Convolutional neural network‐based cow interaction watchdog. Issue 2 (18th December 2017)

• Record Type: Journal Article
• Authors: Ardö, Hakan; Guzhva, Oleksiy; Nilsson, Mikael; Herlin, Anders H.
• Is Part Of: IET computer vision. Volume 12:Issue 2(2018)
• Page Start: 171
• Page End: 177
• Publication Date: 2017-12-18
• Subjects: neural nets -- video recording -- image sequences -- video signal processing; convolutional neural network -- cow interaction watchdog -- animal behaviour -- video sequences -- automated watchdog system -- video recording -- user-defined criteria -- video frames; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2017.0077
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : 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.