Just a thought. I'm not a programmer so I have no idea of difficulty or feasibility, but it would be neat!
Describe what you are trying to accomplish and why in non technical terms
I want to be able to make an object mask from bounding boxes of past detections (or maybe a definable percentage/number of pixels greater since bottom center is used and detection may vary over time) so that I can quickly mask out things incorrectly seen as people like trees at dusk/dawn, cracks in the driveway that never move.
Describe the solution you'd like
Not sure of method of implementation, but some user interface that would allow making a mask as described above with minimal interaction
Describe alternatives you've considered
Only way I know of to do this today is to manually make a mask each time something like what is mentioned above happens.
Just a thought. I'm not a programmer so I have no idea of difficulty or feasibility, but it would be neat!
Describe what you are trying to accomplish and why in non technical terms I want to be able to make an object mask from bounding boxes of past detections (or maybe a definable percentage/number of pixels greater since bottom center is used and detection may vary over time) so that I can quickly mask out things incorrectly seen as people like trees at dusk/dawn, cracks in the driveway that never move.
Describe the solution you'd like Not sure of method of implementation, but some user interface that would allow making a mask as described above with minimal interaction
Describe alternatives you've considered Only way I know of to do this today is to manually make a mask each time something like what is mentioned above happens.