UAV-Human
收藏资源简介:
UAV-Human是由新加坡科技设计大学信息系统技术与设计创建的大型多模态基准数据集,专注于无人机视角下的人类行为理解。该数据集包含67,428个多模态视频序列,涉及119个不同对象,用于动作识别、姿态估计、人物再识别和属性识别等多个任务。数据集通过在多个城市和乡村地区,跨越白天和夜晚,使用无人机搭载多种传感器收集而成,覆盖了广泛的环境多样性,包括不同的光照、天气和遮挡条件。此数据集旨在推动无人机在复杂环境中的人类行为分析技术的发展。
UAV-Human is a large-scale multimodal benchmark dataset dedicated to human behavior understanding from unmanned aerial vehicle (UAV) perspectives, developed by the Department of Information Systems Technology and Design at Singapore University of Technology and Design. This dataset encompasses 67,428 multimodal video sequences involving 119 distinct subjects, and supports a wide range of tasks including action recognition, pose estimation, person re-identification, and attribute recognition. Collected via UAVs equipped with various sensors across diverse urban and rural areas during both daytime and nighttime, the dataset covers extensive environmental diversity, including varying lighting conditions, weather patterns, and occlusion scenarios. This dataset aims to advance the development of human behavior analysis technologies for UAVs in complex environments.




