To date, there is little research on how to design back marks to best support individual-level monitoring of uniform looking species like pigs. With the recent surge of machine learning-based monitoring solutions, there is a particular need for guidelines on the design of marks that can be effectively recognised by such algorithms. This study provides valuable insights on effective back mark design, based on the analysis of a machine learning model, trained to distinguish pigs via their back marks. Specifically, a neural network of type ResNet-50 was trained to classify ten pigs with unique back marks. The analysis of the model's predictions highlights the significance of certain design choices. Most importantly, the set of back marks must be designed such that each mark remains unambiguous under conditions of motion blur, diverse view angles and occlusions, caused by animal behaviour. The generated insights can support individual-level monitoring in future studies and real-world applications by optimizing back mark design.
Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings
School of Electrical Engineering and Computer Science, Queensland University of Technology(昆士兰科技大学电气工程与计算机科学学院);School of Biomedical Science, The University of Queensland(昆士兰大学生物医学科学学院);School of Information Technology and Electrical Engineering, The University of Queensland(昆士兰大学信息技术与电气工程学院)
Unsupervised Pelage Pattern Unwrapping for Animal Re-identification
Computer Vision and Pattern Recognition Laboratory (CVPRL)(计算机视觉与模式识别实验室);Lappeenranta-Lahti University of Technology LUT(拉佩恩拉-拉赫蒂理工大学);Faculty of Information Technology Brno University of Technology (BUT)(信息科技学院布拉格技术大学);Rensselaer Polytechnic Institute (RPI)(伦塞拉尔理工学院)
Animal Identification with Independent Foreground and Background Modeling
University of West Bohemia(西波希米亚大学);Inria(法国国家信息与自动化研究所);University of Montpellier(蒙彼利埃大学);CNRS(法国国家科学研究中心);Czech Technical University in Prague(捷克布拉格技术大学)
提出一种独立建模前景与背景的动物视觉识别方法,利用 Segment Anything 实现自动分离,并通过 Per-Instance Temperature Scaling 结合预测,显著降低相对误差并提升背景漂移下的准确率。
CNN Based Flank Predictor for Quadruped Animal Species
University of Applied Sciences Darmstadt(达姆施塔特应用科学大学);Bavarian Forest National Park(巴伐利亚森林国家公园);University of Freiburg(弗莱堡大学);Inland Norway University of Applied Sciences(挪威内陆应用科学大学);University of KwaZulu-Natal(夸祖鲁-纳塔尔大学)
A non-invasive video-based method for individual identification of wildlife using gait dynamics
Department of Computer Science, University of Oxford(牛津大学计算机科学系);Wildlife Conservation Research Unit, Department of Biology, University of Oxford(牛津大学生物系野生动物保护研究组)
Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation
Microsoft AI for Good(微软AI公益部门);Center for Research and Formation in Artificial Intelligence, Universidad de los Andes(安第斯大学人工智能研究与形成中心);Massachusetts Institute of Technology(麻省理工学院)
Deep Learning Models for Automated Classification of Dog Emotional States from Facial Expressions
Open University(开放大学);Weizmann Institute of Science(魏茨曼科学研究所);University of Bern(伯尔尼大学);University of Lincoln(林肯大学);dogs and science - Institute for Canine Science and Applied Cynology(狗与科学——犬类科学与应用犬学研究所);University of Haifa(海法大学)