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

Hoping someone can help with my problem. I'm using DeepquestAI running on the same computer that BI runs, Windows 10, i7 6700 with 48 gigs RAM, and the AI Tool version 1.67 but I wanted to offload this computer which hovers between 85 and >95% CPU utilization most of the time (I have 7 HD cameras and 8 UHD cameras).

I installed Docker on a separate computer running Ubuntu Desktop 20.04 LTS, 4 gig RAM, Intel Celeron CPU. Docker install went well, no errors, then installed Deepstack which also went well and runs seemingly ok.

However, when I point AI Tool to this Linux computer I'm getting these errors

AI Tool is configured in the Windows firewall.

UFW is not enabled on the Lunix box.

Any help or suggestions is appreciated.




COMMAND TO START DEEPQUEST AI ON UBUNTU
sudo docker run -e VISION-DETECTION=TRUE -v localstorage:/datastore -p 82:5000 deepquestai/deepstack



DEEPQUEST AI SCREEN OUTPUT
/v1/vision/scene
---------------------------------------
v1/vision/addmodel
---------------------------------------
v1/vision/listmodels
---------------------------------------
v1/vision/deletemodel
---------------------------------------
---------------------------------------
v1/backup
---------------------------------------
v1/restore
[GIN] 2020/08/02 - 17:53:15 | 403 | 274.22µs | 192.168.1.24 | POST /v1/vision/detection
[GIN] 2020/08/02 - 17:53:15 | 403 | 72.503µs | 192.168.1.24 | POST /v1/vision/detection
[GIN] 2020/08/02 - 17:53:15 | 403 | 59.593µs | 192.168.1.24 | POST /v1/vision/detection
[GIN] 2020/08/02 - 17:53:15 | 403 | 62.307µs | 192.168.1.24 | POST /v1/vision/detection


[02.08.2020, 14:19:31.171]:
[02.08.2020, 14:19:31.179]: Starting analysis of G:\aiinput\SRTSD.20200802_141930810.jpg
[02.08.2020, 14:19:31.190]: (1/6) Uploading image to DeepQuestAI Server
[02.08.2020, 14:19:31.205]: (2/6) Waiting for results
[02.08.2020, 14:19:31.213]: (3/6) Processing results:
[02.08.2020, 14:19:31.221]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.08.2020, 14:19:31.232]: ERROR: Processing the following image 'G:\aiinput\SRTSD.20200802_141930810.jpg' failed. Failure in AI Tool processing the image.
[02.08.2020, 14:19:36.579]:
[02.08.2020, 14:19:36.591]: Starting analysis of G:\aiinput\GTHSD.20200802_141936570.jpg
[02.08.2020, 14:19:36.603]: (1/6) Uploading image to DeepQuestAI Server
[02.08.2020, 14:19:36.627]: (2/6) Waiting for results
[02.08.2020, 14:19:36.634]: (3/6) Processing results:
[02.08.2020, 14:19:36.641]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.08.2020, 14:19:36.648]: ERROR: Processing the following image 'G:\aiinput\GTHSD.20200802_141936570.jpg' failed. Failure in AI Tool processing the image.
[02.08.2020, 14:19:36.660]:
[02.08.2020, 14:19:36.675]: Starting analysis of G:\aiinput\DWNSD.20200802_141936591.jpg
[02.08.2020, 14:19:36.683]: (1/6) Uploading image to DeepQuestAI Server
[02.08.2020, 14:19:36.695]: (2/6) Waiting for results
[02.08.2020, 14:19:36.706]: (3/6) Processing results:
[02.08.2020, 14:19:36.713]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.08.2020, 14:19:36.723]: ERROR: Processing the following image 'G:\aiinput\DWNSD.20200802_141936591.jpg' failed. Failure in AI Tool processing the image.
 
Last edited:
Coloscott said:
Thanks for the help ReXX, but I did make that change. The error, shown above, is different but still in an error state.

Scott
Click to expand...
When Deepstack starts and lists the v1/xxx urls.. is v1/vision/detection listed?
In your post you still have v1/vision/scene listed.
 
ReXX said:
When Deepstack starts and lists the v1/xxx urls.. is v1/vision/detection listed?
In your post you still have v1/vision/scene listed.
Click to expand...


Apologies for not updating that part of the status, here is what it lists upon startup:


$ sudo docker run -e VISION-DETECTION=TRUE -v localstorage:/datastore -p 82:5000 deepquestai/deepstack
v1/vision/addmodel
---------------------------------------
v1/vision/listmodels
---------------------------------------
v1/vision/deletemodel
---------------------------------------
---------------------------------------
v1/backup
---------------------------------------
v1/restore
 
ReXX said:
That's not right.
It need to list v1/vision/detection before it works.
Click to expand...

ReXX, evidently case matters in the startup. TRUE didn't work but True did. It now status' /v1/vision/detection after startup.

Now there's a new problem. getting this message and there is no updates on the deepstack terminal windows on the Ubuntu box:

[02.08.2020, 15:14:10.144]: read config
[02.08.2020, 15:14:10.161]: add
[02.08.2020, 15:14:10.177]: SUCCESS: BGDSD loaded.
[02.08.2020, 15:14:10.189]: read config
[02.08.2020, 15:14:10.196]: add
[02.08.2020, 15:14:10.203]: SUCCESS: default loaded.
[02.08.2020, 15:14:10.212]: read config
[02.08.2020, 15:14:10.222]: add
[02.08.2020, 15:14:10.229]: SUCCESS: DWNSD loaded.
[02.08.2020, 15:14:10.239]: read config
[02.08.2020, 15:14:10.247]: add
[02.08.2020, 15:14:10.254]: SUCCESS: GTHSD loaded.
[02.08.2020, 15:14:10.262]: read config
[02.08.2020, 15:14:10.269]: add
[02.08.2020, 15:14:10.276]: SUCCESS: SRTSD loaded.
[02.08.2020, 15:14:10.335]: Cleaning cameras/history.csv if neccessary...
[02.08.2020, 15:14:10.386]: Loading history list from cameras/history.csv ...
[02.08.2020, 15:14:10.918]: APP START complete.
[02.08.2020, 15:14:11.423]:
[02.08.2020, 15:14:11.432]: Starting analysis of G:\aiinput\BGDSD.20200802_151411398.jpg
[02.08.2020, 15:14:11.458]: (1/6) Uploading image to DeepQuestAI Server
[02.08.2020, 15:15:51.482]: System.Threading.Tasks.TaskCanceledException | A task was canceled. (code: -2146233029 )
[02.08.2020, 15:15:51.489]: ERROR: Processing the following image 'G:\aiinput\BGDSD.20200802_151411398.jpg' failed. Can't reach DeepQuestAI Server at .
[02.08.2020, 15:15:51.560]:
[02.08.2020, 15:15:51.566]: Starting analysis of G:\aiinput\SRTSD.20200802_151411720.jpg
[02.08.2020, 15:15:51.574]: (1/6) Uploading image to DeepQuestAI Server
 
Coloscott said:
Hoping someone can help with my problem. I'm using DeepquestAI running on the same computer that BI runs, Windows 10, i7 6700 with 48 gigs RAM, and the AI Tool version 1.67 but I wanted to offload this computer which hovers between 85 and >95% CPU utilization most of the time (I have 7 HD cameras and 8 UHD cameras).

I installed Docker on a separate computer running Ubuntu Desktop 20.04 LTS, 4 gig RAM, Intel Celeron CPU. Docker install went well, no errors, then installed Deepstack which also went well and runs seemingly ok.

However, when I point AI Tool to this Linux computer I'm getting these errors

AI Tool is configured in the Windows firewall.

UFW is not enabled on the Lunix box.

Any help or suggestions is appreciated.




COMMAND TO START DEEPQUEST AI ON UBUNTU
sudo docker run -e VISION-DETECTION=TRUE -v localstorage:/datastore -p 82:5000 deepquestai/deepstack



DEEPQUEST AI SCREEN OUTPUT
/v1/vision/scene
---------------------------------------
v1/vision/addmodel
---------------------------------------
v1/vision/listmodels
---------------------------------------
v1/vision/deletemodel
---------------------------------------
---------------------------------------
v1/backup
---------------------------------------
v1/restore
[GIN] 2020/08/02 - 17:53:15 | 403 | 274.22µs | 192.168.1.24 | POST /v1/vision/detection
[GIN] 2020/08/02 - 17:53:15 | 403 | 72.503µs | 192.168.1.24 | POST /v1/vision/detection
[GIN] 2020/08/02 - 17:53:15 | 403 | 59.593µs | 192.168.1.24 | POST /v1/vision/detection
[GIN] 2020/08/02 - 17:53:15 | 403 | 62.307µs | 192.168.1.24 | POST /v1/vision/detection


