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

By Dennis C. Duro, S. Franklin, M. Dubé. 2012

960 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/9c5ea99fac551d997169c944218d65d027d0fa94

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Global and Planetary Change

Citations in the corpus

Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery (2017, background): “Several studies have stated that the satisfactory results could be achieved with the default parameters [12,48–50].”
A Survey on Object Detection in Optical Remote Sensing Images (2016, neutral): “…al., 2015; D'Oleire-Oltmanns et al., 2014; De Pinho et al., 2012; Doleire-Oltmanns et al., 2013; Drăguţ and Blaschke, 2006; Drăguţ and Eisank, 2012; Duro et al., 2012; Eisank et al., 2011; Goodin et al., 2015; Hay et al., 2003; Hofmann et al., 2011; Kim et al., 2011; Leon and Woodroffe, 2011; Li…”
Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, neutral): “incorporated into the classification scheme [28], [49]–[51].”
Automated cropland mapping of continental Africa using Google Earth Engine cloud computing (2017, methodology): “…et al., 2015), spectral matching techniques (Dheeravath et al., 2010), support vector machines (Mountrakis et al., 2011), random forest algorithm (Tatsumi et al., 2015) and a number of other machine learning algorithms (DeFries, 2000; Duro et al., 2012; Lary et al., 2016; Pantazi et al., 2016).”
Land-cover classification with high-resolution remote sensing images using transferable deep models (2018, methodology): “It has been reported that spectral-spatial approaches can effectively boost the categorization accuracy compared with the methods using spectral features (Blaschke, 2010; Yan et al., 2006; Myint et al., 2011; Duro et al., 2012).”
Implementation of machine-learning classification in remote sensing: an applied review (2018, methodology): “Generally, RF has been shown to be robust to complex feature spaces (Guyon and Elissee ﬀ 2003; Lawrence, Wood, and Sheley 2006; Duro, Franklin, and Dubé 2012b).”
Automation in Agriculture by Machine and Deep Learning Techniques: A Review of Recent Developments (2021, methodology): “For example, the classification among agricultural lands was performed and compared by implementing DT, RF, and SVM and it was concluded that object-based SVM got the highest Overall accuracy (Duro et al., 2012).”
Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers (2014, methodology): “This is a common problem when classifying heterogeneous landscapes using high spatial resolution based on per-pixel classification techniques (Lu and Weng 2007; Duro, Franklin, and Dubé 2012).”
How do you find the green sheep? A critical review of the use of remotely sensed imagery to detect and count animals (2018, background): “The time taken to set up and implement OBIA may impede their widespread implementation, mainly as a result of software limitations (Duro et al., 2012); running OBIA algorithms in eCognition, e.”
Assessment of an Operational System for Crop Type Map Production Using High Temporal and Spatial Resolution Satellite Optical Imagery (2015, background): “[37] showed that even for SPOT5 HRG imagery (10 m), there is no statistically-significant advantage to the use of object-based image analysis for agricultural landscapes”
A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform (2018, positive): “…Zhou et al., 2016); (g) the Automated Cropland Classi ﬁ cation Algorithms (Thenkabail and Wu, 2012; Teluguntla et al., 2017a; Waldner et al., 2015); and (h) Machine learning programming involving a combination of multiple methods (DeFries and Chan, 2000; Duro et al., 2012; Pantazi et al., 2016).”