PHDTT: Pedestrian Heads Detection and Tracking with Transformer


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Benchmark:

Short name:

PHDTT

Description:

Reference:

Vo, Xuan-Thuy, et al. "Pedestrian Head Detection and Tracking via Global Vision Transformer." International Workshop on Frontiers of Computer Vision. Springer, Cham, 2022.

Last submitted:

September 06, 2021 (2 years ago)

Published:

August 07, 2021 at 09:52:06 CET

Submissions:

3

Project page / code:

n/a

Open source:

No

Hardware:

Tesla V100

Runtime:

21.2 Hz

Benchmark performance:

Sequence MOTA IDF1 IDEucl HOTA MT ML FP FN Rcll Prcn DetPr DetRe ID Sw. Frag
Head Tracking 2160.647.952.636.11,104 (47.1)188 (8.0)132,714184,21578.183.257.754.215,004 (0.0)41,556 (0.0)

Detailed performance:

Sequence MOTA IDF1 IDEucl HOTA MT ML FP FN Rcll Prcn DetPr DetRe ID Sw. Frag
HT21-1179.063.765.647.88441,4854,62084.794.569.762.42321,254
HT21-1272.057.663.140.75141136,82448,58484.587.858.956.72,35213,883
HT21-1337.324.927.020.21926366,25660,49872.370.447.949.29,96219,005
HT21-1468.459.755.143.42235911,51446,60475.092.468.155.28382,551
HT21-1555.144.352.433.1915116,63523,90974.580.856.852.41,6204,863

Raw data: