This is the implementation of the Poisson Multi Bernoulli Mixture Filter
for the Master Thesis Multi-Object Tracking using either Deep Learning or PMBM filtering
by Erik Bohnsack and Adam Lilja
at Chalmers University of Technology, spring of 2019.
The implementation is done in Python 3.7 and it has only been tested on Ubuntu 16.04 and MacOS 10.13.6.
python 3.7
- Get Murty-submodule
git submodule update
- Install Murty
pip3 install ./murty
- filterpy
pip3 install filterpy
- motmetrics
pip3 install motmetrics
- deap
pip3 install deap
KITTI training sequence 20. Simulated object detections with noise, clutter and miss detections. Constant Acceleration motion model.
KITTI training sequence 16. Simulated object detections with noise, clutter and miss detections. Constant Acceleration motion model.
Check runforrest.ipynb