I'm using 6 images and analyze every 500 ms. I'm curious if that's too few images, since it means it will analyze 6 images within 3 seconds. What settings are you using and do you use different settings for day and night profiles? Thanks!
Deepstack "images" and "analyze every" settings
- Thread starter 105437
- Start date
Every field of view is different. Some only need a few and some may need 10 or more. It comes down to trial and error for your own field of view to make sure it captures what you want.
Keep in mind that unless you add something in the "to cancel" box, that if it identifies the object within 2 images, the remaining 4 are not sent. Only if you add something in the "to cancel" box will it analyze all 6 images in your case.
Yes, I use different ones for day or night for some cameras.
At night, my one camera, that has a straight on angle of the street to get a side profile of a car, 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.
Once I added a cancel banana 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.
Keep in mind that unless you add something in the "to cancel" box, that if it identifies the object within 2 images, the remaining 4 are not sent. Only if you add something in the "to cancel" box will it analyze all 6 images in your case.
Yes, I use different ones for day or night for some cameras.
At night, my one camera, that has a straight on angle of the street to get a side profile of a car, 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.
Once I added a cancel banana 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.