There has been recently lot of car breaking on Stanford campus. A good way to stop this would be to have security through smart video surveillance: surveillance video cameras that can take decisions and alert the security team without a guard watching the video live 24h. We would have caught some of these bad guys in real time if the video surveillance on the campus had for example panic system integrated.

I this blog, I want to focus on the aspect of use/analyses video data it improve video surveillance.

Video data are very large in size, which inherent the name “biggest big data” compare to text and audio data for example.

[1] Dr. Sadiye Guler, founding president of IntuVision said “GPU acceleration enables analysts to get more information out of video in a shorter period time, greatly improving the time to analyze key information critical to resolving an incident, or collecting timely intelligence for security or marketing.”  This means that improvement in GPUs help to analyses shorter video clips reducing the impact of dealing with this very big data set which video data is.

Today, video communication is becoming increasingly the choice of communication: YouTube, imessaging, facebook, snapshot, etc…[2]. Video data analytics are not yet broadly used but the boom in AI and machine learning and analysis technologies are changing that space.

Much of video captured by surveillance video today goes un-analyses, so we are missing great opportunities to get valuable information from them.  [3] “By fully integrating video surveillance and analytics with other security systems, such as access control, field operations and panic alarms, an organization’s response and decision-making capabilities can be even more streamlined. And, when these traditional security technologies are leveraged in combination with emerging systems—such as social media, GIS mapping and databases—the result is actionable intelligence.”  So the real roadblock is to be able to mine this huge amount of video data to improve surveillance and beyond.

Application of better video surveillance still much needed in airports, schools, very busy hotels, stadiums, big event venues, etc..

AI, cloud based control, big data analytics, IOT, all these leading trends technologies we covered during this MC&E238 class are being combined to create a new way of sites security through video surveillance. Cloud based video management allow “companies to take complete advantage of anywhere, anytime, and any device cloud video surveillance.” [4]

Beyond the benefit of video data analytics in for surveillance applications, video “big data” analytics can also help improve following areas [5]:

  1. Customer Demand Behavior: “Collecting and analyzing simple customer behavior “
  2. Customer Service Performance: Video-derived big data can play a role here as well.  In addition to simple tasks like determining queue wait time, intelligent video can also provide data to allow more advanced service analysis and facilitate preventative actions.
  3. Loss Prevention: Notable scenarios include monitoring for a common deceptive practice whereby the clerk moves a product across the checkout scanner and covers the barcode so that the item does not get added to the total.  The video data logs the scanning transaction, but the lack of a corresponding entry in the cash register system, logs a conflict event.












2 comments on “The BIGGEST BIG data!”

  1. This is definitely huge and will only get better as the providers cost for both hardware and software continue evolving. How do you get the human factor out of the equation and let the decision making to the system with accuracy is still the challenge. For example, at my workplace every time the alarm goes on and the police has to come to the premise there is a 4 digit check we have to pay to the county plus after a handful of false calls you can get into more complicated forms of penalties and fines. The accuracy factor added to the cost factor make the decision making more complex however like with other technologies, the gap will continue to evolve.

  2. I like this article! It is so surprising how Tech Savvy the Palo Alto area is and yet there still seems to be quite a few car break-ins. I think in areas like this, while the approach to resolution is simple enough considering the amount of tech we have, what is the benefit to Stanford? How would they make their money back? Anyways, I know the well-being of the people who park on Campus is the benefit, but unless enough people complain, a bigger company might see it as something that is not their concern.


Comments are closed.