Automatic detection of lameness in cattle through 3D kinematic analysis and machine learning: database, training tool and locomotion score identification

• Grant number: 23/00338-3
• Support Opportunities: Scholarships in Brazil - Master
• Start date: January 01, 2024
• End date: July 31, 2025
• Field of knowledge: Agronomical Sciences - Veterinary Medicine
• Principal Investigator: Fabio Celidonio Pogliani
• Grantee: Victoria Portela Diniz Gaia
• Host Institution: Faculdade de Medicina Veterinária e Zootecnia (FMVZ). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated scholarship(s): 24/05468-5 - Automatic detection of lameness in cattle through 3D kinematic analysis and machine learning: database, training tool and locomotion score identification, BE.EP.MS

Abstract

Lameness in cattle is currently one of the biggest health and welfare problems in intensive dairy production systems worldwide, moreover it generates economic losses to the producer with direct and indirect costs. The most used method of evaluating and classifying lameness is still the determination of the locomotion score and, despite its low cost, it is a subjective technique that demands trained labor. An important limitation of this method would be that visually perceptible gait alterations can be noticed later, after the animal has already presented the lesion for some time and, consequently, affecting productivity, health and welfare of the patient in a more prolonged way. Thus, the early and accurate identification of lameness is important sothe diagnosis and treatment can be carried out as soon as possible, preserving the welfare and production of the cow and reducing the economic impact of this morbidity. In this way, automatic detection technologies have stood out for being more objective, minimizing the interruption of the farm's routine, not depending on labor and training and enabling the early identification of alterations in the animals. Therefore, the use of 3D cameras proved to be interesting for this purpose, as it reduces some of the disadvantages of 2D cameras and improves efficiency, in addition to being able to be used from a dorsal view, reducing the space needed on the farm. This research project proposes the identification of anatomical points in dorsal view, with the objective of correlating the movement dynamics of these structures in the animal's gait with the locomotion scores so, later, a computational system capable of performing the automatic diagnosis of lameness in dairy cow can be developed.