Characterizing Everyday Objects using Human Touch: Thermal Dissipation as a Sensing Modality

Emenike, Hilary; Dar, Farooq Ahmad; Liyanage, Mohan; Sharma, Rajesh; Zuniga, Agustin; Hoque, Mohammad A.; Radeta, Marko; Nurmi, Petteri; Flores, Huber

doi:10.1109/percom50583.2021.9439120

Cited by 11 publications

(18 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in such cases it may be possible to use alternative means to recognize humans. For example, people often touch furniture or other objects when they enter indoor areas and this touch results in a temporary thermal footprint [15] that can be captured using a thermal sensor array. Other limitations of thermal arrays include the need for separate power source, even if the power draw is small, and the need for sufficiently unobstructed view of the entrance area.…”

Section: Discussionmentioning

confidence: 99%

How Low Can You Go?

Rinta-Homi

Motlagh

Zuniga

et al. 2021

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

We contribute by systematically analysing the performance trade-offs, costs (privacy loss and deployment cost) and limits of low-resolution thermal array sensors for occupancy detection. First, to assess performance limits, we manipulate the frame rate and resolution of images to establish the lowest possible values where reliable occupancy information can be captured. We also assess the effect of different viewing angles on the performance. We analyse performance using two datasets, an open-source dataset of thermal array sensor measurements (TIDOS) and a proprietary dataset that is used to validate the generality of the findings and to study the effect of different viewing angles. Our results show that even cameras with a 4 × 2 resolution - significantly lower than what has been used in previous research - can support reliable detection, as long as the frame rate is at least 4 frames per second. The lowest tested resolution, 2 × 2, can also offer reliable detection rates but requires higher frame rates (at least 16 frames per second) and careful adjustment of the camera viewing angle. We also show that the performance is sensitive to the viewing angle of the sensor, suggesting that the camera's field-of-view needs to be carefully adjusted to maximize the performance of low-resolution cameras. Second, in terms of costs, using a camera with only 4 × 2 resolution reveals very few insights about the occupants' identity or behaviour, and thus helps to preserve their privacy. Besides privacy, lowering the resolution and frame rate decreases manufacturing and operating costs and helps to make the solution easier to adopt. Based on our results, we derive guidelines on how to choose sensor resolution in real-world deployments by carrying out a small-scale trade-off analysis that considers two representative buildings as potential deployment areas and compares the cost, privacy and accuracy trade-offs of different resolutions.

show abstract

Section: Discussionmentioning

confidence: 99%

How Low Can You Go?

Rinta-Homi

Motlagh

Zuniga

et al. 2021

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Indeed, when individuals touch objects or even walk, thermal footprints caused due to their human-emitted thermal radiation are visible. By analyzing this residual thermal information ( Emenike et al., 2021 ), it is possible to understand not just occupancy of the room, but also the density of interactions that the room has experienced from people visiting it. Another approach is to use air quality sensors to measure PM

, CO

, (relative) humidity and temperature for extrapolating the occupancy in the spaces ( Motlagh et al., 2019 ).…”

Section: Preventionmentioning

confidence: 99%

“…For example, South Korea deployed smart shelters that are equipped with air-conditioning, ultraviolet light air sterilizers, and thermal cameras that allow only people whose body temperature is below 37.5

C to enter the bus. The main limitation of thermal screening is that thermal cameras have limited sensitivity ( Emenike, Dar, Liyanage, Sharma, Zuniga, Hoque, Radeta, Nurmi, Flores, 2021 , Malmivirta, Hamberg, Lagerspetz, Li, Peltonen, Flores, Nurmi, 2019 ). For example, off-the-shelf FLIR technology has an average error of

C whereas more accurate technologies cost significantly more and require special cooling mechanisms.…”

Section: Mitigationmentioning

confidence: 99%

A survey of COVID-19 in public transportation: Transmission risk, mitigation and prevention

Liu

Kortoçi

Motlagh

et al. 2022

Multimodal Transportation

Self Cite

View full text Add to dashboard Cite

“…Deep Thermal Imaging [10] uses thermal images obtained from a smartphone-attachable thermal camera to classify between different surfaces and materials. MIDAS [13] uses a smartphone with an onboard thermal camera to measure the change across thermal images after a subject has touched an object, and trains a classifier to distinguish between different objects. However, none of these solutions are designed for liquid sensing and are instead designed for classification of larger solid objects or surfaces.…”

Section: Related Workmentioning

confidence: 99%

Testing a Drop of Liquid Using Smartphone LiDAR

Chan

Raghunath

Michaelsen

et al. 2022

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

We present the first system to determine fluid properties using the LiDAR sensors present on modern smartphones. Traditional methods of measuring properties like viscosity require expensive laboratory equipment or a relatively large amount of fluid. In contrast, our smartphone-based method is accessible, contactless and works with just a single drop of liquid. Our design works by targeting a coherent LiDAR beam from the phone onto the liquid. Using the phone's camera, we capture the characteristic laser speckle pattern that is formed by the interference of light reflecting from light-scattering particles. By correlating the fluctuations in speckle intensity over time, we can characterize the Brownian motion within the liquid which is correlated with its viscosity. The speckle pattern can be captured on a range of phone cameras and does not require external magnifiers. Our results show that we can distinguish between different fat contents as well as identify adulterated milk. Further, algorithms can classify between ten different liquids using the smartphone LiDAR speckle patterns. Finally, we conducted a clinical study with whole blood samples across 30 patients showing that our approach can distinguish between coagulated and uncoagulated blood using a single drop of blood.

show abstract

Characterizing Everyday Objects using Human Touch: Thermal Dissipation as a Sensing Modality

Cited by 11 publications

References 32 publications

How Low Can You Go?

How Low Can You Go?

A survey of COVID-19 in public transportation: Transmission risk, mitigation and prevention

Testing a Drop of Liquid Using Smartphone LiDAR

Contact Info

Product

Resources

About