Hybrid activity and plan recognition for video streams

Roger Granada, Ramon Fraga Pereira, Juarez Monteiro, Duncan Ruiz, Felipe Meneguzzi

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

20 Citations (Scopus)


Computer-based human activity recognition of daily living has recently attracted much interest due to its applicability to ambient assisted living. Such applications require the automatic recognition of high-level activities composed of multiple actions performed by human beings in an environment.
In this work, we address the problem of activity recognition in an indoor environment, focusing on a kitchen scenario. Unlike existing approaches that identify single actions from video sequences, we also identify the goal towards which the subject of the video is pursuing. Our hybrid approach combines a deep learning architecture to analyze raw video data and identify individual actions which are then processed by a goal recognition algorithm that uses a plan library describing possible overarching activities to identify the ultimate goal of the subject in the video. Experiments show that our approach
achieves the state-of-the-art for identifying cooking activities in a kitchen scenario
Original languageEnglish
Title of host publicationProceedings of the AAAI Workshop on Plan, Activity, and Intent Recognition (PAIR)
Publication statusPublished - 2017

Bibliographical note

The AAAI-17 Workshop on Plan, Activity, and Intent Recognition WS-17-13

This paper was achieved in cooperation with HP Brasil Ind ́ustria e Com ́ercio de Equipamentos Eletrˆonicos LTDA. using incentives of Brazilian Informatics Law (Law n o 8.2.48 of 1991)


Dive into the research topics of 'Hybrid activity and plan recognition for video streams'. Together they form a unique fingerprint.

Cite this