Portal de Periódicos da CAPES

Now You See Me: Convolutional Neural Network Based Tracker for Dairy Cows

2018; Frontiers Media; Volume: 5; Linguagem: Inglês

10.3389/frobt.2018.00107

2296-9144

Oleksiy Guzhva, Håkan Ardö, Mikael Nilsson, Anders Herlin, Linda Tufvesson,

Food Supply Chain Traceability

To maintain dairy cattle health and welfare at commensurable levels, analysis of the behaviours occurring between cows should be performed. This type of behavioural analysis is highly dependent on reliable and robust tracking of individuals, for it to be viable and applicable on-site. In this article, we introduce a novel method for continuous tracking and data-marker based identification of individual cows based on convolutional neural networks (CNNs). The tracker optimises over the sequences of detection likelihoods produced by the CNN and is thus able to utilise all information provided by the CNN using per frame non-maximum suppression. The methodology for data acquisition and overall implementation of tracking/identification is described. The Region of Interest (ROI) for the recordings was limited to a waiting area with free entrances to four automatic milking stations and a total size of 6x18 meters. There were 252 Swedish Holstein cows during the time of study that had access to the waiting area at a conventional dairy barn with varying conditions and illumination. Three Axis M3006-V cameras placed in the ceiling at 3.6 meters height and providing top-down view were used for recordings. The total amount of video data collected was four months, containing 500 million frames. To evaluate the system two one-hour recordings were chosen. The exit time and gate-id found by the tracker for each cow were compared with the exit times produced by the gates. In total there were 26 tracks considered, and 23 were correctly tracked. Given those 26 starting points, the tracker was able to maintain the correct position in a total of 101.29 minutes or 225 s in average per starting point/individual cow.