SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation

31 Jul 2021  ·  Moira Shooter, Charles Malleson, Adrian Hilton ·

Estimating the pose of animals can facilitate the understanding of animal motion which is fundamental in disciplines such as biomechanics, neuroscience, ethology, robotics and the entertainment industry. Human pose estimation models have achieved high performance due to the huge amount of training data available. Achieving the same results for animal pose estimation is challenging due to the lack of animal pose datasets. To address this problem we introduce SyDog: a synthetic dataset of dogs containing ground truth pose and bounding box coordinates which was generated using the game engine, Unity. We demonstrate that pose estimation models trained on SyDog achieve better performance than models trained purely on real data and significantly reduce the need for the labour intensive labelling of images. We release the SyDog dataset as a training and evaluation benchmark for research in animal motion.

PDF Abstract

Datasets


Introduced in the Paper:

SyDog

Used in the Paper:

StanfordExtra
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Animal Pose Estimation StanfordExtra Mask R-CNN PCK@0.1 50.77 # 3
Animal Pose Estimation StanfordExtra 8 Stacked Hourglass Network PCK@0.1 78.65 # 1
Animal Pose Estimation StanfordExtra 2 Stacked Hourglass Network PCK@0.1 77.19 # 2

Methods


No methods listed for this paper. Add relevant methods here