Estimating feature extraction changes of Berkelah Forest, Malaysia from multisensor remote sensing data using and object-based technique

Abstract

The study involves an object-based segmentation method to extract feature changes in tropical rainforest cover using Landsat image and airborne LiDAR (ALS). Disturbance event that are represents the changes are examined by the classification of multisensor data; that is a highly accurate ALS with different resolutions of multispectral Landsat image. Disturbance Index (DI) derived from Tasseled Cap Transformation, Normalized Difference Vegetation Index (NDVI), and the ALS height are the variables for object-based segmentation process. The classification is categorized into two classes; disturbed and non-disturbed forest cover using Nearest Neighbor (NN), Random Forest (RF) and Support Vector Machine (SVM). The overall accuracy ranging from 88% to 96% and kappa ranging from 0.79 to 0.91. Mcnemar’s test p-value (<0.05) is applied to check the classification for each method used which is RF 0.03 and SVM 0.01. The accuracy increases when the integration of ALS in Landsat image (Spectral_Landsat; and Spectral_Landsat + Height_ALS).

Keywords:

• Object-based segmentation
• airborne LiDAR
• remote sensing
• Random Forest
• support vector machine

Acknowledgements

The authors would like to express their gratitude to the Ministry of Higher Education Malaysia for MyBrain15 and Fundamental Research Grant Scheme (FRGS) number 600-IRMI/FRGS 5/3 (319/2019) as the financial support for this research; Airborne Research & Survey Facility, UK (ARSF UK) for providing the Airborne LiDAR data and the United States Geological Survey (USGS) for providing satellite imagery.

Disclosure statement

No potential conflict of interest was reported by the authors.