Automatic Plant Cover Estimation with Convolutional Neural Networks

TL;DR

This paper explores using convolutional neural networks to automatically estimate plant cover from images, aiming to improve accuracy and temporal resolution over manual, subjective methods in plant biodiversity research.

Contribution

It introduces a CNN-based approach with custom architectures and pretraining strategies that outperform previous methods in plant cover estimation from images.

Findings

Achieved a mean absolute error of 5.16% with the CNN model.

Found that higher image resolutions improve estimation accuracy.

Identified occlusion and temporal changes as key challenges.

Abstract

Monitoring the responses of plants to environmental changes is essential for plant biodiversity research. This, however, is currently still being done manually by botanists in the field. This work is very laborious, and the data obtained is, though following a standardized method to estimate plant coverage, usually subjective and has a coarse temporal resolution. To remedy these caveats, we investigate approaches using convolutional neural networks (CNNs) to automatically extract the relevant data from images, focusing on plant community composition and species coverages of 9 herbaceous plant species. To this end, we investigate several standard CNN architectures and different pretraining methods. We find that we outperform our previous approach at higher image resolutions using a custom CNN with a mean absolute error of 5.16%. In addition to these investigations, we also conduct an error analysis based on the temporal aspect of the plant cover images. This analysis gives insight into where problems for automatic approaches lie, like occlusion and likely misclassifications caused by temporal changes.