Detection of Degraded Acacia tree species using deep neural networks on uav drone imagery

TL;DR

This study employs UAV imagery and deep neural networks to detect degraded Acacia trees in flood-affected areas, demonstrating the effectiveness of Retina-Net with notable precision and recall metrics.

Contribution

It introduces a novel application of deep learning for detecting fallen trees in challenging natural environments using UAV imagery.

Findings

Retina-Net achieved 38.9% precision and 57.9% recall.

Deep learning models are effective for tree detection in flood-inundated areas.

The study provides a new dataset with 7,590 annotations for this task.

Abstract

Deep-learning-based image classification and object detection has been applied successfully to tree monitoring. However, studies of tree crowns and fallen trees, especially on flood inundated areas, remain largely unexplored. Detection of degraded tree trunks on natural environments such as water, mudflats, and natural vegetated areas is challenging due to the mixed colour image backgrounds. In this paper, Unmanned Aerial Vehicles (UAVs), or drones, with embedded RGB cameras were used to capture the fallen Acacia Xanthophloea trees from six designated plots around Lake Nakuru, Kenya. Motivated by the need to detect fallen trees around the lake, two well-established deep neural networks, i.e. Faster Region-based Convolution Neural Network (Faster R-CNN) and Retina-Net were used for fallen tree detection. A total of 7,590 annotations of three classes on 256 x 256 image patches were used for this study. Experimental results show the relevance of deep learning in this context, with Retina-Net model achieving 38.9% precision and 57.9% recall.