TrackEval issues

What is the purpose of <conf> column?

1

I am trying to compute MOT metrics. I logically assumed that the **conf** column describes the confidence of an observation (a float between 0 and 1). However, recently I've found...

slavafive

Is there an easy way of evaluating on half of MOT17?

1

I am experimenting quite a lot with trackers and continuously evaluating on MOT17. Even with a multi-gpu setup the evaluation process is very time consuming. Is there an easy way...

mikel-brostrom

How to directly specify sequences to eval and their number of timesteps using `SEQ_INFO`

2

According to: https://github.com/JonathonLuiten/TrackEval/blob/ec237ec3ef654548fdc1fa1e100a45b31a6d4499/trackeval/datasets/mots_challenge.py#L33 It should be possible to specify seq + their associated timesteps such that the `seqinfo.ini` files are not needed. How should the input data look like for...

mikel-brostrom

Should MOTP be higher or lower?

2

First of all thank you for your work on this repository! I'm using this repository to evaluate my custom tracking algorithm and I'm getting MOTP values of around 85%. I'm...

ignaciomendizabal

Support BEV or 3D tracking?

1

Hi~ Thanks for your excellent work! Could the current codebase support BEV or 3D tracking? And if not, how could I modify it to achieve this? Looking forward to your...

PhyllisH

Is there a plan to visualize tracking results?

like add a option for draw and output video

yuanyue668

AttributeError: module 'numpy' has no attribute 'float'

1

In newer numpy versions `np.float` is deprecated. I suggest you change all these: https://github.com/JonathonLuiten/TrackEval/search?q=np.float&type=code For: `np.float64`

mikel-brostrom