Seminar

CVL Talk: Multi-Object Tracking and Pose Estimation for Animals - Urs Waldmann, University of Konstanz

Abstract:

Pose estimation and tracking are among the fundamental problems in computer vision and crucial tasks in many vision applications ranging from sports to human-computer interaction to the study of collective behaviour. Within our centre for the Advanced Study of Collective Behaviour, among other things, we study the collective behaviour of animals. That is why we are interested in real-time multi-animal pose estimation and tracking in the wild. The problem in achieving this goal is that the availability of annotated tracking data for animals is limited, especially for multiple objects. In this talk I would like to show you how we try to bridge this gap between the lack of annotated animal data and the need for real-time multi-animal pose estimation and tracking for the study of collective behaviour.

Bio:

Urs Waldmann obtained both his Bachelor and Master of Science at the Department of Physics at the Ludwig-Maximilians-Universität München in Germany. After a position as a machine vision specialist in the industry, he joined the Centre for the Advanced Study of Collective Behaviour and the Computer Vision and Image Analysis group within the Department of Computer and Information Science at the University of Konstanz, Germany, as a PhD student. He is interested in multi-animal pose estimation and tracking in the wild. His focus is on methods that work without huge amounts of annotated real-world animal data.

Zoom Link

You can see the other CVPR 2023 UBC events here.