Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add detector for moving laser beams #179

Open
cdondrup opened this issue Oct 12, 2015 · 0 comments
Open

Add detector for moving laser beams #179

cdondrup opened this issue Oct 12, 2015 · 0 comments
Assignees

Comments

@cdondrup
Copy link
Member

According to my understanding, please correct me if I'm wrong, everything that moves in an indoor office environment or even AAF is a human or operated by a human. Even if it is a bed or a wheelchair, if it is moved by a human, it's better to treat it as a human than treat it as an object. To this end, I'll try to make a simple detector that clusters laser beams according to the jump distance and uses the mos relation from the qsr_lib to determine if the cluster moves (maybe I'll just include the mos classification directly instead of using the library to speed it up and reduce dependencies but you get the gist). If it does move, it is a human. This should help with the creation of tracks when the humans are far away as the leg detector needs quite some time to create a hypothesis and leg candidates. If it doesn't move, than hopefully the other detectors will pick it up if it's close to the robot. If it's not close to the robot and doesn't move, it will most likely also not interact with the robot in the first place.

If anyone thinks this is a bad idea, please speak now or forever hold your peace.

@cdondrup cdondrup self-assigned this Oct 12, 2015
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant