Search results

  1. TBurt

    People can mask USPS AI detections

    After using this for a few days now I can report it is working very well for me. I am using it for FexEd, UPS, Amazon, DSL, and of course USPS. I had one false positive at night for one of the delivery services. No big deal as I now have it turn off the delivery model at night. I do not get...
  2. TBurt

    Don’t repeat my mistake with the ‘Custom model folder’

    I did the same thing and found out the hard way. My computer's memory usage was hitting 97%-99% and getting the BI error Ai not responding. Then BI would stop responding for several seconds, then start working again only to freeze up again. I now have two Deep Stack model folders. One with...
  3. TBurt

    People can mask USPS AI detections

    Thank you ! Seems to work with the few FedEx and USPS recordings from the last couple of days. I also do not really care about Target, but I left in all the delivery objects to see which may or may not give me false alerts. I like how fast and light on resources this model runs. Openlogo is a...
  4. TBurt

    IP Cam Talk Custom Community DeepStack Model

    I found that general 3.0 gives me more false positives for person/people. This is especially true for trees and bushes. I use it because it never misses a car or person/people at night. I have to mask off trees/etc to fix it. For cameras that send push alerts like my driveway, and front and...
  5. TBurt

    IP Cam Talk Custom Community DeepStack Model

    I think general v3.1 is working great for me. It has grabbed some catches that I had to look twice at. It caught a vehicle it said. I looked at the screen shot thinking it was mistaken. But on second look, it caught my neighbor backing out of their driveway between the "V" of two branches of...
  6. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    The closest thing to that would be to send the alert triggered by the camera to Deep Stack and have it The closest thing to that would be to send the alert triggered by the camera to Deep Stack and have it categorize the alerts. This is actually a little better as DS will label a vehicle for...
  7. TBurt

    Multiple images for the same person

    Just add a number to the end of each image for the face. For example, images for Tim would be something like tim1, tim2, tim3. You have BI look for tim* in the confirm/cancel areas of Blue Iris. If any of the "tim" images match, it will go with that. Just be sure to use the same upper/lower...
  8. TBurt

    IP Cam Talk Custom Community DeepStack Model

    Thank you for this change. That is the one thing that drove me crazy when using the original dark model. I like the "person" or "Person" to differentiate the two running models.
  9. TBurt

    IP Cam Talk Custom Community DeepStack Model

    It's looking good so far on the cams I loaded it one even in this short of time. It appears fast and highly accurate. You have once again outdone yourself! Thanks, Mike!
  10. TBurt

    Alert when dog is at back door for more than 10 seconds?

    It might have loitering detection for the Dahua camera will only work for a person, maybe vehicles. The Ai inside the chip of the camera is are set to ignore everything else as these cameras are really designed to serve companies, not people's homes. For that, they sell Imour line of cameras...
  11. TBurt

    Yet another Custom DeepStack model aimed to detect people

    It seems to when it detects an object that it was trained with t does it fast and accurately. People for example... But if the object is a little different, then it can fail totally and not see anything. I noticed this really on cars. Autos come in all shapes and sizes. Front pickups to cars...
  12. TBurt

    DeepStack Case Study: Performance from CPU to GPU version

    What bitrate do you run your substreams at?
  13. TBurt

    Yet another Custom DeepStack model aimed to detect people

    Ok, it seems to be working correctly now and every model is getting along with each other. I didn't really do anything. Actually, I did reboot the computer so maybe that fixed my DS issues. It seems for cars, it is getting about 10% higher results than the combined model. It seems actually...
  14. TBurt

    Yet another Custom DeepStack model aimed to detect people

    Well, the model is fast and very accurate. Running the model through some saved videos using it and Combined, the new one was just about always higher in %. It also ran about 50 to 60ms per camera on my GTX 1060 3GB. That is up there with combined speed-wise. Now I did run into one problem...
  15. TBurt

    Yet another Custom DeepStack model aimed to detect people

    I put it on a couple of cameras. I will let it run overnight using both the combined model and this one. Should be interesting to compare the two models. I am using person, dog, car (chel, etc) to test it. I will report back tomorrow after I let the two models run.
  16. TBurt

    IP Cam Talk Custom Community DeepStack Model

    I tried your model out last night and found it really nice. I like how you broke "truck" down into types and made trucks, pick-ups, garbage, vans, etc. I just looked through the recordings today and your model works wonderfully. It was not slow, yet seems accurate so far. (as for cars...
  17. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    I noticed that. It had already started working within reason for me just changing the version a while back. It was not placing my starting point for videos all over the place and at least putting it in the middle of the screen. So it was easy enough to find the spot of trigger. It was...
  18. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    I think you explained it better than I did. I have a clone on the camera that is setup with BI+DS, the clone master does the camera ONVIF/external motion triggers. The only thing different between the two are the trigger sources. The BI+DS works perfect, pretrigger buffers and all. The cam...
  19. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    That is how I have it setup up also. Actually, I think it was from reading your posts that I set it up that way. They have been doing a lot of DAT file/database changes in the last several version updates. I think I am off to try some older versions to see if it makes any difference,
  20. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    I have DS working with BI just fine. So, I know what BI is supposed to do... but I haven't used external Ai ONVIF triggering before. It is not behaving anywhere close to what I am used to. I asked to advise on what I should try next. Not to "Works for me!" posts. Obviously, it works for...
  21. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    I am impressed with the accuracy from the onboard AI but with regards to BI recording the triggers it seems to vary wildly. What I mean is when you click the image to load the video of the event BI+ DS usually takes you to the begins of the trigger. With the cam AI Blue Iris seems to randomly...
  22. TBurt

    Is there a way to use Imou ranger 2 as web cam on windows ?

    Imou has a windows app that works a lot like the Android version for the most part. It will allow you to record the camera to your PC directly. I am not sure if it does the AI person detection record to PC though. I think you have to manually hit record, but I could be wrong on that part. I...
  23. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    I thought the same about DS until I added a GTX 1060 to it. Using general.pt (or even the larger combined) model with DS (high, using 640 Sub streams) I have seen detection times dip into the 30ms territory at times. Normal is still fast in the 40s to 50s. s. I tried running it on my main...
  24. TBurt

    Who uses Dahua AI capable cameras? Reliable AI for triggering events? Pro's/con's?

    I just got a Dahua camera with AI (IPC-HDW3849H-AS-PV). I never made it a priority when shopping for cameras. I was using Deep Stack with really good success. But after reading several members posts I decided to try it. I made a clone of the camera (to compare BI+DS vs BI+DS+Dahua AI) and...
  25. TBurt

    IP Cam Talk Custom Community DeepStack Model

    Will do. I will have to go back and reread the label creation part of this thread. I think my ADHD was really bad that day when I originally read your instructions. I will try to get them labeled and ready to send to you by Monday or Tuesday. How many images should I shoot for? How many...
  26. TBurt

    IP Cam Talk Custom Community DeepStack Model

    Strang, it thinks my dog is usually a bird, and on occasions a cat. Then a dog is in third place. To be fair she does kind of look like a bird / cat in the burned screen shots. LOL I am pretty sure I am running the latest combined model, but I will go back and make sure. I've been meaning...
  27. TBurt

    IP Cam Talk Custom Community DeepStack Model

    If it is a good as 1.x versions then I am excited! The first ones were excellent. I used to get a few "person" flags of people in cars driving by my house on the stock/dark objects model. On yours, I got several alone today that I noticed. I had to look twice at what DS was saying was a...
  28. TBurt

    I need advice if one CPU is really better than the other for BI.

    My vote would be the I5 8500. 6 cores without hyperthreading are going to be better overall than 4 cores with hyperthreading. Hyperthreading can make something like from -5% to +20% speed difference depending on the work/threads the CPU core is working on. But two real cores running two more...
  29. TBurt

    DeepStack Case Study: Performance from CPU to GPU version

    Crap, I went with 11.5. It seems to be working so far for the last week on my GTX 1060. What kind of problems would running the newer version cause?
  30. TBurt

    Deepstack not detecting anything, how to debug?

    You have your min duration (make time) set to 120 seconds. That means BI will wait for 120 seconds AFTER the rest of the motion detection parameters (like min object size, contrast, etc) have been met before sending it to Deepstack. So by the time DS gets it, there isn't much to see and DS...