Action categorization from videos sequences

Abstract : This article presents a framework for extracting relevant qualitative chunks from a video sequence. The notion of qualitative descriptors, used to perform the qualitative extraction, will be first described. A grouping algorithm operates on the qualitative descriptions to generate a real-time qualitative segmentation of the image flow. Then, simple pattern recognition methods are used to extract abstract description of basic actions such as "push", "take" or "pull". The method proposed here provides an unsupervised learning technique to generate abstract description of actions from a video sequence.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01573429
Contributor : Lip6 Publications <>
Submitted on : Wednesday, August 9, 2017 - 3:11:04 PM
Last modification on : Thursday, March 21, 2019 - 12:59:53 PM

Identifiers

  • HAL Id : hal-01573429, version 1

Citation

Jean-Christophe Baillie, Jean-Gabriel Ganascia. Action categorization from videos sequences. ECAI 2000 - 14th European Conference on Artificial Intelligence, Aug 2000, Berlin, Germany. pp.643-647. ⟨hal-01573429⟩

Share

Metrics

Record views

224