A system to recover the 3D shape and motion of a wide variety of quadruped animals from video. We overcome the limited availability of animal motion capture data and ensure generalizability to real-world sequences by training on synthetic silhouette images. We apply our method on manually-segmented and automatically-segmented monocular animal videos and require no other form of user intervention.
Computer vision application for verifying regulatory gowning procedures in collaboration with GlaxoSmithKline. Won departmental award for best third year dissertation at the University of Warwick.
Behaviour and key point predictions at ~15fps by a deep learning architecture we refer to as RodentNet. Results shown on validation sequences from the SCORHE dataset.