Coloscott
Young grasshopper
here's the setup and two history shots.Maybe post some pics of ai tool setup and history results
here's the setup and two history shots.Maybe post some pics of ai tool setup and history results
Click here and have it only display positives.. something must be triggering bi to take pics.. have you got any positive alerts with AI tool? Can you walk out there and try to set it off?here's the setup and two history shots.
It sees a "person" in one shot and a "car" in another, neither of which are either and it shows them over and over. Both are stationary. It looks like it's showing the same alerts over and over again every 3 mins which is what I have set for Cooldown Time. This is coming together in my mind now. Is there a way to help "tune" the AI engine so it will ignore those pretty obvious mis identifications?Click here and have it only display positives.. something must be triggering bi to take pics.. have you got any positive alerts with AI tool? Can you walk out there and try to set it off?
I've had that problem when neighbor parks in there back yard and something triggers the camera.. it identifies the car even tho it was already there, it doesn't know that.. solution for me was to mask out tiny areas on the clone camera where ai tool was picking objects up just because they were already there.. maybe turn sensitivity on clone down some tooIt sees a "person" in one shot and a "car" in another, neither of which are either and it shows them over and over. Both are stationary. It looks like it's showing the same alerts over and over again every 3 mins which is what I have set for Cooldown Time. This is coming together in my mind now. Is there a way to help "tune" the AI engine so it will ignore those pretty obvious mis identifications?
You should set your confidence level higher. Around 80 or 90%It sees a "person" in one shot and a "car" in another, neither of which are either and it shows them over and over. Both are stationary. It looks like it's showing the same alerts over and over again every 3 mins which is what I have set for Cooldown Time. This is coming together in my mind now. Is there a way to help "tune" the AI engine so it will ignore those pretty obvious mis identifications?
Done. Thank you! Do I need to restart anything after this change?You should set your confidence level higher. Around 80 or 90%
I think that's a little high, just my opinionYou should set your confidence level higher. Around 80 or 90%
Works great for me. But yes, it may be that different values fits different situations.I think that's a little high, just my opinion
The shadows are too dark for accurate AI, if you can not improve the contrast, then you increasing the confidence levels in BI Tool and masking those problem areas will help.FilterIt sees a "person" in one shot and a "car" in another, neither of which are either and it shows them over and over. Both are stationary. It looks like it's showing the same alerts over and over again every 3 mins which is what I have set for Cooldown Time. This is coming together in my mind now. Is there a way to help "tune" the AI engine so it will ignore those pretty obvious miss identifications?
Yep the AI Tool, identifies objects. Unlike say a Dahua NVR with AI it does not identify new or removed objects. AI Tool analyses each image in isolation, which for me I am very happy with this tool.I've had that problem when neighbor parks in there back yard and something triggers the camera.. it identifies the car even tho it was already there, it doesn't know that.. solution for me was to mask out tiny areas on the clone camera where ai tool was picking objects up just because they were already there.. maybe turn sensitivity on clone down some too
Caused by a corrupt camera file. File deleted and re-installed. Back to normal.Has anyone come across this? My system has been working faulessly for months with V1.65 but found this today. AI Tools final message is can't load cameras.
Exception Text
System.InvalidOperationException: Invoke or BeginInvoke cannot be called on a control until the window handle has been created.
at System.Windows.Forms.Control.MarshaledInvoke(Control caller, Delegate method, Object[] args, Boolean synchronous)
at System.Windows.Forms.Control.Invoke(Delegate method, Object[] args)
at WindowsFormsApp2.Shell.IncrementErrorCounter()
at WindowsFormsApp2.Shell.<Log>d__22.MoveNext()
--- End of stack trace from previous location where exception was thrown ---
at System.Runtime.CompilerServices.AsyncMethodBuilderCore.<>c.<ThrowAsync>b__6_0(Object state)
Loaded Assemblies
mscorlib
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4180.0 built by: NET48REL1LAST_B
CodeBase: file:/C:/Windows/Microsoft.NET/Framework/v4.0.30319/mscorlib.dll
----------------------------------------
aitool
Assembly Version: 1.0.0.0
Win32 Version: 1.0.0.0
CodeBase: file:/C:/Users/Chris%20Cuthbert/Documents/AI%20Tool%201.65/Release/aitool.exe
----------------------------------------
System.Windows.Forms
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4084.0 built by: NET48REL1
CodeBase: file:/C:/WINDOWS/Microsoft.Net/assembly/GAC_MSIL/System.Windows.Forms/v4.0_4.0.0.0__b77a5c561934e089/System.Windows.Forms.dll
----------------------------------------
System
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4084.0 built by: NET48REL1
CodeBase: file:/C:/WINDOWS/Microsoft.Net/assembly/GAC_MSIL/System/v4.0_4.0.0.0__b77a5c561934e089/System.dll
----------------------------------------
System.Drawing
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4084.0 built by: NET48REL1
CodeBase: file:/C:/WINDOWS/Microsoft.Net/assembly/GAC_MSIL/System.Drawing/v4.0_4.0.0.0__b03f5f7f11d50a3a/System.Drawing.dll
----------------------------------------
System.Net.Http
Assembly Version: 4.2.0.0
Win32 Version: 4.6.26011.01
CodeBase: file:/C:/Users/Chris%20Cuthbert/Documents/AI%20Tool%201.65/Release/System.Net.Http.DLL
----------------------------------------
System.Configuration
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4190.0 built by: NET48REL1LAST_B
CodeBase: file:/C:/WINDOWS/Microsoft.Net/assembly/GAC_MSIL/System.Configuration/v4.0_4.0.0.0__b03f5f7f11d50a3a/System.Configuration.dll
----------------------------------------
System.Core
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4180.0 built by: NET48REL1LAST_B
CodeBase: file:/C:/WINDOWS/Microsoft.Net/assembly/GAC_MSIL/System.Core/v4.0_4.0.0.0__b77a5c561934e089/System.Core.dll
----------------------------------------
System.Xml
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4084.0 built by: NET48REL1
CodeBase: file:/C:/WINDOWS/Microsoft.Net/assembly/GAC_MSIL/System.Xml/v4.0_4.0.0.0__b77a5c561934e089/System.Xml.dll
----------------------------------------
System.Windows.Forms.DataVisualization
Assembly Version: 4.0.0.0
Win32 Version: 4.8.4084.0
CodeBase: file:/C:/WINDOWS/Microsoft.Net/assembly/GAC_MSIL/System.Windows.Forms.DataVisualization/v4.0_4.0.0.0__31bf3856ad364e35/System.Windows.Forms.DataVisualization.dll
----------------------------------------
I'm sad to admit I've spent the past 5 hours trying to get DeepStack to work and I have had zero luck. I tried running the Windows version and python kept crashing repeatedly. I saw in the troubleshooting section the recommendation was to just run as a Docker. So I rolled my sleeves up and created a brand new Ubuntu virtual machine in Hyper-V, installed Docker, then ran the docker using DeepStack's instructions. For some reason I am not getting prompted to activate when I browse to the website - it keeps telling me the brand new docker instance is already activated. When I do see AI Tools communicating to DeepStack, I'm getting either 403 or 401 error messages.
It can't/shouldn't be this hard... what in the world am I doing wrong?
View attachment 67006
Post a pic of your bi clone camera record tab settingsShould it literally be "[Summary]" like in the URL example, or is there some sort of variable we're supposed to use or set up?
I really want to like this and use it, but I'm getting an almost 2 minute delay in processing an image - by the time it processes the activity is long over.
View attachment 67128
Is deepstack on the bi machine?If I'm understanding the logs correctly, it's looking like my deepstack processing is averaging 35-40 seconds. Guess I need to focus my attention to speeding that up!