Novelty Detection in Images Using Vector Quantization with Topological Learning - Université de Lorraine Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Novelty Detection in Images Using Vector Quantization with Topological Learning

Résumé

Novelty detection is a key component of biological vision systems, where its role is to extract critical elements for the agents survival from the massive amount of information present in his visual environment. Current vision based embedded systems , such as surveillance cameras, are facing similar challenges as they have to handle a significant amount of sensory data, with limited computing power and memory bandwidth available. In order to perform artificial novelty detection in these systems, it is necessary to have a model able to learn the local visual environment without having any prior knowledge. This study explores bio-inspired unsupervised neural networks models, more precisely self-organizing maps, which are good candidates for this task. We present an original approach consisting of performing novelty detection based on vector quantization and topological learning.
Fichier principal
Vignette du fichier
ICECS_2020___Novelty_Detection (1).pdf (1.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02984427 , version 1 (30-10-2020)

Identifiants

  • HAL Id : hal-02984427 , version 1

Citer

Yann Bernard, Nicolas Hueber, Bernard Girau. Novelty Detection in Images Using Vector Quantization with Topological Learning. ICECS 2020, 27th IEEE International Conference on Electronics Circuits and Systems, Nov 2020, Glasgow/Virtual, United Kingdom. ⟨hal-02984427⟩
64 Consultations
143 Téléchargements

Partager

Gmail Facebook X LinkedIn More