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

cscoppa

Getting the hang of it
Joined
Dec 14, 2019
Messages
50
Reaction score
26
Has anybody else noticed that the x5-beta version of deepstack, while faster, is not as good as the x3 version when it comes to quality of detections? I'm getting more phantom people detected in my images than I used to. I also notice that the people that are detected come with much lower confidence percentages. A person clearly standing in view looking at the camera might still only come back is "65%" whereas on x3-beta it would definitely be 99% or 100%.

It hasn't grossly affecting the function of my system yet but I do get more false positives here and there.
I'm seeing this also. I had a potted plant detected as a human, also confidence percentages on humans is definitely lower.
 

Schrodinger's Cat

Young grasshopper
Joined
Nov 17, 2020
Messages
42
Reaction score
16
Location
USA
I'm seeing this also. I had a potted plant detected as a human, also confidence percentages on humans is definitely lower.
Funny, I'm actually seeing the exact same false label. x3 always correctly labelled a "Potted Plant" on my doorstep. x5 detects the same thing as a "Person". Frustrating because it's not in an area I can mask without literally masking half my doorstep.

I might try changing the mode to "High" when I get a chance although I'm not sure how to do that with the Docker version of deepstack.
 

cscoppa

Getting the hang of it
Joined
Dec 14, 2019
Messages
50
Reaction score
26
Funny, I'm actually seeing the exact same false label. x3 always correctly labelled a "Potted Plant" on my doorstep. x5 detects the same thing as a "Person". Frustrating because it's not in an area I can mask without literally masking half my doorstep.
Exact same thing, x3 always identified the plant correctly. x5 sometimes gets it right, sometimes doesn't.
 

105437

BIT Beta Team
Joined
Jun 8, 2015
Messages
1,995
Reaction score
881
I encourage everyone to try AWS Rekognition for image analysis. It's working very well for me.
 

pmcross

Pulling my weight
Joined
Jan 16, 2017
Messages
371
Reaction score
185
Location
Pennsylvania
I encourage everyone to try AWS Rekognition for image analysis. It's working very well for me.
Can you elaborate on your setup? Are you using AI Tool to send images to Rekognition for analysis?


Sent from my iPhone using Tapatalk
 

105437

BIT Beta Team
Joined
Jun 8, 2015
Messages
1,995
Reaction score
881
Can you elaborate on your setup? Are you using AI Tool to send images to Rekognition for analysis?


Sent from my iPhone using Tapatalk
Yes, the version of AI Tool I'm running has Amazon Rekognition as an option. It's the 11/30/20 release. I have 12 Mbps upload speed and my total time for each image is between 700 - 1,500 milliseconds.

Release Notes:
Amazon Rekognition support. Seems to have really good detection ability so far. Enter 'amazon' in Settings > AI Server setting. It has 5000 free images a month, but you must first set up an account, give credit card info AND download the ROOTKEY.CSV file and place in _SETTINGS folder after creating a new user: Step 1: Set up an AWS account and create an IAM user - Amazon Rekognition

I intend on adding the ability to resize images and jpeg quality before sending to Rekognition to reduce the filesize that has to be transmitted. Which should increase the speed.
 

Schrodinger's Cat

Young grasshopper
Joined
Nov 17, 2020
Messages
42
Reaction score
16
Location
USA
There's no doubt in my mind that AWS Rekognition is going to give amazing results, and I would love to try it, but...... personally a non-local solution is a bit of a non-starter for me, I've tried hard to make this a fully functioning local system and I don't really want to stray away from that now. Plus I live on a busy downtown street and currently deepstack is processing over 1,000 images per day, and that's AFTER spending the last 4+ months doing as much motion detection optimization as I can. That's well outside the AWS free tier and would have me spending almost $400 per year in fees! Deepstack it is, for now.

I'd love to try other local image analysis options and would be absolutely willing to pay for a stellar one, but I don't know of any others.... are there even any?
 

105437

BIT Beta Team
Joined
Jun 8, 2015
Messages
1,995
Reaction score
881
There's no doubt in my mind that AWS Rekognition is going to give amazing results, and I would love to try it, but...... personally a non-local solution is a bit of a non-starter for me, I've tried hard to make this a fully functioning local system and I don't really want to stray away from that now. Plus I live on a busy downtown street and currently deepstack is processing over 1,000 images per day, and that's AFTER spending the last 4+ months doing as much motion detection optimization as I can. That's well outside the AWS free tier and would have me spending almost $400 per year in fees! Deepstack it is, for now.

I'd love to try other local image analysis options and would be absolutely willing to pay for a stellar one, but I don't know of any others.... are there even any?
Completely see your use case. I live in a rural area so the number of images processed is not a real concern for me. Previously I was running Deepstack via a Docker container on my QNAP. Worked well but I wanted to try Rekognition and see if it could identify more wildlife.
 

pmcross

Pulling my weight
Joined
Jan 16, 2017
Messages
371
Reaction score
185
Location
Pennsylvania
Yes, the version of AI Tool I'm running has Amazon Rekognition as an option. It's the 11/30/20 release. I have 12 Mbps upload speed and my total time for each image is between 700 - 1,500 milliseconds.

