Anyone have any ideas why everytime I rebuild a new release and copy and paste the files into my live folder i lose all my camera settings? i.e. cancel URL, trigger URLs, etc. it's soo annoying needing to redo them every few days...
[tool] [tutorial] Free AI Person Detection for Blue Iris
- Thread starter GentlePumpkin
- Start date
New guy here. Sorry if this has been explained already - I could not find anything.... 
Looking for AITool / docker HELP running deepquestai/deepstack:gpu and deepquestai/deepstack:latest - the cpu version (latest) works fine in docker (WSL2/Ubuntu). I cannot get the gpu version to receive data from AITool. I configured AI Server URLs as localhost:8383,localhost:8384 for cpu and gpu respectively.
I am getting this error in AITool ...Problem with AI URL: All is running on the same WIN10 PC. Why is the cpu version connecting fine on port 8383 but not the gpu version on port 8384 ???
Thank you for any hints... !
Looking for AITool / docker HELP running deepquestai/deepstack:gpu and deepquestai/deepstack:latest - the cpu version (latest) works fine in docker (WSL2/Ubuntu). I cannot get the gpu version to receive data from AITool. I configured AI Server URLs as localhost:8383,localhost:8384 for cpu and gpu respectively.
I am getting this error in AITool ...Problem with AI URL: All is running on the same WIN10 PC. Why is the cpu version connecting fine on port 8383 but not the gpu version on port 8384 ???
Thank you for any hints... !
robpur
Getting comfortable
Testing to resolve the all URLs are in use message has continued. I ran with my three old Hikvision cameras for nearly two days without trouble. During that time the new Reolink camera in the driveway was saving images into the aiinput folder, and it was defined in AI Tool, but a box was unchecked so that the images would not be processed by AI. Today I checked the box to start processing the driveway images and the problem came back. The three Hikvision cameras work just fine until I walk in front of the new camera. At that point AI Tool sends the image to DS, receives a result, sees a positive response, and then performs an alert action. Everything looks good up until that point. However, after processing starts for the next image the log shows "All URL's are in use or disabled, waiting...|506|5||17" and AI processing will not continue until I restart AI Tool.
I've tried resizing the image and changing their quality but that didn't help. I tried a different model of Reolink camera and also a spare Hikvision but they all behave the same way. At this point I can't find a way to add a fourth camera to the AI system.
I've tried resizing the image and changing their quality but that didn't help. I tried a different model of Reolink camera and also a spare Hikvision but they all behave the same way. At this point I can't find a way to add a fourth camera to the AI system.
For those running the Windows GPU I noticed Deepstack only uses about 1% of the GPU processing power so this could be of interest if you run the VorlonCD version of AITool. Note AITool will only start one instance at the moment.
From @OlafenwaMoses
You can run N number of DeepStack instances as far as you use different ports for each of the instances.
e.g
deepstack --VISION-DETECTION True --PORT 81
deepstack --VISION-DETECTION True --PORT 82
deepstack --VISION-DETECTION True --PORT 83
deepstack --VISION-DETECTION True --PORT 84
deepstack --VISION-DETECTION True --PORT 85
From @OlafenwaMoses
You can run N number of DeepStack instances as far as you use different ports for each of the instances.
e.g
deepstack --VISION-DETECTION True --PORT 81
deepstack --VISION-DETECTION True --PORT 82
deepstack --VISION-DETECTION True --PORT 83
deepstack --VISION-DETECTION True --PORT 84
deepstack --VISION-DETECTION True --PORT 85
So robpur I was having a similar issue but want to clarify before I give you bad info on what I did 1. the "4th" camera is actually loaded just throwing errors or 2. You can only add 3 total cameras to the system?
When you followed the tutorial by The Hookup have "enable motion detector" and "direct to disk recording" as options for your substream cameras however later in the video for the HD stream cameras that will produce recordings based on triggers you do not clone these cameras because if you did then you would have both "enable motion detector" and "direct to disk recording" and you don't need that on the HD streams.
