A comparative study of different classification techniques for marine oil spill identification using RADARSAT-1 imagery

Xu, Linlin; Li, Jonathan; Brenning, Alexander

doi:10.1016/j.rse.2013.10.012

Cited by 143 publications

(88 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RF method was adopted for this study because of its robustness and effectiveness in the classification of varying object types and ease of the execution. Compared to SVM, RF is able to achieve a comparably high classification precision with fewer initialized parameters [25,26]. Random forest only requires two parameters: the number of decision trees (ntree) and the number of random split variable characteristics (mty) [27,28].…”

Section: Coarse Extraction Of Windthrown Treesmentioning

confidence: 99%

A Novel Approach for Coarse-to-Fine Windthrown Tree Extraction Based on Unmanned Aerial Vehicle Images

2017

View full text Add to dashboard Cite

Surveys of windthrown trees, resulting from hurricanes and other types of natural disasters, are an important component of agricultural insurance, forestry statistics, and ecological monitoring. Aerial images are commonly used to determine the total area or number of downed trees, but conventional methods suffer from two primary issues: misclassification of windthrown trees due to the interference from other objects or artifacts, and poor extraction resolution when trunk diameters are small. The objective of this study is to develop a coarse-to-fine extraction technique for individual windthrown trees that reduces the effects of these common flaws. The developed method was tested using UAV imagery collected over rubber plantations on Hainan Island after the Nesat typhoon in China on 19 October 2011. First, a coarse extraction of the affected area was performed by analyzing the image spectrum and textural characteristics. A thinning algorithm was then used to simplify downed trees into skeletal structures. Finally, fine extraction of individual trees was achieved using a line detection algorithm. The completeness of windthrown trees in the study area was 75.7% and the correctness was 92.5%. While similar values have been reported in other studies, they often include constraints, such as tree height. This technique is proposed to be a more feasible extraction algorithm as it is capable of achieving low commission errors across a broad range of tree heights and sizes. As such, it is a viable option for extraction of windthrown trees with a small trunk diameter.

show abstract

Section: Coarse Extraction Of Windthrown Treesmentioning

confidence: 99%

A Novel Approach for Coarse-to-Fine Windthrown Tree Extraction Based on Unmanned Aerial Vehicle Images

2017

View full text Add to dashboard Cite

show abstract

“…AUC is a very popular way of comparing overall classifier performance and one of the most cited techniques in natural hazard researches Woods et al, 1997;Xu et al, 2014). The success and prediction accuracies of seven flood models were assessed qualitatively and presented in The flood susceptibility maps derived from polygon, 1000, 700, 500, 300, 100 and 50 produced the success rates of 60%, 75%, 82%, 81%, 77%, 72% and 62% respectively, and the prediction rates of 63%, 76%, 88%, 80%, 74%, 71% and 65% respectively.…”

Section: Resultsmentioning

confidence: 99%

Evaluating the Variations in the Flood Susceptibility Maps Accuracies Due to the Alterations in the Type and Extent of the Flood Inventory

Tehrany

Jones

2017

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

View full text Add to dashboard Cite

ABSTRACT:This paper explores the influence of the extent and density of the inventory data on the final outcomes. This study aimed to examine the impact of different formats and extents of the flood inventory data on the final susceptibility map. An extreme 2011 Brisbane flood event was used as the case study. LR model was applied using polygon and point formats of the inventory data. Random points of 1000, 700, 500, 300, 100 and 50 were selected and susceptibility mapping was undertaken using each group of random points. To perform the modelling Logistic Regression (LR) method was selected as it is a very well-known algorithm in natural hazard modelling due to its easily understandable, rapid processing time and accurate measurement approach. The resultant maps were assessed visually and statistically using Area under Curve (AUC) method. The prediction rates measured for susceptibility maps produced by polygon, 1000, 700, 500, 300, 100 and 50 random points were 63%, 76%, 88%, 80%, 74%, 71% and 65% respectively. Evidently, using the polygon format of the inventory data didn't lead to the reasonable outcomes. In the case of random points, raising the number of points consequently increased the prediction rates, except for 1000 points. Hence, the minimum and maximum thresholds for the extent of the inventory must be set prior to the analysis. It is concluded that the extent and format of the inventory data are also two of the influential components in the precision of the modelling.

show abstract

“…Bare soil also showed the highest sensitivity value (~0.99) that indicated the high potential of optimized SVM classifier to detect this class. The sensitivityspecificity pair describes the classification accuracy more meaningfully than the single index of percentage correct, and it has been widely implemented with ROC curve analysis in the literature [Alatorre et al, 2011;Xu et al, 2014]. The approach developed in this study, took two important aspects of the definition of PCC in to consideration.…”

Section: Discussionmentioning

confidence: 99%

A robust approach to generate canopy cover maps using UltraCam-D derived orthoimagery classified by support vector machines in Zagros woodlands, West Iran

Erfanifard

Khodaei

Shamsi

2014

European Journal of Remote Sensing

View full text Add to dashboard Cite

An approach was developed to construct a percent canopy cover (PCC) map of Zagros semi-arid woodlands, West Iran, using UltraCam-D airborne imagery. We detected crowns of Persian oak coppice trees on the imagery by use of the support vector machine (SVM) classifier optimized via Taguchi method. Then, PCC was calculated in raster grids with various block sizes and their accuracy metrics revealed the appropriate sizes. Results showed the optimized SVM success in separating Persian oak crowns as revealed in receiver operating characteristic (ROC) curve analysis (area under curve: AUC ~ 0.82). After filtering the raster maps and reassessing their accuracies, validation outputs of the final PCC map with 3000 m 2 resolution yielded an overall accuracy of 90% (KHAT=0.71) and was introduced as the optimal map in this study.

show abstract

A comparative study of different classification techniques for marine oil spill identification using RADARSAT-1 imagery

Cited by 143 publications

References 40 publications

A Novel Approach for Coarse-to-Fine Windthrown Tree Extraction Based on Unmanned Aerial Vehicle Images

A Novel Approach for Coarse-to-Fine Windthrown Tree Extraction Based on Unmanned Aerial Vehicle Images

Evaluating the Variations in the Flood Susceptibility Maps Accuracies Due to the Alterations in the Type and Extent of the Flood Inventory

A robust approach to generate canopy cover maps using UltraCam-D derived orthoimagery classified by support vector machines in Zagros woodlands, West Iran

Contact Info

Product

Resources

About