FBD-SV-2024
收藏资源简介:
FBD-SV-2024是由Zi-Wei Sun等人创建的飞行鸟类监控视频数据集,旨在促进监控视频中飞行鸟类检测算法的发展和评估。该数据集包含483个视频片段,总计28,694帧,其中23,833帧包含28,366个飞行鸟类实例。数据集从真实的监控场景中收集,鸟类在单帧图像中特征不明显、尺寸小且形状多变,这些特性为算法开发带来了挑战。数据集分为训练集和测试集,分别包含400和83个视频片段。该数据集主要应用于监控视频中的飞行鸟类检测,旨在解决鸟类对人类生产和生活活动带来的潜在危害问题。
FBD-SV-2024 is a flying bird surveillance video dataset created by Zi-Wei Sun et al., which aims to advance the development and evaluation of flying bird detection algorithms in surveillance videos. This dataset includes 483 video clips, totaling 28,694 frames, among which 23,833 frames contain 28,366 instances of flying birds. The dataset is collected from real-world surveillance scenarios, where birds in individual frames exhibit inconspicuous features, small sizes and diverse morphologies, posing significant challenges for algorithm development. The dataset is split into training and test sets, with 400 and 83 video clips respectively. This dataset is primarily applied to flying bird detection in surveillance videos, targeting the mitigation of potential hazards that birds pose to human production and daily living activities.




