GMPHD_HDA: Online Multi-Object Tracking with Hierarchical Data Association using the GMPHD filter

MOT16-01


Benchmark:

MOT16 |

Short name:

GMPHD_HDA

Detector:

Public

Description:

Stage 1: low-level association between targets states and observations(i.e., detection responses), frame by frame
-We only used detection reponses with the positive confidence value among provided detection results

Stage 2: short tracklet elimination under the set length(parameter)
-Minimum tracklet length for mid-level association : 10

Stage 3: mid-level association between rough tracklets(almost fragmented or ID swtiched)
-Only Motion and size are used
-Appearance is not used

Reference:

Y. Song, M. Jeon. Online Multiple Object Tracking with the Hierarchically Adopted GM-PHD Filter using Motion and Appearance. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2016.

Last submitted:

August 07, 2016 (3 years ago)

Published:

August 09, 2016 at 22:37:16 CET

Submissions:

1

Open source:

No

Hardware:

3.5 GHz, 1 Core

Runtime:

13.6 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT1630.533.475.435 (4.6)453 (59.7)5,169120,97033.692.20.9539 (16.0)731 (21.7)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
MOT16-0123.928.072.62131514,69526.691.80.32135
MOT16-0337.438.975.77601,66763,59939.296.11.1206293
MOT16-0628.728.872.8181311,4306,71741.877.11.276116
MOT16-0725.127.874.313528011,90027.194.00.65191
MOT16-0820.023.078.503659912,72324.087.01.06862
MOT16-1221.828.475.82526315,79030.279.90.76242
MOT16-1413.420.174.2512641115,54615.987.70.55592

Raw data:


GMPHD_HDA