Computes Vision Technologies Applied to Lameness Detection in Dairy Cattle

• Grant number: 23/02851-0
• Support Opportunities: Scholarships in Brazil - Master
• Start date: July 01, 2023
• End date: April 30, 2025
• Field of knowledge: Agronomical Sciences - Animal Husbandry - Animal Production
• Principal Investigator: Ricardo Vieira Ventura
• Grantee: Paula de Freitas Curti
• Host Institution: Faculdade de Medicina Veterinária e Zootecnia (FMVZ). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

Lameness is a highly prevalent condition in dairy herds, making it crucial to identifyand monitor affected animals in order to minimize losses associated with this disease. Toassess this problem, a common approach is the adoption of a classification system based onvisual scores, which, as a qualitative evaluation, presents practical obstacles (e.g. subjectivityand experience of the evaluator, scale used, etc.). These problems can be solved through theadoption of new technologies based on the quantitative analysis of bovine gait, whichcurrently involve the use of sensors and computer vision (CV) techniques. Within the field ofCV, video analysis associated with key point detection methodologies stands out as apromising alternative, due to possibility of automation, low cost of implementation and lackof interference in the farm's routine. At the present time, CV techniques are alreadywell-established for humans, however, there is still room for improvement when applied inthe identification of lameness in dairy cattle, considering that researches in this topic mainlyfocus on one anatomical characteristic. Thus, the present study aims to investigate idealparameters for automated high-precision and accurate key point attainment in dairy cattlefrom video images, and elaborate an integrated analysis of characteristics considered asindicators of lameness to automatically differentiate lame and healthy animals. To this end,the study will use CV and machine learning techniques, implemented in Python language.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CURTI, PAULA F.; SOUZA, ANDRE M.; KOBAYASHI, LIVIA L.; CASTANHEIRA, ALINE M.; PINTO, DIOGENES L.; RUIZ, ALEXANDRE M.; ANDRIETTA, LUCAS T.; BALIEIRO, JULIO C. C.; RENNO, FRANCISCO P.; SOUSA, ELAINE P. M.; et al. Respiratory rate regression in Holstein dairy cattle with deep neural networks: An evaluation on different body regions. COMPUTERS AND ELECTRONICS IN AGRICULTURE, v. 239, p. 9-pg., 2025-12-01. (16/19514-2, 23/02851-0, 16/17078-0, 21/03101-9)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

CURTI, Paula de Freitas. Application of computer vision to assess locomotor problems in dairy cattle. 2025. Master's Dissertation - Universidade de São Paulo (USP). Faculdade de Medicina Veterinária e Zootecnia (FMVZ/SBD) Pirassununga.