Skip to Main content Skip to Navigation
Conference papers

View-invariant Pose Analysis for Human Movement Assessment from RGB Data

Abstract : We propose a CNN regression method to generate high-level, view-invariant features from RGB images which are suitable for human pose estimation and movement quality analysis. The inputs to our network are body joint heatmaps and limb-maps to help our network exploit geometric relationships between different body parts to estimate the features more accurately. A new multiview and multimodal human movement dataset is also introduced to evaluate the results of the proposed method. We present comparative experimental results on pose estimation using a manifold-based pose representation built from motion-captured data. We show that the new RGB derived features provide pose estimates of similar or better accuracy than those produced from depth data, even from single views only.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02171028
Contributor : Adeline Paiement <>
Submitted on : Friday, May 15, 2020 - 3:13:53 PM
Last modification on : Friday, May 15, 2020 - 4:21:39 PM

File

ICIAP2019_FS (1).pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Faegheh Sardari, Adeline Paiement, Majid Mirmehdi. View-invariant Pose Analysis for Human Movement Assessment from RGB Data. 20th International Conference on Image Analysis and Processing (ICIAP), Sep 2019, Trento, Italy. ⟨10.1007/978-3-030-30645-8_22⟩. ⟨hal-02171028⟩

Share

Metrics

Record views

117

Files downloads

26