The Technology Headlines DEMAND FORCASTING & AI | Page 38

EXPERT ANALYSIS
THE TECHNOLOGY HEADLINES
DEEP LEARNING TECHNOLOGY APPLICATIONS
FOR VIDEO SURVEILLANCE INDUSTRY
By Paul Sun, President and CEO of IronYun
nets have really started to garner leadingindustrial labs’
attention from the breakthroughs in deep learningwork in
academia at the University of Toronto, NYU, Stanford and
others. Over the past several years, real world applications
of deep learning now encompasses many industries
including handwriting recognition, language translation,
automatic game (chess/go) playing, object classification, face
recognition, medical image analysis, autonomous driving
cars and many other fields.
Paul Sun
PRESIDENT AND CEO OF IRONYUN
One example of the excitement with Deep learning
technology is the recent breakthrough from Google’s
AlphaGo, a computer program that for the first time beat
a professional human Go player in October, 2015. The
sophistication of the Deep learning based program has
astonished many in the field of artificial intelligence due
the complexity of the ancient Asia GO game, which is
considerably more complicated than chess.
Brief introduction of deep learning Video surveillance applications with deep learning
The field of artificial intelligence known as machine
learning or cognitive computing has in recent years
become highly popular. The meteoric rise of deep learning
technology over the past several years has been truly
dramatic in many industries. The machine learning field
has exploded on the scene with the breakthrough in the new
‘Deep learning’ technology. Although deep learning has been applied to many industry
with breakthrough results comparing to legacy systems, not
all applications are suitable using deep learning. In the field
of video surveillance, several applications stands out that
can benefit from deep learning.
The field of Deep learning evolved from ‘artificial neural
nets’ from the 1980s. In the early years of this branch of
Artificial Intelligence, the neural nets are modeled after a
human’s brain, which consists of over 100 billion neurons.
The key limitations of the earlier systems are the difficultly
to train the network; and the hardware CPU technologies
were too slow to properly train a neural net that can solve
meaningful real world applications. Deep learning technology has significantly improved
the accuracy rate of face recognition. Most of today’s top
performing commercial face recognition products are
based on deep learning. The accuracy have reached 99.9%
for controlled environment like airport immigration face
recognition applications.
The 1980s and 1990s were the dark days of neural network
research. Since 2000,the research community of neural Person detection and object detection is another area where
deep learning has shown tremendous progress. For example,
AUGUST 2019
Face recognition
Persons and Object detection
38