Watch the video here and you do NOT want motion selected on HD stream cameras and if you are cloning from other cams you will have that. I followed the video The Hookup has and have Deepstack running in docker on a ESXI server and then I have BlueIris and AItool running on the same machine with 14 cameras and everything seems to work fine and trigger right away, I also reviewed this guys notes to confirm everything
robpur
Getting comfortable
If three of my cameras are set up in AI Tool then everything works correctly. If I add a fourth camera in AI Tool everything works correctly until the fourth camera sees motion. After that AI Tool stops sending images to DS.
I've reported the issue on Gethub and have been pointed to a development version of AI Tool that has a very different way of adding DS URLs but I haven't had time to try it yet.
Ok. I was having a similar issue however I have 8 cameras, I can't say for sure because I didn't put 2&2 together until I read your post, but with me I added a new camera which was a Reolink, after I added it in BI, I noticed in AI-Tool the trigger statement had been added automatically and was different than all my others, again I did not add it it just was there, I left it alone B/C I was getting alerts in Telegram but that is when I started getting the same error as you, I changed the trigger on the Reolink to match all the other cameras and I didn't see the error anymore. *** But I was having unrelated computer issues on my BI box and during the same time I did a clean install and started over, I did change all the triggers AFTER the re install also and I have not seen the error since. My explanation /(maybe) answer could be wrong but you may want to check it and see if it helps.
robpur
Getting comfortable
You may be on to something there. I just checked and I see that I made a stupid mistake. In older versions of AI Tool the trigger line was out in the open where you could see it. Now you have to click on the Settings button next to Actions before entering the Trigger URLs. When setting up the new camera I forgot all about the trigger URL and didn't enter my user name and password. I just fixed the line but I'm not at home and therefore can't do a walk test. I'll give it a try after work. Thanks for the tip!
I endorse the Dane Creek notes. As a total newbie, I found his hints to be very helpful. His process is 95% from The Hookup video, but he incorporates some newer techniques since the video was produced.
@Ripper99 Would you please clarify "clone" terminology? Following The Hookup video, I set mine with one camera using the HD mainstream and a second that uses the low-res substream as its mainstream. I believe everything is working as I intended, i.e. the low-res records continuously and uses motion detection (with AITOOL & Deepstack) to trigger the HD camera. From your comment I quoted above, do I interpret this as NOT a cloned camera setup?
I didn't mean clone as in cloning with in BLue Iris, I meant duplicate camera. Either way, the issue I have is not excessive motion detection, it is delayed processing of the motion. The whole thing works as expected, except it takes 5 seconds before the first motion event triggers the HD recording.
Sorry for the confusion of terms
@Ripper99 is correct. My use of the word "clone" was not actually a clone camera. Blue Iris has a function for cloning a camera. What Rob (and myself and others following the same process) are doing is actually creating a new camera in Blue Iris with just the substream for the detection and 24/7 recording. A true clone camera would be cloned within BI with identical streams to the original camera. This would not work for Rob's 24/7 stream as the HD of the clone would be recorded 24/7. A clone would only be used if you are only recording motion events the AITool flags.
I will use the clone option for my indoor cameras when I set them up as they do not need to record 24/7.
Last edited:
robpur
Getting comfortable
Did a test and the trigger was the issue. All four of the cameras are working with AI now. It was a dumb mistake that cost me time and effort. I guess I wasn't balicudb at the moment
As mentioned the development version of AI Tool has a different way of specifying AI server URLs. It looks like not only can you add multiple servers as you could before, but you can also associate cameras with specific servers. We haven't seen an official AI Tool release for a while but it's good to know that progress is being made and good things are on the way. The development version supports AWS Rekognition Server and DOODS AI Server as well as DeepStack.
Thanks @austwhite and @Ripper99 . This was a huge source of confusion to me when I was trying to figure this out, just a couple of weeks ago. It would have save me a ton of time if I had found a simple paragraph like you just gave me.
Can someone help me understand the AITool service? I've set up the service according to the instructions, and it appears to be active. But I'm not sure how to monitor it when running as a service. Is there a way to open the UI so I can look at the history/logs? If I double click and start the program manually, does that create another instance of the program that might interfere with the service, or does it just bring up the UI for the already running program? What is the best way to take a look at the UI when the service is running?
robpur
Getting comfortable
I don't know if this is still true, but at one time the answer was that you can not view the interface while running as a service, and opening AI Tool while the service is running will open another instance and it can interfere with the service. If things have changed in a later version then I'm sure someone will chime in.
I don't run as a service. My BI machine doesn't have a Windows password so upon reboot it goes directly into Windows and I have AI Tool start automatically. I suppose a disadvantage to not running as a service is that you can not have the service automatically restart or perform some other function if it fails. I use zone crossing at my most critical point just in case AI fails for some reason.
Afternoon all and thanks for all the work both creating the software and answering questions. I am brand new at all of this, but I am gradually getting the hang of much of it (I think). However, there are a few questions I haven’t really been able to answer, and I’d appreciate it if someone was able to steer me in the correct direction. Please forgive any ignorant terminology!
I have BI5 and VorlonCD’s version of AITool running as a service on a dedicated PC. I also have DeepstackAI (cpu-x3-beta) running within a docker container and it is set to auto restart as per GentlePumpkin’s instructions. My setup consists of 6x Hikvision 4MP ColorVu G1 turrets, and I will soon be adding 3x 4MP ColorVu G1 mini bullets.
Initially I set the cameras up in the HD/SD configuration described in The Hook Up’s post, but it seemed that the motion detection using the SD substream was a bit unreliable at detecting motion. I have since found some info suggesting that the number of pixels travelled to trigger the motion on the lower quality substream may need to be reduced, but I am not sure whether that was my issue. I do like the fact that this setup provides a continuous substream recording, just in case there is something important which was missed (even if the recording quality is poorer).
I then decided to switch to the ‘single camera’ setup explained on the FamilyTechExec’s post. It seems to be working quite well, although I’d prefer it if there was a way to avoid getting recordings that ultimately don’t contain any objects of interest (I am only interested in ‘persons’ on my property).
Questions:
1) I setup DeepstackAI in a docker container using GentlePumpkin’s original instructions. They refer to cpu-x3-beta which is what I ‘pulled’. The Hook Up’s post refers to pulling deepstackai:latest, and the Deepquest website also refers to cpu-x4-beta.
I was wondering whether it would be worth pulling the latest version of DeepstackAI using the ‘latest’ option (or the x4 option I presume)? I could do this and set it up to run on a different port so that in the event I stuff it up I can simply remove it and point AITool back to my currently functioning ‘cpu-x3-beta’ version.
In the event I need to remove a DeepstackAI server, is it simply a matter of deleting it from within the Docker for Windows GUI?
2) Under my current single camera setup, I was originally sending full sized JPGs from the mainstream to the aiinput folder. These files were 2688x1520 and 2-3MB in size. This was causing huge processing delays, so I changed the JPG quality to 50% which has retained the 2688x1520 dimensions but dropped the file to size to 200-600kb (according the JPGs currently sitting in my aiinput folder). Processing time has dropped to the point that the queue doesn’t build up, although if I end up with 9 cameras firing at once, I’m guessing I’ll have an issue.
I have seen recent references to using the BI JPG resize option, so I was wondering whether there is some sort of recommendation as to what sort of dimensions, quality or file size is best for the JPGs which are sent to the aiinput folder for analysis?
3) I have set up motion zones within BI as I initially found that sometimes I was getting headlights rapidly moving across some external walls on my front porch which was triggering the motion detection. I am aware that the masking option within AITool works opposite to BI in that the highlighted areas are areas within which to ignore motion. I haven’t really found any definitive instructions as to how to set up a custom mask. From what I can gather though, I need to trigger the relevant camera so that a JPG is sent to the aiinput folder, then go to the custom mask option within AITool and draw on the areas I want ignored before selecting OK and saving the camera?
Initially I was getting info at the top of the AITool dialog box saying that the camera.bmp file was missing, but I think that was because I was yet to draw the custom mask. I’m presuming the .BMP file refers to the file created by AITool once you’ve defined your custom mask areas?
Apologies for the lengthy post, but I figured it helps explain my questions better.
Thanks in advance.
I have BI5 and VorlonCD’s version of AITool running as a service on a dedicated PC. I also have DeepstackAI (cpu-x3-beta) running within a docker container and it is set to auto restart as per GentlePumpkin’s instructions. My setup consists of 6x Hikvision 4MP ColorVu G1 turrets, and I will soon be adding 3x 4MP ColorVu G1 mini bullets.
Initially I set the cameras up in the HD/SD configuration described in The Hook Up’s post, but it seemed that the motion detection using the SD substream was a bit unreliable at detecting motion. I have since found some info suggesting that the number of pixels travelled to trigger the motion on the lower quality substream may need to be reduced, but I am not sure whether that was my issue. I do like the fact that this setup provides a continuous substream recording, just in case there is something important which was missed (even if the recording quality is poorer).
I then decided to switch to the ‘single camera’ setup explained on the FamilyTechExec’s post. It seems to be working quite well, although I’d prefer it if there was a way to avoid getting recordings that ultimately don’t contain any objects of interest (I am only interested in ‘persons’ on my property).
Questions:
1) I setup DeepstackAI in a docker container using GentlePumpkin’s original instructions. They refer to cpu-x3-beta which is what I ‘pulled’. The Hook Up’s post refers to pulling deepstackai:latest, and the Deepquest website also refers to cpu-x4-beta.
I was wondering whether it would be worth pulling the latest version of DeepstackAI using the ‘latest’ option (or the x4 option I presume)? I could do this and set it up to run on a different port so that in the event I stuff it up I can simply remove it and point AITool back to my currently functioning ‘cpu-x3-beta’ version.
In the event I need to remove a DeepstackAI server, is it simply a matter of deleting it from within the Docker for Windows GUI?
2) Under my current single camera setup, I was originally sending full sized JPGs from the mainstream to the aiinput folder. These files were 2688x1520 and 2-3MB in size. This was causing huge processing delays, so I changed the JPG quality to 50% which has retained the 2688x1520 dimensions but dropped the file to size to 200-600kb (according the JPGs currently sitting in my aiinput folder). Processing time has dropped to the point that the queue doesn’t build up, although if I end up with 9 cameras firing at once, I’m guessing I’ll have an issue.
I have seen recent references to using the BI JPG resize option, so I was wondering whether there is some sort of recommendation as to what sort of dimensions, quality or file size is best for the JPGs which are sent to the aiinput folder for analysis?
3) I have set up motion zones within BI as I initially found that sometimes I was getting headlights rapidly moving across some external walls on my front porch which was triggering the motion detection. I am aware that the masking option within AITool works opposite to BI in that the highlighted areas are areas within which to ignore motion. I haven’t really found any definitive instructions as to how to set up a custom mask. From what I can gather though, I need to trigger the relevant camera so that a JPG is sent to the aiinput folder, then go to the custom mask option within AITool and draw on the areas I want ignored before selecting OK and saving the camera?
Initially I was getting info at the top of the AITool dialog box saying that the camera.bmp file was missing, but I think that was because I was yet to draw the custom mask. I’m presuming the .BMP file refers to the file created by AITool once you’ve defined your custom mask areas?
Apologies for the lengthy post, but I figured it helps explain my questions better.
Thanks in advance.
I have it working exactly like this. However I think you need to have a Windows Insider build to enable WSL to access the GPU as per here.New guy here. Sorry if this has been explained already - I could not find anything....
Looking for AITool / docker HELP running deepquestai/deepstack:gpu and deepquestai/deepstack:latest - the cpu version (latest) works fine in docker (WSL2/Ubuntu). I cannot get the gpu version to receive data from AITool. I configured AI Server URLs as localhost:8383,localhost:8384 for cpu and gpu respectively.
I am getting this error in AITool ...Problem with AI URL: All is running on the same WIN10 PC. Why is the cpu version connecting fine on port 8383 but not the gpu version on port 8384 ???
Thank you for any hints... !
I did similar to start with. I have evolved now to having this per camera:
- Low res substream - 24/7 recording with no motion detection.
- High res main stream that records video when triggered by AITool.
- A second high res main stream that records JPEG resized to 1280x720 (and not video) on motion detection that saves to the aiinput folder to trigger the tool.