Skip to content

Latest commit

 

History

History

4_TC_tracker

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 

4_TC_tracker

This is an implementation of tracklet clustering for 2D tracking.

Note that this SCT method has been upgraded to TrackletNet Tracker (TNT). The corresponding paper on arXiv is here. The source code (training + testing) is provided here.

Introduction

In SCT, the loss function in our data association algorithm consists of motion, temporal and appearance attributes. Especially, a histogram-based adaptive appearance model is designed to encode long-term appearance change. The change of loss is incorporated with a bottom-up clustering strategy for the association of tracklets. Robust 2D-to-3D projection is achieved with EDA optimization applied to camera calibration for speed estimation.

How to Build & Use

Please refer to Gaoang Wang's GitHub repository, where detailed instructions of configuration and installation are provided.

Input & Output Format

For input detection results in text, the format of each line is as follows:

<frame_id>,-1,<xmin>,<ymin>,<width>,<height>,<confidence>,-1,-1,-1,<class>

This is similar to the required format of MOTChallenge. The frame ID is 0-based. The confidence is in percentage.

For output 2D tracking results in text, the format of each line is as follows:

<frame_id>,<obj_id>,<xmin>,<ymin>,<width>,<height>,<confidence>,-1,-1,-1,<class>

This is similar to the required format of MOTChallenge. The frame ID and object ID are both 0-based. The confidence is in percentage.

Disclaimer

For any question you can contact Zheng (Thomas) Tang.