Thank you for posting. I like seeing a wide range of responses.

I wanted to let you know that BRS Labs has been difficult to get information from. John Honovich, who reviews IP video products for the industry, has been trying to get a unit from them to test for over a year now, but they refuse to let him try it out. They might have very good reasons for refusing, but this makes it more difficult to find out real information. So, I appreciate what you have let us know.

But I also wanted to let you know that just a week ago I came from a university who was testing the BRS Labs system. They were testing their system side-by-side with our video analytics. So I got to see that they have added rules to their new software, as you said. They didn’t have it originally, but their system has it now.

That’s the right move for them.

I see that they also added the ability to let a user decide when they want to continue seeing an alarm, even if it becomes “normal”. So, they’ve addressed two of the concerns I’ve raised. And now their system is starting to act more like other rules based systems, which as I’ve said makes sense.

By the way, the university who was running their tests were extremely happy with our results. They couldn’t believe how much simpler our system was to set up and that it was working accurately within minutes, without any calibration or tuning.

The BRS Labs takes weeks or longer to learn the environment, while ours does it in a few minutes. Even after weeks, they seem to have far more false alarms than our system, according to the university. When I was there, the person in charge of testing showed me how a beam of sunlight was causing a false alarm for the BRS Labs system. Apparently it thought the beam of light was baggage left behind.

When you ask for other companies doing analytics in a similar way, can you explain what it is you are looking for?

Or, feel free to write to me privately, if you prefer.

Thanks again for posting and sharing your perspective and the information you have about BRS Labs. It is appreciated.

I probably should be writing more often.

I get lots of requests for more posts, and I’ve got a lot of ideas to share, but have been so busy.

I’ll try to post more often.

Thanks.

Doug.

I agree the little details are important. That is exactly why more pixels are needed. Without more pixels, you can’t see the details.

Taking the example that you gave, if you had a person captured with 32 pixels, this would be about 9 pixels tall and 3-4 pixels wide. With only 3-4 pixels wide, you aren’t going to clearly see their arms or legs.

When you look at the distant person in the image, in the middle of the scene, as I said, it was about the 33 pixels tall by maybe 10 pixels wide. You can then see the legs and arms moving, which enables a high quality recognition of this object as a person.

If someone wants to look at pictures or video to recognize who a person is in the picture or to read a license plate, you need a lot more pixels. The general rule is that you need about 50 pixels per foot. That would make a 5.5 foot tall person 275 pixels tall. That’s twice as tall as the closest people in the picture above. If you were using CIF resolution, it would take up the full image, meaning that the camera would have to be looking exactly them, since you wouldn’t be able to see anything else in the scene but one person.

That’s why higher resolution is so valuable for recognition.

Thanks.

Doug.