Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests

Duro, Dennis C.; Franklin, Steven E.; Dubé, Monique G.

doi:10.1080/01431161.2011.649864

Cited by 148 publications

(74 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the performance of a combination of RF approaches with object-based image analysis for crop mapping has garnered much attention [25,41,42]. However, few studies have paid much attention to producing the early seasonal crop type maps for decision-maker management and mapping crop seasonal dynamics based on new "two high resolution" satellite data.…”

Section: Introductionmentioning

confidence: 99%

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Song

Zhou

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Producing accurate crop maps during the current growing season is essential for effective agricultural monitoring. Substantial efforts have been made to study regional crop distribution from year to year, but less attention is paid to the dynamics of composition and spatial extent of crops within a season. Understanding how crops are distributed at the early developing stages allows for the timely adjustment of crop planting structure as well as agricultural decision making and management. To address this knowledge gap, this study presents an approach integrating object-based image analysis with random forest (RF) for mapping in-season crop types based on multi-temporal GaoFen satellite data with a spatial resolution of 16 meters. A multiresolution local variance strategy was used to create crop objects, and then object-based spectral/textural features and vegetation indices were extracted from those objects. The RF classifier was employed to identify different crop types at four crop growth seasons by integrating available features. The crop classification performance of different seasons was assessed by calculating F-score values. Results show that crop maps derived using seasonal features achieved an overall accuracy of more than 87%. Compared to the use of spectral features, a feature combination of in-season textures and multi-temporal spectral and vegetation indices performs best when classifying crop types. Spectral and temporal information is more important than texture features for crop mapping. However, texture can be essential information when there is insufficient spectral and temporal information (e.g., crop identification in the early spring). These results indicate that an object-based image analysis combined with random forest has considerable potential for in-season crop mapping using high spatial resolution imagery.

show abstract

Section: Introductionmentioning

confidence: 99%

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Song

Zhou

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Depending on the selected application, the underlying input imagery, and the environment under analysis, objects of different sizes that depict different land surface features can be produced. OBIA can derive additional geometry and contextual semantic features that are potentially useful for classification studies [49]. Optical images evaluated with OBIA have been increasingly used for landslide inventory mapping, effectively detecting unvegetated landslides [9,22,28,[50][51][52].…”

Section: Introductionmentioning

confidence: 99%

Identification of Forested Landslides Using LiDar Data, Object-based Image Analysis, and Machine Learning Algorithms

et al. 2015

View full text Add to dashboard Cite

For identification of forested landslides, most studies focus on knowledge-based and pixel-based analysis (PBA) of LiDar data, while few studies have examined (semi-) automated methods and object-based image analysis (OBIA). Moreover, most of them are focused on soil-covered areas with gentle hillslopes. In bedrock-covered mountains with steep and rugged terrain, it is so difficult to identify landslides that there is currently no research on whether combining semi-automated methods and OBIA with only LiDar derivatives could be more effective. In this study, a semi-automatic object-based landslide identification approach was developed and implemented in a forested area, the Three Gorges of China. Comparisons of OBIA and PBA, two different machine learning algorithms and their respective sensitivity to feature selection (FS), were first investigated. Based on the classification result, the landslide inventory was finally obtained according to (1) inclusion of holes encircled by the landslide body; (2) removal of isolated segments, and (3) delineation of closed envelope curves for landslide objects by manual digitizing operation. The proposed method achieved the following: (1) the filter features of surface roughness were first applied for calculating object features, and proved useful; (2) FS improved OPEN ACCESSRemote Sens. 2015, 7 9706 classification accuracy and reduced features; (3) the random forest algorithm achieved higher accuracy and was less sensitive to FS than a support vector machine; (4) compared to PBA, OBIA was more sensitive to FS, remarkably reduced computing time, and depicted more contiguous terrain segments; (5) based on the classification result with an overall accuracy of 89.11% ± 0.03%, the obtained inventory map was consistent with the referenced landslide inventory map, with a position mismatch value of 9%. The outlined approach would be helpful for forested landslide identification in steep and rugged terrain.

show abstract

“…ANN, support vector machine). Despite of these reservations, the MLC is still extensively applied in some studies aiming at comparison of various classifiers (Duro et al, 2012). On the contrary, Platt and Rapoza (2008) demonstrated that ML classifier exceeds the accuracy of the k-NN classification in pixel-based comparisons where the feature space (i.e.…”

Section: Maximum Likelihood Classificationmentioning

confidence: 99%

“…The class mean vector and the covariance matrix are the fundamental sources for the function and can be estimated from the training pixels of a specific class (Asmala, 2012). The ML classification has commonly been assumed as unsuited to the classification of data types that can disturb various assumptions of parametric statistical techniques, such as categorical or non-Gaussian distribution of data sets (Duro et al, 2012). The ML algorithm tends to be not as much effective in the overall classification accuracy as modern non-parametric machine learning classifiers (e.g.…”

Section: Maximum Likelihood Classificationmentioning

confidence: 99%

Towards the Optimal Pixel Size of Dem for Automatic Mapping of Landslide Areas

Pawłuszek

Borkowski

Tarolli

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Determining appropriate spatial resolution of digital elevation model (DEM) is a key step for effective landslide analysis based on remote sensing data. Several studies demonstrated that choosing the finest DEM resolution is not always the best solution. Various DEM resolutions can be applicable for diverse landslide applications. Thus, this study aims to assess the influence of special resolution on automatic landslide mapping. Pixel-based approach using parametric and non-parametric classification methods, namely feed forward neural network (FFNN) and maximum likelihood classification (ML), were applied in this study. Additionally, this allowed to determine the impact of used classification method for selection of DEM resolution. Landslide affected areas were mapped based on four DEMs generated at 1m, 2m, 5m and 10m spatial resolution from airborne laser scanning (ALS) data. The performance of the landslide mapping was then evaluated by applying landslide inventory map and computation of confusion matrix. The results of this study suggests that the finest scale of DEM is not always the best fit, however working at 1m DEM resolution on micro-topography scale, can show different results. The best performance was found at 5m DEM-resolution for FFNN and 1m DEM resolution for results. The best performance was found to be using 5m DEM-resolution for FFNN and 1m DEM resolution for ML classification.

show abstract

Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests

Cited by 148 publications

References 79 publications

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest

Identification of Forested Landslides Using LiDar Data, Object-based Image Analysis, and Machine Learning Algorithms

Towards the Optimal Pixel Size of Dem for Automatic Mapping of Landslide Areas

Contact Info

Product

Resources

About