Individual Cattle Identification Using a Deep Learning Based Framework. Issue 30 (2019)

• Record Type: Journal Article
• Authors: Qiao, Yongliang; Su, Daobilige; Kong, He; Sukkarieh, Salah; Lomax, Sabrina; Clark, Cameron
• Is Part Of: IFAC-PapersOnLine. Volume 52:Issue 30(2019)
• Page Start: 318
• Page End: 323
• Publication Date: 2019
• Subjects: Cattle identification -- deep learning -- LSTM -- CNN -- precision livestock farming; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2019.12.558
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: Individual cattle identification is required for precision livestock farming. Current methods for individual cattle identification requires either visual, or unique radio frequency, ear tags. We propose a deep learning based framework to identify beef cattle using image sequences unifying the advantages of both CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) network methods. A CNN network was used (Inception-V3) to extract features from a rear-view cattle video dataset and these extracted features were then used to train an LSTM model to capture temporal information and identify each individual animal. A total of 516 rear- view videos of 41 cattle at three time points separated by one month were collected. Our method achieved an accuracy of 88% and 91% for 15-frame and 20-frame video length, respectively. Our approach outperformed the framework that only uses CNN (identification accuracy 57%). Our framework will now be further improved using additional data before integrating the system into on-farm management processes.