An automatic system for the detection of dairy cows lying behaviour in free-stall barns

Abstract

In this paper, a method for the automatic detection of dairy cow lying behaviour in free-stall barns is proposed. A computer visionbased system (CVBS) composed of a video-recording system and a cow lying behaviour detector based on the Viola Jones algorithm was developed. The CVBS performance was tested in a head-to-head free stall barn. Two classifiers were implemented in the software component of the CVBS to obtain the cow lying behaviour detector. The CVBS was validated by comparing its detection results with those generated from visual recognition. This comparison allowed the following accuracy indices to be calculated: the branching factor (BF), the miss factor (MF), the sensitivity, and the quality percentage (QP). The MF value of approximately 0.09 showed that the CVBS missed one cow every 11 well detected cows. Conversely, the BF value of approximately 0.08 indicated that one false positive was detected every 13 well detected cows. The high value of approximately 0.92 obtained for the sensitivity index and that obtained for QP of about 0.85 revealed the ability of the proposed system to detect cows lying in the stalls.

Optical sensing for stream flow observations: A review

“…Images afford automated and nonintrusive observations. Their potential has been demonstrated in diverse realms of agricultural engineering, such as, the detection of dairy cows lying behaviour (Porto et al, 2013), the determination of the size distribution of wood chips (Febbi et al, 2013), the assessment of basal shear stress in debris-flow mixtures (D'Agostino et al, 2013), and the measurement of kinematic properties of granular flows (Gollin et al, 2015). With regards to fluid flow monitoring, digital images have been traditionally adopted in fluid dynamics laboratories as powerful quantitative fluid visualisation techniques.…”

Automatic recognition of lactating sow behaviors through depth image processing

“…Analysis of digital images obtained from video-recordings is an effective tool for studying livestock behaviors under various environmental conditions (Porto et al, 2013 among the image analysis methods considered. Digital image analysis methods can work well under the following conditions: the animal images have a high contrast with the background to allow for image segmentation; the background is constant or has constant brightness variations to extract the animal features from the image; the color range applied to the animal is different from the background (Porto et al, 2013). However, image segmentation in digital RGB image can be problematic under real farm conditions due to dynamic background restrictions, such as dim or uneven light intensity of the house and varying floor status.…”