Cel
Detecting humans, reconstructing their structure and motion or understanding human action from video sequences are problems of key importance in the advancement of a variety of technological fields including video indexing and coding, entertainment and cul ture, animation and virtual reality, intelligent human-computer interfaces, protection and security. HUMOREV will create technologies that will enable the construction of such systems via a novel association between large scale statistical modeling and lea rning methods, optimization techniques and computer vision. For practical efficiency and robustness, we will devise methods for the automatic learning of adaptive, layered, task-driven human representations and design robust visual reconstruction and recog nition methods that will integrate bottom-up discriminative human detection and action prediction methods with top-down complex, generative, structural physical models. These results will be embodied in two integrated systems: one will target photorealisti c reconstruction of the structure, motion and appearance of multiple interacting humans in movies or archival footage; the other will aim at recognizing human activities in real world image sequences filmed in offices or outdoor environments.
Dziedzina nauki
Słowa kluczowe
Zaproszenie do składania wniosków
FP6-2004-MOBILITY-8
Zobacz inne projekty w ramach tego zaproszenia