AP_HWDPL_p: Appearance Model with R-CNN

PETS09-S2L2


Benchmark:

MOT15 |

Short name:

AP_HWDPL_p

Detector:

Public

Description:

Online tracking with appearance model based on R-CNN from Huawei (HWDPL).

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.

Last submitted:

December 13, 2016 (4 years ago)

Published:

September 26, 2017 at 09:20:18 CET

Submissions:

2

Project page / code:

n/a

Open source:

No

Hardware:

GTX 1080, 2.3 GHz, 1 Core

Runtime:

6.7 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1538.547.135.063 (8.7)270 (37.4)4,00533,20346.087.637.932.942.465.035.467.476.70.7586 (12.8)1,263 (27.5)

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-135.343.634.64105735,41341.887.241.329.444.171.931.766.076.71.13981
ADL-Rundle-343.351.939.8796435,07650.188.843.037.247.170.740.571.781.01.04785
AVG-TownCentre28.444.731.69639414,00544.077.032.031.436.956.534.159.771.72.1169412
ETH-Crossing34.242.330.61162063037.294.931.330.032.772.930.978.881.70.11013
ETH-Jelmoli52.965.545.210131781,00160.589.647.642.954.966.647.269.979.60.41637
ETH-Linthescher39.447.536.5171241855,18541.995.343.231.150.362.632.473.678.80.24471
KITTI-1640.761.137.33216083151.184.541.234.043.868.137.361.774.10.81835
KITTI-1934.350.633.52206632,80547.579.334.732.838.461.036.060.172.60.643147
PETS09-S2L238.934.324.1145525,16446.489.017.932.820.549.534.967.075.01.3179328
TUD-Crossing61.364.144.8521440163.698.044.745.050.968.247.573.277.90.11227
Venice-139.148.735.947762,69241.096.144.129.347.269.930.371.176.40.2927

Raw data:


AP_HWDPL_p