kalman_pub: ByteTrack: Multi-Object Tracking by Associating Every Detection Box

MOT20-04


Benchmark:

MOT17 | MOT20 |

Short name:

kalman_pub

Detector:

Public

Description:

Reference:

Y. Zhang, P. Sun, Y. Jiang, D. Yu, F. Weng, Z. Yuan, P. Luo, W. Liu, X. Wang. ByteTrack: Multi-Object Tracking by Associating Every Detection Box. In Proceedings of the European Conference on Computer Vision (ECCV), 2022.

Last submitted:

November 23, 2021 (8 months ago)

Published:

July 27, 2022 at 18:41:16 CET

Submissions:

1

Open source:

Yes

Hardware:

v100

Runtime:

17.7 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT2067.070.256.4592 (47.7)263 (21.2)9,685160,30369.097.458.354.865.073.657.781.484.12.2680 (0.0)1,738 (0.0)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT20-0484.182.666.4481506,91136,29786.897.264.468.671.077.272.981.784.43.3253755
MOT20-0649.753.742.5551051,28565,24550.998.145.040.251.966.341.880.783.31.3251605
MOT20-0766.267.954.5421490910,17869.396.253.755.760.071.659.382.486.01.691121
MOT20-0836.441.834.4149458048,58337.398.040.129.548.160.730.480.082.70.785257

Raw data:


kalman_pub