Nacala-Roof-Material: Drone Imagery for Roof Detection, Classification, and Segmentation to Support Mosquito-borne Disease Risk Assessment

TL;DR

This paper introduces the Nacala-Roof-Material dataset with drone imagery for classifying and segmenting roof types to aid malaria risk assessment, benchmarking multiple models and proposing a new approach for improved object separation.

Contribution

The paper provides a new high-resolution drone dataset for roof classification and segmentation, benchmarks state-of-the-art models, and proposes a novel deep ordinal watershed variant for better object delineation.

Findings

Different models have unique advantages and no single model excels at all tasks.

The proposed DOW variant improves object separation and segmentation performance.

The dataset supports multi-task learning research for remote sensing applications.

Abstract

As low-quality housing and in particular certain roof characteristics are associated with an increased risk of malaria, classification of roof types based on remote sensing imagery can support the assessment of malaria risk and thereby help prevent the disease. To support research in this area, we release the Nacala-Roof-Material dataset, which contains high-resolution drone images from Mozambique with corresponding labels delineating houses and specifying their roof types. The dataset defines a multi-task computer vision problem, comprising object detection, classification, and segmentation. In addition, we benchmarked various state-of-the-art approaches on the dataset. Canonical U-Nets, YOLOv8, and a custom decoder on pretrained DINOv2 served as baselines. We show that each of the methods has its advantages but none is superior on all tasks, which highlights the potential of our dataset for future research in multi-task learning. While the tasks are closely related, accurate segmentation of objects does not necessarily imply accurate instance separation, and vice versa. We address this general issue by introducing a variant of the deep ordinal watershed (DOW) approach that additionally separates the interior of objects, allowing for improved object delineation and separation. We show that our DOW variant is a generic approach that improves the performance of both U-Net and DINOv2 backbones, leading to a better trade-off between semantic segmentation and instance segmentation.