MDP: Learning to Track: Online Multi-Object Tracking by Decision Making

ADL-Rundle-1


Benchmark:

MOT15 |

Short name:

MDP

Detector:

Public

Description:

Online Multi-Object Tracking (MOT) has wide applications in time-critical video analysis scenarios, such as robot navigation and autonomous driving. In tracking-by-detection, a major challenge of online MOT is how to robustly associate noisy object detections on a new video frame with previously tracked objects. In this work, we formulate the online MOT problem as decision making in Markov Decision Processes (MDPs), where the lifetime of an object is modeled with a MDP. Learning a similarity function for data association is equivalent to learning a policy for the MDP, and the policy learning is approached in a reinforcement learning fashion which benefits from both advantages of offline-learning and online-learning for data association. Moreover, our framework can naturally handle the birth/death and appearance/disappearance of targets by treating them as state transitions in the MDP while leveraging existing online single object tracking methods. We conduct experiments on the MOT Benchmark to verify the effectiveness of our method.

Reference:

Y. Xiang, A. Alahi, S. Savarese. Learning to Track: Online Multi-Object Tracking by Decision Making. In International Conference on Computer Vision (ICCV), 2015.

Last submitted:

April 20, 2015 (9 years ago)

Published:

March 31, 2015 at 12:53:29 CET

Submissions:

5

Open source:

Yes

Hardware:

3.5 Ghz, 8 cores

Runtime:

1.1 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1530.344.732.594 (13.0)277 (38.4)9,71732,42247.274.934.331.337.767.836.257.475.21.7680 (14.4)1,500 (31.8)

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: