Executive Vice President & Chief Technology Officer, Motorola
Search every verified Mahesh Saptharishi interview, podcast appearance, and on-the-record quote — each transcript cross-checked by AI and human review to confirm speaker identity. In a 2016 presentation, Mahesh Saptharishi, then Chief Technology Officer at Avigilon, discussed the company's Appearance Search technology, which he described as an artificial intelligence-driven system for video analysis. He argued that traditional video surveillance suffers from an "attention gap," noting that only 5% of recorded video is ever reviewed. Saptharishi stated that the goal of AI in this context is to filter out uninteresting content so that human attention can focus on important events. He described Appearance Search as a foundational step toward "site-wide intelligence," allowing users to search for an individual across all cameras in a facility rather than within a single camera's field of view. Saptharishi emphasized that the system is designed to be efficient and affordable for mainstream use, without requiring supercomputers or significant server costs)Skip.
“Imagine that you could use the internet, but you had no access to a service like Google enabling you to search for specific things that you're looking for... everything takes that much longer and given that human attention, human resources are at a premium, unless there is a real need for you to be looking at video, no...”
“Only 5% of video is actually ever used, 95% of video is never actually touched, never looked at in any particular way.”
“Yet, we spend a lot of money both collecting video and storing it for an extended period of time.”
“Decisive action requires that we understand who, when, where and what associated with any given event.”
“One way to augment that attention gap... is by adding the power of artificial intelligence. The goal of AI in this case is to filter out everything that is uninteresting so that human attention can be focused on only those things that are truly important.”
“One of the foundational steps to go from single camera based searches to site-wide searches is being able to search for the presence of a single actor who's involved in an important event not just within a single camera, but across all the cameras in the site.”
“Appearance Search is the first step in the artificial intelligence sequence of capabilities that Avigilon is going to release. This starts with understanding who in the scene showed up in your entire site.”
“We need to architect a full solution in a way where computation and intelligence is spread through the entire solution... and the total cost of the system is something that we can use in the mainstream, the mass market, without needing super computers or spending a huge amount of money on servers.”
“All you want to be able to do is, for the sake of simplicity, click on a person, and the act of clicking on a person should enable you to find this individual across all your cameras in the entire site.”
“This is fundamentally an AI driven system... The human brain is always going to be able to do anything better than the neural network... but where such systems really shine is when we have to look through lots of video where human attention is at a premium.”
Avigilon's Chief Technology Officer, Dr. Mahesh Saptharishi, discusses Artificial Intelligence (AI) Driven Appearance Search. Connect with Avigilon! Twitter: / avigilon LinkedIn: / 797614 Facebook: / avigiloncorporation
Sign in to search the full transcript archive, filter by topic, and access every quote from Mahesh Saptharishi.
The summary and quote tags on this profile are produced with AI assistance from verified, first-person interview transcripts, then checked by our team to confirm the speaker's identity and the accuracy of every quote. See how we verify →