Class segmentation and object localization with superpixel neighborhoods

Fulkerson, Brian; Vedaldi, Andrea; Soatto, Stefano

doi:10.1109/iccv.2009.5459175

Cited by 537 publications

(390 citation statements)

References 32 publications

Supporting

Mentioning

384

Contrasting

Unclassified

Order By: Relevance

“…Therefore, this popular procedure [13] is not consistent with the principles of optimal canonization. This might explain why others have advocated forgoing feature selection altogether [14], or have simply moved to sampling translations, along with scale [34].…”

Section: Local Invariant Framesmentioning

confidence: 99%

Video-based descriptors for object recognition

Lee

Soatto

2011

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Section: Local Invariant Framesmentioning

confidence: 99%

Video-based descriptors for object recognition

Lee

Soatto

2011

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

“…The cluster graph is then partitioned based on color information yielding a coarse segmentation of the image. Recent conditional random field-based (CRF) segmentation approaches such as [17], [18] rely on image clustering not only to reduce memory overhead but also to collect image features from clusters and their neighborhood.…”

Section: A Graph Cut In Segmentation and Its Complexitymentioning

confidence: 99%

Shortest-Path Constraints for 3D Multiobject Semiautomatic Segmentation Via Clustering and Graph Cut

Kéchichian

Valette

Desvignes

et al. 2013

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

To cite this version:Razmig Kéchichian, Sébastien Valette, Michel Desvignes, Rémy Prost. Shortest-path constraints for 3D multiobject semiautomatic segmentation via clustering and Graph Cut. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2013, 22 (11) Abstract-We derive shortest-path constraints from graph models of structure adjacency relations and introduce them in a joint centroidal Voronoi image clustering and Graph Cut multiobject semiautomatic segmentation framework. The vicinity prior model thus defined is a piecewise-constant model incurring multiple levels of penalization capturing the spatial configuration of structures in multiobject segmentation. Qualitative and quantitative analysis and comparison with a Potts prior-based approach and our previous contribution on synthetic, simulated and real medical images show that the vicinity prior allows for the correct segmentation of distinct structures having identical intensity profiles and improves the precision of segmentation boundary placement while being fairly robust to clustering resolution. The clustering approach we take to simplify images prior to segmentation strikes a good balance between boundary adaptivity and cluster compactness criteria furthermore allowing to control the trade-off. Compared to a direct application of segmentation on voxels, the clustering step improves the overall runtime and memory footprint of the segmentation process up to an order of magnitude without compromising the quality of the result.

show abstract

“…Many vision applications benefit from representing an image as a collection of superpixels, for example [1][2][3][4][5][6][7][8], to cite just a few. While the exact definition of a superpixel is not feasible, it is regarded as a perceptually meaningful atomic region.…”

Section: Introductionmentioning

confidence: 99%

Superpixels and Supervoxels in an Energy Optimization Framework

Veksler

Boykov

Mehrani

2010

Lecture Notes in Computer Science

324

269

View full text Add to dashboard Cite

Abstract. Many methods for object recognition, segmentation, etc., rely on tessellation of an image into "superpixels". A superpixel is an image patch which is better aligned with intensity edges than a rectangular patch. Superpixels can be extracted with any segmentation algorithm, however, most of them produce highly irregular superpixels, with widely varying sizes and shapes. A more regular space tessellation may be desired. We formulate the superpixel partitioning problem in an energy minimization framework, and optimize with graph cuts. Our energy function explicitly encourages regular superpixels. We explore variations of the basic energy, which allow a trade-off between a less regular tessellation but more accurate boundaries or better efficiency. Our advantage over previous work is computational efficiency, principled optimization, and applicability to 3D "supervoxel" segmentation. We achieve high boundary recall on 2D images and spatial coherence on video. We also show that compact superpixels improve accuracy on a simple application of salient object segmentation.

show abstract

Class segmentation and object localization with superpixel neighborhoods

Cited by 537 publications

References 32 publications

Video-based descriptors for object recognition

Video-based descriptors for object recognition

Shortest-Path Constraints for 3D Multiobject Semiautomatic Segmentation Via Clustering and Graph Cut

Superpixels and Supervoxels in an Energy Optimization Framework

Contact Info

Product

Resources

About