A Review in the Automatic Detection of Pigs Behavior with Sensors

Abstract

In the trend of large-scale and intensive livestock farming, it has become difficult to monitor the physical health and breeding performance of animals accurately, quickly, and comprehensively in the traditional feeding management mode, and with the development of computer technology, machine vision has been widely used as a non-contact sensor technology. In this work, it reviews the current automatic behavior detection methods. The chapters are summarized with machine vision technology as the core and classical behavior detection techniques are added for comparison. It is classified into three aspects: breeding performance, disease and health, and social behavior, and then discusses in detail daily behaviors (lying, drinking, feeding, lameness, etc.) and complex behaviors (mounting, aggression, tail biting, etc.).