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

[GentlePumpkin]

New update for AITool;

bi-aidetection/src/UI/Installer at master · VorlonCD/bi-aidetection

Alarm system for Blue Iris based on Artificial Intelligence. - VorlonCD/bi-aidetection

github.com

Thank you, I finally updated the first post here to reflect the changes since VorlonCD invested so much effort developing AI Tool. The Download Link for the latest version can now be found there, and more prominently than before.

 

[GentlePumpkin]

Regarding Flagging clips using a trigger url and flagalert=x

http://localip/admin?camera=[cam]&flagalert=[x]&memo=[y]&user=[user]&pw=[pw]&flagclip

I figured there is a number of values for flagalert=x that place several different flags, for reference:

1 = flag
2 = green hook
3 = flag + green checkmark
4 = person
5 = flag + person
6 = person + green checkmark
7 = person + green checkmark + flag
8 = auto + cancelled
9 = car + flag
10 = car + green checkmark
11 = car + flag + green checkmark
12 = car + person + cancelled
13 = car + person + flag
14 = car + person + green checkmark
15 = car + person + green checkmark + flag
16 = cancelled

View attachment 143307

 

[Pentagano]

Would like to upgrade my cheap basic motherboard to support my gtx970 fully as I believe it's only using half of the lanes.
Would the gpu work faster with an upgraded board using all 16?

Could do with more sata ports also for extra drives on my truenas.

ASrock B550 or X570 possibly. X570 looks like a decent option with 2 x PCI Exporess slots, 8 sata connectors and 2 x M.2ockets.

Any other recommendations?

 

[Pentagano]

Another question

In regards to size of prediction -I want to customize the size of objects like you can in Frigate.

I am sometimes picking up humans as cats or dogs (very large!).
How can I reduce the size limit of the detection of a cat or dog in relation to the image?
I knew how to do it for Frigate in the yaml but not sure how to do this in the AITool options.
Could be under the camera settings: Limit Size Percentage?
For example a human was detected as a Dog in the prediction details : PercentOfImage = 1.9%
In the setting above I have max 95%. Would I change this to max x% maybe 1%



Thanks

 

[Chris Dodge]

Would like to upgrade my cheap basic motherboard to support my gtx970 fully as I believe it's only using half of the lanes.
Would the gpu work faster with an upgraded board using all 16?

Could do with more sata ports also for extra drives on my truenas.

ASrock B550 or X570 possibly. X570 looks like a decent option with 2 x PCI Exporess slots, 8 sata connectors and 2 x M.2ockets.

Any other recommendations?

View attachment 166014

Find the motherboard manual/pdf - Some slots dont support full x16 speed. It will tell you which do and dont. Typically slot 1 is the fastest and is assumed the video card will be there. And sometimes a slot speed will be reduced depending on what other devices you have plugged in (sata, nvme, etc). I disable sata on my motherboard to get better speed in one slot.

 

[Chris Dodge]

Another question

In regards to size of prediction -I want to customize the size of objects like you can in Frigate.

I am sometimes picking up humans as cats or dogs (very large!).
How can I reduce the size limit of the detection of a cat or dog in relation to the image?
I knew how to do it for Frigate in the yaml but not sure how to do this in the AITool options.
Could be under the camera settings: Limit Size Percentage?
For example a human was detected as a Dog in the prediction details : PercentOfImage = 1.9%
In the setting above I have max 95%. Would I change this to max x% maybe 1%

View attachment 166017

Thanks

Yes thats the right spot to change the min size for a specific animal. Be aware it can be highly dependent on how far away the object is. If you have a camera that sees both near and far it may mess with detecting farther objects if you set that higher.

Maybe look at the "PercentSizeStats" column for a better estimate of what you should limit it to.

I wanted to know when dis fucking groundhog was munching on me flowers and he was often detected as a squirrel so I set it higher so I would only get really fat squirrels

 

[Pentagano]

I've always had doubts about these 2 settings on the AI tool.
Do we have documentation anywhere or can someone explain please?
Also the Cooldown seconds?
Many thanks

 

[HillSonMX]

Hi everyone, back here, just having some issues with AITOOLS not receiving telegram cams screenshot, I already upgrade version hoping this work again but still not working......here are some pictures waiting for help from your, my community. Good weekend !!

Telegram and AITools Logs

 

[Pentagano]

Hi everyone, back here, just having some issues with AITOOLS not receiving telegram cams screenshot, I already upgrade version hoping this work again but still not working......here are some pictures waiting for help from your, my community. Good weekend !!

Telegram and AITools Logs

Says you are using the same bot somewhere. You need a unique one for AItools. This happened to me a while back.

 

[barnyard]

Hey guys, my setup has been in a box for over a year and a half, but was working fine before the move. I'm trying to get it set up in the new place. Detection and everything appears to be working fine, but telegram notifications aren't working. I deleted my bot, and created a new one, but still nothing. Any ideas on how to troubleshoot?

edit I updated to the latest version of AIToo, and it's working again!

 

[nirt00]

HI, I am trying to add a Camara to new installation of AItool. every time it crashes when I choose camara.
I installed it via the AIToolSetup.2.5.44.EXE.

 

[Pentagano]

Is this still maintained? Anyone still using it?
Been a while since I last used it. See the last version was 8 months ago.
Or with the advancements and development of BI and CPAI most have stopped using it?
Some of the finer adjustments were useful

 

[cscoppa]

Is this still maintained? Anyone still using it?
Been a while since I last used it. See the last version was 8 months ago.
Or with the advancements and development of BI and CPAI most have stopped using it?
Some of the finer adjustments were useful

Between what you can do in Blue Iris and the settings of CodeProject's AI server, you can pretty much do everything and this isn't needed.

Some good info: Blue Iris Webcam Software - CodeProject.AI Server v2.5.0

 

[robpur]

Is this still maintained? Anyone still using it?
Been a while since I last used it. See the last version was 8 months ago.
Or with the advancements and development of BI and CPAI most have stopped using it?
Some of the finer adjustments were useful

I still use AI Tool. I tried the AI built into BI, but I came back to AI Tool for two primary reasons. AI Tool allows the use of multiple AI servers so it can spread the workload across multiple machines for speed and redundancy. But more importantly when using AI Tool along with BI you have separate motion and AI masks. I find this feature useful for a few of my cameras.

 

[Pentagano]

I still use AI Tool. I tried the AI built into BI, but I came back to AI Tool for two primary reasons. AI Tool allows the use of multiple AI servers so it can spread the workload across multiple machines for speed and redundancy. But more importantly when using AI Tool along with BI you have separate motion and AI masks. I find this feature useful for a few of my cameras.

Great - that's why I was considering going back to it for redunancy and the extra stationary object function was very useful.
So still all working fine I see.
Is the developer still maintaining it do you know?

 

[Pentagano]

I still use AI Tool. I tried the AI built into BI, but I came back to AI Tool for two primary reasons. AI Tool allows the use of multiple AI servers so it can spread the workload across multiple machines for speed and redundancy. But more importantly when using AI Tool along with BI you have separate motion and AI masks. I find this feature useful for a few of my cameras.

What set up in the tool did you use to have a 2nd server of codeproject/deepstack to only use if the 1st option fails?
I've used several different services with different ports to work together on the same server but not before in the tool to failover to another url/port if the 1st one fails.

Thanks

 

[Chris Dodge]

Great - that's why I was considering going back to it for redunancy and the extra stationary object function was very useful.
So still all working fine I see.
Is the developer still maintaining it do you know?

I've made few changes in the last couple weeks to make working with redundant servers a little more reliable and fewer errors. Will try to release an update in a few days. I still personally use it because its more powerful and flexible compared to built in BI functionality. FYI you mentioned Deepstack, but you should really be using this as a replacement for deepstack: CodeProject.AI Server: AI the easy way.

 

[Pentagano]

I've made few changes in the last couple weeks to make working with redundant servers a little more reliable and fewer errors. Will try to release an update in a few days. I still personally use it because its more powerful and flexible compared to built in BI functionality. FYI you mentioned Deepstack, but you should really be using this as a replacement for deepstack: CodeProject.AI Server: AI the easy way.

Yes been using CPAI for a good while now - got rid of DS - thanks!

 

[Chris Dodge]

What set up in the tool did you use to have a 2nd server of codeproject/deepstack to only use if the 1st option fails?

I think in general it should use all the servers if needed in any case, but:

Settings > Queued:
On = All URL's will take a turn processing the images if not busy or offline.
Off = The original order is used. So for example the second one in the list will only be used if the first one is busy or is offline.

I'd also like to point out the latest version of CPAI has a "mesh" feature. I havent used it yet, but in theory that could do kind of the same thing AITOOL is doing. IE you only point to one server and IT connects to the other servers when needed.

 

[Pentagano]

I think in general it should use all the servers if needed in any case, but:

Settings > Queued:
On = All URL's will take a turn processing the images if not busy or offline.
Off = The original order is used. So for example the second one in the list will only be used if the first one is busy or is offline.

I'd also like to point out the latest version of CPAI has a "mesh" feature. I havent used it yet, but in theory that could do kind of the same thing AITOOL is doing. IE you only point to one server and IT connects to the other servers when needed.

ok thanks - got my CPAI running as a docker container on my NAS server (unraid) as this has the gpu.
Blueiris on a VM on proxmox.

If the NAS goes down for whatever reason then obviously have no connection. I have codeproject on the proxmox also as a proxmox lxc as a backup. Had to swap it over a couple of times.
Slower processing time on the intel but still better than nothing. Was thinking of using the lxc as the backup.