Near Online Multi-target Tracker with Aggregated Local Flow Descriptor with SDP detections

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

Short name:

NOMTwSDP

Benchmark:

Description:

We trained a private detector (SDP + RPN) using the MOT16 training dataset. The tracker model/parameters are identical to NOMT.

The detections are available at http://www-personal.umich.edu/~wgchoi/mot2d_sdp_dets.zip. Notice that there are many same videos in MOT2D and MOT16 training dataset. So, one should be careful using the detections for the training dataset.

The timing excludes detection time. With a K40 GPU, the detector runs at approximately 2 FPS.

@inproceedings{yang2016sdp,
title={Exploit All the Layers: Fast and Accurate CNN
Object Detector with Scale Dependent Pooling and
Cascaded Rejection Classifiers},
author={Fan Yang and Wongun Choi and Yuanqing Lin},
booktitle={Proceedings of the IEEE International
Conference on Computer Vision and Pattern Recognition},
year={2016}
}

Hardware:

2.4 GHz Xeon, 16 Cores

Detector:

Private

Processing:

Batch

Last submitted:

April 19, 2016 (1 year ago)

Published:

April 19, 2016 at 19:03:12 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
55.576.61.039.0 % 25.8 % 5,59421,3224277012.4 GHz Xeon, 16 CoresPrivate
IDF1ID PrecisionID Recall
59.169.351.5

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing80.480.474.80.11361.5 % 7.7 % 121941010
PETS09-S2L265.947.375.71.14228.6 % 7.1 % 4632,697124190
ETH-Jelmoli51.063.578.91.14540.0 % 37.8 % 469766820
ETH-Linthescher66.070.379.60.519741.1 % 35.5 % 5682,4234156
ETH-Crossing60.870.782.80.22626.9 % 50.0 % 38347810
AVG-TownCentre56.664.972.21.522641.2 % 22.1 % 6582,324121177
ADL-Rundle-147.555.076.32.23237.5 % 21.9 % 1,0963,7692530
ADL-Rundle-355.454.382.40.84434.1 % 15.9 % 4704,0214239
KITTI-1647.769.571.21.71741.2 % 5.9 % 3515281027
KITTI-1939.462.368.71.36237.1 % 14.5 % 1,3811,82533137
Venice-144.850.776.80.21729.4 % 47.1 % 882,42855

Raw data:


NOMTwSDP