8000 GitHub - thanhtinhvan/MCMOT: Real time one-stage multi-class & multi-object tracking based on anchor-free detection and re-id
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Real time one-stage multi-class & multi-object tracking based on anchor-free detection and re-id

Notifications You must be signed in to change notification settings

thanhtinhvan/MCMOT

 
 

Repository files navigation

MCMOT

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
You can refer to origin fork FairMOT

Tracking demo

image

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.


[baidu drive link](https://pan.baidu.com/s/1imrim0kt72_Ay9w-X4kqdw) extract code:ej4p
[one drive link](https://1drv.ms/u/s!AmgjV-Jny9CqkX2EneIkb6Q8x6WI?e=Lsqx4G)

About

Real time one-stage multi-class & multi-object tracking based on anchor-free detection and re-id

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.6%
  • Shell 0.4%
0