Maqola

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

Jordi Pont-TusetDepartment of Signal Theory and Communications, Universitat Politècnica de Catalunya, BarcelonaTech, Barcelona, SpainPablo ArbeláezDepartment of Biomedical Engineering, Universidad de los Andes, Bogota, ColombiaJonathan T. BarronDepartment of Electrical Engineering and Computer Science, University of California at Berkeley, Berkeley, CAFerran MarquésDepartment of Signal Theory and Communications, Universitat Politècnica de Catalunya, BarcelonaTech, Barcelona, SpainJitendra MalikDepartment of Electrical Engineering and Computer Science, University of California at Berkeley, Berkeley, CA

2016en

ABI

Annotatsiya

We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm. We then propose a high-performance hierarchical segmenter that makes effective use of multiscale information. Finally, we propose a grouping strategy that combines our multiscale regions into highly-accurate object proposals by exploring efficiently their combinatorial space. We also present Single-scale Combinatorial Grouping (SCG), a faster version of MCG that produces competitive proposals in under five seconds per image. We conduct an extensive and comprehensive empirical validation on the BSDS500, SegVOC12, SBD, and COCO datasets, showing that MCG produces state-of-the-art contours, hierarchical regions, and object proposals.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.1109/tpami.2016.2537320

Iqtiboslar va manbalar

2 ta iqtibos0 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar