SMOT: The Way They Move: Tracking Multiple Targets with Similar Appearance


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Benchmark:

MOT15 |

Short name:

SMOT

Detector:

Public

Description:

We introduce a computationally efficient algorithm for
multi-object tracking by detection that addresses four main
challenges: appearance similarity among targets, missing
data due to targets being out of the field of view or oc-
cluded behind other objects, crossing trajectories, and cam-
era motion. The proposed method uses motion dynamics as
a cue to distinguish targets with similar appearance, min-
imize target mis-identification and recover missing data.
Computational efficiency is achieved by using a General-
ized Linear Assignment (GLA) coupled with efficient proce-
dures to recover missing data and estimate the complexity
of the underlying dynamics. The proposed approach works
with tracklets of arbitrary length and does not assume a
dynamical model a priori, yet it captures the overall mo-
tion dynamics of the targets. Experiments using challenging
videos show that this framework can handle complex target
motions, non-stationary cameras and long occlusions, on
scenarios where appearance cues are not available or poor.

[Parameters]
min_s=0.017883
mota_th=0.52953
hor=13.3269
eta_max=0.72506

Reference:

C. Dicle, O. Camps, M. Sznaier. The Way They Move: Tracking Targets with Similar Appearance. In ICCV, 2013.

Last submitted:

February 20, 2015 (7 years ago)

Published:

November 01, 2014 at 03:09:33 CET

Submissions:

1

Project page / code:

Open source:

Yes

Hardware:

2.6 GHz, 16 Cores

Runtime:

2.7 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1518.20.00.020 (2.8)395 (54.8)8,78040,31034.470.60.00.00.00.00.00.00.01.51,148 (33.4)2,132 (62.0)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
ADL-Rundle-10.00.00.000000.00.00.00.00.00.00.00.00.00.000
ADL-Rundle-30.00.00.000000.00.00.00.00.00.00.00.00.00.000
AVG-TownCentre0.00.00.000000.00.00.00.00.00.00.00.00.00.000
ETH-Crossing0.00.00.000000.00.00.00.00.00.00.00.00.00.000
ETH-Jelmoli0.00.00.000000.00.00.00.00.00.00.00.00.00.000
ETH-Linthescher0.00.00.000000.00.00.00.00.00.00.00.00.00.000
KITTI-160.00.00.000000.00.00.00.00.00.00.00.00.00.000
KITTI-190.00.00.000000.00.00.00.00.00.00.00.00.00.000
PETS09-S2L20.00.00.000000.00.00.00.00.00.00.00.00.00.000
TUD-Crossing0.00.00.000000.00.00.00.00.00.00.00.00.00.000
Venice-10.00.00.000000.00.00.00.00.00.00.00.00.00.000

Raw data: