Skip to Main content Skip to Navigation
Journal articles

A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera

Abstract : We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB sensors using simple cameras. The approach proceeds along two stages. In the first, a real-time 2D pose detector is run to determine the precise pixel location of important keypoints of the human body. A two-stream deep neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second stage, the Efficient Neural Architecture Search (ENAS) algorithm is deployed to find an optimal network architecture that is used for modeling the spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, MSR Action3D and SBU Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that the method requires a low computational budget for training and inference. In particular, the experimental results show that by using a monocular RGB sensor, we can develop a 3D pose estimation and human action recognition approach that reaches the performance of RGB-depth sensors. This opens up many opportunities for leveraging RGB cameras (which are much cheaper than depth cameras and extensively deployed in private and public places) to build intelligent recognition systems.
Document type :
Journal articles
Complete list of metadata

Cited literature [78 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02970860
Contributor : Open Archive Toulouse Archive Ouverte (oatao) Connect in order to contact the contributor
Submitted on : Monday, October 19, 2020 - 9:36:48 AM
Last modification on : Wednesday, November 3, 2021 - 3:59:02 AM
Long-term archiving on: : Wednesday, January 20, 2021 - 6:16:19 PM

File

pham_26382.pdf
Files produced by the author(s)

Identifiers

Citation

Huy-Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Sergio A. Velastin, et al.. A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera. Sensors, MDPI, 2020, 20 (7), pp.1-15. ⟨10.3390/s20071825⟩. ⟨hal-02970860⟩

Share

Metrics

Record views

63

Files downloads

166