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

whoami ™

Pulling my weight
Joined
Aug 4, 2019
Messages
230
Reaction score
224
Location
South Florida
I'd appreciate it if someone that's confident they have their authentication setting dialed in could share a screen shots of their settings to effectively use the username / password configured URL so server isn't left unsecure on LAN.

Here's a example of what I have working.

3.PNG
 
Last edited:

seth-feinberg

Young grasshopper
Joined
Aug 28, 2020
Messages
87
Reaction score
15
Thanks @GreyTheOld ! That tutorial was based on The Hook Up video that I set things up with so I was close, but that tutorial still highlighted a few things that I had either missed or were new (like adding the substream to the HD camera setup, which coincidently ALSO helped me understand my Dual Stream vs Cloned cam confusion!).

However, I still feel like this step:
2020-11-20 14_46_04-Integrating with BlueIris · danecreekphotography_node-deepstackai-trigger ...png
and this step:
2020-11-20 14_46_16-Integrating with BlueIris · danecreekphotography_node-deepstackai-trigger ...png

seem to create "double instances" of each camera in BI each at a different resolution. But I've followed the guide twice (and clearly you did too) and if you say that's not cloning that good enough for me!

On another note, after firing up the latest version of AI Tool from Chris Dodge, I have an error in my Log: another instance is already running, is this common on upgrade? related to the custom service i set up for AI Tool from the first post?

edit: the hyperlinks I originally included seemed to cause some problems so I just attached some screenshots.
 

GreyTheOld

Young grasshopper
Joined
Oct 26, 2017
Messages
40
Reaction score
6
I'm not familiar enough to answer with confidence however my system is working at this moment however I'm struggling hard on telegram alerts.

The tutorial DOES clone and DOES USE DUAL STREAMS. I think that probably adding the second url to the HD cam is probably an attempt to save cpu but doesn't actually do anything. I PREFER this method because I like the granularity of being able to have cameras with different names and thus different triggers, plus not ALL my cams are dual-stream capable.

Re: Remote access authentication here's me:
1605925236495.png


1605925319961.png

For Trigger URL's, the [Camera] variable doesn't seem to work for me in any format of Long or sho
rt name of the camera, so I just hardcoded it in the URL:
 

Attachments

GreyTheOld

Young grasshopper
Joined
Oct 26, 2017
Messages
40
Reaction score
6
Reporting back that I got telegram working, I was using the wrong chat ID.
Steps:
Message @BotFather to make a bot. Name it whatever.
Send /token and get the Token
Then go to the telegram menu and make a new group chat, then add your @botname_bot to it
Then send at least one message. Doesn't matter what you send.
Now if you're lazy, copy your Token and go here: Get Telegram Chat ID - CodeSandbox
Paste your key, press go...It'll return the number, make sure it has a - in front.

In AiTool settings page, paste in your Token and chat ID in, then in the actions page on each individual camera make sure to check "send alert images to Telegram".

Fin!

Caveat: I'm getting a number of failed to send errors, but I think it's a frequency issue. All cameras are reliably sending images.
 

whoami ™

Pulling my weight
Joined
Aug 4, 2019
Messages
230
Reaction score
224
Location
South Florida
Is anyone else using POST when triggered instead of RECORD when triggered having a issue with Blue Iris not deleting jpegs once the folder reaches limit set in Clips & Archiving? Or is anyone successful maintaining folder size limit using that method?

Wondering if something was updated and changed in BI at some point so working for others but not me. Im still running 5.2.7.12 and it appears that BI isn't updating the db and keeping a eye on file size of AI_Input folder when using the post method.
 
Last edited:

Village Guy

Pulling my weight
Joined
May 6, 2020
Messages
291
Reaction score
161
Location
UK
Can't offer any real help but BI is up to 5.3.3.16 now so it is probably worth updating to see if it resolves the issue.
 
Joined
Nov 22, 2020
Messages
2
Reaction score
0
Location
UK
Trying to use this app. I have set up deepstack and can access the web page.

When I copy images into the folder listed in the input path the overview changes to processing and back to running but shows an error opening the log then reports

[22.11.2020, 21:19:11]: ERROR: Could not access image 'C:\Users\Kingdel\Pictures\camera\front2020-11-22_21-12-06_287.jpg'.

for each image and nothing in the processed history. Any ideas where I should be looking for this fault.
 

Vettester

Getting comfortable
Joined
Feb 5, 2017
Messages
740
Reaction score
693
Is anyone else using POST when triggered instead of RECORD
I'm on the latest version and tried using the post option for a few days and found that it created a lot more false alerts so I went back to using the record option.
 

ChrisX

Getting the hang of it
Joined
Nov 18, 2016
Messages
130
Reaction score
4
how can i use face recognition ? Its working with BI?
 

GreyTheOld

Young grasshopper
Joined
Oct 26, 2017
Messages
40
Reaction score
6
Currently running - Release 5.2.9.2 x64

Everything seems to be working fine except for the trigger. I can see the AITool sending the trigger to BlueIris but it doesn't start recording..
I can verify that the trigger within blue iris does work by right-clicking a camera and selecting Trigger Now.. which then shows a clip on the righthand side.
Ensure that recording is set to "on trigger" and alerts are set to "on trigger, external". You should be able to paste your trigger URL into a browser window and press enter, you should get a confirmation message in the browser if it's working. Feel free to paste screenshots of your trigger/record/alert settings, also your web server tabs if you can't get the confirmation message in the browser.
 
