Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting
With increasing herd sizes came an enhanced requirement for automated systems to support the farmers in the monitoring of the health and welfare status of their livestock. Cattle are a highly sociable species, and the herd structure has important impact on the animal welfare. As the behaviour of the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/10/12/2402 |
| _version_ | 1797544603591639040 |
|---|---|
| author | Jennifer Salau Joachim Krieter |
| author_facet | Jennifer Salau Joachim Krieter |
| author_sort | Jennifer Salau |
| collection | DOAJ |
| description | With increasing herd sizes came an enhanced requirement for automated systems to support the farmers in the monitoring of the health and welfare status of their livestock. Cattle are a highly sociable species, and the herd structure has important impact on the animal welfare. As the behaviour of the animals and their social interactions can be influenced by the presence of a human observer, a camera based system that automatically detects the animals would be beneficial to analyse dairy cattle herd activity. In the present study, eight surveillance cameras were mounted above the barn area of a group of thirty-six lactating Holstein Friesian dairy cows at the Chamber of Agriculture in Futterkamp in Northern Germany. With Mask R-CNN, a state-of-the-art model of convolutional neural networks was trained to determine pixel level segmentation masks for the cows in the video material. The model was pre-trained on the Microsoft common objects in the context data set, and transfer learning was carried out on annotated image material from the recordings as training data set. In addition, the relationship between the size of the used training data set and the performance on the model after transfer learning was analysed. The trained model achieved averaged precision (Intersection over union, IOU = 0.5) 91% and 85% for the detection of bounding boxes and segmentation masks of the cows, respectively, thereby laying a solid technical basis for an automated analysis of herd activity and the use of resources in loose-housing. |
| first_indexed | 2024-03-10T14:02:52Z |
| format | Article |
| id | doaj.art-57b663e96758423183d99c11a91980b8 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-10T14:02:52Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-57b663e96758423183d99c11a91980b82023-11-21T00:56:06ZengMDPI AGAnimals2076-26152020-12-011012240210.3390/ani10122402Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera SettingJennifer Salau0Joachim Krieter1Institute of Animal Breeding and Husbandry, Kiel University, Olshausenstraße 40, 24098 Kiel, GermanyInstitute of Animal Breeding and Husbandry, Kiel University, Olshausenstraße 40, 24098 Kiel, GermanyWith increasing herd sizes came an enhanced requirement for automated systems to support the farmers in the monitoring of the health and welfare status of their livestock. Cattle are a highly sociable species, and the herd structure has important impact on the animal welfare. As the behaviour of the animals and their social interactions can be influenced by the presence of a human observer, a camera based system that automatically detects the animals would be beneficial to analyse dairy cattle herd activity. In the present study, eight surveillance cameras were mounted above the barn area of a group of thirty-six lactating Holstein Friesian dairy cows at the Chamber of Agriculture in Futterkamp in Northern Germany. With Mask R-CNN, a state-of-the-art model of convolutional neural networks was trained to determine pixel level segmentation masks for the cows in the video material. The model was pre-trained on the Microsoft common objects in the context data set, and transfer learning was carried out on annotated image material from the recordings as training data set. In addition, the relationship between the size of the used training data set and the performance on the model after transfer learning was analysed. The trained model achieved averaged precision (Intersection over union, IOU = 0.5) 91% and 85% for the detection of bounding boxes and segmentation masks of the cows, respectively, thereby laying a solid technical basis for an automated analysis of herd activity and the use of resources in loose-housing.https://www.mdpi.com/2076-2615/10/12/2402machine learningMask-R-convolutional neural networksdairy cattlemulti-camera video surveillanceobject recognition |
| spellingShingle | Jennifer Salau Joachim Krieter Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting Animals machine learning Mask-R-convolutional neural networks dairy cattle multi-camera video surveillance object recognition |
| title | Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting |
| title_full | Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting |
| title_fullStr | Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting |
| title_full_unstemmed | Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting |
| title_short | Instance Segmentation with Mask R-CNN Applied to Loose-Housed Dairy Cows in a Multi-Camera Setting |
| title_sort | instance segmentation with mask r cnn applied to loose housed dairy cows in a multi camera setting |
| topic | machine learning Mask-R-convolutional neural networks dairy cattle multi-camera video surveillance object recognition |
| url | https://www.mdpi.com/2076-2615/10/12/2402 |
| work_keys_str_mv | AT jennifersalau instancesegmentationwithmaskrcnnappliedtoloosehouseddairycowsinamulticamerasetting AT joachimkrieter instancesegmentationwithmaskrcnnappliedtoloosehouseddairycowsinamulticamerasetting |