Video-based cattle identification and action recognition

TL;DR

This paper presents a deep learning-based system for monitoring cow welfare through video analysis, achieving high accuracy in identifying individual cows and their behaviors like drinking and grazing, with a new public dataset.

Contribution

The study introduces a novel deep learning approach for cow identification and behavior recognition, along with the first public dataset for this purpose.

Findings

81.2% accuracy in cow identification

84.4% accuracy in detecting drinking events

94.4% accuracy in detecting grazing events

Abstract

We demonstrate a working prototype for the monitoring of cow welfare by automatically analysing the animal behaviours. Deep learning models have been developed and tested with videos acquired in a farm, and a precision of 81.2\% has been achieved for cow identification. An accuracy of 84.4\% has been achieved for the detection of drinking events, and 94.4\% for the detection of grazing events. Experimental results show that the proposed deep learning method can be used to identify the behaviours of individual animals to enable automated farm provenance. Our raw and ground-truth dataset will be released as the first public video dataset for cow identification and action recognition. Recommendations for further development are also provided.