mosse-object-tracking's Introduction

MOSSE Tracking Algorithm

This is the python implementation of the - Visual object tracking using adaptive correlation filters.

Requirements

python - 3.5.2
opencv-python

How to use the code

Step 1

python demo.py

Step2

Use mouse to select the object which needs to be tracked and Press Enter to start tracking.

Demo

Reference:

[1] Visual object tracking using adaptive correlation filters

mosse-object-tracking's People

Contributors

Stargazers

Watchers

mosse-object-tracking's Issues

about PSR

Very poor performance when rotate init_frame

There is low Peak-to-Sidelobe Ratio in the method

I have read the paper and used the calculate method of PSR to measure the code of this repository. I found that the psr is lower than the paper say. MOSSE usually has 20 ~60 psr. But this code only has 7 psr in your demo. Why is this?

An exception has occurred, use %tb to see the full traceback. SystemExit: 2

When run this program on own my system as well as on google colab
It show following error

usage: ipykernel_launcher.py [-h] [--lr LR] [--sigma SIGMA]
[--num_pretrain NUM_PRETRAIN] [--rotate]
[--record]
ipykernel_launcher.py: error: unrecognized arguments: -f /home/devendra/.local/share/jupyter/runtime/kernel-d371ed5b-4ea8-4af0-8766-421c787c2c38.json

An exception has occurred, use %tb to see the full traceback.

SystemExit: 2

Please give solution

Recommend Projects