The Way They Move: Tracking Multiple Targets with Similar Appearance

TUD-Crossing PETS09-S2L2 ETH-Jelmoli ETH-Linthescher ETH-Crossing AVG-TownCentre ADL-Rundle-1 ADL-Rundle-3 KITTI-16 KITTI-19

Short name:

SMOT

Benchmark:

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

Hardware:

2.6 GHz, 16 Cores

Detector:

Public

Processing:

Batch

Last submitted:

February 20, 2015 (2 years ago)

Published:

November 01, 2014 at 03:09:33 CET

Submissions:

1

Open source:

Yes

Project page / code:

Reference:

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

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
18.271.21.52.8 % 54.8 % 8,78040,3101,1482,1322.6 GHz, 16 CoresPublic
IDF1ID PrecisionID Recall
0.00.00.0

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing43.90.073.00.2137.7 % 15.4 % 355503348
PETS09-S2L234.40.070.01.1420.0 % 23.8 % 4755,602251514
ETH-Jelmoli28.10.073.50.6458.9 % 40.0 % 2711,5124183
ETH-Linthescher14.80.074.10.11971.5 % 78.7 % 837,46958106
ETH-Crossing19.30.074.70.1263.8 % 65.4 % 16784911
AVG-TownCentre15.00.070.01.32262.2 % 58.4 % 5995,40476217
ADL-Rundle-16.70.071.46.6326.3 % 25.0 % 3,2905,172221373
ADL-Rundle-317.90.072.43.6446.8 % 25.0 % 2,2335,873240255
KITTI-1619.70.073.20.6170.0 % 29.4 % 1151,2094276
KITTI-1914.10.066.50.8621.6 % 48.4 % 8803,61098307
Venice-112.60.071.71.7170.0 % 41.2 % 7833,12579142

Raw data:


CEM
SMOT
TBD