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

Thug

n3wb
Joined
Apr 11, 2017
Messages
5
Reaction score
2
I found that using only AITools/DeepquestAI some triggers were being missed as it failed to recognise a person on my driveway so had to enable some basic motion detection to mop the missed triggers.
I’ve had it running for only 24 hours so I may well find myself in the same boat as you yet, but it’s not missed anything so far that I know of. I’ll have to go through my recorded footage today to make sure.
But between this, my ring doorbell and my IR trip wires, I shouldn’t mulish anything at all now
 

pmcross

Pulling my weight
Joined
Jan 16, 2017
Messages
371
Reaction score
185
Location
Pennsylvania
That's not true at all. It just means there was nothing in the image that falls within the detection criteria for that camera.

The whole point of the AI Tools/Deep Stack setup is to take away the alert decision from BI. For that to happen you need to make sure AI Tools/Deep Stack doesn't miss any motion events by making sure BI is sending anything remotely important.
Which means that an alert wasn’t sent. The decision to fire an alert is made by AI Tool once it hears back from Deepstack. At any rate an alert wasn’t sent.


Sent from my iPhone using Tapatalk
 

Judman

Getting the hang of it
Joined
Oct 23, 2016
Messages
52
Reaction score
37
Which means that an alert wasn’t sent. The decision to fire an alert is made by AI Tool once it hears back from Deepstack. At any rate, an alert wasn’t sent.


Sent from my iPhone using Tapatalk
My mistake, I misunderstood the issue. You are correct!
 
Joined
Jul 5, 2020
Messages
2
Reaction score
1
Location
Canada
Hello, totally newbie to this. My situation is that the camera pointing at the driveway and I always park my car there. So whenever the camera detects motion that's from unwanted alerts (changing sunlight) it sends a picture to the aitool and it detects my car already in the driveway and wasn't moving. I try masking but that would pretty much cover my whole driveway which is flat out useless.
 

pbc

Getting comfortable
Joined
Jul 11, 2014
Messages
1,024
Reaction score
156
Okay, so had to redo my system with a fresh windows install. Managed to get everything up and running again, and am getting notifications via gmail. But 2 things aren't happening:

1. Not getting the alert image in BI. I.e., in the below shot it doesn't show my alerts after I turned on the AI cameras. But I am getting the emails.

1593958645007.png

2. No alerts come up in BI's android app either.


Settings are below for AI Cams and regular cams:

1593958747355.png
1593958831681.png1593958850055.png
1593958873282.png1593958888062.png

1593958909515.png1593958942382.png

AI Camera;

1593958970810.png1593958988265.png

1593959004753.png

I have not set up Alerts in the AICamera, since I believe AITools only Triggers the normal FrontDoor camera?

1593959124443.png1593959168579.png

Must have gotten something mixed up between the two cameras somewhere?
 

IAmATeaf

Known around here
Joined
Jan 13, 2019
Messages
3,287
Reaction score
3,252
Location
United Kingdom
Then how do I get notified when there is a car pull in my driveway?
What I’ve done is in the AITools I disable car then in the main cam I also have a motion alert setup but in the area towards where the back/front of the car would be when it pulls in so that motion would then trigger the cam as well.
 

IAmATeaf

Known around here
Joined
Jan 13, 2019
Messages
3,287
Reaction score
3,252
Location
United Kingdom
@pbc what happens if in the Trigger tab on the main cam you enable capture image? And disable it on the clone AI cam?
 

BeerNut

Getting the hang of it
Joined
Dec 4, 2014
Messages
51
Reaction score
35
Is there a away to automatically start Deepstack windows version?
 

pbc

Getting comfortable
Joined
Jul 11, 2014
Messages
1,024
Reaction score
156
@pbc what happens if in the Trigger tab on the main cam you enable capture image? And disable it on the clone AI cam?
Will try that. Said it before, but this is a confusing line:

2.5 Store alert images in 'Input Path'
now go to Record, check 'JPEG snapshot each (mm:ss)', select the folder you created in step 2.1, check the box 'Only when triggered' and set the interval to p.e. 0:05.0 (one image every 5 second). Furthermore, you might want to disable 'Create Alert list images when triggered', because otherwise alot of false-alarm images (remember we set the motion detection to be very sensitive) will be stored in your alerts folder.
Now go to 'Trigger', check 'Capture an alert list image' and set the Break time 'End trigger unless retriggered' to p.e. 4s, so that a short alert only causes one image to analyze. If you think that the AI Software might overlook an object "on first sight" because it's only party visible (which most times is no problem at all for the AI Software), you can also make the break time longer than the 5s interval. In this case, multiple images will be analyze by the AI Software.


Because there is no "Create Alert List images when Triggered" in the Record tab to disable, and only the "Capture Alert List Image" in the Trigger section, which the above implies to keep on in the AI clone camera.

Edit: So if I check Capture an Alert List image" only in the FrontDoor camera and not in the AIFrontDoor camera, no image gets processed by AITools. So it's definitely correct to be checking that in the AI camera.

Still getting no alerts in my BI Android app though. Also not getting any images showing in the Alerts section of BI.

But I do get the images emailed and they show up in AITools.
 
Last edited:

PiTAFlight

n3wb
Joined
Jul 2, 2020
Messages
4
Reaction score
1
Location
USA
RePost: Can someone help me?

I have the following issue:

Starting DeepStack with VISION-DETECTION=True gives me the following error:
[02.07.2020, 17:25:57.546]: (1/6) Uploading image to DeepQuestAI Server
[02.07.2020, 17:25:58.043]: Cleaning cameras/history.csv if neccessary...
[02.07.2020, 17:25:59.807]: System.Net.Http.HttpRequestException | An error occurred while sending the request. (code: -2146233079 )
[02.07.2020, 17:25:59.816]: ERROR: Processing the following image 'D:\BlueIris\aiinput/IPC08.20200702_172557513.jpg' failed. Can't reach DeepQuestAI Server at
.

When I visit the webpage
I can see DeepStack is running and activated.

When I start DeepStack with VISION-SCENE=True or VISION-FACE=True i get this error:
[02.07.2020, 17:21:26.236]: (1/6) Uploading image to DeepQuestAI Server
[02.07.2020, 17:21:26.249]: (2/6) Waiting for results
[02.07.2020, 17:21:26.257]: (3/6) Processing results:
[02.07.2020, 17:21:26.265]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.07.2020, 17:21:26.273]: ERROR: Processing the following image 'D:\BlueIris\aiinput/IPC08.20200702_172126168.jpg' failed. Failure in AI Tool processing the image.

This seems logic to me since it needs VISION-DETECTION, but it shows DeepStack in this case can be reached.

This is how I start Deepstack (Linux Debian 10 in VM under MSWindows10):
sudo docker run -e VISION-DETECTION=True -v localstorage:/datastore -p 80:5000 deepquestai/deepstack

I already tried the windows version of deepstack in windows 10. Same problem after selecting the checkbox after DETECTION.
I tried to install DeepStack on a docker version in Synology NAS. When entering enviroment variable VISION-DETECTION=TRUE Same problem without this variable server can be reached but processing error.

Please Help.

PiTA
 

PiTAFlight

n3wb
Joined
Jul 2, 2020
Messages
4
Reaction score
1
Location
USA
RePost: Can someone help me?

I have the following issue:

Starting DeepStack with VISION-DETECTION=True gives me the following error:
[02.07.2020, 17:25:57.546]: (1/6) Uploading image to DeepQuestAI Server
[02.07.2020, 17:25:58.043]: Cleaning cameras/history.csv if neccessary...
[02.07.2020, 17:25:59.807]: System.Net.Http.HttpRequestException | An error occurred while sending the request. (code: -2146233079 )
[02.07.2020, 17:25:59.816]: ERROR: Processing the following image 'D:\BlueIris\aiinput/IPC08.20200702_172557513.jpg' failed. Can't reach DeepQuestAI Server at
.

When I visit the webpage
I can see DeepStack is running and activated.

When I start DeepStack with VISION-SCENE=True or VISION-FACE=True i get this error:
[02.07.2020, 17:21:26.236]: (1/6) Uploading image to DeepQuestAI Server
[02.07.2020, 17:21:26.249]: (2/6) Waiting for results
[02.07.2020, 17:21:26.257]: (3/6) Processing results:
[02.07.2020, 17:21:26.265]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.07.2020, 17:21:26.273]: ERROR: Processing the following image 'D:\BlueIris\aiinput/IPC08.20200702_172126168.jpg' failed. Failure in AI Tool processing the image.

This seems logic to me since it needs VISION-DETECTION, but it shows DeepStack in this case can be reached.

This is how I start Deepstack (Linux Debian 10 in VM under MSWindows10):
sudo docker run -e VISION-DETECTION=True -v localstorage:/datastore -p 80:5000 deepquestai/deepstack

I already tried the windows version of deepstack in windows 10. Same problem after selecting the checkbox after DETECTION.
I tried to install DeepStack on a docker version in Synology NAS. When entering enviroment variable VISION-DETECTION=TRUE Same problem without this variable server can be reached but processing error.

Please Help.

PiTA
I also have attempted port 83 and 5000 on linux and windows executable. Iptables opened all ports. Windows added firewall rule. No success
 

pmcross

Pulling my weight
Joined
Jan 16, 2017
Messages
371
Reaction score
185
Location
Pennsylvania
RePost: Can someone help me?

I have the following issue:

Starting DeepStack with VISION-DETECTION=True gives me the following error:
[02.07.2020, 17:25:57.546]: (1/6) Uploading image to DeepQuestAI Server
[02.07.2020, 17:25:58.043]: Cleaning cameras/history.csv if neccessary...
[02.07.2020, 17:25:59.807]: System.Net.Http.HttpRequestException | An error occurred while sending the request. (code: -2146233079 )
[02.07.2020, 17:25:59.816]: ERROR: Processing the following image 'D:\BlueIris\aiinput/IPC08.20200702_172557513.jpg' failed. Can't reach DeepQuestAI Server at
.

When I visit the webpage
I can see DeepStack is running and activated.

When I start DeepStack with VISION-SCENE=True or VISION-FACE=True i get this error:
[02.07.2020, 17:21:26.236]: (1/6) Uploading image to DeepQuestAI Server
[02.07.2020, 17:21:26.249]: (2/6) Waiting for results
[02.07.2020, 17:21:26.257]: (3/6) Processing results:
[02.07.2020, 17:21:26.265]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[02.07.2020, 17:21:26.273]: ERROR: Processing the following image 'D:\BlueIris\aiinput/IPC08.20200702_172126168.jpg' failed. Failure in AI Tool processing the image.

This seems logic to me since it needs VISION-DETECTION, but it shows DeepStack in this case can be reached.

This is how I start Deepstack (Linux Debian 10 in VM under MSWindows10):
sudo docker run -e VISION-DETECTION=True -v localstorage:/datastore -p 80:5000 deepquestai/deepstack

I already tried the windows version of deepstack in windows 10. Same problem after selecting the checkbox after DETECTION.
I tried to install DeepStack on a docker version in Synology NAS. When entering enviroment variable VISION-DETECTION=TRUE Same problem without this variable server can be reached but processing error.

Please Help.

PiTA
Have you tried the noavx version of Docker? Your CPU may not support AVX. Try the following commands:

sudo docker pull deepquestai/deepstack:noavx

sudo docker run -e VISION-DETECTION=True -v localstorage:/datastore \-p 80:5000 deepquestai/deepstack:noavx
 

PiTAFlight

n3wb
Joined
Jul 2, 2020
Messages
4
Reaction score
1
Location
USA
Have you tried the noavx version of Docker? Your CPU may not support AVX. Try the following commands:

sudo docker pull deepquestai/deepstack:noavx

sudo docker run -e VISION-DETECTION=True -v localstorage:/datastore \-p 80:5000 deepquestai/deepstack:noavx
OMG that seemed to work in my VM running Debian 10. Thank you so much!
 
Joined
Jun 1, 2018
Messages
2
Reaction score
0
Location
New Zealand
Before I put a lot of time into this I thought I would throw this out to the group and see if this has already been sorted or if there is a better suggestion.

The issue I'm having is that something is triggering my cameras and because there are normally cars in 2 of my camera's they always trigger. Now I could take the car trigger out of these cameras but I want them to trigger when cars come down the road or up the driveway.

This got me thinking that Blue Iris can place a rectangle around the moving object that triggered the alert. If I read that picture and kept all the rest of the picture transparent except for the movement and passed that onto Deepstack (aitool) then it should stop all these false positives.

Has anyone headed down this track before?
 

pmcross

Pulling my weight
Joined
Jan 16, 2017
Messages
371
Reaction score
185
Location
Pennsylvania
Before I put a lot of time into this I thought I would throw this out to the group and see if this has already been sorted or if there is a better suggestion.

The issue I'm having is that something is triggering my cameras and because there are normally cars in 2 of my camera's they always trigger. Now I could take the car trigger out of these cameras but I want them to trigger when cars come down the road or up the driveway.

This got me thinking that Blue Iris can place a rectangle around the moving object that triggered the alert. If I read that picture and kept all the rest of the picture transparent except for the movement and passed that onto Deepstack (aitool) then it should stop all these false positives.

Has anyone headed down this track before?
Others who had this problem usually set up another camera clone and mask the are where the parked cars are usually parked. This camera would be set to only trigger on vehicles and the other clone should be not masked and set to only trigger on people. That way you get alerts for cars outside of the masked areas and alerts for people any where.
 

tripp396

Getting the hang of it
Joined
Jun 18, 2020
Messages
65
Reaction score
30
Location
Minnesota
Went back a few pages but I have this setup with a camera setup on the substream that takes the pictures and sends them over to the aitool to process and then that triggers my main stream. I saw with the newest version of Blue Iris you can combine the main stream and substream into one camera. Is it possible to use the single setup to still use the substream to record and capture images for processing and have the main stream record when triggered?
 

IAmATeaf

Known around here
Joined
Jan 13, 2019
Messages
3,287
Reaction score
3,252
Location
United Kingdom
That would work if you have a large or long driveway, I can’t do this as my front driveway is only just lightly longer then my cars so masking the area wouldn’t detect a car which is why I have motion detection enabled on the main camera to detect movement where the front/back of the car would end up when parked.
 
Top