Recurrent Autoregressive Networks for Online Multi-Object Tracking

MOT16-01 MOT16-03 MOT16-06 MOT16-07 MOT16-08 MOT16-12 MOT16-14

Short name:

RAR16wVGG

Benchmark:

Description:

Recurrent autoregressive networks tracking framework with faster R-CNN detections

Hardware:

Titan X, 1.5GHZ, 1Core

Detector:

Private

Processing:

Online

Last submitted:

March 17, 2017 (2 years ago)

Published:

July 23, 2018 at 09:33:01 CET

Submissions:

2

Open source:

No

Project page / code:

Reference:

K. Fang, Y. Xiang, X. Li, S. Savarese. Recurrent Autoregressive Networks for Online Multi-Object Tracking. In The IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
63.078.82.339.9 % 22.1 % 13,66353,2484821,251Titan X, 1.5GHZ, 1CorePrivate
IDF1ID PrecisionID Recall
63.872.656.9

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0159.558.578.01.22352.2 % 8.7 % 5452,0202244
MOT16-0371.368.478.75.814860.8 % 9.5 % 8,70021,129134579
MOT16-0666.073.180.60.822150.2 % 21.3 % 9482,9323783
MOT16-0759.355.178.91.25431.5 % 7.4 % 6075,96079130
MOT16-0836.340.381.01.16322.2 % 33.3 % 6899,88380116
MOT16-1246.660.279.70.78624.4 % 41.9 % 6553,7433044
MOT16-1450.257.476.22.016423.2 % 26.8 % 1,5197,581100255

Raw data:


RAR16wVGG
HCC