Upgrading parts in Blue Iris PC

[Virga]

When I needed a PC for Blue Iris in early 2023, I re-purposed an older PC I had laying around. Since then, I added three WD purple drives to it.

The BI PC is a 2015/2016 build with an i5 6500 3.2 GHz (sixth gen) CPU, Z170 mini-ITX motherboard, 16 GB of DDR 3000 memory, a GTX960 video card, and Windows 10. This ITX case can contain three full size drives, and two 2.5” drives, not counting M.2 drives on the motherboard. Plan is to keep this case as the BI PC and upgrade components as needed.

I have got cameras, Blue Iris, remote access, and notification working. Now am thinking of getting into AI, a good reason to see if I should upgrade some PC hardware. At some point would have to upgrade hardware for Windows 11.

As a minimal upgrade, for $135 I can replace the motherboard with a Z690 2-NIC mobo, $300 will get me an i5-14600K CPU (a little lesser if I drop the “K” version), and these will enable the existing license to install Windows 11. For another $72 could replace the memory with 32 GB of DDR4 4000 memory. All other at-hand components could move over from the existing build.

Request opinions and input.

 

[wittaj]

Why not try running AI and see if the system chokes first?

Do you have cameras with built-in AI - that might be more than adequate for your needs?

If you aren't using the computer for anything other than BI, then who cares if it is running Win10. It is still more secure than an NVR.

 

[Virga]

@wittaj My cams are mostly Dahuas from your list of suggested cameras, and a couple of Hik's.
Sounds like I should get to know better the capabilities of my cameras.
Thanks for the suggestions.
Also - you are a great resource for this forum, thank you for all your posts and responses which are always very helpful.

 

[wittaj]

In that case you may find that the camera AI has got so good that doing camera AI and then BI AI is kinda overkill and adds more complexity, time delay, and potential for issues.

Whether you use the camera AI or BI motion and then send to BI AI, there are scenarios in each situation that could cause the BI AI to miss it, in particular if the camera AI was slow to react, by the time BI AI gets a snapshot, the object may be out of view. People still have plenty of BI AI that shows up as nothing detected.

Whether to use camera AI or BI AI is obviously up to you, but of course, the AI in the camera may be more than sufficient for your needs without needing BI AI. Do you need the orange box around every object? Do you want to identify animals or logos? Or is just human or vehicle sufficient.

The camera AI is useful to many people, but BI has way more motion setting granularity than the cameras, and some people need that additional detail, especially if wanting AI for more than a car or person. For folks that want AI and alerts on animals or specifically a UPS truck then they need the additional AI.

There isn't really a best practice because every field of view is different and use case and needs are different.

To many here, BI motion without AI is more than adequate for what they do.

To many here, camera AI is more than adequate for what they do.

To many here, using the BI AI adds additional functionality that the above alone can not do.

It comes down to testing with each field of view and which one gives you the most consistent results.


While some of that third party stuff is cool like tagging was it a dog or a bear, I don't need all that fancy stuff. If my camera triggers BI to tag an alert for human or vehicle and BI can accomplish what I need by way of a text or email or push or whatever, that is sufficient for my needs. I just want to be alerted if a person or vehicle is on my property and the camera AI does a fine job with that.

However, I do run BI AI on a few cameras so that it knocks out headlight shine so that the alert image includes the vehicle. The camera AI will trigger for a car, but the alert image was always just the headlights. I also run the ANPR AI module.

The true test....I have found the AI of the cameras to work even in a freakin blizzard....imagine how much the CPU would be maxing out sending all the snow pictures for analysis to CodeProject LOL. My non-AI cams in BI were triggering all night. This picture was ran through Deepstack (without the IVS or red lines on it) and it failed to recognize a person in the picture, but the camera AI did. This pic says it all and the video had the red box over it even in complete white out on the screen:

See this thread on how using just Dahua AI may be sufficient for your needs:

Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?


If you decide to go with the camera AI, then set up the IVS rules within the camera and let it do its thing!

Go into the camera and set up smart plan with IVS, then go to the IVS screen and draw IVS rules (tripwire or intrusion box) and then select the AI you want it to trigger on (human or vehicle).

Then in BI, there are a few places you need to set this up in BI (assuming you already set up the IVS rules in the camera GUI):

In Camera configure setting check the box "Get ONVIF triggers".

Hit Find/Inspect on the camera setting to pull the coding for the triggers.

Go into Motion Setting and select the "Cameras digital input" or "ONVIF triggers" box (depending on your BI version).

On the Alerts tab uncheck the Motions Zones tab (those are alerting you to any BI motion in those areas in Zones A thru H)

On the alerts tab set up how to be notified.

 

[Virga]

$226.95 plus sales tax, shipping included, got me a 12th gen CPU ($126.49 for new i5-12,600K, $100.46 for new LGA1700 socket Z690 motherboard with two NICs).
The items were sitting in my cart; when I dropped, by a "combo" discount of $10 had become $78, and that did it. Minor assembly required of course.

Addendum:
Am following @wittaj suggestions above and trying BI and camera features for now.
The reason for this post is to note that once in a while with the right buying opportunity PC hardware upgrades can be made efficiently.

 

[Skispcs]

Experiment with AI with what you have first.
If you really like it, I would suggest getting a GTX 1650 or 1660 GPU and run that AI on that.
The 1650 and 1660 are best tradeoff on power usage versus CUDA ability in my opinion.

Using substreams and direct to disc are two settings you want to use to cut down on CPU util.

I am running 16 cameras on a I7 4790K with AI running on the GTX 1650 and my cpu usages is typically about 25%.
I am running two linux VMs at the same time on that computer as well.

 

[Virga]

Swapped CPU and motherboard in Blue Iris PC a couple of days ago, and updated existing Windows 10 Pro license to Windows 11 Pro.
CPU dropped to 0%-1% from 30% and higher,
GPU (no physical change) dropped to 0%-1% from 15%-20% and now sometimes the GPU % does not even show at the bottom of BI screen. Could be that BI is using the GPU in the CPU, because I don't recall telling it otherwise (yet).
RAM is now 900M-plus, used to be plus/minus 800M (physical memory is 16 GB).
… CPU now is i5-12600K, used to be i5-6500.
Relative to the time and $’s in cameras and infrastructure, not bad for $227.
From inception have used direct-to-disk recording, substreams, and 15 FPS, probably could do more as I learn more.

Setting up BI over is a good exercise.
It helped having exported BI settings from the original install, and importing them into the new install.
Still, there are other related setup things to be done on a new PC, some of which I had kept notes on, some I missed and am re-discovering.
Now back to using more features of Blue Iris.