The Institute - September 2020 - TI12

tech takes on COVID-19

Vision interface standard can transmit high-speed video and related
control data over an Ethernet connection. Genlcam is a common
programming interface used for
machine vision in cameras.
BCB's TempScan is connected
to the camera through a computer.
When checking a person, the camera's operator will see a detailed
thermogram. An alarm will sound
if a fever is detected, de Griñó says,
and the operator then will recommend to the person that he or she
be tested for COVID-19.

The Pro-Cam infrared camera that
Ebrahimi and his students built
combines infrared, thermal, and
visible-light sensors while capturing visible-light images.
"We designed and built a new
type of connected camera with
multiple sensors that can track
people, also known as proximity
or contact tracing, while protecting their privacy," he says.
The c ameras, made from
off-the-shelf components and
open-source software, are less
expensive than existing thermal
cameras. The team also created
a custom enclosure to protect the
camera components.
Using real-time streaming, Ebrahimi says, the camera sends the
images to a server. The system
protects the anonymity of the
individual in the scene, he says,
by hiding the visible-light images
inside thermal images using transmorphing, a cryptographic tool.
A dedicated server records all
the captured footage in a secure,
anonymized way, he says, adding that there is the possibility



SEP 2020



for further analysis, visualization,
and eventual de-anonymization.
Ebrahimi says the camera
is more accurate than current
contact-tracing methods that use
smartphone positions or Bluetooth discovery to determine the
relative distance between devices.
The Pro-Cam also doesn't require
individuals to carry a smartphone
or install a contact-tracing app.
The technologies pose ethical
challenges, including invasion of
privacy. Ebrahimi says it will be possible to recover a person's identity
using cryptographic keys if consent
is given or if the proper authorities
request the information.
The project wasn't without its
challenges, he says. Because lowcost infrared and thermal sensors
have lower resolution and precision, the team combined three
such sensors along with advanced
image-processing algorithms.
"Even though everyone on the
project worked remotely, they
came up with the camera's design
from scratch and had it ready to
build in 72 hours," Ebrahimi says.
Three students will continue
building other cameras as part of
their senior project and will run
trials on them, Ebrahimi says. He
says further enhancements will
include the ability to perform
artificial intelligence-based video
analytics, trace people between
cameras, and merge with other
proximity-tracing approaches such
as those based on smart cameras.

This article originally appeared online
as "Thermal Cameras Are Being Outfitted to Detect Fever and Conduct
Contact Tracing for COVID-19."

Arm Scours
Nooks and


roperly disinfecting public spaces can
help stop the spread of COVID-19, but
cleaning crews often are not trained
how to do so. Also, the workers risk infection, especially if they do not wear personal
protective equipment.
IEEE Fellow Satyandra K. Gupta is leading a research team at the University of
Southern California's Viterbi Center for
Advanced Manufacturing, in Los Angeles,
that is building a robotic arm. The machine
uses an ultraviolet-light sanitizer to clean
contaminated areas.
Gupta is a mechanical engineering professor at the university.
This interview, conducted in April, has
been edited and condensed for clarity.
What problem are you trying to solve?

In order to thoroughly clean cluttered work
spaces, janitorial staff must move items so
that all high-touch surfaces can be disinfected. This requires a significant amount
of time and effort. It also puts the lives of
the workers at risk.
There are a few robots that are used to
disinfect areas on the market. However,
they do not have the ability to pick up and
move objects in their way. Therefore, they
cannot effectively clean the surfaces.

The Institute - September 2020

Table of Contents for the Digital Edition of The Institute - September 2020

The Institute - September 2020 - TI1
The Institute - September 2020 - TI2
The Institute - September 2020 - TI3
The Institute - September 2020 - TI4
The Institute - September 2020 - TI5
The Institute - September 2020 - TI6
The Institute - September 2020 - TI7
The Institute - September 2020 - TI8
The Institute - September 2020 - TI9
The Institute - September 2020 - TI10
The Institute - September 2020 - TI11
The Institute - September 2020 - TI12
The Institute - September 2020 - TI13
The Institute - September 2020 - TI14
The Institute - September 2020 - TI15
The Institute - September 2020 - TI16