Mapping Countrywide Historical Tree Cover Using Semantic Segmentation

2025/01/01 by Yuanyuan Gui, Wei Li, Xiang-Gen Xia +4 · 1 citation
Computer Science · Earth and Planetary Sciences · Environmental Science · #Archaeological Research and Protection #Image Processing and 3D Reconstruction #Remote Sensing and LiDAR Applications

paper · doi:10.1109/tgrs.2025.3532248

openalex publication_date 2025/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/06

Abstract

Accurate and comprehensive tree cover mapping plays a vital role in forest management and ecosystem assessment. However, the lack of spectral information and the low quality of available black and white (B&W) imagery makes it difficult to retroactively predict an historical tree cover map using common methods. Here, a network structure called B&WTreeNet, based on semantic segmentation, is proposed to make full use of the limited labeled training remote sensing data to obtain tree cover information from historical datasets. The proposed B&WTreeNet is capable of cross-temporal semantic segmentation, including various data augmentation methods, to address inconsistent tree cover features caused by variations in image quality. The luminance enhancer (LE) and other modules in B&WTreeNet can extract the characteristics of tree cover effectively, successfully compensating for the limited spectral information in B&W image datasets. The countrywide historical tree cover map in Switzerland generated for the 1980s using a limited training dataset from 2018 to 2019 agrees well with manual interpretation results.

Citations

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Albumentations: fast and flexible image augmentations
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems

Cited by

• Multi-modal Uncertainty Robust Tree Cover Segmentation For High-Resolution Remote Sensing Images

Related

• OAM-TCD: A globally diverse dataset of high-resolution tree cover maps
• Texture based Prototypical Network for Few-Shot Semantic Segmentation of Forest Cover: Generalizing for Different Geographical Regions
• Tree semantic segmentation from aerial image time series
• Tree semantic segmentation from aerial image time series
• TreeSatAI Benchmark Archive: a multi-sensor, multi-label dataset for tree species classification in remote sensing