Open kevtan opened 3 years ago
Hi again Kevin, you sound like you really know your stuff and have some great ideas. Is this something you've already worked with in another context? Again, I know nothing about current ML methods of object tracking but certainly a better autotracker is always desirable. Tell us more!
On Sat, Nov 14, 2020 at 10:04 AM Kevin Tan notifications@github.com wrote:
Hi there again! This is a RFC to see if people would be interested in an ML-based auto-tracking tool. It seems like the current auto-tracker uses a slightly brittle template-matching system and I've been having trouble with it especially when the lighting in the image in variable and an object (e.g. a bouncy ball) enters and exits a shadowy region. I think a lot of modern object detection/localization ML methods might be able to dramatically increase the fidelity of the auto-tracking system. Let me know what you think!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/OpenSourcePhysics/tracker/issues/33, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAXIBFH6ZBEZJ73C7TJADEDSP3BC5ANCNFSM4TVVXEAA .
Hi Doug, again, sorry for the untimely response. Happy Thanksgiving! I haven't worked on specifically object tracking but I have worked on some machine learning projects in the past. I'm more of a computer systems guy than an artificial intelligence person, but I can ask around to see what I might be able to find out. I'll touch base when I hear back!
Hi there again! This is a RFC to see if people would be interested in an ML-based auto-tracking tool. It seems like the current auto-tracker uses a slightly brittle template-matching system and I've been having trouble with it especially when the lighting in the image in variable and an object (e.g. a bouncy ball) enters and exits a shadowy region. I think a lot of modern object detection/localization ML methods might be able to dramatically increase the fidelity of the auto-tracking system. Let me know what you think!