ERA Dataset

Along with the increasing use of unmanned aerial vehicles (UAVs), large volumes of aerial videos have been produced. It is unrealistic for humans to screen such big data and understand their contents. Hence methodological research on the automatic understanding of UAV videos is of paramount importance. In this paper, we introduce a novel problem of event recognition in unconstrained aerial videos in the remote sensing community and present a large-scale, human-annotated dataset, named ERA (Event Recognition in Aerial videos), consisting of 2,864 videos each with a label from 25 different classes corresponding to an event unfolding 5 seconds. The ERA dataset is designed to have a significant intra-class variation and inter-class similarity and captures dynamic events in various circumstances and at dramatically various scales. Moreover, to offer a benchmark for this task, we extensively validate existing deep networks. We expect that the ERA dataset will facilitate further progress in automatic aerial video comprehension. The website is \url{https://lcmou.github.io/ERA_Dataset/}.

随着无人飞行器（Unmanned Aerial Vehicles，UAV）应用的日益普及，海量航拍视频应运而生。人工筛选此类海量数据并理解其内容并不现实，因此针对无人机视频自动理解的方法学研究至关重要。本文提出了遥感领域内无约束航拍视频的事件识别这一新颖问题，并发布了一个大规模人工标注数据集ERA（Event Recognition in Aerial videos，航拍视频事件识别数据集），该数据集包含2864段视频，每段视频均带有25个不同类别中的一个标签，对应一段时长5秒的事件过程。ERA数据集具有显著的类内差异与类间相似性，能够捕捉不同场景下、尺度跨度极大的动态事件。此外，为了给该任务提供基准测试平台，我们对现有深度神经网络进行了充分的验证实验。我们期望ERA数据集能够推动航拍视频自动理解领域的进一步发展。该数据集的官方网站为https://lcmou.github.io/ERA_Dataset/。

搜集汇总

背景与挑战

背景概述

ERA Dataset是一个专注于无人机（UAV）视频事件识别的大规模数据集，包含2,864个视频，每个视频标注了25个不同类别的事件，每个事件持续5秒。该数据集设计具有显著的类内变化和类间相似性，覆盖多种动态事件和环境尺度，旨在推动自动空中视频理解的研究，适用于人工智能、计算机视觉和遥感等领域。