This software package provides a reference implementation for the classic object tracker used in: The tracker operates in three stages: First, objects are detected in each frame independently using the DPM object detector by Ross Girshick and Pedro Felzenszwalb. Second, all detections with a positive score are associated to detections in the next frame using appearance and the bounding box overlap. Prediction is performed using a Kalman filter and we associate detections between both frames via the Hungarian method for bipartite matching. To gap occlusions and missed detections, we also associate tracklets with each other in a third stage. Similarly to the second stage, the Hungarian algorithm is employed but this time based on an occlusion sensitive appearance model and regression of the bounding boxes in one tracklet from the bounding boxes in the other tracklet. The algorithm outputs all associated tracklets which are longer than three frames. We tried to keep dependencies as small as possible, but to get started you are going to need at least: This code is published under the GNU General Public License. Instructions on how to use these datasets to demo this software package are contained in the accompanying readme file. When using this software we will be happy if you cite the following related publications:
@phdthesis{Geiger2013,
  author = {Andreas Geiger},
  title = {Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms},
  school = {KIT},
  year = {2013}
}
@article{Geiger2014PAMI,
  author = {Andreas Geiger and Martin Lauer and Christian Wojek and Christoph Stiller and Raquel Urtasun},
  title = {3D Traffic Scene Understanding from Movable Platforms},
  journal = {Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2014}
}
@inproceedings{Zhang2013ICCV,
  author = {Hongyi Zhang and Andreas Geiger and Raquel Urtasun},
  title = {Understanding High-Level Semantics by Modeling Traffic Patterns},
  booktitle = {International Conference on Computer Vision (ICCV)},
  year = {2013}
}