[tool] [tutorial] Free AI Person Detection for Blue Iris

What a bummer memo doesn't work with flag. With the flag setup you set primary as HD and sub feed as SD?
 
ManImCool said:
Is there any way to tweak settings so that AI Tool is more likely to trigger BI? My tolerances are already 0-100% on AI Tool, yet there are plenty of images it scans where a person is in the picture but it fails to see the person and incorrectly calls it a false alert.
Click to expand...

I've been messing with Coral USB Accelerator to process every single frame. I've bumped my confidence to > 40%. Sure, it will miss persons in some frames, but in the end it will always have identified it in one of the others... Will share here once it's ready for prime time.
 
Anyone have issue with HD play back? Most the files I try to play back from All clips I get error stating "Sorry, the file could not be found". The clip is 00 secs. Not sure if its incorrect setting or a bug.
 
I was one of the initial testers, couldn't get it working too great on Windows. It would work for a while then completely bomb out and stop processing for a few hours. Decided to give docker version of Deepquest a shot - wow! It's running really well now, especially with GentlePumpkin improving the AI Tool.
Using version 1.65, sending alerts to my Alexa devices via notifyme when someone is detected at the front door, no more senseless recording either of car headlights either. Cool!

@GentlePumpkin Face detection could be quite nice in certain instances, such as for automation. Example, turning on the hallway lights automatically when a known member of the family is home. I've got a 4K camera at the front door - how much of a processing delay is there?

I had a question as well - When AI Tool is running as a service, is there a 'proper' way to view stats? I generally like to babysit the tool for a while to gauge how well it works and tweak masks etc to make it work better. The AI itself seems to be a lot more accurate than when I initially tried this out.
 
Forid200 said:
I was one of the initial testers, couldn't get it working too great on Windows. It would work for a while then completely bomb out and stop processing for a few hours. Decided to give docker version of Deepquest a shot - wow! It's running really well now, especially with GentlePumpkin improving the AI Tool.
Using version 1.65, sending alerts to my Alexa devices via notifyme when someone is detected at the front door, no more senseless recording either of car headlights either. Cool!

@GentlePumpkin Face detection could be quite nice in certain instances, such as for automation. Example, turning on the hallway lights automatically when a known member of the family is home. I've got a 4K camera at the front door - how much of a processing delay is there?

I had a question as well - When AI Tool is running as a service, is there a 'proper' way to view stats? I generally like to babysit the tool for a while to gauge how well it works and tweak masks etc to make it work better. The AI itself seems to be a lot more accurate than when I initially tried this out.
Click to expand...

It's great to hear such improvement :D
Regarding the face recognition: Today made a test setup and experimented with it, but even though you can teach Deepstack with multiple sample images for a person, the detection rate remains very low. I used high quality images where the face alone covers an area of p.e. 1000x600px and the results still lacked reliability entirely. I pushed the test setup with one additional Faces tab in AI Tool to github in the branch gp-face, so everyone is free to try it. Currently, I don't see how this could work reliably.

Regarding viewing stats: The stats raw data is stored in the history.csv located in the cameras subfolder. But there is no comfortable way to review them when you can't access the interface of AI Tool.
 
  • Like
Reactions: Judman and Forid200
naidu said:
How does blueiris setup differ from what in this video:

Click to expand...


It's way simpler! I'll explain it in detail later. Meanwhile, you can still use the duplicate camera setup if you prefer that. I always try to update AI Tool in a way so that you can stick with a specific setup if you prefer it. Sometimes it's not possible, but I always invest alot of time trying to.
 
  • Like
Reactions: seth-feinberg and Judman
GentlePumpkin said:
It's way simpler! I'll explain it in detail later. Meanwhile, you can still use the duplicate camera setup if you prefer that. I always try to update AI Tool in a way so that you can stick with a specific setup if you prefer it. Sometimes it's not possible, but I always invest alot of time trying to.
Click to expand...

For some reason my HD recording are missing on trigger.

1591894129640.png

I wonder using other method will fix the issue.
 
Hi @GentlePumkin. Awesome Application. worked for me with 8 Camera right from the get go and almost 96% hits. The only issue I got so far was that as per my BlueIris setting I delete all my JPEGS from the AIINPUT folder when it reaches 1 GB. I wasn't anticipating hitting this anytime soon but I have 2 kids who decided to have play in the backyard for a couple of hours and yes I had a TON of pictures captured on the folder and the AI application caught all of them.

Now as soon as the 1GB Limit hit the folder files were deleted and when I clicked on the AI Tool --> History tab and clicked one of the alerts the application crashed.

Not a biggy but I had to restart it again and it was all good but since a new release is planned wanted to let you know
 
usually AI Tool automatically deletes entrys for images that were deleted during runtime. And starting takes a few seconds with a large history because AI Tool is checking if all entries are still valid. Your problem though indicates that there might be something wrong with the code that monitors the input folder.
 
  • Like
Reactions: Judman
GentlePumpkin said:
usually AI Tool automatically deletes entrys for images that were deleted during runtime. And starting takes a few seconds with a large history because AI Tool is checking if all entries are still valid. Your problem though indicates that there might be something wrong with the code that monitors the input folder.
Click to expand...

is there a setting i need to check for this?
 
GentlePumpkin said:
I tried the face recognition feature. I guess most people would like to use this to get information like "person xy is home" or to block alerts when a known person is detected. Generally a good idea I had in mind too, but I think it would undermine the reliability as p.e. anyone could just print your face and wear it. Additionally and probably most importantly, the face recognition seldomly works if the face resolution is as low as it usually is on p.e. a 2MP camera. On higher res cameras this probably is a less important point. Third point is that face detection is significantly slower than usual object detection in my experience (can someone confirm that?).
Click to expand...
Thanks for the reply! And i am interested in it for all the reasons above as well as a couple more, like for technician recognition for access to restricted tools etc... (i own and operate an auto repair facility that is completely automated), not to mention the cool factor would be through the roof! LOL . I am running my automation system as well as security and surveillance on a dell 720 server with dual zeons and over 100 gb ram so i am a little better off than some in the power area and my 13 cameras are 2 mp 1920x1080 so they are border line. I certainly wouldn't want to cause reliability issues with the current software, it's rock solid here and works flawlessly. With that said I would be glad to beta test if you or anyone were so inclined to make this a feature that a person could switch on if their hardware and situation would allow reliable use. And turn off if not. Thank You again for your valuable time!
 
You must log in or register to reply here.
Top Bottom