)
  • J.R. Otukei et al.

    Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms

    International Journal of Applied Earth Observation and Geoinformation

    (2010)
  • R.V. Platt et al.

    An evaluation of an object-oriented paradigm for land use/land cover classification

    The Professional Geographer

    (2008)
  • N.E. Seitz et al.

    Bringing science into river systems cumulative effects assessment practice

    Environmental Impact Assessment Review

    (2011)
  • C. Song et al.

    Classification and Change detection using Landsat TM data: When and how to correct atmospheric effects?

    Remote Sensing of Environment

    (2001)
  • S.V. Stehman

    Selecting and interpreting measures of thematic classification accuracy

    Remote Sensing of Environment

    (1997)
  • J. Stuckens et al.

    Integrating contextual information with per-pixel classification for improved land cover classification

    Remote Sensing of Environment

    (2000)
  • F.M.B. Van Coillie et al.

    Feature selection by genetic algorithms in object-based classification of IKONOS imagery for forest mapping in Flanders, Belgium

    Remote Sensing of Environment

    (2007)
  • T.G. Whiteside et al.

    Comparing object-based and pixel-based classifications for mapping savannas

    International Journal of Applied Earth Observation and Geoinformation

    (2011)
  • A. Agresti

    Categorical data analysis

    (2002)
  • E. Alpaydin

    Introduction to machine learning

    (2004)
  • M. Baatz et al.

    Multiresolution segmentation—an optimization approach for high quality multi-scale image segmentation

  • B. Bhanu et al.

    Adaptive image segmentation using a genetic algorithm

    IEEE Transactions on Systems, Man, and Cybernetics

    (1995)
  • L. Breiman

    Random Forests

    Machine Learning

    (2001)
  • L. Breiman et al.

    Random forests — Classification description

    (2007)
  • L. Breiman et al.

    Classification and regression trees, Belmont, California, U.S.A

    (1984)
  • A. Brenning

    Land cover classification by multisource remote sensing: Comparing classifiers for spatial data

  • C. Burges

    A tutorial on Support Vector Machines for Pattern Recognition

    Data Mining and Knowledge Discovery

    (1998)
  • G. Castilla et al.

    Image objects and geographic objects

  • CNES

    SPOT image quality performances

  • J. Cohen

    A coefficient of agreement for nominal scales

    Educational and psychological measurement

    (1960)
  • R.G. Congalton et al.

    Assessing the accuracy of remotely sensed data: Principles and practices

    (1998)
  • C. Cortes et al.

    Support-vector networks

    Machine Learning

    (1995)
  • G.A.O.P. Costa et al.

    Genetic adaptation of segmentation parameters

  • Cited by (783)

    View all citing articles on Scopus
    View full text