Can someone tell me that these two blue dots with yellow outlines mean in the AI window? I am not getting an MQTT message here on this alert, but it seems to be reading the plate.
When I get a green check mark-- (second picture) I get the message....
Man, you have the world's most useless cat. It just watched that raccoon stroll into your house....
If you catch in the cage, just submerge the cage in a river or tub.
In Massachsetts the environmental police would make you keep it there since it is "natural"....
I have something similar near me. How do you saw underwater?
So not sure if I should post this in ALPR or AI. Figured here would be better.
I am detecting cars passing and reading their plates. I am also using zones to determine direction.
I have Zone A cover the whole area for detection. I was using zones B and C split down the middle. I'd trigger...
My understanding in the slow ALPR won't really matter-- it will just queue up the data and take longer....
What is interesting to me is that at T0 you get a hit on the BVR but on the AI history T0 was a miss for you....
Are you sending the substream to AI by change? Post your AI setting....
Ok... spoke to Ken-- I unclicked the "highlight motion rectangles" in the AI box and it went away! Seems obvious in hindsight-- but LOADS of options with BI.
So I am getting some poor AI detection despite having some pretty damn crisp photos of some plates. This first picture- a plate when by and it was missed. If you look at the Alert AI-- the image is in yellow and it doesn't get read.
Picture 2 is the same frame paused.. The AI is able to read...
Ok, so I opened up the zone detection window after looking through everything else and those zones were GONE. It went back to two zones that I had a LONG time ago. I set up a Zone A which is the whole field of view. Then Zone B is a box on the left and C is on the right. I use this to...
So I reset BI and the Camera and suddenly my "cancelled" alerts show up.
Interesting here that this bus image fails but the image shown clearly has some artifacts.. If I pause BI on that frame, the plate reads just fine. I don't see ANY artifacts on the playback.
Same with this SUV. Feel...
I too had a triggering issue and dropped from 30 FPS to 10 and now 20.
The issue here though is that I am triggering and just not reading the plates....
I did look closer at my AI debug log in BI and it says that my round trip analysis times are 250ms going to my Linux server....
At 50ms a...
I copied yours about an hour ago to make mine identical.
It made matter much worse. I captured one plate out of ten... which is actually good. Fixing more intermittent problems is a PITA.
Here is a video (#2) and Blue Iris highlights the plate when I pause it while playing back. (#1)
The...
Mike..
Attached and also see post #9 for sub menus...
5 seconds after the trigger.... Maybe that is too long? Wouldn't that just mean more processing?
Thanks again guys....
Looks like mine that get a "hit" go backwards too.
I guess I am getting a hit BEFORE the trigger. Mine are showing every 50 MS then going backwards.... to 200 ms, then looks like many are not printing.... Not quite sure where the ones in the 100ms range are?
I assume that is because it...
I wonder if in some cases my trigger is too late...
Since I have my pre-trigger set up, I wonder if it would be possible to have Ken either start the AI process with frames that happened BEFORE the trigger by some configurable amount.. Or maybe search through them if it didn't get a hit. The...
So the video I posed initially shows a cancelled alert. I NEVER get more than ONE of these even on a good capture that reports the plate..
ie. Mine looks nothing like yours...
Gravity might have pulled it down a tad. Good catch. I’ll muck with that tomorrow.
Here are my motion settings. Zone A is basically the road minus those bushes in front. Zone b is left and zone c is ten pixels to the right or so. Tells me direction.
Ok. So I am still missing them some.
This one here, the image on the clips doesn’t show anything.
I am wondering if the trigger is too late in some cases.
Maybe I should zoom out.
So I am getting great shots of cars coming up the road. This is an Amazon truck with clear plates that it somehow missed.
Weirdly: I am playing back this video with AI debugging and in the right window it shows the plate, but on the left window I don't see it in the log on the left. It shows...
So is there an optimal size image to send to Codeproject.AI from Blue Iris for those of us with TPUs? Maybe one or two/
Thanks for the explanation on the multiple TPUs. Makes sense.
I am running 2.5 RC 9 on my Windows box now. I have a Dual TPU and a relative old Xeon that has Intel decoding....
The Coral object detection is pretty good. I am sending a picture from the Explorer and the inference time is 60ms (processing 161.. analysis 406)...
By comparison, on my other...
Actually, I just did something similar to what you did-- but I think I made it easier...
12[5S] ?76[5S]
where the pairs [5S] are things it can confuse (Ses and 5s)... and the " ?" means zero or one space... I did the same for [B8] and [71] etc....
I'll let you know how it goes...