Segmentation of body parts of cows in RGB-depth images based on template matching

Body cleanliness is considered an important indicator for evaluating cow welfare. At present, assessing the cleanliness of different cow body parts is considered as a subjective and labor-intensive task. Automatic body cleanliness scoring needs to start with body parts segmentation. Despite the fact that pattern recognition methods for human body detection and analysis have flourished in the last decade, computer vision analysis of cow body-part is scarce in literature, and most of cow body detection in video images recognizes and segments the cow as a whole, not using all of the body part information. This study presents a computer vision method that automatically identifies nine cow's body parts, i.e. head, torso, udder, belly (or rear), left foreleg, right foreleg, left hindleg right hindleg and tail. We used a method for body parts detection using an improved version of template matching. The entire image process included video recording, image restoration and pre-processing, skeleton extraction, templates matching, recognition of right or left leg, calibration and body parts identification. 1421 side-view images of 113 cows and 859 back-view images of 75 cows were collected on a Chinese research dairy farm using an RGB-depth camera installed in the barn for Holstein lactating cows. The average body parts segmentation accuracies for side-view and back-view were 96% and 91%, respectively. The results indicate that it is possible to automatically detect and extract body parts from RGB-depth images without any manual interference.