Assessment of pleiades satellite image for mangrove forest classification / Sharul Nizam Rosli
Recent developments in high resolution remote sensing have created a wide array of potential new mangrove applications. In this study the concept of Pleiades is applied to mapping and exposes the current system developments and spatial industry needs to delineate individual tree canopy. By exploring...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | http://ir.uitm.edu.my/id/eprint/31247/1/TD_SHARUL%20NIZAM%20ROSLI%20AP%20R%2019_5.pdf http://ir.uitm.edu.my/id/eprint/31247/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Recent developments in high resolution remote sensing have created a wide array of potential new mangrove applications. In this study the concept of Pleiades is applied to mapping and exposes the current system developments and spatial industry needs to delineate individual tree canopy. By exploring developments in a Pleiades technology and investigating the use of the technology in mapping, a lot of advantages for spatial industry have been explored. Along advancements in technology, there were various methods have been developed to delineate individual tree canopy. The Pleiades image which is 0.63 m resolution was used. The study area was covered in mangrove are at Bagan Datuk, Perak. The major research strategy used in this project, are detecting, classify, and analyze the classification on mangrove family. Segmentation and classification approach were developed for this delineation canopy in the study area. Method that being used are Support Vector Machine (SVM) and K-Nearest Neighborhood (K-NN) that being apply in Object Based Image Analysis (OBIA). The information was used to identify individual tree canopies and delineated their boundaries. The results of segmentation and classification were used to know which classifier have the highest accuracy assessment in the study area that correspond with the result images obtained. This research show that SVM has the highest accuracy with 63.8156% overall accuracy and 0.5513 kappa coefficient better than K-NN that has 59.8303% overall accuracy and 0.5018 kappa coefficient. |
|---|