Using Height Sensors for Biometric Identification in Multi-resident Homes

Srinivasan, Vijay; Stankovic, John A.; Whitehouse, Kamin

doi:10.1007/978-3-642-12654-3_20

Cited by 48 publications

(24 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[25] try to capture soft biometrics from a ceiling. A user's height captured by ultrasonic distance sensors mounted above doorways is used for person identification.…”

Section: Device-free Person Identification With Soft Biometricsmentioning

confidence: 99%

Unconstrained Person Identification from Ceiling Using Multiview Learning for Tabletop Users

Namioka

Masuda

Maekawa

2017

Journal of Information Processing

View full text Add to dashboard Cite

A novel unconstrained person identification method is presented in this paper. This method is for tabletop systems which exist not only in daily life but also in working environments such as offices and factories. Recent state-of-the-art ubicomp, computer-vision, and CSCW studies have tried to recognize a user's activities and actions on a table using a ceiling-mounted device that overlooks the table, since we can install the ceiling-mounted device in an environment with limited space such as daily life environments and factory environments. Instead of conventional unconstrained person identification methods, such as face identification, we focus on a user's soft biometrics that can be captured from the ceiling such as the shoulder length, shape of the head, and posture of the back to achieve unconstrained person identification by using a ceiling-mounted depth camera. We achieve robust person identification by combining the soft biometrics within a framework of multiview learning. Multiview learning allows us to deal effectively with data consisting of features from multiple sources with different data distributions, i.e., multiple soft biometrics in our case. Our experimental evaluation revealed that our proposed method achieved high identification accuracy of about 94%.

show abstract

“…[25] try to capture soft biometrics from a ceiling. A user's height captured by ultrasonic distance sensors mounted above doorways is used for person identification.…”

Section: Device-free Person Identification With Soft Biometricsmentioning

confidence: 99%

Unconstrained Person Identification from Ceiling Using Multiview Learning for Tabletop Users

Namioka

Masuda

Maekawa

2017

Journal of Information Processing

View full text Add to dashboard Cite

show abstract

“…In chapter 6, we present our solution for identifying residents in multi-person homes for activity recognition purposes [39]. We propose using ultrasonic height sensors above doorways for resident identification in homes.…”

Section: Outline Of Our Activity Recognition Approachmentioning

confidence: 99%

“…In chapter 6, we propose a non-invasive convenient solution for resident identification in homes, that shows high accuracy in initial experiments in the lab [39]. In chapter 7, we present a novel wireless snooping based privacy attack on resident activity recognition systems, and propose solutions to protect against such an attack in future smart homes [37].…”

Section: Unsupervised Learningmentioning

confidence: 99%

“…Thirdly, our height sensor based resident identification approach [39] is a significant contribution over existing inconvenient approaches that require users to carry a tag or allow camera use at all times [31,32,35]. Our solution is particularly useful in non-critical applications such as peace of mind elderly monitoring or home energy conservation applications.…”

Section: More Convenient Resident Identificationmentioning

confidence: 99%

See 1 more Smart Citation

Non-Invasive Sensor Solutions for Activity Recognition in SmartHomes

Srinivasan

Self Cite

View full text Add to dashboard Cite

Smart home sensor systems that infer residents' activities enable a number of exciting medical monitoring and energy conservation applications. Existing home activity recognition systems are invasive, since they require significant manual effort from the end user in installing or training the system, inconvenience the resident by requiring them to constantly wear tags, or require invasive cameras or expensive sensors. Our main hypothesis is that by effectively using data fusion techniques, leveraging the existing smart meter infrastructure in homes, and using only weak biometric sensing, we can build convenient, accurate home activity recognition solutions for the end user.The key challenges for home activity recognition systems addressed in this dissertation include reducing configuration effort from the end user, reducing sensor installation effort, and identifying residents in multi-person homes without using invasive sensors. To reduce user configuration effort, we develop an unsupervised activity recognition algorithm called AUTOLABEL that leverages data fusion and cross-home activity models to accurately recognize resident activities without user training. To eliminate many direct sensors in the home for activity recognition, we develop effective Bayesian data fusion techniques, which combine the existing smart meter infrastructure in homes, with one low cost, non-invasive sensor per room. In our WaterSense approach, we combine a single smart water meter per home, with an occupancy sensor per room to eliminate direct sensors on individual water fixtures. In our LightSense approach, we combine a single smart energy meter per home with a light sensor per room, to eliminate direct sensors on individual light fixtures. Finally, we propose the use of resident height, which is a weak biometric, in an effective data fusion approach, to identify residents for activity recognition in multi-person homes.We evaluate our proposed activity recognition solutions through short term prototype sensor deployments in home environments lasting from 7 to 10 days each. We show that our low cost, ii convenient solutions satisfy the activity recognition needs of numerous smart home applications, such as remote medical monitoring for elderly residents, and fine-grained resource consumption monitoring of light and water fixtures in the home. Finally, we observe that our unsupervised activity recognition algorithm can be used in a wireless snoop attack on smart homes, to infer the residents' daily activities with high accuracy in spite of encrypted wireless transmissions. We propose and evaluate a suite of privacy solutions to mitigate the inference accuracy of such an attack without affecting the performance or functionality of the home activity recognition system. iv

show abstract

“…al. [22] have proposed using height as a tracking system and show that identity can be obtained through repeated measurements. Several systems were built and deployed in various houses to gather real-world data sets based on this weak biometric height information.…”

Section: Heightmentioning

confidence: 99%

Infrastructure-based Occupant Localization for Indoor Home Environments

Hnat¹

View full text Add to dashboard Cite

People spend 62 percent of their time within the confines of their home. However, localization technologies such as GPS fail to accurately identify their indoor location. A key requirement of creating a smart home is both identifying each person and their current room location. Many techniques for identification or localization of people in indoor environments are being developed but most require either a privacy-invading camera system or participation by the tracked individuals to either perform actions or wear a device. These systems are useful in an office/industrial setting where the expectation of privacy is different, and an identification badge can be carried. In home environments, active participation and intrusive technologies are not ideal and should be avoided.The goals of this dissertation are 1) to identify simultaneously and track multiple people within home environments in a non-intrusive manner and 2) to enable a new set of applications based on location and identity awareness. A custom hardware platform is developed and deployed at the top of doorways to collect both the height and direction of a person as he/she crosses through it. Next, signal processing algorithms are developed to convert the raw data into person-events. Finally, a tracking algorithm, based on simultaneously checking multiple paths, assigns identities and locations to the event stream. The results show the tracking system obtains a 90 percent room-level accuracy on average when tested on 3,000 manually recorded doorway crossings.

show abstract

Using Height Sensors for Biometric Identification in Multi-resident Homes

Cited by 48 publications

References 16 publications

Unconstrained Person Identification from Ceiling Using Multiview Learning for Tabletop Users

Unconstrained Person Identification from Ceiling Using Multiview Learning for Tabletop Users

Non-Invasive Sensor Solutions for Activity Recognition in SmartHomes

Infrastructure-based Occupant Localization for Indoor Home Environments

Contact Info

Product

Resources

About