Blue Iris Version 6.0.1.24 Now Supports Custom Models

[Vettester]

Newbie question here....Why is nothing showing in my AI Inspector window?

While holding down the control key double click on an alert. Alternatively you can drag and drop .dat files from your "new" directory in windows explorer onto the analysis pane (lower right).

 

[Vettester]

So how is it going on your demo machine?
Have the occupied detections stopped?
Do you believe that cleaning up that registry key made the difference, or was it something else?
I tried a number of things, with no improvement so far.
Thanks

I still think this is by design. I've got almost 350 "occupied" canceled alerts today and every one of them has something in them that AI picked up. However, none of them contain anything I have defined in the AI "To confirm" field.

 

[Vettester]

I asked ChatGPT "What causes a canceled alert in blue iris to be occupied?"

Here's the response...

In Blue Iris, “Canceled (occupied)” on an alert basically means:

Blue Iris wanted to create or process an alert, but the camera/alert pipeline was already busy doing something else.

Here are the most common reasons it happens, in plain terms

---

The main causes​

1. Camera is already handling another alert​

If motion triggers happen back-to-back (or overlap), Blue Iris may cancel the newer alert because:

• The camera is still recording
• The previous alert hasn’t finished its post-trigger time
• The alert list/AI analysis queue is still busy

This is very common with:

• High-motion scenes
• Short alert cooldowns
• AI + motion triggers combined

---

2. AI analysis (DeepStack / CodeProject.AI) is overloaded​

If you’re using AI:

• The AI server can only process so many images at once
• When it’s backed up, Blue Iris marks new alerts as occupied and cancels them

Signs:

• CPU/GPU spikes
• Alerts firing but no confirmations
• Lots of “canceled (occupied)” during busy periods

---

3. Alert cooldown or “cancel duplicates” settings​

Some alert settings intentionally suppress alerts:

• “Cancel duplicates”
• Alert cooldown timers
• Break time between alerts

If motion happens again too soon, BI may cancel it as occupied instead of creating a new alert.

---

4. Continuous recording + alerts competing​

If the camera is set to:

• Continuous recording and
• Alerts with snapshots, AI, or push notifications

…Blue Iris may prioritize recording and cancel alerts when resources are tight.

---

5. System performance limits​

When the system is near its limits:

• CPU maxed out
• Disk I/O bottleneck
• RAM pressure

Blue Iris starts dropping lower-priority alert tasks → shows as occupied.

---

How to reduce or eliminate it​

Try a mix of these (you usually don’t need all):

Alert tuning​

• Increase minimum time between alerts
• Disable cancel duplicates only if you truly need every alert
• Increase post-trigger recording time so alerts don’t stack

Motion tuning​

• Reduce false motion (trees, shadows, reflections)
• Use zones and minimum object size
• Lower frame rate for motion detection

AI optimization​

• Limit how often AI runs (e.g., once every X seconds)
• Reduce snapshot resolution sent to AI
• Make sure CodeProject.AI / DeepStack isn’t CPU-starved

System tweaks​

• Move DB to an SSD
• Lower camera FPS or resolution
• Enable hardware acceleration (Quick Sync / NVENC)

---

When it’s not a problem​

If:

• You’re still getting alerts for real events
• The canceled ones are duplicates or near-simultaneous motion

…then “Canceled (occupied)” is normal and expected behavior, not an error.

---

 

[Tinman]

so maybe the "max connects" could come into play. On my setup it's not uncommon for 4 to 5 cams firing almost the same time when I car drives around house. I had mine set to 4, but it was at 32. I'll try bumping it up again and test tonight. All of my occupied alerts are cars, and I have cars in confirmed box. The saga continues

 

[Vettester]

The saga continues

Yes, it's quite the rabbit hole. I've spent the last 30 minutes responding to ChatGPT questions.
The conclusion so far is:

If you want this almost gone​

Your best options (ranked):

1. Tight motion zones + 1.0s object duration
2. Alert break time ≥15s
3. Day/Night profiles
4. P-core affinity
5. GPU-based AI (NVIDIA or CodeProject AI)