SynthoGestures: A Novel Framework for Synthetic Dynamic Hand Gesture Generation for Driving Scenarios
This work addresses a domain-specific problem for automotive gesture recognition systems by providing a time-saving tool, though it is incremental as it builds on existing synthetic data methods.
The paper tackles the challenge of creating diverse hand gesture datasets for automotive human-machine interfaces by proposing a synthetic generation framework using Unreal Engine, which improves gesture recognition accuracy and can replace or augment real datasets.
Creating a diverse and comprehensive dataset of hand gestures for dynamic human-machine interfaces in the automotive domain can be challenging and time-consuming. To overcome this challenge, we propose using synthetic gesture datasets generated by virtual 3D models. Our framework utilizes Unreal Engine to synthesize realistic hand gestures, offering customization options and reducing the risk of overfitting. Multiple variants, including gesture speed, performance, and hand shape, are generated to improve generalizability. In addition, we simulate different camera locations and types, such as RGB, infrared, and depth cameras, without incurring additional time and cost to obtain these cameras. Experimental results demonstrate that our proposed framework, SynthoGestures (https://github.com/amrgomaaelhady/SynthoGestures), improves gesture recognition accuracy and can replace or augment real-hand datasets. By saving time and effort in the creation of the data set, our tool accelerates the development of gesture recognition systems for automotive applications.