One-shot multi-class multi-object tracking(单阶段实时多类别多目标跟踪)
This is an extention work of FairMOT, which extends the one-class multi-object tracking to multi-class multi-object tracking
Pretained model for detection and tracking
HRNet18 with bi-linear upsampling replaced with de-convolution
The pre-trained model is for 5 classes detection & tracking: car, bicycle, person, cyclist, tricycle, which can be used for road traffic video surveillance and analysis.