Characterizing wave propagation to improve indoor step-level person localization using floor vibration

Counting the number of occupants in building areas over time-occupancy tracking-provides valuable information for responding to emergencies, optimizing thermal conditions or managing personnel. This capability is distinct from tracking individual building occupants as they move within a building, has lower complexity than conventional tracking algorithms require, and avoids privacy concerns that tracking individuals may pose. The approach proposed here is a novel combination of data analytics applied to measurements from a building's structural dynamics sensors (e.g., accelerometers or geophones). Specifically, measurements of footstep-generated structural waves provide evidence of occupancy in a building area. These footstep vibrations can be distinguished from other vibrations, and, once identified, the footsteps can be located. These locations, in turn, form the starting point of estimating occupancy in an area. In order to provide a meaningful occupancy count, however, it is first necessary to associate discrete footsteps with individuals. The proposed framework incorporates a tractable algorithm for this association task. The proposed algorithms operate online, updating occupancy count over time as new footsteps are detected. Experiments with measurements from a public building illustrate the operation of the proposed framework. This approach offers an advantage over others based on conventional technologies by avoiding the cost of a separate sensor system devoted to occupancy tracking.

Section: Footstep Event Detection Modulementioning

confidence: 99%

Section: Research Motivationmentioning

confidence: 99%

A Framework for Occupancy Tracking in a Building via Structural Dynamics Sensing of Footstep Vibrations

Poston

Buehrer

Tarazaga

2017

“…This compactness results in easier event detection because fewer features can represent the event of interest. Wavelet analysis has been widely applied as a promising tool to extract structural dynamic characteristics in structural health monitoring and other related fields (Chang, 1999;Hera and Hou, 2004;Taha et al, 2006;Noh et al, , 2011Noh et al, , 2012Mirshekari et al, 2015Mirshekari et al, , 2016aPan et al, 2015aPan et al, ,b, 2016Lam et al, 2016). Similarly, we use wavelet to extract structural dynamic characteristics that change with train activities.…”

Section: Extract Wavelet-based Featuresmentioning

confidence: 99%

An Information-Theoretic Approach for Indirect Train Traffic Monitoring Using Building Vibration

Zhang

et al. 2017

Self Cite

This paper introduces an indirect train traffic monitoring method to detect and infer real-time train events based on the vibration response of a nearby building. Monitoring and characterizing traffic events are important for cities to improve the efficiency of transportation systems (e.g., train passing, heavy trucks, and traffic). Most prior work falls into two categories: (1) methods that require intensive labor to manually record events or (2) systems that require deployment of dedicated sensors. These approaches are difficult and costly to execute and maintain. In addition, most prior work uses dedicated sensors designed for a single purpose, resulting in deployment of multiple sensor systems. This further increases costs. Meanwhile, with the increasing demands of structural health monitoring, many vibration sensors are being deployed in commercial buildings. Traffic events create ground vibration that propagates to nearby building structures inducing noisy vibration responses. We present an information-theoretic method for train event monitoring using commonly existing vibration sensors deployed for building health monitoring. The key idea is to represent the wave propagation in a building induced by train traffic as information conveyed in noisy measurement signals. Our technique first uses wavelet analysis to detect train events. Then, by analyzing information exchange patterns of building vibration signals, we infer the category of the events (i.e., southbound or northbound train). Our algorithm is evaluated with an 11-story building where trains pass by frequently. The results show that the method can robustly achieve a train event detection accuracy of up to a 93% true positive rate and an 80% true negative rate. For direction categorization, compared with the traditional signal processing method, our information-theoretic approach reduces categorization error from 32.1 to 12.1%, which is a 2.5× improvement.

“…When people walk on the floor, the footstep-induced structural vibration can be used to track, identify, and count pedestrian in the sensing area (Pan et al, 2014Mirshekari et al, 2016). When people lie on the bed, their heartbeat-induced vibration can also be detected, hence be used for health status estimation (Jia et al, 2016).…”

Section: Motivating Use-casesmentioning

confidence: 99%

“…A large amount of research has been focusing on feature extraction and information learning for different vibration-based applications (Dobbler et al, 2014;Mirshekari et al, 2015Mirshekari et al, , 2016Pan et al, 2015Pan et al, , 2016Bales et al, 2016b). However, if the raw signals acquired are already distorted (signal clipping) or of low resolution, the learning can hardly compensate for such information loss.…”

Section: Introductionmentioning

confidence: 99%

Collaboratively Adaptive Vibration Sensing System for High-fidelity Monitoring of Structural Responses Induced by Pedestrians

Pan

Mirshekari

et al. 2017

Self Cite

This paper presents a collaboratively adaptive vibration monitoring system that captures high-fidelity structural vibration signals induced by pedestrians. These signals can be used for various human activities' monitoring by inferring information about the impact sources, such as pedestrian footsteps, door opening and closing, and dragging objects. Such applications often require high-fidelity (high resolution and low distortion) signals. Traditionally, expensive high resolution and high dynamic range sensors are adopted to ensure sufficient resolution. However, for sensing systems that use low-cost sensing devices, the resolution and dynamic range are often limited; hence this type of sensing methods is not well explored ubiquitously. We propose a low-cost sensing system that utilizes (1) a heuristic model of the investigating excitations and (2) shared information through networked devices to adapt hardware configurations and obtain high-fidelity structural vibration signals. To further explain the system, we use indoor pedestrian footstep sensing through ambient structural vibration as an example to demonstrate the system performance. We evaluate the application with three metrics that measure the signal quality from different aspects: the sufficient resolution rate to present signal resolution improvement without clipping, the clipping rate to measure the distortion of the footstep signal, and the signal magnitude to quantify the detailed resolution of the detected footstep signal. In experiments conducted in a school building, our system demonstrated up to 2× increase on the sufficient resolution rate and 2× less error rate when used to locate the pedestrians as they walk along the hallway, compared to a fixed sensing setting.