Is it possible to setup Blue Iris to use the Dahua AI instead of Codeproject or DeepStack? I'm currently have Deepstack reporting the following triggers: Human, Vehicle, Any general motion (so nothing fancy). I would like to eliminate the Deepstack and be able to see these different events on my timeline using the built in Dahua AI engine with the cute little icons (person, vehicle, bolt) lol.....any advice?
Dahua AI
- Thread starter Vansmak
- Start date
You may find that the camera AI has got so good that doing CodeProject is kinda overkill and adds more complexity, time delay, and potential for issues.
Whether to use camera AI or BI AI is obviously up to you, but of course, the AI in the camera may be more than sufficient for your needs without needing BI AI. Do you need the orange box around every object? Do you want to identify animals or logos? Or is just human or vehicle sufficient.
The camera AI is useful to many people, but BI has way more motion setting granularity than the cameras, and some people need that additional detail, especially if wanting AI for more than a car or person. For folks that want AI and alerts on animals or specifically a UPS truck then they need the additional AI.
There isn't really a best practice because every field of view is different and use case and needs are different.
To many here, BI motion without AI is more than adequate for what they do.
To many here, camera AI is more than adequate for what they do.
To many here, using the BI AI adds additional functionality that the above alone can not do.
It comes down to testing with each field of view and which one gives you the most consistent results.
While some of that third party stuff is cool like tagging was it a dog or a bear, I don't need all that fancy stuff. If my camera triggers BI to tag an alert for human or vehicle and BI can accomplish what I need by way of a text or email or push or whatever, that is sufficient for my needs. I just want to be alerted if a person or vehicle is on my property and the camera AI does a fine job with that.
However, I do run BI AI on a few cameras so that it knocks out headlight shine so that the alert image includes the vehicle. The camera AI will trigger for a car, but the alert image was always just the headlights. I also run the ANPR AI module.
The true test....I have found the AI of the cameras to work even in a freakin blizzard....imagine how much the CPU/GPU would be maxing out sending all the snow pictures for analysis to CodeProject LOL. My non-AI cams in BI were triggering all night. This picture was ran through AI (without the IVS or red lines on it) and it failed to recognize a person in the picture, but the camera AI did. This pic says it all and the video had the red box over it even in complete white out on the screen:
See this thread on how using just Dahua AI may be sufficient for your needs:
Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?
Last edited:
You may find that the camera AI has got so good that doing CodeProject is kinda overkill and adds more complexity, time delay, and potential for issues.
Whether to use camera AI or BI AI is obviously up to you, but of course, the AI in the camera may be more than sufficient for your needs without needing BI AI. Do you need the orange box around every object? Do you want to identify animals or logos? Or is just human or vehicle sufficient.
The camera AI is useful to many people, but BI has way more motion setting granularity than the cameras, and some people need that additional detail, especially if wanting AI for more than a car or person. For folks that want AI and alerts on animals or specifically a UPS truck then they need the additional AI.
There isn't really a best practice because every field of view is different and use case and needs are different.
To many here, BI motion without AI is more than adequate for what they do.
To many here, camera AI is more than adequate for what they do.
To many here, using the BI AI adds additional functionality that the above alone can not do.
It comes down to testing with each field of view and which one gives you the most consistent results.
While some of that third party stuff is cool like tagging was it a dog or a bear, I don't need all that fancy stuff. If my camera triggers BI to tag an alert for human or vehicle and BI can accomplish what I need by way of a text or email or push or whatever, that is sufficient for my needs. I just want to be alerted if a person or vehicle is on my property and the camera AI does a fine job with that.
However, I do run BI AI on a few cameras so that it knocks out headlight shine so that the alert image includes the vehicle. The camera AI will trigger for a car, but the alert image was always just the headlights. I also run the ANPR AI module.
The true test....I have found the AI of the cameras to work even in a freakin blizzard....imagine how much the CPU/GPU would be maxing out sending all the snow pictures for analysis to CodeProject LOL. My non-AI cams in BI were triggering all night. This picture was ran through AI (without the IVS or red lines on it) and it failed to recognize a person in the picture, but the camera AI did. This pic says it all and the video had the red box over it even in complete white out on the screen:
See this thread on how using just Dahua AI may be sufficient for your needs:
Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?
Fantastic answer as always, do the cameras supplied by Andy wong have Dahua Onvif as well?
I have some cameras in front that have the same issue with car headlights but the cameras behind my house dont have that so I might go Dahu Onvif for some spare CPU capacity.
Yes his cameras do that.
While I am a big fan of advocate for the camera AI, there are a few instances that CPAI is better or a better compliment.
Here is an example. At night the camera AI would struggle with this tight view. It has a straight on angle of the street to get a side profile of a car and it would miss it a lot of times because the vehicle just isn't in the field of view long enough, so this is a great candidate for CPAI.
Now the issue I had with CPAI is that it would either find a car but the alert image would be the lightshine on the street or just a part of the vehicle, or it would trigger out nothing found due to headlight bounce off the street.
CPAI has a "to cancel" option, which means it will analyze EVERY image to determine if the item is in it. Once I added a cancel Giraffe in the field, it now will go thru all the images and select the best one, which gives me the whole vehicle in the frame and it eliminated the nothing found as well. It makes for scrubbing video much quicker as I can skip looking at video of known vehicles.
While I am a big fan of advocate for the camera AI, there are a few instances that CPAI is better or a better compliment.
Here is an example. At night the camera AI would struggle with this tight view. It has a straight on angle of the street to get a side profile of a car and it would miss it a lot of times because the vehicle just isn't in the field of view long enough, so this is a great candidate for CPAI.
Now the issue I had with CPAI is that it would either find a car but the alert image would be the lightshine on the street or just a part of the vehicle, or it would trigger out nothing found due to headlight bounce off the street.
CPAI has a "to cancel" option, which means it will analyze EVERY image to determine if the item is in it. Once I added a cancel Giraffe in the field, it now will go thru all the images and select the best one, which gives me the whole vehicle in the frame and it eliminated the nothing found as well. It makes for scrubbing video much quicker as I can skip looking at video of known vehicles.
Yes his cameras do that.
While I am a big fan of advocate for the camera AI, there are a few instances that CPAI is better or a better compliment.
Here is an example. At night the camera AI would struggle with this tight view. It has a straight on angle of the street to get a side profile of a car and it would miss it a lot of times because the vehicle just isn't in the field of view long enough, so this is a great candidate for CPAI.
Now the issue I had with CPAI is that it would either find a car but the alert image would be the lightshine on the street or just a part of the vehicle, or it would trigger out nothing found due to headlight bounce off the street.
CPAI has a "to cancel" option, which means it will analyze EVERY image to determine if the item is in it. Once I added a cancel Giraffe in the field, it now will go thru all the images and select the best one, which gives me the whole vehicle in the frame and it eliminated the nothing found as well. It makes for scrubbing video much quicker as I can skip looking at video of known vehicles.
Thanks for your detailed explanations on the pros and cons of Camera AI. I would be very interested in setting up a camera or two to test it out versus CodeProject. Would it be possible to outline the setup involved to make the cameras talk to BI when passing the AI information for those that aren't as versed?
With the addition of "animals" to the latest firmware in the 5442 s3 series, I quit CodeProject for now and am relying on the cam's IVS and it has performed very well.
In the camera's web setup, just enable IVS and draw your tripwires and intrusion areas.
In BI's Video Tab, under Configure, be sure "Get ONVIF trigger events is checked.
Under the Trigger" tab, UNcheck Motion Sensor, and CHECK ONVIF/Camera events.
Under the configure part of that, I disable all profiles except "RuleEngine/LineDetector/Crossed" and "RuleEngine/FieldDetector/Objects inside"
Under "alert" tab, I disable the motion zones in the Trigger sources and zones section.
I think that's all you need to start...