Motion-based video monitoring for early detection of livestock diseases: The case of African swine fever
Investigation published in PLoS ONE
September 6th, 2017
Early detection of infectious diseases can substantially reduce the health and economic impacts on livestock production. Here we describe a system for monitoring animal activity based on video and data processing techniques, in order to detect slowdown and weakening due to infection with African swine fever (ASF), one of the most significant threats to the pig industry. The system classifies and quantifies motion-based animal behaviour and daily activity in video sequences, allowing automated and non-intrusive surveillance in real-time. The aim of this system is to evaluate significant changes in animals` motion after being experimentally infected with ASF virus. Indeed, pig mobility declined progressively and fell significantly below pre-infection levels starting at four days after infection at a confidence level of 95%. Furthermore, daily motion decreased in infected animals by approximately 10% before the detection of the disease by clinical signs. These results show the promise of video processing techniques for real-time early detection of livestock infectious diseases
Fernandez-Carrion E., Martinez-Aviles M., Ivorra B., Martinez-Lopez B., Ramos AM. and Sanchez-Vizcaino JM..
 | Servicio de Inmunología Viral y Medicina Preventiva (SUAT). Centro de Vigilancia Sanitaria Veterinaria (VISAVET). Universidad Complutense (UCM). |
| Departamento de Sanidad Animal. Facultad de Veterinaria. Universidad Complutense (UCM). |
| Grupo de Investigación ´Modelos Matemáticos en Ciencia y Tecnología: Desarrollo, Análisis, Simulación Numérica y Control´ (MOMAT). Facultad de Ciencias Matemáticas. Universidad Complutense (UCM). |
 | University of California-Davis (UCDAVIS). |
