When: Thurs 8th of Oct, 1p AEST
Where: This seminar will be presented online, RSVP here.
Speaker: Yongliang Qiao
Title: Deep learning based cattle welfare measurement for precision livestock farming
Abstract: With the increasing consumption demand on livestock production, global livestock industry has to feed more animals with limited environmental resources and the shortage of livestock labor-force. In this situation, precision livestock farming plays an important role in achieving high efficiency with low cost, in an environmentally sustainable. Here, automatic obtaining welfare, wellbeing and behaviour information of individual cattle makes a significant contribution in livestock farming management decision making. In this talk, we will present deep learning-based approaches for solving cattle body segmentation, identification. We consider using data augmentation and Mask R-CNN to segment cattle from complex background, and using BiLSTM and self-attention to identify individual cattle. Our approach can enables automated cattle segmentation and identification for precision livestock farming.
Bio: Yongliang Qiao received M.S. degree from Northwest A&F University, Yangling, China, in 2013， and the Ph.D. degree in computer science from the University of Technology of Belfort-Montbéliard, France, in 2017. He is currently a Research Associate with the Australian Centre for Field Robotics, the University of Sydney, Australia. His research interests include agricultural robots, deep learning, image segmentation, and pattern recognition.