Rights statement: This is an Accepted Manuscript of an article published by Taylor & Francis in Geocarto International on 27/12/2020, available online: https://www.tandfonline.com/doi/full/10.1080/10106049.2020.1852610
Accepted author manuscript, 255 KB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Estimating feature extraction changes of Berkelah Forest, Malaysia from multisensor remote sensing data using an object-based technique
AU - Rozali, Syaza
AU - Abd Latif, Zulkiflee
AU - Adnan, Nor Aizam
AU - Hussin, Yousif
AU - Blackburn, Alan
AU - Pradhan, Biswajeet
PY - 2020/12/27
Y1 - 2020/12/27
N2 - 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 (SpectralLandsat; and SpectralLandsat + HeightALS).
AB - 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 (SpectralLandsat; and SpectralLandsat + HeightALS).
KW - Object-based segmentation
KW - airborne LiDAR
KW - remote sensing
KW - Random Forest
KW - support vector machine
U2 - 10.1080/10106049.2020.1852610
DO - 10.1080/10106049.2020.1852610
M3 - Journal article
JO - Geocarto International
JF - Geocarto International
SN - 1010-6049
ER -