Estrus Detection Using Background Image Subtraction Technique in Tie-Stalled Cows

Abstract

In this study, we determined the applicability of the background image subtraction technique to detect estrus in tie-stalled cows. To investigate the impact of the camera shooting direction, webcams were set up to capture the front, top, and rear views of a cow simultaneously. Video recording was performed for a total of ten estrous cycles in six cows. Standing estrus was confirmed by testing at 6 h intervals. From the end of estrus, transrectal ultrasonography was performed every 2 h to confirm ovulation time. Foreground objects (moving objects) were extracted in the videos using the background subtraction technique, and the pixels were counted at each frame of five frames-per-second sequences. After calculating the hourly averaged pixel counts, the change in values was expressed as the pixel ratio (total value during the last 24 h/total value during the last 24 to 48 h). The mean pixel ratio gradually increased at approximately 48 h before ovulation, and the highest value was observed at estrus, regardless of the camera shooting direction. When using front-view videos with an appropriate threshold, estrus was detected with 90% sensitivity and 50% precision. The present method in particular has the potential to be a non-contact estrus detection method for tie-stalled cows.

A Cervix Detection Driven Deep Learning Approach for Cow Heat Analysis from Endoscopic Images

“…Several works have been proposed in the literature for cow heat detection from the analysis of its visual behavior [13,14,15]. To this end, the proposed methods aim to exploit recorded videos in the farms in order to detect automatically special postures of the cows, such as being-mounted or standing-to-be-mounted, which are considered as the main heat indicators [3].…”

“…To this end, the proposed methods aim to exploit recorded videos in the farms in order to detect automatically special postures of the cows, such as being-mounted or standing-to-be-mounted, which are considered as the main heat indicators [3]. Basically, the proposed methods, exploit either handcrafted features to characterize video frames then analyze their spatio-temporal evolution to detect a behavior change [14,15] or exploit CNN models trained for posture detection [13]. However, the exploitation of these methods in the context of farms represents a real challenge in reason of cameras deployment issues both on ethical and logistic plans.…”

Differences in Milk Proteomic Profiles between Estrous and Non-Estrous Dairy Cows

“…Moreover, visual observation is labor intensive, and the development of modern large dairy herds pattern hinders this method to a certain extent [ 2 ]. Nowadays, several automated technologies such as pressure-sensitive devices, activity monitoring devices, and body temperature detecting devices have been developed to detect estrus [ 3 ]. Nevertheless, the accuracy of these devices is still not completely reliable, and these technologies require potentially burdensome investments in management and equipment [ 4 ].…”