FBD-SV-2024: Flying Bird Object Detection Dataset in Surveillance Video

TL;DR

The paper introduces the FBD-SV-2024 dataset, a comprehensive collection of surveillance videos featuring flying birds, designed to evaluate and improve bird detection algorithms in challenging real-world scenarios.

Contribution

It provides a new, publicly available dataset of flying birds in surveillance videos, addressing challenges like small size and shape variability, and evaluates existing detection algorithms on it.

Findings

Existing algorithms find the dataset challenging due to bird characteristics.

The dataset highlights the need for improved detection methods.

Baseline results demonstrate room for advancement in flying bird detection.

Abstract

A Flying Bird Dataset for Surveillance Videos (FBD-SV-2024) is introduced and tailored for the development and performance evaluation of flying bird detection algorithms in surveillance videos. This dataset comprises 483 video clips, amounting to 28,694 frames in total. Among them, 23,833 frames contain 28,366 instances of flying birds. The proposed dataset of flying birds in surveillance videos is collected from realistic surveillance scenarios, where the birds exhibit characteristics such as inconspicuous features in single frames (in some instances), generally small sizes, and shape variability during flight. These attributes pose challenges that need to be addressed when developing flying bird detection methods for surveillance videos. Finally, advanced (video) object detection algorithms were selected for experimentation on the proposed dataset, and the results demonstrated that this dataset remains challenging for the algorithms above. The FBD-SV-2024 is now publicly available: Please visit https://github.com/Ziwei89/FBD-SV-2024_github for the dataset download link and related processing scripts.