Head Tracking 21 Results

Click on a measure to sort the table accordingly. See below for a more detailed description.



Benchmark Statistics

TrackerMOTAIDF1IDEuclHOTAMTMLFPFNRcllPrcnDetPrDetReID Sw.FragHz
HeadHunterT
1. online method
57.8
±17.4
53.9 54.2 36.8 747 (31.9)465 (19.9)51,840 299,459 64.4 91.3 60.8 42.9 4,394 (0.0)15,146 (0.0)0.4
R. Sundararaman, C. De Almeida Braga, E. Marchand, J. Pettre. Tracking Pedestrian Heads in Dense Crowd. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
SequencesFramesTrajectoriesBoxes
5572329651086790

Difficulty Analysis

Sequence difficulty (from easiest to hardest, measured by average MOTA)

HT21-11

HT21-11

(82.3 MOTA)

HT21-15

HT21-15

(77.0 MOTA)

HT21-14

HT21-14

(68.4 MOTA)

HT21-12

HT21-12

(60.7 MOTA)

HT21-13

HT21-13

(32.7 MOTA)


Evaluation Measures

Lower is better. Higher is better.
Measure Better Perfect Description
MOTA higher 100%Multi-Object Tracking Accuracy (+/- denotes standard deviation across all sequences) [1]. This measure combines three error sources: false positives, missed targets and identity switches.
IDF1 higher 100%ID F1 Score [2]. The ratio of correctly identified detections over the average number of ground-truth and computed detections.
IDEucl higher 100%IDEucl [3]. Duration correctly tracked in image coordinates (IDEucl = % of length covered in image coordinate),IDEucl,ASC,Computes the ratio of the track length covered by the best possible hypothesis (in terms of image coordinates) to the ground truth trajectory le...
HOTA higher 100%Higher Order Tracking Accuracy [4]. Geometric mean of detection accuracy and association accuracy. Averaged across localization thresholds.
MT higher 100%Mostly tracked targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at least 80% of their respective life span.
ML lower 0%Mostly lost targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at most 20% of their respective life span.
FP lower 0The total number of false positives.
FN lower 0The total number of false negatives (missed targets).
Rcll higher 100%Ratio of correct detections to total number of GT boxes.
Prcn higher 100%Ratio of TP / (TP+FP).
DetPr higher 100%Detection Precision [4]. TP /(TP + FP) averaged over localization thresholds.
DetRe higher 100%Detection Recall [4]. TP /(TP + FN) averaged over localization thresholds.
ID Sw. lower 0Number of Identity Switches (ID switch ratio = #ID switches / recall) [5]. Please note that we follow the stricter definition of identity switches as described in the reference
Frag lower 0The total number of times a trajectory is fragmented (i.e. interrupted during tracking).
Hz higher Inf.Processing speed (in frames per second excluding the detector) on the benchmark. The frequency is provided by the authors and not officially evaluated by the MOTChallenge.

Legend

Symbol Description
online method This is an online (causal) method, i.e. the solution is immediately available with each incoming frame and cannot be changed at any later time.
using public detections This method used the provided detection set as input.
using private detections This method used a private detection set as input.
new This entry has been submitted or updated less than a week ago.

References:


[1] Bernardin, K. & Stiefelhagen, R. Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics. Image and Video Processing, 2008(1):1-10, 2008.
[2] Ristani, E., Solera, F., Zou, R., Cucchiara, R. & Tomasi, C. Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. In ECCV workshop on Benchmarking Multi-Target Tracking, 2016.
[3] Sundararaman, R., Braga, C.D.A., Marchand, E. & Pettre, J. Tracking Pedestrian Heads in Dense Crowd. In Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[4] Jonathon Luiten, A.O. & Leibe, B. HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking. International Journal of Computer Vision, 2020.
[5] Li, Y., Huang, C. & Nevatia, R. Learning to associate: HybridBoosted multi-target tracker for crowded scene. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009.