Robust Online Multi-target Visual Tracking using a HISP Filter with Discriminative Deep Appearance Learning


Short name:

HISP_DAL

Benchmark:

Description:

n/a

Hardware:

3 GHZ, 1 Core

Detector:

Public

Processing:

Online

Last submitted:

July 09, 2019 (3 months ago)

Published:

July 27, 2019 at 15:09:33 CET

Submissions:

2

Open source:

No

Project page / code:

n/a

Reference:

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
37.476.30.57.6 % 50.9 % 3,222108,8652,1012,1513 GHZ, 1 CorePublic
IDF1ID PrecisionID Recall
30.551.521.7

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0124.125.473.30.1238.7 % 56.5 % 574,7485168
MOT16-0344.232.076.50.814811.5 % 27.7 % 1,19056,2119251,150
MOT16-0640.142.873.70.32217.2 % 52.0 % 2996,408209183
MOT16-0732.127.474.40.8547.4 % 48.1 % 41710,381279278
MOT16-0827.523.979.70.8637.9 % 46.0 % 48111,385267172
MOT16-1234.233.777.20.58610.5 % 51.2 % 4874,773200104
MOT16-1416.621.175.40.41643.0 % 72.0 % 29114,959170196

Raw data:

n/a


HISP_DAL