[tool] [tutorial] Free AI Person Detection for Blue Iris
- Thread starter GentlePumpkin
- Start date
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:
astroshare
Young grasshopper
Do you mind sharing your trigger URL?
This is the one I use.
Code:
http://127.0.0.1:81/admin?camera=[camera]&flagalert=3&memo=[summary]&user=[Username]&pw=[Password]&flagclipastroshare
Young grasshopper
Thank you! Is it necessary to enable Alerts in BI if I'm only using the Telegram notification directly from AITOOL?
astroshare
Young grasshopper
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).
astroshare
Young grasshopper
Yup, that did it. Thanks!
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.
astroshare
Young grasshopper
Yes, it's the BI IP/Port
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;
spammenotinoz
Pulling my weight
Hi Tinbum, thanks for this I can confirm this version is working and I did not detect any malicious activity. (For others doesn't mean this is safe)
As it's not the version referenced in the Official Manual or Doco, do you have any background on where this version came from?
I do note a bug, where Mode = Low performs better than omitting the mode or putting Mode = High, other than that the Windows GPU performance is good.
I am using an old GTX 745 with no display connected (although this overclocks very high, just running stock) ~66ms to process 180x720 resolution images, compared to 300ms with an i7-6700.
Using on-board graphics for the display, to avoid conflicting with BI QuickSync.
by perform better, do you mean it has a faster response time?
omitting the mode likely defaults to the medium accuracy setting. I think 'low' (accuracy) should be fastest, followed by default, and then high (accuracy).
spammenotinoz
Pulling my weight
Yes, by better I meant faster.
Thankyou for clarifying what mode meant, I incorrectly believed it was performance not accuracy.
GPU bursts to 2% usage, so will try your multi-deepstack instance suggestion.
It's official Deepstack, that's not a bug it will be faster in low.
Last edited:
Still having major issues on the person identification side. Constantly missing things as obvious as this.
Cool down period was not an issue (it picked up the person walking up on my driveway camera, but clicked only 2 pics in 4 minutes for this food delivery guy, and both times picked up the potted plants only.
Also the driveway cam while it caught the person walking from his car towards my door, didn't capture him when he left the door and went back to his car a few minutes later, I assume that's more of a BI settings issue, though not sure why it captures the person on the way in but not the way out?
Cool down period was not an issue (it picked up the person walking up on my driveway camera, but clicked only 2 pics in 4 minutes for this food delivery guy, and both times picked up the potted plants only.
Also the driveway cam while it caught the person walking from his car towards my door, didn't capture him when he left the door and went back to his car a few minutes later, I assume that's more of a BI settings issue, though not sure why it captures the person on the way in but not the way out?
When using the latest VorlonCD / bi-aidetection
In the log sometimes I see:
"Could not trigger URL xx.xx.xx.xx"
It looks like this only happens when it is already triggered. Am I correct in assuming it will throw this error while it is already triggered or should I look further into what is happening in my system?
In the log sometimes I see:
"Could not trigger URL xx.xx.xx.xx"
It looks like this only happens when it is already triggered. Am I correct in assuming it will throw this error while it is already triggered or should I look further into what is happening in my system?
Anyone that is running the 2020.12 beta of deepstack, any clue what this is causing the below error? this is what is coming of in the stderr.txt file ( I am running the CPU version)
Here is the error:
Process Process-1:
Traceback (most recent call last):
File "D:\obj\windows-release\37amd64_Release\msi_python\zip_amd64\process.py", line 297, in _bootstrap
File "D:\obj\windows-release\37amd64_Release\msi_python\zip_amd64\process.py", line 99, in run
File "C:\DeepStack\intelligencelayer\shared\detection.py", line 138, in objectdetection
os.remove(img_path)
FileNotFoundError: [WinError 2] The system cannot find the file specified: 'C:\\Users\\baluc\\AppData\\Local\\Temp\\DeepStack\\f28c9002-abb6-4e2e-a531-e7aa45b48e81'
Here is the error:
Process Process-1:
Traceback (most recent call last):
File "D:\obj\windows-release\37amd64_Release\msi_python\zip_amd64\process.py", line 297, in _bootstrap
File "D:\obj\windows-release\37amd64_Release\msi_python\zip_amd64\process.py", line 99, in run
File "C:\DeepStack\intelligencelayer\shared\detection.py", line 138, in objectdetection
os.remove(img_path)
FileNotFoundError: [WinError 2] The system cannot find the file specified: 'C:\\Users\\baluc\\AppData\\Local\\Temp\\DeepStack\\f28c9002-abb6-4e2e-a531-e7aa45b48e81'