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

Yep added that to the Enviroment tab.

I am running Deepstack and the AI tool on a different PC than i am running Blue Iris. Would that be an issue? I tested that the triggers work and i have access to the still that are being analyzed so i don't think it is a problem just figured i would mention. I'm also seeing the requests into DeepStack so i don't think that is the issue.

[GIN] 2020/05/23 - 19:50:24 | 403 | 64.764µs | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:50:27 | 403 | 90.153µs | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:52:15 | 403 | 141.876µs | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:52:17 | 403 | 91.782µs | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:52:20 | 403 | 137.769µs | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:52:22 | 403 | 147.11µs | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:52:25 | 403 | 1.763197ms | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:52:27 | 403 | 675.513µs | 192.168.XX.XX | POST /v1/vision/detection

[GIN] 2020/05/23 - 19:54:54 | 403 | 64.74µs | 192.168.XX.XX | POST /v1/vision/detection



View attachment 62294
I figured it out. Change your docker image to deepquestai/deepstack:noavx (instead of :latest) and it'll then work after you input your key into the web interface.
 
  • Like
Reactions: Bisquit4407
Hi all just started using this and so far like it alot better than sentry... any idea why its not detecting objects at night? the truck is "masked" as its my normal parking spot, but when a new car entered driveway last night it was not deteced.


1590852544764.png

1590852561850.png
 
Still not being avble to run.
When putting just the deepstack server IP, it's taking 2 minutes en send error back.
When putting URL (using http:// prefix), I get this below.
I could admit there is an error with communicating to Deepstack server, but Telegram notification should work no? Not getting anything there either.

Code:
[29.05.2020, 22:31:55.559]: Starting analysis of C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg
[29.05.2020, 22:31:55.587]: (1/6) Uploading image to DeepQuestAI Server
[29.05.2020, 22:31:57.957]: System.Net.Http.HttpRequestException | An error occurred while sending the request. (code: -2146233079 )
[29.05.2020, 22:31:57.977]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg' failed. Can't reach DeepQuestAI Server at http://192.168.0.113:85.
[29.05.2020, 22:31:57.991]: ERROR: Could not send text "[29.05.2020, 22:31:57.977]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg' failed. Can't reach DeepQuestAI Server at http://192.168.0.113:85." to Telegram.
[29.05.2020, 22:31:58.085]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg to Telegram.
[29.05.2020, 22:31:58.093]: ERROR: Could not send text "[29.05.2020, 22:31:58.085]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg to Telegram." to Telegram.
You're correct, as long as you have 'Send Errors and Warnings to Telegram' selected under Settings of AI Tool it should work regardless of Deepstack communication.
A couple questions:
-What's the error you're getting after 2 minutes when putting the Deepstack IP without http://?

-Are you able to send your telegram bot a message manually?

-Like devastator, are you able to reach your DeepQuestAI Server with a web browser? In your case, '192.168.0.113:85'?
 
Still not being avble to run.
When putting just the deepstack server IP, it's taking 2 minutes en send error back.
When putting URL (using http:// prefix), I get this below.
I could admit there is an error with communicating to Deepstack server, but Telegram notification should work no? Not getting anything there either.

Code:
[29.05.2020, 22:31:55.559]: Starting analysis of C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg
[29.05.2020, 22:31:55.587]: (1/6) Uploading image to DeepQuestAI Server
[29.05.2020, 22:31:57.957]: System.Net.Http.HttpRequestException | An error occurred while sending the request. (code: -2146233079 )
[29.05.2020, 22:31:57.977]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg' failed. Can't reach DeepQuestAI Server at http://192.168.0.113:85.
[29.05.2020, 22:31:57.991]: ERROR: Could not send text "[29.05.2020, 22:31:57.977]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg' failed. Can't reach DeepQuestAI Server at http://192.168.0.113:85." to Telegram.
[29.05.2020, 22:31:58.085]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg to Telegram.
[29.05.2020, 22:31:58.093]: ERROR: Could not send text "[29.05.2020, 22:31:58.085]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_223155515.jpg to Telegram." to Telegram.

Can't get it to run. DeepStack is runing on another host for me. Running this python script (copied the url from the AI tool), runs fine
Code:
import requests

image_data = open("test-image3.jpg","rb").read()
print("test")
response = requests.post("http://192.168.0.145/v1/vision/detection",files={"image":image_data}).json()
print(response)
for object in response["predictions"]:
    print(object["label"])

print(response)
 
Right. I started up an Ubuntu (19.10) VM. Then I used the Get started with the USB Accelerator information on google to install the dependencies needed for linux. I then downloaded the MobileNet SSD v2 (COCO) object detection Edge TPU model from Models | Coral. I then installed coral-pi-rest-server on the server. This is basically the "deepstack" equivelent and you point the AI Tool to that instead of the deepstack program. This will use the COCO object detection instead of sending off the images. Of course, you could also make your own object detection to make the processing even better.
I'm very tempted in giving this a try, How's it working for you?
 
  • Like
Reactions: Cameraguy
-What's the error you're getting after 2 minutes when putting the Deepstack IP without http://?

Code:
[29.05.2020, 22:53:05.093]: Starting analysis of C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg
[29.05.2020, 22:53:05.126]: (1/6) Uploading image to DeepQuestAI Server
[29.05.2020, 22:54:45.151]: System.Threading.Tasks.TaskCanceledException | Une tâche a été annulée. (code: -2146233029 )
[29.05.2020, 22:54:45.158]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg' failed. Can't reach DeepQuestAI Server at 192.168.0.113:85.
[29.05.2020, 22:54:45.170]: ERROR: Could not send text "[29.05.2020, 22:54:45.158]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg' failed. Can't reach DeepQuestAI Server at 192.168.0.113:85." to Telegram.
[29.05.2020, 22:54:45.223]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg to Telegram.
[29.05.2020, 22:54:45.229]: ERROR: Could not send text "[29.05.2020, 22:54:45.223]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg to Telegram." to Telegram.

-Are you able to send your telegram bot a message manually?

Of course, using the same bot for many other purposes, checked URL multiple times.

-Like devastator, are you able to reach your DeepQuestAI Server with a web browser? In your case, '192.168.0.113:85'?

Yes, both in the same VM, but also on other PC.
 
Recently the tool has been working for a while and then stopping. There are no error notices or anything to indicated that something is wrong.
When I start the tool it processes images without issue. After a while I'll notice that there are no recent alerts. When I check the tool I see that it has stopped processing images.
Below is a screenshot of my log. It was processing fine until 06:30 this morning. Then there are 5.5 hours of nothing and then it's "Loading object rectangles".
Any idea why this is happening and how to fix it?

G0Re3fo.png
 
Edit: I see in #501 and #502 discussions about the changes to urls. Is that what's breaking the program>

Did the latest update of BI change something in the URL triggering?

I started getting this message after updating BlueIris to 5.2.9.2.
Code:
[28.05.2020, 12:17:24.308]: ERROR: Could not trigger URL 'http://localhost:81/admin?trigger&camera=FWC&user=DQAI&pw=DeepAI', please check if 'http://localhost:81/admin?trigger&camera=FWC&user=DQAI&pw=DeepAI' is correct and reachable.

The Deepstack AI is functioning just fine, it's just the triggers aren't hitting BI.

Is there still an error with release > 5.2.9.2 and more ?
 
edit:
looks like 3 of my camera files in camera's folder were corrupt, they had nothing but null characters only. I had to remove them
and recreate the camera setups from scratch. Plus with the new blue Iris bug I had to add &user=username&pw=password to the all the camera url.
i do recall one time my windows 10 system was hung, I had to power it off.

---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Anyone noticed AITool throwing unhandled exception on startup. It was working for a while, I've had a few windows 10 updates, last one I forgot to test if it broke anything.
running it manually I get this error. I've tried unzip from 1.65 again, moving the entire aitool install folder to c:\Users\myusername\ no difference.

View attachment 62576

when I click continue
View attachment 62577

finally AITool can't find any of my configured cameras, the files are there in cameras folder

View attachment 62578
Check the camera folder to make sure their isn't a rogue text file in there.
 
@GentlePumpkin sorry if this has been asked/explored... I just was told about your app, today so have only read the first post. Have you contacted the BI team to see if there was a way to auto-create the duplicate cameras and set the appropriate settings on them... and hide them from the GUI? It would be great to have the AI be seamless and not have to manage multiple cams that are not 'directly used' Just a thought. thx!
I don't use duplicate cameras at all. Tried it but then found there was no need.
 
Interesting... the documentation I read said to do it, didnt know we didnt need it.
Duplicate cameras are only needed if you don't want to have your BI alert view to be cluttered with false alerts that didn't get triggered. Having duplicate cameras keeps the alert view much cleaner.
 
Interesting... the documentation I read said to do it, didnt know we didnt need it.

There are some perks if you use AI clone camera and the original.
In the AI camera where I can have a lot of false positives, I don't set any Alert actions (on Alert, or on Reset).
The Original camera is triggered by AITool after it meets confidence criteria ,
So I have higher confidence this is a notification I really want to know about
i've setup MQTT and HTTP (for IFTTT) actions in camera settings->Alerts->Actions-> On Alerts On Resets
i've successfully set MQTT Topic, and sometimes even made IFTTT http web request
to communicate directly or in-directly to my Home Assistant there is an actual Alert, the Alert right now
go to an echo DOT announcement via Home Assistant.

The original Cameras via MQTT behave like accurate motion sensors in Home Assistant.
The trick is getting the Motion detection rules just right on the AI camera so it at least fires when there is a real activity
even if it includes some false positives, but that is ongoing.

if you are not planning to use Alerts then you can probably skip Cloned camera's
 
  • Like
Reactions: pmcross
there was no file unrecognized file, it was definitely 3 camera files were corrupt.
I had that happen once about a month ago. I had backups so just copied them in to the camera folder. If I recall all the corrupt files were showing as a different size to the ok ones so they were easy to spot.
 
I've been playing with this and have identified what looks like a bug in the masking implementation. I think occurrs when I create multiple mask areas in close proximity to one another and Deepstack detects an object across the two masks.
When sending a series of test images from BlueIris (Trigger now) some will experience the error and some won't. Those that experience the error won't show in the AI Tool history and will leave an error in the log
[01.06.2020, 21:18:38.356]: System.ArgumentOutOfRangeException | Index was out of range. Must be non-negative and less than the size of the collection. Parameter name: index (code: -2146233086


Has anyone else had the same error?