作者: Brunetta Alessandro , D'ercoli Francesco , Marinoni Silvia , Benghi Davide
DOI:
关键词: Segmentation 、 Image (mathematics) 、 Discriminative model 、 3d vision 、 Set (abstract data type) 、 Machine vision 、 Artificial intelligence 、 Cognitive neuroscience of visual object recognition 、 Computer vision 、 Computer science 、 Identification (information)
摘要: Various embodiments of the invention are implemented for an entry level, compact and lightweight single package apparatus combining a conventional high-resolution two-dimensional (2D) camera with low-resolution three-dimensional (3D) depth image camera, capable to learn, through information, how improve performance set 2D identification machine vision algorithms in terms speed-up (e.g. regions interests (ROIs)) raw discriminative power. The cameras simultaneously capture images that processed by Intelligent Segmentation Engine system facilitate object recognition.