A method and system of identifying in an image captured by a second camera a target object captured by a first camera is disclosed. The method comprises using image captured by the 1st camera for generating a first set of objects comprising the target object and other objects; classifying each object to generate a reference group of attribute values characterizing the objects; using image captured by the 2nd camera for generating second sets of objects; classifying each object in each second set to generate, for each second set, a corresponding group of attribute values characterizing the objects in the corresponding second set; selecting the second set of objects corresponding to the group of attribute values best matching the reference group of attribute values; and identifying the target object in the selected second set of objects in accordance with a position of the target object in the first set of objects.
MULTI-CAMERA VEHICLE IDENTIFICATION SYSTEM
MEHRFACHKAMERASYSTEM ZUR FAHRZEUGIDENTIFIKATION
SYSTÈME D'IDENTIFICATION DE VÉHICULES PAR CAMÉRAS MULTIPLES
2018-05-09
Patent
Elektronische Ressource
Englisch