Security Sales & Integration September 2022 - 12

INDUSTRY PULSE HOT SEAT
Fulfilling the Promise of
Intelligent Video Analytics
▶ Megh Computing is a fully customizable,
cross-platform video analytics
solution provider for real-time actionable
insights. The company was established in
2017 and is based in Portland, Ore., with
development offices in Bangalore, India.
Co-founder and CEO PK Gupta joins
the conversation to talk analytics deployment,
customization and more.
As technology continually moves
to the edge with video analytics
and smart sensors, what are
the tradeoffs versus Cloud
deployment?
▶ GUPTA: The demand for edge analytics
is increasing rapidly with the explosion of
streaming data from sensors, cameras and
other sources. Of these, video remains the
dominant data source with over a billion
cameras deployed globally. Enterprises
want to extract intelligence from these
data streams using analytics to create
business value. Most of this processing is
increasingly being done at the edge close
to the data source. Moving the data to the
Cloud for processing incurs transmission
costs, potentially increases security risks
and introduces latencies in the response
time. Hence intelligent video analytics
[IVA] is moving to the edge.
Many end users are concerned
about sending video data offpremises;
what options are there
for processing on-premises yet
leveraging Cloud benefits?
▶ GUPTA: Many IVA solutions force
users to choose between deploying
their solution on-premises at the edge
or hosted in the Cloud. Hybrid models
allow on-premises deployments to
benefit from the scalability and flexibility
of Cloud computing. In this
model, the video processing pipeline
is split between on-premises processing
and Cloud processing. In a simple
implementation, only the metadata is
forwarded to the Cloud for storage and
12
search. In another implementation, the
data ingestion and transformation are
done at the edge. Only frames with activity
are forwarded to the Cloud for
processing for the analytics. This model
is a good compromise between balancing
the latency and costs between edge
processing and Cloud computing.
Image-based video analytics
has historically needed filtering
services due false positives; how
does deep learning reduce those?
▶ GUPTA: Traditional attempts at IVA
have not met the expectations of enterprises
because of limited functionality
and poor accuracy. These solutions use
image-based video analytics with computer
vision processing for object detection
and classification. These techniques
are prone to errors necessitating the need
to deploy filtering services. In contrast,
techniques using optimized deep learning
models trained to detect people or
objects coupled with analytics libraries
for the business rules can essentially
eliminate false positives. Special deep
learning models can be created for custom
use cases like PPE compliance, collision
avoidance, etc.
We hear " custom use case "
frequently with video AI; what does
it mean?
▶ GUPTA: Most use cases must be customized
to meet the functional and performance
requirements to deliver IVA.
The first level of customization required
universally includes the ability to configure
the monitoring zones in the camera
field of view, set up thresholds for the
analytics, configure the alarms and set
up the frequency and recipients of notifications.
These configuration capabilities
should be provided via a dashboard using
graphical interfaces to allow the users
to set up the analytics for proper operation.
The second level of customization
involves updating the video analytics
Security Sales & Integration SEPTEMBER 2022
PRABHAT K. GUPTA
Co-founder & CEO,
Megh Computing
pipeline with new deep learning models
or new analytics libraries to improve the
performance. The third level includes
training and deploying new deep learning
models to implement new use cases,
e.g., a model to detect PPE for worker
safety, or to count inventory items in a
retail store.
Can smart sensors such as lidar,
presence detection, radar, etc.
be integrated into an analytics
platform?
▶ GUPTA: IVA typically processes video
data from cameras only and delivers
insights based on analyzing the images.
And sensor data are typically analyzed
by separate systems to produce insights
from lidar, radar and other sensors. A human
operator is inserted in the loop to
combine the results from the disparate
platforms to reduce false positives for
specific use cases like tailgating, employee
authentication, etc. An IVA platform that
can ingest data from cameras and sensors
using the same pipeline and use machine
learning-based contextual analytics can
deliver insights for these and other use
cases. The contextual analytics component
can be configured with simple rules
and then it can learn to improve the rules
over time to deliver highly accurate and
meaningful insights.
securitysales.com
http://www.securitysales.com
Security Sales & Integration September 2022

Table of Contents for the Digital Edition of Security Sales & Integration September 2022
