Sonicdoor: scaling person identification with ultrasonic sensors by novel modeling of shape, behavior and walking patterns

Non-intrusive occupant identification enables numerous applications in Smart Buildings such as personalization of climate and lighting. Current non-intrusive identification techniques do not scale beyond 20 people whereas commercial buildings can have 100 or more people. This paper proposes a new method to identify occupants by sensing their body shape, movement and walking patterns as they walk through a SonicDoor, a door instrumented with three ultrasonic sensors. The proposed method infers contextual information such as path detection and historical walks through different doors of the building in order to enhance the identification accuracy. Each SonicDoor is instrumented with ultrasonic ping sensors, one on the top to sense height and two on the sides of the door to sense width of the person walking through the door. SonicDoor detects a walking event and analyzes it to infer whether the Walker is using a phone, holding a handbag, or wearing a backpack. It extracts a set of features from the walking event and corrects them using a set of transformation functions to mitigate the bias. We deployed five SonicDoors in a real building for two months and collected data consisting of over 9000 walking events spanning over 170 people. The proposed method identifies up to 100 occupants with an accuracy of 90.2%, which makes it suitable for large-scale realistic buildings. SonicDoor method surpasses the state of the art by a factor of five, which is limited to 20 people.