Naive: Naive

ZebraFish-05


Benchmark:

Short name:

Naive

Description:

Utilizes a "Naive" object detection approach in order to detect the fish and their head points. Tracklet creation is performed first in each 2D view and then associated across views. Lastly the tracklets are combined in to full tracks when possible.

Reference:

M. Pedersen, J. Haurum, S. Bengtson, T. Moeslund. 3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

Last submitted:

June 16, 2020 (3 months ago)

Published:

June 16, 2020 at 11:44:29 CET

Submissions:

1

Project page / code:

Open source:

Yes

Hardware:

4 GHZ, 1 Core

Runtime:

1.8 Hz

Benchmark performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag MTBFm
3D-ZeF2051.063.034.42 (11.1)0 (0.0)1,3706,55259.687.60.418 (30.2)520 (8.7)9.0

Detailed performance:

Sequence MOTA IDF1 MOTP MT ML FP FN Recall Precision FAF ID Sw. Frag MTBFm
ZebraFish-0579.488.934.6102815782.696.40.003012.2
ZebraFish-0678.488.236.6104534480.997.00.104416.2
ZebraFish-0740.354.932.8005772,10453.280.60.662005.9
ZebraFish-0848.058.634.6007203,94756.187.50.8122469.8

Raw data: