Driver Micro Hand Gestures (DriverMHG)

DriverMHG数据集由慕尼黑工业大学人机通信研究所创建，专注于驾驶员微手势的动态识别。该数据集包含RGB、红外和深度三种模态，通过25名参与者的驾驶模拟器收集，旨在解决车载场景中的人机交互问题。数据集设计考虑了手势的自然性和不分散驾驶员注意力的需求，适用于训练轻量级卷积神经网络，以实现实时、高效的手势识别。该数据集的应用领域主要集中在提高汽车安全性，通过识别驾驶员的手势来减少因操作车辆而分散注意力的风险。

The DriverMHG Dataset was developed by the Institute of Human-Machine Communication at the Technical University of Munich, focusing on dynamic recognition of driver micro-gestures. It includes three modalities: RGB, infrared, and depth, and was collected via a driving simulator with 25 participants. This dataset is designed to address human-computer interaction (HCI) issues in in-vehicle scenarios. With considerations for the naturalness of gestures and the requirement of not distracting drivers, the dataset is suitable for training lightweight convolutional neural networks (CNNs) to enable real-time and efficient gesture recognition. Its primary applications center on improving automotive safety: recognizing drivers' gestures helps reduce the risk of distraction caused by manual vehicle operation.