A dataset of ground-dwelling nocturnal fauna for object detection and classification

Abstract

The exploration of ground-dwelling nocturnal fauna represents a significant challenge due to its broad implications across various sectors, including pesticide management, crop yield forecasting, and plant disease identification. This paper unveils an annotated dataset, BioAuxdataset, aimed at facilitating the recognition of such fauna through field images gathered across multiple years. Culled from a collection exceeding 100,000 raw field images over a span of four years, this meticulously curated dataset features seven prevalent species of nocturnal ground-dwelling fauna: carabid, mouse, opilion, slug, shrew, small-slug, and worm. In instances of underrepresented species within the dataset, we have implemented straightforward yet potent image augmentation techniques to enhance data quality. BioAuxdataset stands as a valuable resource for the detection and identification of these organisms, leveraging the power of deep learning algorithms to unlock new potentials in ecological research and beyond. This dataset not only enriches the academic discourse but also opens up avenues for practical applications in agriculture, environmental science, and biodiversity conservation.

Keywords

• Multi-class recognition
• Ground-dwelling nocturnal fauna
• Biodiversity
• Deep learning
• Mask-RCNN
• Computer vision