IMM UKF PDA - Multiple Object Tracking

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?? Since the Joint Probability is not being calculated and will make the association more robust?

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?

Please follow our support guidelines.

Thanks for your question. However we ask that you please ask questions on http://answers.ros.org following our support guidelines: http://wiki.ros.org/Support

ROS Discourse is for news and general interest discussions. ROS Answers provides a Q&A site which can be filtered by tags to make sure the relevant people can find and/or answer the question, and not overload everyone with hundreds of posts.