Action Inference of Rear Seat Passenger for In-Vehicle Service

In order to meet the demand for safety, usability, comfortability, and entertainment for rear seat passenger service, we introduce Skeleton motion dataset of Vehicle Rear seat Passenger (SVRP) which is a world first skeleton motion dataset for rear seat passenger with 22 different actions publicly available†. The dataset was trained and tested by a neural network with CTR-GCN [10] for action inference. The result shows the accuracy is 78.3 percent for 25 joint 2D skeleton and 80.2 percent for 32 joint 3D skeleton by sliding 4 second observation window. We also found that a longer observation window is crucial for a stable inference while time frame resolution can be reduced to 5 frames per second for lightweight computation without much accuracy drop. The number of skeleton joints can be also reduced with same accuracy from 25 points to 10 points, which is a mostly upper body part, by a proposed heatmap correlation method.†SVRP dataset available at conference on web https://github.com/DensoITLab/pvi