Paul Johannes Claasen

Results 3 issues of Paul Johannes Claasen

I believe the Jacobian should be computed after the predict step instead of before. https://github.com/rlabbe/filterpy/blob/1d2834d5d162e17bcb5e8328e4d0f97392b0ff03/filterpy/kalman/EKF.py#L222-L242

Hi, would it be possible to share the detection results for the Dancetrack and Kitti datasets? I realise that the paper says bytetrack and permatrack were used respectively, but it...

Hello, thank you very much for making detections on the KITTI test set publicly available. Would it be possible to do the same for the KITTI training set? The reason...