Saved in:
Bibliographic Details
Main Authors: Haque, Maisha, Ayshi, Israt Jahan, Anis, Sadaf M., Tasnim, Nahian, Moontaha, Mithila, Ahmed, Md. Sabbir, Hossain, Muhammad Iqbal, Parvez, Mohammad Zavid, Chakraborty, Subrata, Pradhan, Biswajeet, Banik, Biswajit
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.23196
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914358225797120
author Haque, Maisha
Ayshi, Israt Jahan
Anis, Sadaf M.
Tasnim, Nahian
Moontaha, Mithila
Ahmed, Md. Sabbir
Hossain, Muhammad Iqbal
Parvez, Mohammad Zavid
Chakraborty, Subrata
Pradhan, Biswajeet
Banik, Biswajit
author_facet Haque, Maisha
Ayshi, Israt Jahan
Anis, Sadaf M.
Tasnim, Nahian
Moontaha, Mithila
Ahmed, Md. Sabbir
Hossain, Muhammad Iqbal
Parvez, Mohammad Zavid
Chakraborty, Subrata
Pradhan, Biswajeet
Banik, Biswajit
contents This research proposes "ForCM", a novel approach to forest cover mapping that combines Object-Based Image Analysis (OBIA) with Deep Learning (DL) using multispectral Sentinel-2 imagery. The study explores several DL models, including UNet, UNet++, ResUNet, AttentionUNet, and ResNet50-Segnet, applied to high-resolution Sentinel-2 Level 2A satellite images of the Amazon Rainforest. The datasets comprise three collections: two sets of three-band imagery and one set of four-band imagery. After evaluation, the most effective DL models are individually integrated with the OBIA technique to enhance mapping accuracy. The originality of this work lies in evaluating different deep learning models combined with OBIA and comparing them with traditional OBIA methods. The results show that the proposed ForCM method improves forest cover mapping, achieving overall accuracies of 94.54 percent with ResUNet-OBIA and 95.64 percent with AttentionUNet-OBIA, compared to 92.91 percent using traditional OBIA. This research also demonstrates the potential of free and user-friendly tools such as QGIS for accurate mapping within their limitations, supporting global environmental monitoring and conservation efforts.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23196
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ForCM: Forest Cover Mapping from Multispectral Sentinel-2 Image by Integrating Deep Learning with Object-Based Image Analysis
Haque, Maisha
Ayshi, Israt Jahan
Anis, Sadaf M.
Tasnim, Nahian
Moontaha, Mithila
Ahmed, Md. Sabbir
Hossain, Muhammad Iqbal
Parvez, Mohammad Zavid
Chakraborty, Subrata
Pradhan, Biswajeet
Banik, Biswajit
Computer Vision and Pattern Recognition
Artificial Intelligence
This research proposes "ForCM", a novel approach to forest cover mapping that combines Object-Based Image Analysis (OBIA) with Deep Learning (DL) using multispectral Sentinel-2 imagery. The study explores several DL models, including UNet, UNet++, ResUNet, AttentionUNet, and ResNet50-Segnet, applied to high-resolution Sentinel-2 Level 2A satellite images of the Amazon Rainforest. The datasets comprise three collections: two sets of three-band imagery and one set of four-band imagery. After evaluation, the most effective DL models are individually integrated with the OBIA technique to enhance mapping accuracy. The originality of this work lies in evaluating different deep learning models combined with OBIA and comparing them with traditional OBIA methods. The results show that the proposed ForCM method improves forest cover mapping, achieving overall accuracies of 94.54 percent with ResUNet-OBIA and 95.64 percent with AttentionUNet-OBIA, compared to 92.91 percent using traditional OBIA. This research also demonstrates the potential of free and user-friendly tools such as QGIS for accurate mapping within their limitations, supporting global environmental monitoring and conservation efforts.
title ForCM: Forest Cover Mapping from Multispectral Sentinel-2 Image by Integrating Deep Learning with Object-Based Image Analysis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.23196