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

meissen

Young grasshopper
Joined
Jun 28, 2017
Messages
61
Reaction score
10
But there are no images being generated because the cameras are not being triggered. It seems like more of a BI issue that i have to figure out first before trying to figure out why i'm getting so many false alerts still. I am wondering if my memory is causing the issue for BI? I have no idea.
Can you show a screenshot of your trigger and record settings on the cloned camera?
 

Coloscott

Young grasshopper
Joined
Dec 13, 2018
Messages
33
Reaction score
3
Location
United States
Can you copy and paste the log messages in here so we can see? Maybe we'll be able to help figure it out that way.
I just saved my AI Tool configs in a text file, deleted AI Tool, and started over. If it continues to be an issue I'll update here including the logs.
 
Joined
Oct 22, 2015
Messages
29
Reaction score
9
Did you find a solution for this yet? Someone has noted the commands to create a service from NSSM for deepstack: Windows Auto Startup and Minimize

However, I'm trying to figure out how to add service dependencies with NSSM so that the services will start in order

Just started looking into this, I'm going to apologise as I've not read this entire thread, just the first and last few pages but I have a few annoying/noddy questions.

DeepQuestAI is now DeepStackAI? When I registered I didn't get an API key, just what I think is a product key. Does this affect/impact the product and what I want from it?


I run my system headless, I've configured AITool.exe to run as a service using NSSM but what do people do about DeepStackAI which needs to be manually started and the key and port number entered each time? Wondering if I can just disconnect from my RDP session if that will leave DeepStackAI still running.

Still getting my head around it so wish me luck :D
 
Joined
Oct 22, 2015
Messages
29
Reaction score
9
Right have DeepStack running within Docker, can access the DQAI webpage using localhost and the port number but I'm getting the following errors in the log file for AI Tools?

[22.06.2020, 15:46:56.117]: Starting analysis of C:\BlueIris\AI-Input/AI-Drive1_C.20200622_154656086.jpg
[22.06.2020, 15:46:56.123]: System.IO.IOException | The process cannot access the file 'C:\BlueIris\AI-Input\AI-Drive1_C.20200622_154656086.jpg' because it is being used by another process. (code: -2147024864 )
[22.06.2020, 15:46:56.129]: Could not access file - will retry after 10 ms delay
[22.06.2020, 15:46:56.157]: Retrying image processing - retry 1
[22.06.2020, 15:46:56.163]: (1/6) Uploading image to DeepQuestAI Server
[22.06.2020, 15:46:56.174]: (2/6) Waiting for results
[22.06.2020, 15:46:56.178]: (3/6) Processing results:
[22.06.2020, 15:46:56.184]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[22.06.2020, 15:46:56.188]: ERROR: Processing the following image 'C:\BlueIris\AI-Input/AI-Drive1_C.20200622_154656086.jpg' failed. Failure in AI Tool processing the image.
How did fix this error?
 

ReXX

Young grasshopper
Joined
Dec 28, 2018
Messages
47
Reaction score
15
Location
Denmark
Did you find a solution for this yet? Someone has noted the commands to create a service from NSSM for deepstack: Windows Auto Startup and Minimize

However, I'm trying to figure out how to add service dependencies with NSSM so that the services will start in order
I'm Boost on the other forum.
I have made a post here with screenshots

 

meissen

Young grasshopper
Joined
Jun 28, 2017
Messages
61
Reaction score
10
Nothing is glaring me in the eye on the settings -- every thing seems to be right. What if you move the sensitivity sliders all the way to the left?
 

Netwalker

Getting the hang of it
Joined
Aug 8, 2017
Messages
46
Reaction score
28
Hello,
I recently set this all up and was super excited to reduce the amount of false alerts I was getting. I am running blue iris on a dell optiplex i7-6700 with 8gb of ram and it's been working great. I have seven Dahua IPC-HDW5231R-Z cameras and one Dahua SD49225T-HN. I followed the guide from this thread + this video to get everything setup. I am running DeepStack on my Synology NAS in a docker container. I have everything setup correctly as far as i know, and AI Tool is working as expected....but i have some serious issues and can't figure out why.

I have never had any issues getting cameras to trigger until now. All of the secondary cameras i added with continuous recording cameras responsible for triggering and putting images into the directory to be analyzed are now all of the sudden not triggering. I can walk right in front of them waving my arms or slowly walking normal from 10 feet away and all of them but one do not trigger. There seems to be one camera that is triggering as expected, but at the same time i still get TON of false alerts from it. Based on what most everyone else's experience has been with this...i have to be doing something wrong, or have something incorrectly configured (hopefully?).

If anyone has any suggestions on things I could try to make this experience a bit better before i give up that would be awesome.

FYI: I am using a min object size of 292, a min contrast size of 19, and a min duration of 0.5 to try to get them to over-trigger.
I'm guessing that if you followed the video, you are using "SD'' camera feeds @ 640x480 but with your old motion detection settings of the full resolution image. 292 pixels in a 640x480 image is very large. Try lowering it.
 

kosh42efg

n3wb
Joined
Aug 14, 2020
Messages
29
Reaction score
13
I think I'm getting there with this. Thanks to all the community hard work for creating guides and tools like this.

I was maxing out my ancient CPU (i7 960 from back in the day) trying to run Deepstack, with image processing times being multiple seconds. Not workable.

However, given the recent(ish) announcement of the CUDA toolkit being available in WSL 2, I know have a GPU based Deepstack Docker running. I can access this fine in a Browser, and put this URL in to the AITool. However, I get this in the error log:

Code:
[14.08.2020, 20:28:49.612]: Starting analysis of C:\aiinput\frontsd.20200814_202849597.jpg
[14.08.2020, 20:28:49.617]: (1/6) Uploading image to DeepQuestAI Server
[14.08.2020, 20:28:49.633]: (2/6) Waiting for results
[14.08.2020, 20:28:49.639]: (3/6) Processing results:
[14.08.2020, 20:28:49.640]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[14.08.2020, 20:28:49.676]: ERROR: Processing the following image 'C:\aiinput\frontsd.20200814_202849597.jpg' failed. Failure in AI Tool processing the image.
Any ideas? I'm thinking that the image is getting to the docker container fine, and being processed (below is the Docker log), but then not getting passed back to AI Tool. However, I am finding my way by feel...
Code:
[GIN] 2020/08/14 - 19:19:40 | 403 |       237.6µs |      172.20.0.1 | POST     /v1/vision/detection
[GIN] 2020/08/14 - 19:28:49 | 403 |        38.5µs |      172.20.0.1 | POST     /v1/vision/detection
Any thoughts? I'm not sure if the 403 is referencing an http forbidden error, which is why it's returning null? So it gets the request, and understands it, but says no you're not allowed to make that request?
 

meissen

Young grasshopper
Joined
Jun 28, 2017
Messages
61
Reaction score
10
I think I'm getting there with this. Thanks to all the community hard work for creating guides and tools like this.

I was maxing out my ancient CPU (i7 960 from back in the day) trying to run Deepstack, with image processing times being multiple seconds. Not workable.

However, given the recent(ish) announcement of the CUDA toolkit being available in WSL 2, I know have a GPU based Deepstack Docker running. I can access this fine in a Browser, and put this URL in to the AITool. However, I get this in the error log:

Code:
[14.08.2020, 20:28:49.612]: Starting analysis of C:\aiinput\frontsd.20200814_202849597.jpg
[14.08.2020, 20:28:49.617]: (1/6) Uploading image to DeepQuestAI Server
[14.08.2020, 20:28:49.633]: (2/6) Waiting for results
[14.08.2020, 20:28:49.639]: (3/6) Processing results:
[14.08.2020, 20:28:49.640]: System.NullReferenceException | Object reference not set to an instance of an object. (code: -2147467261 )
[14.08.2020, 20:28:49.676]: ERROR: Processing the following image 'C:\aiinput\frontsd.20200814_202849597.jpg' failed. Failure in AI Tool processing the image.
Any ideas? I'm thinking that the image is getting to the docker container fine, and being processed (below is the Docker log), but then not getting passed back to AI Tool. However, I am finding my way by feel...
Code:
[GIN] 2020/08/14 - 19:19:40 | 403 |       237.6µs |      172.20.0.1 | POST     /v1/vision/detection
[GIN] 2020/08/14 - 19:28:49 | 403 |        38.5µs |      172.20.0.1 | POST     /v1/vision/detection
Any thoughts? I'm not sure if the 403 is referencing an http forbidden error, which is why it's returning null? So it gets the request, and understands it, but says no you're not allowed to make that request?
Do you have the API key entered into Deep Stack? I believe when I was having problems with the key I was getting 403 errors. If you browse to your Deep Stack instance via a web browser, does it show the installation as activated with a key?
 

kosh42efg

n3wb
Joined
Aug 14, 2020
Messages
29
Reaction score
13
Do you have the API key entered into Deep Stack? I believe when I was having problems with the key I was getting 403 errors. If you browse to your Deep Stack instance via a web browser, does it show the installation as activated with a key?
I'm running Deepstack as the latest docker version (deepquestai/deepstack:gpu) that doesn't require a key. The URL in a browser gives me the activated message:
1597435393883.png

However, that's on a 127.20.9.x subnet, where the log was talking about 127.0.0.x subnets. Hmmm....
 

kosh42efg

n3wb
Joined
Aug 14, 2020
Messages
29
Reaction score
13
FYI - My docker in WSL isn't the Docker Desktop version with WSL, it's the version of Docker in my Ubuntu install so I could get all the nvidia gubbins...

I tested using the GPU on Docker with this:
Code:
tim@WinServer:~$ docker run --gpus all nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -gpu -benchmark
Run "nbody -benchmark [-numbodies=<numBodies>]" to measure performance.
        -fullscreen       (run n-body simulation in fullscreen mode)
        -fp64             (use double precision floating point values for simulation)
        -hostmem          (stores simulation data in host memory)
        -benchmark        (run benchmark to measure performance)
        -numbodies=<N>    (number of bodies (>= 1) to run in simulation)
        -device=<d>       (where d=0,1,2.... for the CUDA device to use)
        -numdevices=<i>   (where i=(number of CUDA devices > 0) to use for simulation)
        -compare          (compares simulation results running once on the default GPU and once on the CPU)
        -cpu              (run n-body simulation on the CPU)
        -tipsy=<file.bin> (load a tipsy model file for simulation)

NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

> Windowed mode
> Simulation data stored in video memory
> Single precision floating point simulation
> 1 Devices used for simulation
GPU Device 0: "GeForce GT 1030" with compute capability 6.1

> Compute 6.1 CUDA device: [GeForce GT 1030]
3072 bodies, total time for 10 iterations: 2.987 ms
= 31.594 billion interactions per second
= 631.882 single-precision GFLOP/s at 20 flops per interaction
This is the Docker for Deepstack:
Code:
sudo docker run --restart=always --gpus all -e VISION-SCENE=True -v localstorage:/datastore -p 83:5000 --name deepstackgpu2 deepquestai/deepstack:gpu
 
Last edited:

merkaba

Young grasshopper
Joined
Aug 4, 2017
Messages
95
Reaction score
19
Edge Vector is probably the issue. For Edge Vector to work the slider settings need to be quite a way to the left. Change Edge Vector to Simple and see if that fixes the issue.
dang, was hoping this would be it...but unfortunately same result. still makes no sense to me...i'm wondering if my ~80% RAM usage is the issue...maybe i need 16GB instead of 8gb to accommodate the break time which as far as i know is stored in RAM?
 

merkaba

Young grasshopper
Joined
Aug 4, 2017
Messages
95
Reaction score
19
Nothing is glaring me in the eye on the settings -- every thing seems to be right. What if you move the sensitivity sliders all the way to the left?
i moved two of my cameras all the way to the left just now and walked right by both of them and not a single trigger/new image showed up to be processed.
 

merkaba

Young grasshopper
Joined
Aug 4, 2017
Messages
95
Reaction score
19
I'm guessing that if you followed the video, you are using "SD'' camera feeds @ 640x480 but with your old motion detection settings of the full resolution image. 292 pixels in a 640x480 image is very large. Try lowering it.
I did follow the guide but 640x480 was too crappy for me so I switched back and used full 1080p resolution.
 
Top