EAGS16: Enhancing Association Graph with Super-voxel for Multi-object Tracking

MOT16-01


Benchmark:

MOT16 |

Short name:

EAGS16

Detector:

Public

Description:

n/a

Reference:

H. Sheng, X. Zhang, Y. Zhang, Y. Wu, J. Chen. Enhanced Association with Supervoxels in Multiple Hypothesis Tracking. In IEEE Access, 2018.

Last submitted:

July 08, 2017 (3 years ago)

Published:

December 07, 2018 at 09:50:50 CET

Submissions:

2

Project page / code:

n/a

Open source:

No

Hardware:

3 GHZ, 1 Core

Runtime:

197.3 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1647.450.175.9131 (17.3)324 (42.7)8,36986,93152.391.91.4575 (11.0)913 (17.5)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0137.748.672.76101383,83340.194.90.31439
MOT16-0354.852.375.939265,04841,95059.992.53.4280441
MOT16-0649.661.674.6461115225,24554.592.30.45093
MOT16-0743.545.674.45165698,58047.493.21.170123
MOT16-0832.139.779.7102195210,34438.287.01.57487
MOT16-1239.854.478.115446034,37347.386.70.71727
MOT16-1428.539.875.3109653712,60631.891.60.770103

Raw data: