作者: Timothy J. Roberts , Stephen J. McKenna , Ian W. Ricketts
DOI: 10.1007/978-3-540-24673-2_24
关键词: Space (mathematics) 、 Artificial intelligence 、 3D pose estimation 、 Clutter 、 Image (mathematics) 、 Computer vision 、 Pose 、 Texture (geology) 、 Probabilistic logic 、 Pattern recognition 、 Computer science 、 Configuration space
摘要: A model of human appearance is presented for efficient pose estimation from real-world images. In common with related approaches, a high-level defines space configurations which can be associated image measurements and thus scored. search performed to identify good configuration(s). Such an approach challenging because the configuration high dimensional, global, humans in images complex due background clutter, shape uncertainty texture.