The detections provided by KDNT tracker


Short name:

KDNT

Benchmark:

Description:

We implement our detector based on Faster R-CNN
In our implementation, the CNN model is fine-tuned from the VGG-16 on ImageNet.

Hardware:

3.5 GHZ ,1 Core

Detector:

Public

Last submitted:

August 02, 2017 (1 year ago)

Published:

August 02, 2017 at 15:04:04 CET

Submissions:

1

Open source:

No

Project page / code:

n/a

Reference:

F. Yu, W. Li, Q. Li, Y. Liu, X. Shi, J. Yan. POI: Multiple Object Tracking with High Performance Detection and Appearance Feature. In BMTT, SenseTime Group Limited, 2016.

Benchmark performance:

APSpecifications
0.893.5 GHZ ,1 Core

Detailed performance:

Sequence AP
MOT17-010.8746
MOT17-030.9005
MOT17-060.8131
MOT17-070.8960
MOT17-080.9014
MOT17-120.7192
MOT17-140.7665

Raw data:


KDNT