Convolutional neural network‐based cow interaction watchdog
In the field of applied animal behaviour, video recordings of a scene of interest are often made and then evaluated by experts. This evaluation is based on different criteria (number of animals present, an occurrence of certain interactions, the proximity between animals and so forth) and aims to fi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-03-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2017.0077 |
| _version_ | 1797684965329076224 |
|---|---|
| author | Hakan Ardö Oleksiy Guzhva Mikael Nilsson Anders H. Herlin |
| author_facet | Hakan Ardö Oleksiy Guzhva Mikael Nilsson Anders H. Herlin |
| author_sort | Hakan Ardö |
| collection | DOAJ |
| description | In the field of applied animal behaviour, video recordings of a scene of interest are often made and then evaluated by experts. This evaluation is based on different criteria (number of animals present, an occurrence of certain interactions, the proximity between animals and so forth) and aims to filter out video sequences that contain irrelevant information. However, such task requires a tremendous amount of time and resources, making manual approach ineffective. To reduce the amount of time the experts spend on watching the uninteresting video, this study introduces an automated watchdog system that can discard some of the recorded video material based on user‐defined criteria. A pilot study on cows was made where a convolutional neural network detector was used to detect and count the number of cows in the scene as well as include distances and interactions between cows as filtering criteria. This approach removed 38% (50% for additional filter parameters) of the recordings while only losing 1% (4%) of the potentially interesting video frames. |
| first_indexed | 2024-03-12T00:37:28Z |
| format | Article |
| id | doaj.art-beed7f66ef69402e984605e54c654f01 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:37:28Z |
| publishDate | 2018-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-beed7f66ef69402e984605e54c654f012023-09-15T09:32:39ZengWileyIET Computer Vision1751-96321751-96402018-03-0112217117710.1049/iet-cvi.2017.0077Convolutional neural network‐based cow interaction watchdogHakan Ardö0Oleksiy Guzhva1Mikael Nilsson2Anders H. Herlin3Centre for Mathematical SciencesLund UniversitySölvegatan 18LundSwedenSwedish University of Agricultural SciencesDepartment of Biosystems and TechnologyBox 10323053AlnarpSwedenCentre for Mathematical SciencesLund UniversitySölvegatan 18LundSwedenSwedish University of Agricultural SciencesDepartment of Biosystems and TechnologyBox 10323053AlnarpSwedenIn the field of applied animal behaviour, video recordings of a scene of interest are often made and then evaluated by experts. This evaluation is based on different criteria (number of animals present, an occurrence of certain interactions, the proximity between animals and so forth) and aims to filter out video sequences that contain irrelevant information. However, such task requires a tremendous amount of time and resources, making manual approach ineffective. To reduce the amount of time the experts spend on watching the uninteresting video, this study introduces an automated watchdog system that can discard some of the recorded video material based on user‐defined criteria. A pilot study on cows was made where a convolutional neural network detector was used to detect and count the number of cows in the scene as well as include distances and interactions between cows as filtering criteria. This approach removed 38% (50% for additional filter parameters) of the recordings while only losing 1% (4%) of the potentially interesting video frames.https://doi.org/10.1049/iet-cvi.2017.0077convolutional neural networkcow interaction watchdoganimal behaviourvideo sequencesautomated watchdog systemvideo recording |
| spellingShingle | Hakan Ardö Oleksiy Guzhva Mikael Nilsson Anders H. Herlin Convolutional neural network‐based cow interaction watchdog IET Computer Vision convolutional neural network cow interaction watchdog animal behaviour video sequences automated watchdog system video recording |
| title | Convolutional neural network‐based cow interaction watchdog |
| title_full | Convolutional neural network‐based cow interaction watchdog |
| title_fullStr | Convolutional neural network‐based cow interaction watchdog |
| title_full_unstemmed | Convolutional neural network‐based cow interaction watchdog |
| title_short | Convolutional neural network‐based cow interaction watchdog |
| title_sort | convolutional neural network based cow interaction watchdog |
| topic | convolutional neural network cow interaction watchdog animal behaviour video sequences automated watchdog system video recording |
| url | https://doi.org/10.1049/iet-cvi.2017.0077 |
| work_keys_str_mv | AT hakanardo convolutionalneuralnetworkbasedcowinteractionwatchdog AT oleksiyguzhva convolutionalneuralnetworkbasedcowinteractionwatchdog AT mikaelnilsson convolutionalneuralnetworkbasedcowinteractionwatchdog AT andershherlin convolutionalneuralnetworkbasedcowinteractionwatchdog |