multi Correlation filter tracking using hierarchy of convolution features + minimum-cost network flow.

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

Short name:

RSCNN

Benchmark:

Description:

n/a

Hardware:

Detector:

Public

Processing:

Batch

Last submitted:

October 07, 2017 (2 months ago)

Published:

July 08, 2017 at 23:21:06 CET

Submissions:

4

Open source:

No

Project page / code:

n/a

Reference:

Heba Mahgoub, Khaled Mostafa, Khaled T. Wassif and Ibrahim Farag, “Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues” International Journal of Advanced Computer Science and Applications(IJACSA), 8(11), 2017.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
29.573.12.112.9 % 36.3 % 11,86630,4749761,176Public
IDF1ID PrecisionID Recall
37.045.031.4

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing75.563.876.00.21361.5 % 0.0 % 432091818
PETS09-S2L240.029.371.81.6429.5 % 14.3 % 6784,885222255
ETH-Jelmoli51.157.676.10.84531.1 % 31.1 % 3398693341
ETH-Linthescher35.440.476.80.11978.6 % 58.9 % 1435,5725564
ETH-Crossing26.930.477.90.1263.8 % 69.2 % 2270655
AVG-TownCentre28.640.169.71.72268.8 % 35.0 % 7484,157200283
ADL-Rundle-120.133.172.66.93225.0 % 9.4 % 3,4573,828150152
ADL-Rundle-336.039.177.52.04415.9 % 18.2 % 1,2505,1718681
KITTI-1641.342.072.01.51711.8 % 5.9 % 3116464257
KITTI-1930.844.567.31.06211.3 % 22.6 % 1,0252,57995160
Venice-1-26.523.770.28.61729.4 % 17.6 % 3,8501,8527060

Raw data:

n/a


RSCNN