Projects per year
Abstract
In this work we present a novel publicly available stereo based 3D RGB dataset for multi object zebrafish tracking, called 3D-ZeF. Zebrafish is an increasingly popular model organism used for studying neurological disorders, drug addiction, and more. Behavioral analysis is often a critical part of such research.
However, the high occlusion frequency, visual similarity, and erratic movement of the zebrafish makes robust 3D tracking a challenging and unsolved problem.
The proposed dataset consists of eight sequences with a duration between 15-120 seconds and 1-10 free moving zebrafish. The videos have been annotated with a total of 86,400 points and bounding boxes; and a complexity measure, based on the level of occlusions, is provided for all the sequences. Furthermore, we present a novel open-source modular baseline system for 3D tracking of zebrafish. The performance of the system is measured on behalf of two detectors: a naive approach and a Faster R-CNN based fish head detector. The system reaches a MOTA of up to 77.6% but there are indications that the trained head detector do not generalize well between different cohorts of zebrafish.
However, the high occlusion frequency, visual similarity, and erratic movement of the zebrafish makes robust 3D tracking a challenging and unsolved problem.
The proposed dataset consists of eight sequences with a duration between 15-120 seconds and 1-10 free moving zebrafish. The videos have been annotated with a total of 86,400 points and bounding boxes; and a complexity measure, based on the level of occlusions, is provided for all the sequences. Furthermore, we present a novel open-source modular baseline system for 3D tracking of zebrafish. The performance of the system is measured on behalf of two detectors: a naive approach and a Faster R-CNN based fish head detector. The system reaches a MOTA of up to 77.6% but there are indications that the trained head detector do not generalize well between different cohorts of zebrafish.
Original language | English |
---|---|
Title of host publication | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Number of pages | 11 |
Place of Publication | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Publisher | IEEE |
Publication date | 5 Aug 2020 |
Pages | 2426-2436 |
ISBN (Print) | 978-1-7281-7169-2 |
ISBN (Electronic) | 978-1-7281-7168-5 |
DOIs | |
Publication status | Published - 5 Aug 2020 |
Event | 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Seattle, United States Duration: 14 Jun 2020 → 19 Jun 2020 |
Conference
Conference | 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
---|---|
Country/Territory | United States |
City | Seattle |
Period | 14/06/2020 → 19/06/2020 |
Series | I E E E Conference on Computer Vision and Pattern Recognition. Proceedings |
---|---|
ISSN | 1063-6919 |
Keywords
- Computer vision
- Zebrafish
- Tracking
- Multi-object tracking
Fingerprint
Dive into the research topics of '3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset'. Together they form a unique fingerprint.Projects
- 1 Finished
Datasets
-
3D-ZeF
Pedersen, M. (Creator), Haurum, J. B. (Creator), Bengtson, S. H. (Creator) & Moeslund, T. B. (Creator), MOTChallenge, 2020
https://motchallenge.net/data/3D-ZeF20/
Dataset