TrackEval
TrackEval copied to clipboard
JonathonLuiten
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
Hi Jonathon, this is Alessandro, we got in touch by email ([email protected]). This is the pull request for the addition of our new PersonPath22 benchmark. As mentioned in the email,...
It is easy to calculate hota metrics after detection/gt match. But it is quite confusing about matching rule. From the paper, hota is calculated independently under different iou threshold for...
Hi I'm trying to evaluate tracking results on a custom dataset which has been converted to the KITTI 2d format. I downloaded the example data for some clarity on the...
When running `scripts/run_mot_challenge.py` and specifying `SEQMAP_FILE` in the command line, the script crashes. This is because the script parses this argument as a list ([line 56](https://github.com/JonathonLuiten/TrackEval/blob/master/scripts/run_mot_challenge.py#L56)) while `/trackeval/datasets/mot_challenge_2d_box.py` expects it...
The MOT challenge format description for tracking with bounding boxes on the MOT challenge website as well as here: https://github.com/JonathonLuiten/TrackEval/blob/master/docs/MOTChallenge-format.txt say that the columns are: > \, \, \, \,...
Where is work examples? where is the description for the supported track data formats? You are compare your code with py-motmetrics in benchmark, but documentation and decription py-motmetrics is much...
Consider as a thought experiment a ground truth object and two prediction cases. Case 1: Detections are predicted that perfectly match the ground truth object positions. The first 90% have...
Hey, first of all thank you for your great work. And second I have a little question about the computation of the TP FN and FP. There have to be...
I downloaded data.zip file as recommended on the repository Readme (https://github.com/JonathonLuiten/TrackEval#quickly-evaluate-on-supported-benchmarks). I noticed that gt (groundtruth) data for the mot_challenge contains 9 fields. Whereas, on the TrackEval repo (in the...
Hey, Im using TrackEval for evaluation of the same tracker with different parameter. So I have arround 120 tracker Folder each with to result files of two sequences. Im using...
Metadata
Owner
Metadata
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).