Release Notes:
Amazon Rekognition support. Seems to have really good detection ability so far. Enter 'amazon' in Settings > AI Server setting. It has 5000 free images a month, but you must first set up an account, give credit card info AND download the ROOTKEY.CSV file and place in _SETTINGS folder after creating a new user: Step 1: Set up an AWS account and create an IAM user - Amazon Rekognition

I intend on adding the ability to resize images and jpeg quality before sending to Rekognition to reduce the filesize that has to be transmitted. Which should increase the speed.
Thanks for this. I am going to give it a try. I agree with others about the cost of Rekonition due to exceeding 500 images per month. I’m not exactly sure how many images Deepstack processes daily for me, but I imagine that I exceed 500 images a month.


Sent from my iPhone using Tapatalk
 

105437

BIT Beta Team
Joined
Jun 8, 2015
Messages
1,995
Reaction score
881
Thanks for this. I am going to give it a try. I agree with others about the cost of Rekonition due to exceeding 500 images per month. I’m not exactly sure how many images Deepstack processes daily for me, but I imagine that I exceed 500 images a month.


Sent from my iPhone using Tapatalk
It's 5,000 images per month.
 

djborden

Getting the hang of it
Joined
Jul 19, 2017
Messages
50
Reaction score
25
Thanks all. What finally sorted it out for me was to reinstall and then run deepquestai/deepstack:noavx using powershell. that way i could specify the port number of the deepstack url, and the VISION-DETECTION=True (not scene-detection) [code shown below], and then I used that port info for the AITool settings tab Deepstack URL.

PS C:\Users\me> docker run -e VISION-DETECTION=True -v localstorage:/datastore -p 85:5000 deepquestai/deepstack:noavx

then the AITool setting tab deepstack URL used was: :85

and what was probably obvious for everyone, but I never found any info on... BI - settings - webserver tab - http server option - should be ticked 'on'. (and use same LAN and port # that you use in AITool camera tab - Trigger URL field)

Thanks pmcross, gentle pumpkin, and any other content creators!
Ive spent hours trying to get Deepstack working in Docker Desktop on Windows 10. I got it all working using the Deepstack Windows 10 install, but based on everyones suggestions here, it made sense to get it running in Docker.

First I had issues figuring out how to manually set the ports, then once I figured that out, it still would not work. Once I downloaded the image to Docker, running this line from the Windows Power Shell and changing the port in AI Tools to 85, it worked !! I have the AVX version so left that off your command line.

-------------------------
C:\Users\me> docker run -e VISION-DETECTION=True -v localstorage:/datastore -p 85:5000 deepquestai/deepstack
------------------------

Will it autostart automatically if the machine reboots?

Thank you, again!
 

Village Guy

Pulling my weight
Joined
May 6, 2020
Messages
291
Reaction score
161
Location
UK
Ive spent hours trying to get Deepstack working in Docker Desktop on Windows 10. I got it all working using the Deepstack Windows 10 install, but based on everyones suggestions here, it made sense to get it running in Docker.

First I had issues figuring out how to manually set the ports, then once I figured that out, it still would not work. Once I downloaded the image to Docker, running this line from the Windows Power Shell and changing the port in AI Tools to 85, it worked !! I have the AVX version so left that off your command line.

-------------------------
C:\Users\me> docker run -e VISION-DETECTION=True -v localstorage:/datastore -p 85:5000 deepquestai/deepstack
------------------------

Will it autostart automatically if the machine reboots?

Thank you, again!
When you load the deepstack app you have an option to start automatically and also choose the version of Deepstack that you wish to load. Here is an example:

docker run --restart=always -e VISION-DETECTION=True -v localstorage:/datastore -p 85:5000 deepquestai/deepstack:cpu-x5-beta
 

balucanb

Getting the hang of it
Joined
Sep 19, 2020
Messages
146
Reaction score
23
Location
TX
Yes, the version of AI Tool I'm running has Amazon Rekognition as an option. It's the 11/30/20 release. I have 12 Mbps upload speed and my total time for each image is between 700 - 1,500 milliseconds.

Release Notes:
Amazon Rekognition support. Seems to have really good detection ability so far. Enter 'amazon' in Settings > AI Server setting. It has 5000 free images a month, but you must first set up an account, give credit card info AND download the ROOTKEY.CSV file and place in _SETTINGS folder after creating a new user: Step 1: Set up an AWS account and create an IAM user - Amazon Rekognition

I intend on adding the ability to resize images and jpeg quality before sending to Rekognition to reduce the filesize that has to be transmitted. Which should increase the speed.
@105437 just to clarify, you are using a version of AI Tool that has been written to to take advantage of the Amazon Rekognition that you have compiled from GH, correct?
 

105437

BIT Beta Team
Joined
Jun 8, 2015
Messages
1,995
Reaction score
881
@105437 just to clarify, you are using a version of AI Tool that has been written to to take advantage of the Amazon Rekognition that you have compiled from GH, correct?
Yes, that is correct. It's the 11/30/20 release that was compiled and posted here previously.
 

cjowers

Getting the hang of it
Joined
Jan 28, 2020
Messages
107
Reaction score
36
Location
AUS
Once I downloaded the image to Docker, running this line from the Windows Power Shell and changing the port in AI Tools to 85, it worked !!
Just remember that every time you do the run command it will create another instance of deepstack running in the background. which, if not closed properly, can slow things down a lot.
when i was trying to match up the ports to get things working, i accidentally had several instances going, and response time suffered until I ended the processes.
 
Top