Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Recognition of Scene-interactive Behaviors of Calves Based on Video Analysis

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2018 ASABE Annual International Meeting  1800769.(doi:10.13031/aim.201800769)
Authors:   Yangyang Guo, Mr., Dongjian He, Dr., Huaibo Song, Dr.
Keywords:   computer vision, scene-interaction, calf, classification

Abstract. Animal behavior provides an important index for evaluating animal welfare. To achieve automatic monitoring of calf behavior, a method of recognizing scene-interactive behaviors based on computer vision technology is proposed. The method automatically identifies drinking, feeding, entering and leaving the resting area, and also remaining stationary or turning within the inlet and outlet area of resting area. First, the drinking area, the feeding area, and the inlet and outlet area of resting area in the scene were marked; second, the target was detected and tracked; finally, the calf‘s movement characteristics in different areas of the scene were extracted to identify specific behaviors. In these trials, the recognition rate for the calf entering the resting area, leaving the resting area, static behavior and turning around were 94.38%, 92.86%, 96.85% and 93.51%, respectively, and the recognition rates for feeding and drinking were 79.69% and 81.73%, respectively.

(Download PDF)    (Export to EndNotes)