Similar to my post #3 in this thread, here is another example of the Dahua AI.
I will preface this with this camera is dialed in to this location for when the flood lights come on, so that is why the picture is so dark. One of the big issues people do not account for is what happens when a floodlight comes in - if the camera is on auto/default settings, the image will look ok when the floodlights are off, but then the camera gets temporarily blinded when the floodlights turn on. So the best option is to dial it in for when the floodlight is on knowing that they will kick on and you will get a great capture once they do.
So I have several IVS tripwires on this camera instead of an intrusion because this camera also acts as a spotter cam for my PTZ and I only wanted to spot it of people heading towards and not away. Obviously at the street, this camera is not being used for IDENTIFY purposes.
Here is a middle of the night capture (the red and blue lines are the IVS rules and when it triggered). My non AI cameras totally missed this event, including my overview when this person was in front of my house and was lit better from the lights off my house. The middle of the night, 50+ feet away from the overview cams, and dark clothing got right past the BI motion that I have fairly sensitive. So since BI motion didn't pick it up, obviously neither did DeepStack. In playback tuning, DeepStack dark model did pick it up, but we all know that tuning and live DS are two different things at the moment.
One of the many reasons why we have redundant cameras, record 24/7, and utilize different methods of motion detection.