Skip to Main content Skip to Navigation

Reconnaissance d'actions humaines dans des vidéos, en particulier lors d'interaction avec des objets

Camille Maurice 1
1 LAAS-RAP - Équipe Robotique, Action et Perception
LAAS - Laboratoire d'analyse et d'architecture des systèmes
Abstract : In this thesis we study the recognition of actions of daily life. Typically, different actions take place in the same place and involve various objects. This problem is difficult because of the variety and resemblance of some actions and the clutter in the background. Many computer vision approaches study this problem and their performance is often dependent on the setting of certain hyper-parameters. For example, for deep learning approaches there are: the initialization of the learning-rate, the size of the mini-batch... Based on this observation, we begin with a comparative study of hyper-parameter optimization tools from the literature applied to a computer vision problem. Then we propose a first Bayesian approach for online action recognition based on high-level 3D primitives: the observation of the human skeleton and surrounding objects. The parameters to be set are optimized thanks to the optimization tool that emerges from our comparative study. The performances of this first approach are compared to a deep state of the art learning network, and a certain complementarity emerges that we propose to exploit through a fusion mechanism. Finally, following recent advances in graph convolutional networks, we propose a light and modular approach based on the construction of spatio-temporal graphs of the skeleton and objects. The validity of the different approaches is evaluated, in raw performance and with respect to under-represented actions on different public data sets that propose sequences of actions of everyday life. Our approaches show interesting results compared to the literature especially regarding imbalanced data and under-represented classes in datasets.
Document type :
Complete list of metadata
Contributor : Abes Star :  Contact
Submitted on : Monday, March 15, 2021 - 6:07:10 PM
Last modification on : Thursday, June 10, 2021 - 3:04:18 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03138294, version 2


Camille Maurice. Reconnaissance d'actions humaines dans des vidéos, en particulier lors d'interaction avec des objets. Robotique [cs.RO]. Université Paul Sabatier - Toulouse III, 2020. Français. ⟨NNT : 2020TOU30188⟩. ⟨tel-03138294v2⟩



Record views


Files downloads