Rights statement: The final publication is available at Springer via http://dx.doi.org/10.1007/s11263-019-01192-2
Accepted author manuscript, 7.04 MB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
AU - Liu, Jian
AU - Rahmani, Hossein
AU - Akhtar, Naveed
AU - Mian, Ajmal
N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/s11263-019-01192-2
PY - 2019/8/6
Y1 - 2019/8/6
N2 - We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images where all factors are varied for every human pose. Capturing such data is prohibitively expensive. Therefore, we develop a framework for synthesizing the training data. First, we learn representative human poses from a large corpus of real motion captured human skeleton data. Next, we fit synthetic 3D humans with different body shapes to each pose and render each from 180 camera viewpoints while randomly varying the clothing textures, background and lighting. Generative Adversarial Networks are employed to minimize the gap between synthetic and real image distributions. CNN models are then learned that transfer human poses to a shared high-level invariant space. The learned CNN models are then used as invariant feature extractors from real RGB and depth frames of human action videos and the temporal variations are modelled by Fourier Temporal Pyramid. Finally, linear SVM is used for classification. Experiments on three benchmark human action datasets show that our algorithm outperforms existing methods by significant margins for RGB only and RGB-D action recognition.
AB - We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images where all factors are varied for every human pose. Capturing such data is prohibitively expensive. Therefore, we develop a framework for synthesizing the training data. First, we learn representative human poses from a large corpus of real motion captured human skeleton data. Next, we fit synthetic 3D humans with different body shapes to each pose and render each from 180 camera viewpoints while randomly varying the clothing textures, background and lighting. Generative Adversarial Networks are employed to minimize the gap between synthetic and real image distributions. CNN models are then learned that transfer human poses to a shared high-level invariant space. The learned CNN models are then used as invariant feature extractors from real RGB and depth frames of human action videos and the temporal variations are modelled by Fourier Temporal Pyramid. Finally, linear SVM is used for classification. Experiments on three benchmark human action datasets show that our algorithm outperforms existing methods by significant margins for RGB only and RGB-D action recognition.
U2 - 10.1007/s11263-019-01192-2
DO - 10.1007/s11263-019-01192-2
M3 - Journal article
JO - International Journal of Computer Vision
JF - International Journal of Computer Vision
SN - 0920-5691
ER -