Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 509-516 |
| Seitenumfang | 8 |
| Fachzeitschrift | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Jahrgang | XLIII-B2-2022 |
| Publikationsstatus | Veröffentlicht - 30 Mai 2022 |
| Veranstaltung | 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission III - Nice, Frankreich Dauer: 6 Juni 2022 → 11 Juni 2022 |
Abstract
Automatic detection and tracking of individual animals is important to enhance their welfare and to improve our understanding of their behaviour. Due to methodological difficulties, especially in the context of poultry tracking, it is a challenging task to automatically recognise and track individual animals. Those difficulties can be, for example, the similarity of animals of the same species which makes distinguishing between them harder, or sudden changes in their body shape which may happen due to putting on or spreading out the wings in a very short period of time. In this paper, an automatic poultry tracking algorithm is proposed. This algorithm is based on the well-known tracktor approach and tackles multi-object tracking by exploiting the regression head of the Faster R-CNN model to perform temporal realignment of object bounding boxes. Additionally, we use a multi-scale re-identification model to improve the re-association of the detected animals. For evaluating the performance of the proposed method in this study, a novel dataset consisting of seven image sequences that show chicks in an average pen farm in different stages of growth is used.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Information systems
- Sozialwissenschaften (insg.)
- Geografie, Planung und Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jahrgang XLIII-B2-2022, 30.05.2022, S. 509-516.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - Deep Learning-Based Tracking of Multiple Objects in the Context of Farm Animal Ethology
AU - Ali, R.
AU - Dorozynski, M.
AU - Stracke, J.
AU - Mehltretter, M.
PY - 2022/5/30
Y1 - 2022/5/30
N2 - Automatic detection and tracking of individual animals is important to enhance their welfare and to improve our understanding of their behaviour. Due to methodological difficulties, especially in the context of poultry tracking, it is a challenging task to automatically recognise and track individual animals. Those difficulties can be, for example, the similarity of animals of the same species which makes distinguishing between them harder, or sudden changes in their body shape which may happen due to putting on or spreading out the wings in a very short period of time. In this paper, an automatic poultry tracking algorithm is proposed. This algorithm is based on the well-known tracktor approach and tackles multi-object tracking by exploiting the regression head of the Faster R-CNN model to perform temporal realignment of object bounding boxes. Additionally, we use a multi-scale re-identification model to improve the re-association of the detected animals. For evaluating the performance of the proposed method in this study, a novel dataset consisting of seven image sequences that show chicks in an average pen farm in different stages of growth is used.
AB - Automatic detection and tracking of individual animals is important to enhance their welfare and to improve our understanding of their behaviour. Due to methodological difficulties, especially in the context of poultry tracking, it is a challenging task to automatically recognise and track individual animals. Those difficulties can be, for example, the similarity of animals of the same species which makes distinguishing between them harder, or sudden changes in their body shape which may happen due to putting on or spreading out the wings in a very short period of time. In this paper, an automatic poultry tracking algorithm is proposed. This algorithm is based on the well-known tracktor approach and tackles multi-object tracking by exploiting the regression head of the Faster R-CNN model to perform temporal realignment of object bounding boxes. Additionally, we use a multi-scale re-identification model to improve the re-association of the detected animals. For evaluating the performance of the proposed method in this study, a novel dataset consisting of seven image sequences that show chicks in an average pen farm in different stages of growth is used.
KW - Animal Science
KW - Image Sequence Analysis
KW - Multi-Object Tracking
KW - Poultry Tracking
KW - Tracktor
UR - http://www.scopus.com/inward/record.url?scp=85132038792&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLIII-B2-2022-509-2022
DO - 10.5194/isprs-archives-XLIII-B2-2022-509-2022
M3 - Conference article
AN - SCOPUS:85132038792
VL - XLIII-B2-2022
SP - 509
EP - 516
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SN - 1682-1750
T2 - 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission III
Y2 - 6 June 2022 through 11 June 2022
ER -