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

[sunnyhaibin]

Hi @GentlePumpkin , I was able to launch 1.63 of AI Tool. Loving it so far! One issue I am having now is that I cannot start 1.65 on 3 of my machines whatsoever. I have tried:

• Uninstalled/disabled all versions of .Net Framework
• Reinstalled .Net Framework 4.8
• Reboot multiple times
• Compatibility mode in Windows 8, 7, Vista

Do you know what the issue might be? Thank you in advance!

 

[pnakashian]

Hi @GentlePumpkin , I was able to launch 1.63 of AI Tool. Loving it so far! One issue I am having now is that I cannot start 1.65 on 3 of my machines whatsoever. I have tried:

• Uninstalled/disabled all versions of .Net Framework
• Reinstalled .Net Framework 4.8
• Reboot multiple times
• Compatibility mode in Windows 8, 7, Vista

Do you know what the issue might be? Thank you in advance!

I don't know much about the inner workings of the code, but not much clue to go on, without error message.
can you open a command prompt cmd.exe change directory to the Aitool release folder and launch from command aitool.exe

maybe it'll give a message that's not seen in popup gui.

Do you have Antivirus software, if yes, can you check if the Antivirus may have quarantined/blocked it from running?

 

[pmcross]

Has anyone seen a significant delay when AI Tool triggers the camera externally? I have been testing this and I receive the alert via Telegram almost instantaneously, but the push alert from BI is delayed. Sometimes the alert is triggered after the motion has stopped meaning that the event was missed all together. My resources on my BI machine are within normal range (less than 50-60% CPU usage during peak usage, i.e motion events) when this occurs. Just wondering if others ran into this issue as well.

 

[pnakashian]

Has anyone seen a significant delay when AI Tool triggers the camera externally? I have been testing this and I receive the alert via Telegram almost instantaneously, but the push alert from BI is delayed. Sometimes the alert is triggered after the motion has stopped meaning that the event was missed all together. My resources on my BI machine are within normal range (less than 50-60% CPU usage during peak usage, i.e motion events) when this occurs. Just wondering if others ran into this issue as well.

I've seen that time to time, that's why in my camera settings->Record->Options
i've checked the box Pre-trigger video buffer 30 sec.

the 30 sec video before trigger only works if you have Continuous recording, maybe a few other ones, but not just "When triggered"

 

[pmcross]

I've seen that time to time, that's why in my camera settings->Record->Options
i've checked the box Pre-trigger video buffer 30 sec.

the 30 sec video before trigger only works if you have Continuous recording, maybe a few other ones, but not just "When triggered"

Glad to hear that I’m not the only one seeing this

I have my cameras set to record continuously. I currently have the pre-trigger video set to 5 seconds. I’ll have to give the 30 second pre-trigger setting a shot.


Sent from my iPhone using Tapatalk

 

[lukyjay]

Installed in a completely different computer using a different install method and still same errors.

[01.06.2020, 16:38:01.103]: Starting analysis of E:\aiinput/FCSD.20200525_194239018.jpg
[01.06.2020, 16:38:01.148]: (1/6) Uploading image to DeepQuestAI Server
[01.06.2020, 16:38:01.260]: (2/6) Waiting for results
[01.06.2020, 16:38:01.418]: (3/6) Processing results:
[01.06.2020, 16:38:01.426]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[01.06.2020, 16:38:01.432]: ERROR: Processing the following image 'E:\aiinput/FCSD.20200525_194239018.jpg' failed. Failure in AI Tool processing the image.
[01.06.2020, 16:38:45.485]:
[01.06.2020, 16:38:45.492]: Starting analysis of E:\aiinput/FCSD.20200601_163845468.jpg
[01.06.2020, 16:38:45.499]: (1/6) Uploading image to DeepQuestAI Server
[01.06.2020, 16:38:45.516]: (2/6) Waiting for results
[01.06.2020, 16:38:45.523]: (3/6) Processing results:
[01.06.2020, 16:38:45.531]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[01.06.2020, 16:38:45.537]: ERROR: Processing the following image 'E:\aiinput/FCSD.20200601_163845468.jpg' failed. Failure in AI Tool processing the image.
[01.06.2020, 16:38:50.592]:
[01.06.2020, 16:38:50.598]: Starting analysis of E:\aiinput/FCSD.20200601_163850579.jpg
[01.06.2020, 16:38:50.604]: (1/6) Uploading image to DeepQuestAI Server
[01.06.2020, 16:38:50.614]: (2/6) Waiting for results
[01.06.2020, 16:38:50.624]: (3/6) Processing results:
[01.06.2020, 16:38:50.631]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[01.06.2020, 16:38:50.636]: ERROR: Processing the following image 'E:\aiinput/FCSD.20200601_163850579.jpg' failed. Failure in AI Tool processing the image.

DeepStack Successfully Activated
/v1/vision/scene
---------------------------------------
v1/vision/addmodel
---------------------------------------
v1/vision/listmodels
---------------------------------------
v1/vision/deletemodel
---------------------------------------
v1/vision/setadminkey
---------------------------------------
v1/vision/setapikey
---------------------------------------
v1/vision/backup
---------------------------------------
v1/vision/restore
[GIN] 2020/06/01 - 21:36:31 | 200 | 5.524963418s | 172.17.0.1 | POST /v1/admin/activate
[GIN] 2020/06/01 - 21:38:01 | 200 | 582.3µs | 172.17.0.1 | POST /v1/vision/detection
[GIN] 2020/06/01 - 21:38:45 | 200 | 19.2µs | 172.17.0.1 | POST /v1/vision/detection
[GIN] 2020/06/01 - 21:38:50 | 200 | 19.2µs | 172.17.0.1 | POST /v1/vision/detection

Is your deepstack running on Docker? You need to use the :noavx tag when pulling the image or you'll ge the above error

 

[sn0000py]

i have a question about the url,
if an motion is detected i can add a url which is executed, can i put a variable with the name of the actual image?

 

[freefaller85]

Is your deepstack running on Docker? You need to use the :noavx tag when pulling the image or you'll ge the above error

Yes. I ran both to no avail. Get the same error with both the :latest and :noavx. I also tried running both in Portainer in Home Assistant on a different PC with the same results.

 

[pnakashian]

Yes. I ran both to no avail. Get the same error with both the :latest and :noavx. I also tried running both in Portainer in Home Assistant on a different PC with the same results.

This may be nothing, but in windows docker,it runs in 2 modes linux platform or windows platform, I'm running my deepstack docker in linux platform. I've never tried it running in windows platform, don't know if it would run perfectly or run with errors in windows platform.
if you are using docker desktop gui rick click you should see something. I use the command line i specify volume mount point, which I can't do in docker desktop.
i also mapped the port to 8080 for AI Tool to use. e:\dockerData is folder i precreated before running docker for deepquestAI to store whatever data it wants there permanently.

i got this working only couple weeks ago, though the image I downloaded 5 weeks ago.

docker run --platform linux -dti --name "deepquestAI" --restart always --net="bridge" -v e:/dockerData:/datastore -e MODE=Medium -e VISION-SCENE=True -e VISION-FACE=True -e VISION-DETECTION=True -p 8080:5000 deepquestai/deepstack:latest

 

[biiiipy]

Hi, does anyone know if this can be used with existing NVR (Hikvision) and not Blue Iris?

 

[pmcross]

Hi, does anyone know if this can be used with existing NVR (Hikvision) and not Blue Iris?

It should be able to be. AI Tool just watches a folder for snapshots that were generated by a motion event. I’m not sure if the NVR supports dropping images into a folder on a Windows machine but, at a minimum, you could have each camera do this. You could then receive alerts from AI Tool via Telegram, or you could trigger the camera using the Url to the NVR.


Sent from my iPhone using Tapatalk

 

[ajuhawk]

I've had this successfully working using a docker image on windows and setting it to port 80, but any time I try to use a port other than 80, it fails to get a response from deep stack. Seems like everyone else is able to use a non port 80, so wondering if anyone has a clue of what I'm missing... tried looking at firewall ports, etc...

ERROR: Processing the following image 'D:\BlueIris\AiInput\ai_test.20200605_083635650.jpg' failed. Can't reach DeepQuestAI Server at http://192.168.xxx.xxx:83/v1/vision/detection

Thanks for any thoughts.

