Posture standardization of pig point cloud based on skeleton extraction and transformation

Pig body measurement is an important evaluation criterion for breeding and production management. Automatic measurement algorithms for pig body sizes exhibit sensitivity to the point cloud posture, but non-standard pig postures may result in inaccurate joint point localization in body measurement, further affecting measurement accuracy and the commercial application of these algorithms. To address this challenge, this paper proposed a pig point cloud posture transformation method based on pig’s skeleton model to adjust non-standard postures before conducting body size measurements. The method utilized an improved L1-median skeleton model to extract the three-dimensional skeleton of the pig point cloud, capturing the skeleton joint points on the target pig’s head, body, and limbs. By binding the skeleton joint points with the local point cloud and using rotation matrices, non-standard postures were adjusted to standard ones, enabling accurate body size measurements. The experimental results demonstrated that the average relative errors between the transferred posture and the original standard posture were reduced to 0.89% in body length, 0.76% in body width (front), 1% in body width (back), 0.89% in body height (front), 1.7% in body height (back), 2.03% in thoracic circumference, 3.37% in abdominal circumference, and 1.89% in rump circumference. To conclude, the posture standardization transfer method can significantly reduce errors in important body size parameters such as body length, body height, and body width. The method displays a greater stability and robustness compared to existing posture normalization and regression adjustment methods, providing both guidance and insight for future research in intelligent agriculture.