Automatically drawing vegetation classification maps using digital time‐lapse cameras in alpine ecosystems

• Published in: Remote sensing in ecology and conservation Vol. 10; no. 2; pp. 188 - 202
• Main Authors: Okamoto, Ryotaro, Ide, Reiko, Oguma, Hiroyuki
• Format: Journal Article
• Language: English
• Published: Oxford John Wiley & Sons, Inc 01.04.2024; Wiley
• Subjects: Accuracy; Airborne sensing; Alpine ecosystem; Alpine environments; Alpine regions; Automation; Cameras; Classification; Climate change; Conservation; deep learning; Digital cameras; Digital mapping; Distribution patterns; ecosystem monitoring; Ecosystems; Flowers & plants; Geographic information systems; ground‐based imagery; Image acquisition; Methods; Monitoring; Native species; Neural networks; Nonnative species; Phenology; Recurrent neural networks; Remote sensing; Satellite observation; Snow; Snowmelt; Spatial data; time‐lapse camera; Unmanned aerial vehicles; Vegetation; vegetation mapping; Alps; Japan
• ISSN: 2056-3485; 2056-3485
• DOI: 10.1002/rse2.364

Alpine ecosystems are particularly vulnerable to climate change. Monitoring the distribution of alpine vegetation is required to plan practical conservation activities. However, conventional field observations, airborne and satellite remote sensing are difficult in terms of coverage, cost and resolution in alpine areas. Ground‐based time‐lapse cameras have been used to observe the regions' snowmelt and vegetation phenology and offer significant advantages in terms of cost, resolution and frequency. However, they have not been used in research monitoring of vegetation distribution patterns. This study proposes a novel method for drawing georeferenced vegetation classification maps from ground‐based imagery of alpine regions. Our approach had two components: vegetation classification and georectification. The proposed vegetation classification method uses a pixel time series acquired from fall images, utilizing the fall leaf color patterns. We demonstrated that the performance of the vegetation classification could be improved using time‐lapse imagery and a Recurrent Neural Network. We also developed a novel method to accurately transform ground‐based images into georeferenced data. We propose the following approaches: (1) an automated procedure to acquire Ground Control Points and (2) a camera model that considers lens distortions for accurate georectification. We demonstrated that the proposed approach outperforms conventional methods, in addition to achieving sufficient accuracy to observe the vegetation distribution on a plant‐community scale. The evaluation revealed an F1 score and root‐mean‐square error of 0.937 and 3.4 m in the vegetation classification and georectification, respectively. Our results highlight the potential of inexpensive time‐lapse cameras to monitor the distribution of alpine vegetation. The proposed method can significantly contribute to the effective conservation planning of alpine ecosystems. This study aimed to develop a novel method to draw georeferenced vegetation classification maps from ground‐based imagery of alpine regions. Using time‐lapse imagery and a recurrent neural network, we reliably classified the vegetation in our study area in the Japanese Alps. We also showed that our novel approach to georectification outperformed conventional methods.