From local occlusion cues to global monocular depth estimation
Tipo de documentoTexto en actas de congreso
Fecha de publicación2012
EditorInstitute of Electrical and Electronics Engineers (IEEE)
Condiciones de accesoAcceso restringido por política de la editorial
In this paper, we propose a system to obtain a depth ordered seg- mentation of a single image based on low level cues. The algorithm first constructs a hierarchical, region-based image representation of the image using a Binary Partition Tree (BPT). During the building process, T-junction depth cues are detected, along with high convex boundaries. When the BPT is built, a suitable segmentation is found and a global depth ordering is found using a probabilistic framework. Results are compared with state of the art depth ordering and figure/ground labeling systems. The advantage of the proposed ap- proach compared to systems based on a training procedure is the lack of assumptions about the scene content. Moreover, it is shown that the system outperforms previously low-level cue based systems, while offering similar results to a priori trained figure/ground label- ing algorithms
CitaciónPalou, G.; Salembier, P. From local occlusion cues to global monocular depth estimation. A: IEEE International Conference on Acoustics, Speech, and Signal Processing. "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing: March 25–30, 2012, Kyoto, Japan". Kyoto: Institute of Electrical and Electronics Engineers (IEEE), 2012, p. 793-796.
Versión del editorhttp://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6288003