Joined
Nov 22, 2020
Messages
2
Reaction score
0
Location
UK
Trying to use this app. I have set up deepstack and can access the web page.

When I copy images into the folder listed in the input path the overview changes to processing and back to running but shows an error opening the log then reports

[22.11.2020, 21:19:11]: ERROR: Could not access image 'C:\Users\Kingdel\Pictures\camera\front2020-11-22_21-12-06_287.jpg'.

for each image and nothing in the processed history. Any ideas where I should be looking for this fault.

FIxed this.

It seems that there is a max image resolution. Not sure what the limit is but using 640 x 320 works every time.
 

Village Guy

Pulling my weight
Joined
May 6, 2020
Messages
291
Reaction score
161
Location
UK
FIxed this.

It seems that there is a max image resolution. Not sure what the limit is but using 640 x 320 works every time.
Not sure what you fixed. My images are 12 Mega pixels and are roughly 8 megabytes in size.
 

Jooced

n3wb
Joined
Jul 9, 2017
Messages
7
Reaction score
1
Location
California
Can anyone help me get the memo field working? I feel like I've tried everything and I have yet to see it work.

My trigger URLs:
Code:
http://192.168.x.x:x/admin?trigger&camera=Front&user=x&pw=x
http://192.168.x.x:x/admin?camera=Front&trigger&memo=[summary]&user=x&pw=x
Either one results in:
Code:
signal=green
profile=1
lock=0
camera=Front
In Alerts or Flagged I always see the thumbnail and:
Code:
Front
11/18/2020 6:41:33 PM
11 sec jpg H265
..never the memo. Any ideas what I'm doing wrong?
Is anyone able to offer help on the memo lines not working? All I ever see is this:
 

Attachments

seth-feinberg

Young grasshopper
Joined
Aug 28, 2020
Messages
87
Reaction score
15
The tutorial DOES clone and DOES USE DUAL STREAMS.
HAHA YES! thank gawd, that was bothering me so much and finally makes logical sense to me. How do most people on here do it? with the cloned low res streams and recording the hi res? Or just do everything on the HI res if computational/storage capacity isn't really a problem...
 

Netwalker

Getting the hang of it
Joined
Aug 8, 2017
Messages
46
Reaction score
28
HAHA YES! thank gawd, that was bothering me so much and finally makes logical sense to me. How do most people on here do it? with the cloned low res streams and recording the hi res? Or just do everything on the HI res if computational/storage capacity isn't really a problem...
After a few tries at different ways over the last months, I've settled on:

Using IVS detection on the cameras, limit decoding on the BI camera streams. Full res only, recording 24x7, all BI motion detection turned off.
When the Camera causes a motion alert, BI creates an event and saves an image to the AI_Input folder. *
AI_tool then sends it to deepstack for analysis and if it returns positive;
Ai_tool flags the event in BI &
Telegram sends me an alert with an image and the detected object outlined.

The only issue I have with this setup is that I almost feel guilty how little it uses BI. The positive is since BI isn't doing any motion detection, I have nearly nothing for an average CPU load with very close to perfect alerts (I actually haven't noticed anything that either should or shouldn't be in the alerts I'm getting from Telegram, but I'm sure it can't be perfect). Using the newest Deepstack (/deepquestai/deepstack:latest ) it's processing images in ~400ms on a dinosaur i5. Read this issue thread on how to update deepstack if you don't know: Future of DeepQuest and DeepStack? · Issue #65 · VorlonCD/bi-aidetection

* I tried having the cameras upload FTP images. I think that would be the best way, but there are a lot of small house keeping issues with it I don't have the time to fix. file permissions, cleaning directories, etc.
 
Last edited:

seth-feinberg

Young grasshopper
Joined
Aug 28, 2020
Messages
87
Reaction score
15
After a few tries at different ways over the last months, I've settled on:

Using IVS detection on the cameras, limit decoding on the BI camera streams. Full res only, recording 24x7, all BI motion detection turned off.
When the Camera causes a motion alert, BI creates an event and saves an image to the AI_Input folder. *
AI_tool then sends it to deepstack for analysis and if it returns positive;
Ai_tool flags the event in BI &
Telegram sends me an alert with an image and the detected object outlined.

The only issue I have with this setup is that I almost feel guilty how little it uses BI. The positive is since BI isn't doing any motion detection, I have nearly nothing for an average CPU load with very close to perfect alerts (I actually haven't noticed anything that either should or shouldn't be in the alerts I'm getting from Telegram, but I'm sure it can't be perfect). Using the newest Deepstack (/deepquestai/deepstack:latest ) it's processing images in ~400ms on a dinosaur i5. Read this issue thread on how to update deepstack if you don't know: Future of DeepQuest and DeepStack? · Issue #65 · VorlonCD/bi-aidetection

* I tried having the cameras upload FTP images. I think that would be the best way, but there are a lot of small house keeping issues with it I don't have the time to fix. file permissions, cleaning directories, etc.
This sounds amazing! Thanks so much for sharing. I def am not experiencing near perfect alerts, so I'm eager to try to replicate your setup. Did you follow a particular tutorial? If not, would you be willing to share any tips on how you implemented it? (I'm embarrassed to say I even needed to google the IVS acronym).

For clarity, you are recording the HD stream 24x7 but are you quickly discarding any "clips" that are not relevant? What does your long(er) term storage strategy look like? Currently, I keep the 6tb HDD on my Blue Iris box full which I think should get me CLOSE to a month of motion captured 4k h265 and then offloading anything older to a unraid server on the LAN...
 
Top