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


Benchmark:

Short name:

RSCNN

Detector:

Public

Description:

n/a

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.

Processing:

Batch

Last submitted:

October 07, 2017 (2 years ago)

Published:

July 08, 2017 at 23:21:06 CET

Submissions:

4

Open source:

No

Hardware:

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
2D MOT 201529.537.073.193.0262.011,86630,474976

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN ID Sw.
ADL-Rundle-120.133.172.68.03.03,4573,828150
ADL-Rundle-336.039.177.57.08.01,2505,17186
AVG-TownCentre28.640.169.720.079.07484,157200
ETH-Crossing26.930.477.91.018.0227065
ETH-Jelmoli51.157.676.114.014.033986933
ETH-Linthescher35.440.476.817.0116.01435,57255
KITTI-1641.342.072.02.01.031164642
KITTI-1930.844.567.37.014.01,0252,57995
PETS09-S2L240.029.371.84.06.06784,885222
TUD-Crossing75.563.876.08.00.04320918
Venice-1-26.523.770.25.03.03,8501,85270

Raw data:


RSCNN