A new bag of visual words encoding method for human action recognition

Xavier Cortés (1) , Donatello Conte (1) , Hubert Cardot (1)

1 LIFAT - Laboratoire d'Informatique Fondamentale et Appliquée de Tours

Human action recognition in videos is one of the key problems in computer vision. Inspired by image classification models, techniques based on bags of visual words have become one of the most effective approaches to solve this problem. The most usual way to engage an interest point in a bag of words is by means of the closest word found in a previously trained codebook. However, the quality of representation decreases when interest points have different visual words at similar distances or when we map noisy interest points. The aim of this paper is to present a new encoding procedure to engage the interest points in a bag of visual words improving the quality of the representation. The encoding that we propose tries to map only the relevant interest points detected in the scene. We experimentally show that using the new encoding method we can significantly improve the classification ratio.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]; Informatique; Traitement du signal et de l'image [eess.SP]

Xavier Cortés, Donatello Conte, Hubert Cardot. A new bag of visual words encoding method for human action recognition. 24th International Conference on Pattern Recognition (ICPR), Aug 2018, Beijing, China. pp. 2480-2485. ⟨hal-01879975⟩