[02.08.2020, 14:19:31.171]:
[02.08.2020, 14:19:31.179]: Starting analysis of G:\aiinput\SRTSD.20200802_141930810.jpg
[02.08.2020, 14:19:31.190]: (1/6) Uploading image to DeepQuestAI Server
[02.08.2020, 14:19:31.205]: (2/6) Waiting for results
[02.08.2020, 14:19:31.213]: (3/6) Processing results:
[02.08.2020, 14:19:31.221]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.08.2020, 14:19:31.232]: ERROR: Processing the following image 'G:\aiinput\SRTSD.20200802_141930810.jpg' failed. Failure in AI Tool processing the image.
[02.08.2020, 14:19:36.579]:
[02.08.2020, 14:19:36.591]: Starting analysis of G:\aiinput\GTHSD.20200802_141936570.jpg
[02.08.2020, 14:19:36.603]: (1/6) Uploading image to DeepQuestAI Server
[02.08.2020, 14:19:36.627]: (2/6) Waiting for results
[02.08.2020, 14:19:36.634]: (3/6) Processing results:
[02.08.2020, 14:19:36.641]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.08.2020, 14:19:36.648]: ERROR: Processing the following image 'G:\aiinput\GTHSD.20200802_141936570.jpg' failed. Failure in AI Tool processing the image.
[02.08.2020, 14:19:36.660]:
[02.08.2020, 14:19:36.675]: Starting analysis of G:\aiinput\DWNSD.20200802_141936591.jpg
[02.08.2020, 14:19:36.683]: (1/6) Uploading image to DeepQuestAI Server
[02.08.2020, 14:19:36.695]: (2/6) Waiting for results
[02.08.2020, 14:19:36.706]: (3/6) Processing results:
[02.08.2020, 14:19:36.713]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.08.2020, 14:19:36.723]: ERROR: Processing the following image 'G:\aiinput\DWNSD.20200802_141936591.jpg' failed. Failure in AI Tool processing the image.
Click to expand...
Have you tried the run command with :noavx
 
Tack it to the end of both the pull and the run command. The celeron cpu probably does not have avx
 
eman said:
Tack it to the end of both the pull and the run command. The celeron cpu probably does not have avx
Click to expand...
It's working!! Awesome! Thanks so much eman! Thanks to ReXX as well!

Offloading this to a cheap computer I had sitting around has taken CPU load on my BI server from ~99% to 58%.
 
  • Like
Reactions: ReXX
eman said:
@pbc Whenever I got the little boxes above v1/backup I had a problem with deepstack. Proabably did not load properly
Strangely the only way I get deepstack to work is if I use the :noavx parameter even though I have an i7 8700 cpu which has avx2
I stop deepstack with docker stop containerid then docker rm containerid and redo the run command
Click to expand...

So I turned on the GPU version again and left for a night, the GPU version will process an image in ~0.7 seconds to 1.06 seconds. Unfortunately I get those squares, and ultimately it just stops working for no reason.

I tried the regular version (without GPU), and it processes in ~3.7 to 4.0 seconds.

But it is also giving me the same squares.

1596408471858.png

Anyone know what causes those? Guess I will try the noavx version?
 
Here's what I get in AITools...
[02.08.2020, 21:02:20]: ERROR: Processing the following image 'D:\aiinput\Backyard.20200802_210040285.jpg' failed. Can't reach DeepQuestAI Server at .

Though when I go to localhost:81, deepstack seems to be fine?

1596416658451.png
 
Anyhow, switched over to noavx for now. Anyone know why my timezone command isn't working?

Code: 
docker run --restart=always -e TZ=America/Toronto -e VISION-DETECTION=True -v localstorage:/datastore -p 81:5000 --name deepstack deepquestai/deepstack:noavx

Should show 9:57pm below vs 1:57..

1596419845225.png
 
UTC time format maybe? The AITool should probably have it formatted for your time zone I would think.

pbc, did you try installing any nvidea gpu drivers for this?
or maybe try '--rm --runtime=nvidia' argument?
docker run --rm --runtime=nvidia -e VISION-DETECTION=True -v localstorage:/datastore -p 81:5000 deepquestai/deepstack:gpu

Didn't work for me, but you never know.... as mentioned earlier, linux is recommended

Seems the deepstack gpu version only runs on linux right now.

Using DeepStack with NVIDIA GPU — DeepStack 0.1 documentation
Click to expand...

pdf here:
 
Last edited:
Can anyone explain the masks in v1.67 AI tool?

I'd like to add one over a tree which looks like a person. But I don't see how to achieve this.

And is there a way to only trigger jpeg capture from a specific motion zone in BI? Looks like I can only use the zones to trigger the alert actions, not snapshot record...?
 
@cjowers
My understanding is that if you are using a camera without a clone it is envisaged you will be continously recording. Presently I believe you still need a clone to trigger the record.

I drove myself crazy trying to make a single camera work in the same way as my clone configuration. IMHO It's unfortunate that this restriction is not made clear in the setup instructions.

@GentlePumpkin
If my take above is correct it might be useful to add a note to the setup guide clarifying this point.

Thanks for all the work you have put into aitools.
 
  • Like
Reactions: seth-feinberg and cjowers
You must log in or register to reply here.
Top Bottom