PERPUSTAKAAN BIG

  • Beranda
  • Informasi
  • Berita
  • Bantuan
  • Area Pustakawan
  • Area Anggota
  • Pilih Bahasa :
    Bahasa Arab Bahasa Bengal Bahasa Brazil Portugis Bahasa Inggris Bahasa Spanyol Bahasa Jerman Bahasa Indonesia Bahasa Jepang Bahasa Melayu Bahasa Persia Bahasa Rusia Bahasa Thailand Bahasa Turki Bahasa Urdu
Image of Instance segmentation of standing dead trees in dense forest from aerial imagery using deep learning

Text

Instance segmentation of standing dead trees in dense forest from aerial imagery using deep learning

Abubakar Sani-Mohammed - Nama Orang; Wei Yao - Nama Orang; Marco Heurich - Nama Orang;

Mapping standing dead trees, especially, in natural forests is very important for evaluation of the forest's health status, and its capability for storing Carbon, and the conservation of biodiversity. Apparently, natural forests have larger areas which renders the classical field surveying method very challenging, time-consuming, labor-intensive, and unsustainable. Thus, for effective forest management, there is the need for an automated approach that would be cost-effective. With the advent of Machine Learning, Deep Learning has proven to successfully achieve excellent results. This study presents an adjusted Mask R-CNN Deep Learning approach for detecting and segmenting standing dead trees in a mixed dense forest from CIR aerial imagery using a limited (195 images) training dataset. First, transfer learning is considered coupled with the image augmentation technique to leverage the limitation of training datasets. Then, we strategically selected hyperparameters to suit appropriately our model's architecture that fits well with our type of data (dead trees in images). Finally, to assess the generalization capability of our model's performance, a test dataset that was not confronted to the deep neural network was used for comprehensive evaluation. Our model recorded promising results reaching a mean average precision, average recall, and average F1-Score of 0.85, 0.88, and 0.87 respectively, despite our relatively low resolution (20 cm) dataset. Consequently, our model could be used for automation in standing dead tree detection and segmentation for enhanced forest management. This is equally significant for biodiversity conservation, and forest Carbon storage estimation.


Ketersediaan
22621.3678Perpustakaan BIG (Eksternal Harddisk)Tersedia
Informasi Detail
Judul Seri
ISPRS Open Journal of Photogrammetry and Remote Sensing
No. Panggil
-
Penerbit
Amsterdam : Elsevier., 2022
Deskripsi Fisik
14 hlm PDF, 17.476 KB
Bahasa
Inggris
ISBN/ISSN
1872-8235
Klasifikasi
NONE
Tipe Isi
text
Tipe Media
-
Tipe Pembawa
-
Edisi
Vol.6, December 2022
Subjek
Carbon storage
CIR Aerial imagery
Forest management
Instance segmentation
Mask R-CNN
Standing dead tree
Info Detail Spesifik
-
Pernyataan Tanggungjawab
-
Versi lain/terkait

Tidak tersedia versi lain

Lampiran Berkas
  • Instance segmentation of standing dead trees in dense forest from aerial imagery using deep learning
    Mapping standing dead trees, especially, in natural forests is very important for evaluation of the forest's health status, and its capability for storing Carbon, and the conservation of biodiversity. Apparently, natural forests have larger areas which renders the classical field surveying method very challenging, time-consuming, labor-intensive, and unsustainable. Thus, for effective forest management, there is the need for an automated approach that would be cost-effective. With the advent of Machine Learning, Deep Learning has proven to successfully achieve excellent results. This study presents an adjusted Mask R-CNN Deep Learning approach for detecting and segmenting standing dead trees in a mixed dense forest from CIR aerial imagery using a limited (195 images) training dataset. First, transfer learning is considered coupled with the image augmentation technique to leverage the limitation of training datasets. Then, we strategically selected hyperparameters to suit appropriately our model's architecture that fits well with our type of data (dead trees in images). Finally, to assess the generalization capability of our model's performance, a test dataset that was not confronted to the deep neural network was used for comprehensive evaluation. Our model recorded promising results reaching a mean average precision, average recall, and average F1-Score of 0.85, 0.88, and 0.87 respectively, despite our relatively low resolution (20 cm) dataset. Consequently, our model could be used for automation in standing dead tree detection and segmentation for enhanced forest management. This is equally significant for biodiversity conservation, and forest Carbon storage estimation.
Komentar

Anda harus masuk sebelum memberikan komentar

PERPUSTAKAAN BIG
  • Informasi
  • Layanan
  • Pustakawan
  • Area Anggota

Tentang Kami

Perpustakaan Badan Informasi Geospasial (BIG) adalah sebuah perpustakaan yang berada di bawah Badan Informasi Geospasial Indonesia. Perpustakaan ini memiliki koleksi yang berkaitan dengan informasi geospasial, termasuk peta, data geospasial, dan literatur terkait. Selengkapnya

Cari

masukkan satu atau lebih kata kunci dari judul, pengarang, atau subjek

Donasi untuk SLiMS Kontribusi untuk SLiMS?

© 2025 — Senayan Developer Community

Ditenagai oleh SLiMS
Pilih subjek yang menarik bagi Anda
  • Batas Wilayah
  • Ekologi
  • Fotogrametri
  • Geografi
  • Geologi
  • GIS
  • Ilmu Tanah
  • Kartografi
  • Manajemen Bencana
  • Oceanografi
  • Penginderaan Jauh
  • Peta
Icons made by Freepik from www.flaticon.com
Pencarian Spesifik