 

[sunnyhaibin]

I've had this successfully working using a docker image on windows and setting it to port 80, but any time I try to use a port other than 80, it fails to get a response from deep stack. Seems like everyone else is able to use a non port 80, so wondering if anyone has a clue of what I'm missing... tried looking at firewall ports, etc...

ERROR: Processing the following image 'D:\BlueIris\AiInput\ai_test.20200605_083635650.jpg' failed. Can't reach DeepQuestAI Server at http://192.168.xxx.xxx:83/v1/vision/detection

Thanks for any thoughts.

Refer to post #338 ([tool] [tutorial] Free AI Person Detection for Blue Iris) - I'm using 1.63 cause I could not get 1.65 to run on all of my machines, but one of the machines had the exact issue like yours, and installing the mentioned Visual C++ resolved the issue after a couple of restarts of AI Tool and Deepstack server.

 

[ajuhawk]

Refer to post #338 ([tool] [tutorial] Free AI Person Detection for Blue Iris) - I'm using 1.63 cause I could not get 1.65 to run on all of my machines, but one of the machines had the exact issue like yours, and installing the mentioned Visual C++ resolved the issue after a couple of restarts of AI Tool and Deepstack server.

I'm not sure how that would be related to the port issue. Deep Stack is running fine and can be accessed via the port in a web browser.. I've also installed a docker image under home assistant and get the same result from AI Tool...seems to be an issue with AI Tool not connecting to the right port... and why would it work on port 80 just fine?

Anyway, I'll give it a shot and see if it changes anything... thanks for the idea!

 

[pnakashian]

I've had this successfully working using a docker image on windows and setting it to port 80, but any time I try to use a port other than 80, it fails to get a response from deep stack. Seems like everyone else is able to use a non port 80, so wondering if anyone has a clue of what I'm missing... tried looking at firewall ports, etc...

ERROR: Processing the following image 'D:\BlueIris\AiInput\ai_test.20200605_083635650.jpg' failed. Can't reach DeepQuestAI Server at http://192.168.xxx.xxx:83/v1/vision/detection

Thanks for any thoughts.

Try starting docker with Network in Bridge mode. In Bridge mode the port 80 will be listened not just at your 192.168.xxx.xxx machine ip, but also 127.0.0.1 if you are running AITool on the same
machine, if your issue is W10 firewall, maybe the firewall wont block if your Deepstack url in AItool is changed to 127.0.0.1:80 or another port # of your choice.
I think firewalls are less restrictive to listening ports on loopback (127.0.0.1) interface

you can also try port 8080 Some firewalls treat port 8080 similar to 80.

 

[ajuhawk]

Try starting docker with Network in Bridge mode. In Bridge mode the port 80 will be listened not just at your 192.168.xxx.xxx machine ip, but also 127.0.0.1 if you are running AITool on the same
machine, if your issue is W10 firewall, maybe the firewall wont block if your Deepstack url in AItool is changed to 127.0.0.1:80 or another port # of your choice.
I think firewalls are less restrictive to listening ports on loopback (127.0.0.1) interface

you can also try port 8080 Some firewalls treat port 8080 similar to 80.

Yeah, nothing obvious there either unfortunately. Guess I should be content I have it working on port 80 for now.

Thanks!

 

[pnakashian]

1 more trick you can try . click Windows key then type -> Windows Defender with Advanced Security
then click on->Inbound Rules

you'll see somewhere in inbound rules 2 com.docker.backend
1 is for tcp
1 is for udp


double click on the row for tcp
General tab-> change action from "block the connection" to "allow the connection"
Protocols and Ports tab-> change Local port from 80 to All ports

click ok

I may have changed mine a long time ago.

i don't recall if I had to reboot for it to take affect.

 

[ajuhawk]

double click on the row for tcp
General tab-> change action from "block the connection" to "allow the connection"
Protocols and Ports tab-> change Local port from 80 to All ports

Mine's already set that way... it's probably another setting like that somewhere I'll have to dig for when I have more time... but I've tried docker on the same machine, Virtualbox on another machine, same deal....80 works. Thanks for the suggestions!

 

[cloudy]

Thanks for the great work - any plans to support pushover notifications in future? (Pushover: API)

 

[devastator]

Got my Google Coral USB Accelerator yesterday. I currently have it parsing the rtsp streams. Getting detection times of <30 ms.