Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos

TL;DR

This paper introduces the Visual WetlandBirds Dataset, a comprehensive collection of videos with detailed annotations for bird species and behaviors, aimed at advancing biodiversity monitoring and deep learning models.

Contribution

It provides the first fine-grained bird video dataset with behavior annotations, enabling improved species identification and behavior recognition models.

Findings

Baseline models achieved promising accuracy in species classification.

Baseline models demonstrated effective behavior recognition capabilities.

The dataset fills a critical gap in bird video data for ecological research.

Abstract

The current biodiversity loss crisis makes animal monitoring a relevant field of study. In light of this, data collected through monitoring can provide essential insights, and information for decision-making aimed at preserving global biodiversity. Despite the importance of such data, there is a notable scarcity of datasets featuring videos of birds, and none of the existing datasets offer detailed annotations of bird behaviors in video format. In response to this gap, our study introduces the first fine-grained video dataset specifically designed for bird behavior detection and species classification. This dataset addresses the need for comprehensive bird video datasets and provides detailed data on bird actions, facilitating the development of deep learning models to recognize these, similar to the advancements made in human action recognition. The proposed dataset comprises 178 videos recorded in Spanish wetlands, capturing 13 different bird species performing 7 distinct behavior classes. In addition, we also present baseline results using state of the art models on two tasks: bird behavior recognition and species classification.