This paper comprehensively reviews hand gesture datasets based on Ultraleap's leap motion controller, a popular device for capturing and tracking hand gestures in real-time. The aim is to offer researchers and practitioners a valuable resource for developing and evaluating gesture recognition algorithms. The review compares various datasets found in the literature, considering factors such as target domain, dataset size, gesture diversity, subject numbers, and data modality. The strengths and limitations of each dataset are discussed, along with the applications and research areas in which they have been utilized. An experimental evaluation of the leap motion controller 2 device is conducted to assess its capabilities in generating gesture data for various applications, specifically focusing on touchless interactive systems and virtual reality. This review serves as a roadmap for researchers, aiding them in selecting appropriate datasets for their specific gesture recognition tasks and advancing the field of hand gesture recognition using leap motion controller technology.

翻译：本文全面评述了基于Ultraleap公司Leap Motion控制器的手势数据集，该设备是一种用于实时捕捉和追踪手部动作的流行装置。本综述旨在为研究人员和从业者提供开发与评估手势识别算法的宝贵资源。通过文献调研，我们对多个数据集进行了比较分析，考量因素包括目标领域、数据集规模、手势多样性、受试者数量及数据模态。本文详细讨论了各数据集的优势与局限，以及其在各应用场景与研究领域中的使用情况。同时，我们对Leap Motion控制器二代设备进行了实验评估，以验证其在生成手势数据支持各类应用（尤其关注无接触交互系统与虚拟现实领域）方面的能力。本综述为研究人员提供了路线图，帮助其根据特定手势识别任务选择合适的数据集，并推进基于Leap Motion控制器技术的手势识别领域发展。