I might be wrong, but I don't think you can modify it that way. The way I understand it, the confidence level adjustments mean that if DeepStack sends the image back with 40% dog or 40% cat detection, and you have the minimum level set to 50, then it won't alert. I don't believe you can adjust it by type of detection (dog, cat or person). I have this happen all the time also with my cat. She always gets picked up as dog or cow (since she is white with black spots), rarely as a cat.
[tool] [tutorial] Free AI Person Detection for Blue Iris
- Thread starter GentlePumpkin
- Start date
I have not been following this thread for the last 4 months. Has the algorithm for motion detection been improved (especially at night)? Or is it still exactly the same?
Well I can only speak for me and my set up- Never really had any daytime issues. Night is better than it was...but still problematic, There have been numerous other improvements however.
Anyone know how to get the cameras working on their side (portrait) whe you turn the image 90deg in BI it distorts the jpg snapshot and deep stack can’t really accurately detect.....
spammenotinoz
Getting comfortable
There is now a Windows NVIDIA GPU version of Deepstack AI
docs.deepstack.cc
To install and use DeepStack GPU version on your Windows machine, follow the steps below
>> Download GPU version for Windows
Note: Both the new CPU and GPU versions can be started from either Powershell or Windows Command-lines making them easy to start\automate.
Using DeepStack with Windows 10 (CPU and GPU)
docs.deepstack.cc
To install and use DeepStack GPU version on your Windows machine, follow the steps below
- Ensure your machine has an NVIDIA GPU
- Download and Install CUDA 10.1 from NVIDIA
- Download and Install cuDNN from NVIDIA
>> Download GPU version for Windows
Note: Both the new CPU and GPU versions can be started from either Powershell or Windows Command-lines making them easy to start\automate.
spammenotinoz
Getting comfortable
Seems it was intentional before 5.3.7.13. When I added "trigger" to the url (/admin?trigger&camera=) the clips would get flagged but then I had some other issues with clips being labeled as 0 secs.
I contacted BI support, explained how I have mine setup and they replied:
A day later I received:
This is the one I use.
Code:
http://127.0.0.1:81/admin?camera=[camera]&flagalert=3&memo=[summary]&user=[Username]&pw=[Password]&flagclipThat will flag and set it as a confirmed alert (S logo). If you just want to flag it then use flagalert=1. My alert settings are setup like this
Thank you! Is it necessary to enable Alerts in BI if I'm only using the Telegram notification directly from AITOOL?
Still getting 0 sec clips with the trigger URL below... Camera is recording only when triggered by Motion in BI. Clip gets flagged correctly though.
Cooldown time in AI TOOL camera setting is 0.25 minutes. No cancel URL.
Cooldown time in AI TOOL camera setting is 0.25 minutes. No cancel URL.
Code:
http://192.168.5.15:8181/admin?camera=backyard1&trigger&user=aiuser&pw=password&flagalert=3&memo=[detection]&flagclipTry removing the trigger part so that it looks like this:
Code:
http://192.168.5.15:8181/admin?camera=backyard1&user=aiuser&pw=password&flagalert=3&memo=[detection]&flagclipIt should be fine since Ai is doing all the notifications through telegram once it processes an image. I never tried unchecking everything since the main one I use is "Extern" that creates an alert when AI sends a trigger to BI (External).
Sorry for the stupid question but the IP/port in your trigger is pointing to what? is that you BI box or deepstack? I use [BlueIrisURL] in my trigger is why I am asking.
Please pardon my ignorance. I haven't looked through the entirety of the thread, but the last 50 pages or so. I've gotten everything setup with the latest release of the forked AI tool. Now I'm just wrapping my brain around how best to process images without too many alerts.
Going to use my driveway as an example and see if I've got this right. I'm using the single camera method, and record 24/7.
So if I'm correct I should:
1. Still use blue iris motion zones and masking to filer out unwanted motion tigger's. For example, cars coming down the road.
2. In AI tools, I should use dynamic masking so it doesn't flag my cars in the driveway when a motion trigger does occur. (I think that's what dynamic masking is for???? Stuff that's always there.)
3. Additionally, I should set a static mask in AI to prevent any AI detection at the road level. I've also set my minimum to 30% positive to filter out junk.
4. Then use AI for my notifications.
Sound about right?
Going to use my driveway as an example and see if I've got this right. I'm using the single camera method, and record 24/7.
So if I'm correct I should:
1. Still use blue iris motion zones and masking to filer out unwanted motion tigger's. For example, cars coming down the road.
2. In AI tools, I should use dynamic masking so it doesn't flag my cars in the driveway when a motion trigger does occur. (I think that's what dynamic masking is for???? Stuff that's always there.)
3. Additionally, I should set a static mask in AI to prevent any AI detection at the road level. I've also set my minimum to 30% positive to filter out junk.
4. Then use AI for my notifications.
Sound about right?
That version doesn't work use;