Superpixel lattices

Moore, Alastair; Prince, Simon J. D.; Warrell, Jonathan; Mohammed, Umar; Jones, Graham

doi:10.1109/cvpr.2008.4587471

Cited by 335 publications

(233 citation statements)

References 15 publications

Supporting

Mentioning

223

Contrasting

Unclassified

Order By: Relevance

“…We also compare the performance of our approach with other recent techniques for computing superpixels [3], [13], [18], [22], both in terms of the characteristics of output superpixels and the computational speed.…”

Section: Introductionmentioning

confidence: 99%

“…We evaluate the MCL-superpixels through qualitative comparison with four other existing methods which we refer to as: NCuts (the Normalized Cuts) [18], Quick shift [22], Lattice [13] and Graph-based [3]. We employ the Berkeley database [11] and use all 300 images in the experiments.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…An alternative method is to employ mode seeking techniques such as mean shift [1], [2], [4], medoid shift [19], or the recently introduced quick shift [22] which was employed for example in the context of localising object classes in images [5]. Other methods include top-down approaches such as superpixel lattices [13] or TurboPixels [8], and bottom-up approaches such as the graph-based approach in [3] which * This work first appeared in a shortened form in Perbet and Maki [17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Homogeneous Superpixels from Markov Random Walks

Perbet

Stenger

Maki

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper presents a novel algorithm to generate homogeneous superpixels from Markov random walks. We exploit Markov clustering (MCL) as the methodology, a generic graph clustering method based on stochastic flow circulation. In particular, we introduce a graph pruning strategy called compact pruning in order to capture intrinsic local image structure. The resulting superpixels are homogeneous, i.e. uniform in size and compact in shape. The original MCL algorithm does not scale well to a graph of an image due to the square computation of the Markov matrix which is necessary for circulating the flow. The proposed pruning scheme has the advantages of faster computation, smaller memory footprint, and straightforward parallel implementation. Through comparisons with other recent techniques, we show that the proposed algorithm achieves state-ofthe-art performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Homogeneous Superpixels from Markov Random Walks

Perbet

Stenger

Maki

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…They seek superpixels that conform to a grid, which has storage and efficiency advantages. The work in [20] is based on greedy optimization, and [21] uses a more global optimization, which, like our work, is also based on graph cuts. The formulation in [20,21] poses certain restrictions on superpixel shapes: the boundary between superpixels cannot "turn back" on itself.…”

Section: Introductionmentioning

confidence: 99%

Superpixels and Supervoxels in an Energy Optimization Framework

Veksler

Boykov

Mehrani

2010

Lecture Notes in Computer Science

320

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

“…Commonly image segmentation algorithms like [4,5] are used to generate superpixels. Recently many algorithms have been proposed for high level grouping of the superpixels, e.g., [6].…”

Section: Introductionmentioning

confidence: 99%

Distance Learning Based on Convex Clustering

Yang

Latecki

Gross

2009

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Clustering has been among the most active research topics in machine learning and pattern recognition. Though recent approaches have delivered impressive results in a number of challenging clustering tasks, most of them did not solve two problems. First, most approaches need prior knowledge about the number of clusters which is not practical in many applications. Second, non-linear and elongated clusters cannot be clustered correctly. In this paper, a general framework is proposed to solve both problems by convex clustering based on learned distance. In the proposed framework, the data is transformed from elongated structures into compact ones by a novel distance learning algorithm. Then, a convex clustering algorithm is used to cluster the transformed data. Presented experimental results demonstrate successful solutions to both problems. In particular, the proposed approach is very suitable for superpixel generation, which are a common base for recent high level image segmentation algorithms.

show abstract

Superpixel lattices

Cited by 335 publications

References 15 publications

Homogeneous Superpixels from Markov Random Walks

Homogeneous Superpixels from Markov Random Walks

Superpixels and Supervoxels in an Energy Optimization Framework

Distance Learning Based on Convex Clustering

Contact Info

Product

Resources

About