V_IOU: Visual Intersection Over Union Tracker

CVPR19-04


Short name:

V_IOU

Detector:

Public

Description:

Extending IOU Based Multi-Object Tracking by Visual Information

Reference:

E. Bochinski, T. Senst, T. Sikora. Extending IOU Based Multi-Object Tracking by Visual Information. In IEEE International Conference on Advanced Video and Signals-based Surveillance, 2018.

Last submitted:

June 11, 2019 (1 year ago)

Published:

June 16, 2019 at 00:00:00 CET

Submissions:

1

Open source:

No

Hardware:

3.4GHz, 1 Core

Runtime:

18.2 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
CVPR 2019 Tracking Challenge46.746.078.2288 (22.9)306 (24.4)33,776261,96453.289.87.52,589 (48.6)4,354 (81.8)

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag
CVPR19-0462.355.481.22151011,970117,09863.299.00.99441,290
CVPR19-0626.431.971.6269617,11078,48740.175.517.09451,775
CVPR19-0753.650.575.936201,47413,68258.792.92.5218334
CVPR19-0814.225.870.1118913,22252,69731.965.116.4482955

Raw data: