Multi-View Tracker

PETS09-S2L2 AVG-TownCentre

Short name:

SVT

Benchmark:

Description:

Incorporating multiple cameras is an effective solution to improve the performance and robustness of multitarget tracking to occlusion and appearance ambiguities. In this paper,we propose a new multi-camera multi-target tracking method based on a space-time-view hyper-graph that encodes higher-order constraints (i.e., beyond pairwise relations) on 3D geometry, appearance, motion continuity, and trajectory smoothness among 2D tracklets within and across different camera views.We solve tracking in each single view
and reconstruction of tracked trajectories in 3D environment simultaneously by formulating the problem as an efficient search of dense sub-hypergraphs on the space-time-view hyper-graph using a sampling based approach.

Hardware:

2.7GHZ, 1 Core

Detector:

Public

Processing:

Batch

Last submitted:

December 10, 2015 (2 years ago)

Published:

February 20, 2017 at 18:52:50 CET

Submissions:

3

Open source:

No

Project page / code:

n/a

Reference:

Longyin Wen, Zhen Lei, Ming-Ching Chang, Honggang Qi, Siwei Lyu. Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph. IJCV, 2016.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
34.255.83.511.2 % 25.4 % 3,0577,4545326112.7GHZ, 1 CorePublic
IDF1ID PrecisionID Recall
0.00.00.0

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
PETS09-S2L247.20.056.62.64211.9 % 4.8 % 1,1403,710245292
AVG-TownCentre16.80.054.24.322611.1 % 29.2 % 1,9173,744287319

Raw data:


SVT