Descrizione del progetto
Un cambiamento epocale nella visione artificiale
Per anni la visione artificiale ha cercato di eguagliare le straordinarie capacità del sistema visivo umano, ma non ci è riuscita. In quest’ottica, il progetto HOMOVIS, finanziato dall’UE, proporrà un’iniziativa visionaria che mira a colmare il divario tra la visione artificiale e la percezione simile a quella umana. In particolare, il progetto sfrutta la potenza di una straordinaria architettura a tre strati, che copia l’efficienza del sistema visivo umano. Questa architettura consiste in uno strato di basso livello, che identifica le caratteristiche fondamentali dell’immagine, uno strato di medio livello, che consente la disocclusione visiva e il completamento dei confini, e uno strato di alto livello, responsabile del riconoscimento degli oggetti. Integrando precedenti di alto livello in modelli variazionali di basso livello, HOMOVIS introdurrà un quadro matematico unificato. I suoi progressi matematici spingeranno il campo oltre i modelli variazionali convenzionali.
Obiettivo
Since more than 50 years, computer vision has been a very active research field but it is still far away from the abilities of the human visual system. This stunning performance of the human visual system can be mainly contributed to a highly efficient three-layer architecture: A low-level layer that sparsifies the visual information by detecting important image features such as image gradients, a mid-level layer that implements disocclusion and boundary completion processes and finally a high-level layer that is concerned with the recognition of objects.
Variational methods are certainly one of the most successful methods for low-level vision. However, it is very unlikely that these methods can be further improved without the integration of high-level prior models. Therefore, we propose a unified mathematical framework that allows for a natural integration of high-level priors into low-level variational models. In particular, we propose to represent images in a higher-dimensional space which is inspired by the architecture for the visual cortex. This space performs a decomposition of the image gradients into magnitude and direction and hence performs a lifting of the 2D image to a 3D space. This has several advantages: Firstly, the higher-dimensional embedding allows to implement mid-level tasks such as boundary completion and disocclusion processes in a very natural way. Secondly, the lifted space allows for an explicit access to the orientation and the magnitude of image gradients. In turn, distributions of gradient orientations – known to be highly effective for object detection – can be utilized as high-level priors. This inverts the bottom-up nature of object detectors and hence adds an efficient top-down process to low-level variational models.
The developed mathematical approaches will go significantly beyond traditional variational models for computer vision and hence will define a new state-of-the-art in the field.
Campo scientifico
- natural sciencesphysical sciencesopticsmicroscopysuper resolution microscopy
- natural sciencescomputer and information sciencesartificial intelligencecomputer vision
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- natural sciencesmathematicsapplied mathematicsmathematical model
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
Programma(i)
Argomento(i)
Meccanismo di finanziamento
ERC-STG - Starting GrantIstituzione ospitante
8010 Graz
Austria