Ask Your Question
0

IMM UKF PDA - Multiple Object Tracking

asked 2019-08-29 08:57:50 -0500

controlsgeek gravatar image

Hi! Thank You kosuke_murakami for providing the package. I have gone through the package thoroughly.

From what I understand, there are multiple PDAF running in parallel which is not similar to JointPDAF (JPDAF), isn't it? I wanted to confirm this since I was planning to implement JPDAF with existing code.

Apart from that, will it be useful to do gating not only using Mahalanobis distance but also using euclidean distance??

In one of my dataset, there are 2 cars taking a right turn, and the cars come very close. After passing each other, and few seconds later the id of one car is assigned to another car, and the first car is assigned a new id. I guess the covariance matrices grow large and cause this switch. But an euclidean gating of reasonable threshold might solve it. Any views?

Thanks

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted
1

answered 2019-09-02 02:52:49 -0500

kosuke_murakami gravatar image

Thank you for the question.

will it be useful to do gating not only using Mahalanobis distance but also using euclidean distance??

It could be useful. You can use Hungarian algorithm for dealing with various costs. If you want to do that, you need to write on your own codes. This package could be helpful. https://gitlab.com/autowarefoundation...

edit flag offensive delete link more

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

Stats

Asked: 2019-08-28 21:30:10 -0500

Seen: 32 times

Last updated: Sep 02