Automated Segmentation and Classification of Aerial Forest Imagery

EasyChair Preprint 9211

Abstract

Monitoring the health and safety of forests has become a rising problem with the advent of global wildfires, rampant logging, and reforestation efforts. This paper proposes a model for automatic segmentation and classification of aerial forest imagery. The model is based on U-net architecture and relies on dice coefficients, binary cross-entropy, and accuracy as loss functions. While other models reached an accuracy of 45%, this model achieved a classification accuracy of 82.51% and a dice coefficient percentage of 79.85%. This paper demonstrates how complex convolutional neural networks can be applied to aerial forest images to help preserve and save the forest environment.

Keyphrases: Aerial Forest Image, Climate awareness, climate change, computer vision, deep learning, image segmentation

@booklet{EasyChair:9211,
  author    = {Kieran Pichai and Benjamin Park and Aaron Bao and Yiqiao Yin},
  title     = {Automated Segmentation and Classification of Aerial Forest Imagery},
  howpublished = {EasyChair Preprint 9211},
  year      = {EasyChair, 2022}}