UWBCarGraz Dataset for Car Occupancy Detection using Ultra-Wideband Radar

We present a data-driven car occupancy detection algorithm using ultra-wideband radar based on the Res Net architecture. The algorithm is trained on a dataset of channel impulse responses obtained from measurements at three different activity levels of the occupants (i.e. breathing, talking, moving). We compare the presented algorithm against a state-of-the-art car occupancy detection algorithm based on variational message passing (VMP). Our presented Res Net architecture is able to outperform the VMP algorithm in terms of the area under the receiver operating curve (AUC) at low signal-to-noise ratios (SNRs) for all three activity levels of the target. Specifically, for an SNR of - 20 dB our ResNet architecture achieves an AUC of 0.91 while the VMP detector only achieves an AUC of 0.87 if the target is sitting still and breathing naturally. The difference in performance for the other activities is similar. Furthermore, to facilitate the implementation in the onboard computer of a car, we train a collection of different ResNet architectures to find a balance between the detection performance and computational complexity. The VWBCarGraz dataset used to train and evaluate the algorithm is openly accessible.