Appearance Model with R-CNN

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

Short name:

APRCNN_Pub

Benchmark:

Description:

Online tracking with appearance model based on R-CNN

Hardware:

GTX 1080, 2.3 GHz, 1 Core

Detector:

Public

Processing:

Online

Last submitted:

December 13, 2016 (10 months ago)

Published:

September 26, 2017 at 09:20:18 CET

Submissions:

3

Open source:

No

Project page / code:

n/a

Reference:

C. Long, A. Haizhou, S. Chong, Z. Zijie, B. Bo. Online Multi-Object Tracking with Convolutional Neural Networks. In 2017 IEEE International Conference on Image Processing (ICIP), 2017.

Benchmark performance:

MOTAMOTPFAFMTMLFPFNID Sw.FragSpecificationsDetector
38.572.60.78.7 % 37.4 % 4,00533,2035861,263GTX 1080, 2.3 GHz, 1 CorePublic
IDF1ID PrecisionID Recall
47.168.435.9

Detailed performance:

Sequence MOTA IDF1 MOTP FAF GT MT ML FP FN ID Sw Frag
TUD-Crossing61.364.173.10.11338.5 % 15.4 % 144011227
PETS09-S2L238.934.370.81.3422.4 % 9.5 % 5525,164179328
ETH-Jelmoli52.965.575.90.44522.2 % 28.9 % 1781,0011637
ETH-Linthescher39.447.575.20.21978.6 % 62.9 % 1855,1854471
ETH-Crossing34.242.379.50.1263.8 % 61.5 % 206301013
AVG-TownCentre28.444.766.92.12264.0 % 27.9 % 9414,005169412
ADL-Rundle-135.343.672.21.13212.5 % 31.3 % 5735,4133981
ADL-Rundle-343.351.977.61.04415.9 % 20.5 % 6435,0764785
KITTI-1640.761.168.90.81717.6 % 11.8 % 1608311835
KITTI-1934.350.667.70.6623.2 % 32.3 % 6632,80543147
Venice-139.148.771.80.21723.5 % 41.2 % 762,692927

Raw data:

n/a


APRCNN_Pub