Dronescape: A High-Resolution Drone Footage Dataset for Tree Region Segmentation

Nair, Ashwin; Mehendale, Ninad

doi:10.2139/ssrn.4512595

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In RGB drone-based applications, SAM is being utilized for measuring crop yields for agricultural purposes, and conducting tree-segmentation to measure forest density and health [28], [29], [30], [31], [32]. These methods are also being applied to understand the built environment, including infrastructure health [33], from railroad integrity, to bridge structures, and detecting road cracks [34], [35], [36], [37].…”

Section: Related Workmentioning

confidence: 99%

A Multispectral Automated Transfer Technique (MATT) for machine-driven image labeling utilizing the Segment Anything Model (SAM)

Gallagher,

Gogia,

Oughton

2024

Preprint

View full text Add to dashboard Cite

Segment Anything Model (SAM) is drastically accelerating the speed and accuracy of automatically segmenting and labeling large Red-Green-Blue (RGB) imagery datasets. However, SAM is unable to segment and label images outside of the visible light spectrum, for example, for multispectral or hyperspectral imagery. Therefore, this paper outlines a method we call the Multispectral Automated Transfer Technique (MATT). By transposing SAM segmentation masks from RGB images we can automatically segment and label multispectral imagery with high precision and efficiency. For example, the results demonstrate that segmenting and labeling a 2,400-image dataset utilizing MATT achieves a time reduction of 87.8% in developing a trained model, reducing roughly 20 hours of manual labeling, to only 2.4 hours. This efficiency gain is associated with only a 6.7% decrease in overall mean average precision (mAP) when training multispectral models via MATT, compared to a manually labeled dataset. We consider this an acceptable level of precision loss when considering the time saved during training, especially for rapidly prototyping experimental modeling methods. This research greatly contributes to the study of multispectral object detection by providing a novel and open-source method to rapidly segment, label, and train multispectral object detection models with minimal human interaction. Future research needs to focus on applying these methods to (i) space-based multispectral, and (ii) drone-based hyperspectral imagery.

show abstract