Skip to Main content Skip to Navigation
Conference papers

Low Cost Activity Recognition Using Depth Cameras and Context Dependent Spatial Regions

Abstract : Recognition of human activities is usually based on expensive sensor setups to extract rich information such as body posture or object interaction. We investigate the use of inexpensive depth cameras to perform activity recognition using context dependent spatial regions with two different approaches: Spatio-Temporal Plan Representations and Hierarchical Hidden Markov Models. We evaluate both approaches in a simulated and a real-world environment.
Complete list of metadatas

Cited literature [4 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01691651
Contributor : Alexandra Kirsch <>
Submitted on : Wednesday, January 24, 2018 - 11:10:46 AM
Last modification on : Friday, January 26, 2018 - 3:27:32 PM
Document(s) archivé(s) le : Thursday, May 24, 2018 - 6:55:52 PM

File

karg14lowcost-short-preprint.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01691651, version 1

Citation

Michael Karg, Alexandra Kirsch. Low Cost Activity Recognition Using Depth Cameras and Context Dependent Spatial Regions. 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), 2014, Paris, France. ⟨hal-01691651⟩

Share

Metrics

Record views

92

Files downloads

16