Hands-Up: Leveraging Synthetic Data for Hands-On-Wheel Detection
This addresses the challenge of training computer vision algorithms in domains like automotive safety where real data is hard to collect, but it is incremental as it applies existing synthetic data methods to a specific use case.
The paper tackled the problem of detecting whether a driver's hands are on the wheel using a Driver Monitoring System, and demonstrated that synthetic photo-realistic data can boost performance when real data is scarce, though no concrete numbers are provided.
Over the past few years there has been major progress in the field of synthetic data generation using simulation based techniques. These methods use high-end graphics engines and physics-based ray-tracing rendering in order to represent the world in 3D and create highly realistic images. Datagen has specialized in the generation of high-quality 3D humans, realistic 3D environments and generation of realistic human motion. This technology has been developed into a data generation platform which we used for these experiments. This work demonstrates the use of synthetic photo-realistic in-cabin data to train a Driver Monitoring System that uses a lightweight neural network to detect whether the driver's hands are on the wheel. We demonstrate that when only a small amount of real data is available, synthetic data can be a simple way to boost performance. Moreover, we adopt the data-centric approach and show how performing error analysis and generating the missing edge-cases in our platform boosts performance. This showcases the ability of human-centric synthetic data to generalize well to the real world, and help train algorithms in computer vision settings where data from the target domain is scarce or hard to collect.