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

KITTI-19


Benchmark:

MOT15 |

Short name:

RSCNN

Detector:

Public

Description:

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.

Last submitted:

October 07, 2017 (4 years ago)

Published:

July 08, 2017 at 23:21:06 CET

Submissions:

4

Project page / code:

n/a

Open source:

No

Hardware:

Runtime:

4.0 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1529.537.029.693 (12.9)262 (36.3)11,86630,47450.472.327.232.630.067.139.256.276.72.1976 (19.4)1,176 (23.3)

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-120.133.128.8833,4573,82858.961.325.433.326.972.645.747.676.36.9150152
ADL-Rundle-336.039.130.8781,2505,17149.180.027.035.228.375.240.065.180.12.08681
AVG-TownCentre28.640.130.020797484,15741.880.031.229.635.665.532.361.773.91.7200283
ETH-Crossing26.930.423.21182270629.693.123.522.826.370.023.774.681.10.155
ETH-Jelmoli51.157.642.1141433986965.783.141.043.346.768.750.964.379.40.83341
ETH-Linthescher35.440.431.3171161435,57237.695.934.228.837.075.729.876.080.10.15564
KITTI-1641.342.031.42131164662.077.225.139.730.746.247.559.176.31.54257
KITTI-1930.844.530.87141,0252,57951.772.929.832.334.458.038.153.672.51.095160
PETS09-S2L240.029.323.4466784,88549.387.515.934.717.357.137.466.475.61.6222255
TUD-Crossing75.563.845.5804320981.095.436.057.643.958.562.673.779.30.21818
Venice-1-26.523.723.3533,8501,85259.441.321.525.823.959.246.632.473.38.67060

Raw data: