Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts
The identification of social interactions is of fundamental importance for animal behavioral studies, addressing numerous problems like investigating the influence of social hierarchical structures or the drivers of agonistic behavioral disorders. However, the majority of previous studies often rely...
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/1b25f2a545b4466b9a69717a97227715 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:1b25f2a545b4466b9a69717a97227715 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:1b25f2a545b4466b9a69717a972277152021-11-25T18:57:03ZDetecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts10.3390/s212275121424-8220https://doaj.org/article/1b25f2a545b4466b9a69717a972277152021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7512https://doaj.org/toc/1424-8220The identification of social interactions is of fundamental importance for animal behavioral studies, addressing numerous problems like investigating the influence of social hierarchical structures or the drivers of agonistic behavioral disorders. However, the majority of previous studies often rely on manual determination of the number and types of social encounters by direct observation which requires a large amount of personnel and economical efforts. To overcome this limitation and increase research efficiency and, thus, contribute to animal welfare in the long term, we propose in this study a framework for the automated identification of social contacts. In this framework, we apply a convolutional neural network (CNN) to detect the location and orientation of pigs within a video and track their movement trajectories over a period of time using a Kalman filter (KF) algorithm. Based on the tracking information, we automatically identify social contacts in the form of head–head and head–tail contacts. Moreover, by using the individual animal IDs, we construct a network of social contacts as the final output. We evaluated the performance of our framework based on two distinct test sets for pig detection and tracking. Consequently, we achieved a Sensitivity, Precision, and F1-score of 94.2%, 95.4%, and 95.1%, respectively, and a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>O</mi><mi>T</mi><mi>A</mi></mrow></semantics></math></inline-formula> score of 94.4%. The findings of this study demonstrate the effectiveness of our keypoint-based tracking-by-detection strategy and can be applied to enhance animal monitoring systems.Martin WutkeFelix HeinrichPronaya Prosun DasAnita LangeMaria GentzImke TraulsenFriederike K. WarnsArmin Otto SchmittMehmet GültasMDPI AGarticlepig detectionpig trackingconvolutional neural networkKalman filterprecision livestock farmingChemical technologyTP1-1185ENSensors, Vol 21, Iss 7512, p 7512 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
pig detection pig tracking convolutional neural network Kalman filter precision livestock farming Chemical technology TP1-1185 |
| spellingShingle |
pig detection pig tracking convolutional neural network Kalman filter precision livestock farming Chemical technology TP1-1185 Martin Wutke Felix Heinrich Pronaya Prosun Das Anita Lange Maria Gentz Imke Traulsen Friederike K. Warns Armin Otto Schmitt Mehmet Gültas Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts |
| description |
The identification of social interactions is of fundamental importance for animal behavioral studies, addressing numerous problems like investigating the influence of social hierarchical structures or the drivers of agonistic behavioral disorders. However, the majority of previous studies often rely on manual determination of the number and types of social encounters by direct observation which requires a large amount of personnel and economical efforts. To overcome this limitation and increase research efficiency and, thus, contribute to animal welfare in the long term, we propose in this study a framework for the automated identification of social contacts. In this framework, we apply a convolutional neural network (CNN) to detect the location and orientation of pigs within a video and track their movement trajectories over a period of time using a Kalman filter (KF) algorithm. Based on the tracking information, we automatically identify social contacts in the form of head–head and head–tail contacts. Moreover, by using the individual animal IDs, we construct a network of social contacts as the final output. We evaluated the performance of our framework based on two distinct test sets for pig detection and tracking. Consequently, we achieved a Sensitivity, Precision, and F1-score of 94.2%, 95.4%, and 95.1%, respectively, and a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>O</mi><mi>T</mi><mi>A</mi></mrow></semantics></math></inline-formula> score of 94.4%. The findings of this study demonstrate the effectiveness of our keypoint-based tracking-by-detection strategy and can be applied to enhance animal monitoring systems. |
| format |
article |
| author |
Martin Wutke Felix Heinrich Pronaya Prosun Das Anita Lange Maria Gentz Imke Traulsen Friederike K. Warns Armin Otto Schmitt Mehmet Gültas |
| author_facet |
Martin Wutke Felix Heinrich Pronaya Prosun Das Anita Lange Maria Gentz Imke Traulsen Friederike K. Warns Armin Otto Schmitt Mehmet Gültas |
| author_sort |
Martin Wutke |
| title |
Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts |
| title_short |
Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts |
| title_full |
Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts |
| title_fullStr |
Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts |
| title_full_unstemmed |
Detecting Animal Contacts—A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social Contacts |
| title_sort |
detecting animal contacts—a deep learning-based pig detection and tracking approach for the quantification of social contacts |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/1b25f2a545b4466b9a69717a97227715 |
| work_keys_str_mv |
AT martinwutke detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT felixheinrich detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT pronayaprosundas detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT anitalange detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT mariagentz detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT imketraulsen detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT friederikekwarns detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT arminottoschmitt detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts AT mehmetgultas detectinganimalcontactsadeeplearningbasedpigdetectionandtrackingapproachforthequantificationofsocialcontacts |
| _version_ |
1718410509650231296 |