Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification

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

Short name:

MOTDT

Benchmark:

Description:

Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

Hardware:

GTX 1080, 2.3 GHz, 1 Core

Detector:

Public

Processing:

Online

Last submitted:

October 30, 2017 (11 months ago)

Published:

July 06, 2018 at 09:12:13 CET

Submissions:

2

Open source:

Yes

Project page / code:

Reference:

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
47.674.81.615.2 % 38.3 % 9,25385,4317921,858GTX 1080, 2.3 GHz, 1 CorePublic
IDF1ID PrecisionID Recall
50.969.240.3

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
MOT16-0140.142.871.30.52317.4 % 30.4 % 2293,5643577
MOT16-0355.454.774.83.514826.4 % 15.5 % 5,28840,937361848
MOT16-0645.151.373.60.522115.4 % 44.3 % 5875,66782219
MOT16-0744.148.673.61.35411.1 % 29.6 % 6448,374101263
MOT16-0834.639.579.01.16315.9 % 36.5 % 66910,173104143
MOT16-1238.951.776.30.98614.0 % 40.7 % 7684,2623576
MOT16-1426.441.174.01.41646.1 % 54.3 % 1,06812,45474232

Raw data:


MOTDT