SegTrack: Joint Tracking and Segmentation of Multiple Targets


Benchmark:

Short name:

SegTrack

Detector:

Public

Description:

We propose a multi-target tracker that exploits low level image
information and associates every (super)-pixel to a specific target or
classifies it as background. As a result, we obtain a video
segmentation in addition to the classical bounding-box representation in
unconstrained, real-world videos.

Project page / code:

Reference:

A. Milan, L. Leal-Taixé, K. Schindler, I. Reid. Joint Tracking and Segmentation of Multiple Targets. In CVPR, 2015.

Processing:

Batch

Last submitted:

April 10, 2015 (4 years ago)

Published:

April 10, 2015 at 11:33:33 CET

Submissions:

3

Open source:

Yes

Hardware:

2.7 GHz, 1 Core

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201522.531.571.742.0461.07,89039,020697

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-17.835.872.38.011.03,3815,11686
ADL-Rundle-330.834.973.95.014.09146,04968
AVG-TownCentre3.38.669.32.0195.02356,528151
ETH-Crossing23.430.774.01.017.0217398
ETH-Jelmoli28.943.072.94.019.02821,50914
ETH-Linthescher11.115.173.86.0160.02077,70627
KITTI-1640.255.273.80.03.01468656
KITTI-1921.835.465.92.026.08793,22279
PETS09-S2L246.135.870.611.07.01,2133,773211
TUD-Crossing53.949.372.83.03.03745615
Venice-119.729.171.90.06.05753,05732

Raw data:


SegTrack