The Technology Headlines DEMAND FORCASTING & AI | Page 39

“
EXPERT ANALYSIS
The 1980s and 1990s were the dark days of neural network research.
over the past five years, IMAGENET [3] has organized the
large scale visual recognition challenge, where image
software algorithms are challenged to detect, classify and
localize a database of over 150,000 photographs collected
from flickr and other search engines. The dataset are
labeled into 1,000 object categories.
New applications and features of deep learning based
video surveillance solutions
A key advantage of deep learning based algorithms over
legacy computer vision algorithms is that deep learning
system can be continuously trained and improved
with better and more datasets. Many applications have
shown that deep learning systems can “learn” to achieve
99.9% accuracy for certain tasks. Unlike rigid computer
algorithms where it is very difficult to improve a system
past 95% accuracy.
The second advantage with deep learning system is
the “abnormal” event detection. Deep learning system
has shown remarkable ability to detect undefined or
AUGUST 2019
“
THE TECHNOLOGY HEADLINES
unexpected events. This feature has the true potential of
significantly reduce false positive detection events that
plagues many security video analytics systems. In fact, the
inability to reduce false positive detection rate is the key
problem in video surveillance industry; and has to-date
prevented the wide scale acceptance of many vendor’s
intelligent video analytics solutions.
Conclusion
Similar to cloud computing and big data technologies,
deep learning technology is now emerging as the
third wave of rapid advances that have taken over the
information industry by storm.
Over the next decade, very few areas in the technology
sector that will not be touched by the advances of cloud,
big data and machine learning. For the video surveillance
industry, this is welcome news, for the industry has been
lacking in innovations that can significantly advance the
state-of-the art.
39