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

TL;DR

This paper introduces FBD-SV-2024, a surveillance-video focused flying bird object dataset designed to address the challenges of detecting small, inconspicuous birds whose appearances vary during flight. It details dataset collection (483 clips, 28,694 frames), two frame-naming schemes for image- and video-based methods, and a rigorous three-round annotation process that includes difficulty levels and track IDs. Through extensive experiments with both image- and video-based state-of-the-art detectors, the work demonstrates that the dataset remains challenging, with image-based methods generally performing better and temporal aggregation (as in FBOD-SV) offering the best but not yet close-to-perfect results. The dataset provides a realistic benchmark to drive improvements in surveillance-focused bird detection, emphasizing small-object and multi-frame context considerations for practical deployment.

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.

Figures (8)

• Figure 1: Examples of flying bird objects with inconspicuous features in single-frame images (red boxes indicate the bounding boxes of the flying bird objects).
• Figure 2: Screenshots of the corresponding flying bird objects in Fig. \ref{['Difficulty_diagram']} across 5 consecutive frames (highlighted by the yellow dashed box in Fig. \ref{['Difficulty_diagram']}).
• Figure 3: Schematic diagram of a surveillance camera capturing flying bird objects and the sizes of their imaging representations.
• Figure 4: Distribution of flying bird object sizes within the dataset.
• Figure 5: Scatter plot of object sizes in the dataset.