Efficient hierarchical graph-based video segmentation

Grundmann, Matthias; Kwatra, Vivek; Han, Moonsik; Essa, Irfan

doi:10.1109/cvpr.2010.5539893

Cited by 601 publications

(789 citation statements)

References 25 publications

Supporting

Mentioning

780

Contrasting

Unclassified

Order By: Relevance

“…Causal methods consider only past data for segmenting each next frame [16,19]. Omniscient techniques use both past and future data by treating the video as a 3D space-time volume, so that segmentation of the entire image set supports each of the individual segmentations [7,10].…”

Section: Introductionmentioning

confidence: 99%

Enforcing Monotonous Shape Growth or Shrinkage in Video Segmentation

Tarabalka¹,

Charpiat²,

Brucker³

et al. 2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

We propose a new method based on graph cuts for joint segmentation of monotonously growing or shrinking shapes in time series of noisy images. By introducing directed infinite links connecting pixels at the same spatial locations in successive image frames, we impose shape growth/shrinkage constraint in graph cuts. Minimization of energy computed on the resulting graph of the image sequence yields globally optimal segmentation. We validate the proposed approach on two applications: segmentation of melting sea ice floes from a time series of multimodal satellite images and segmentation of a growing brain tumor from sequences of 3D multimodal medical scans. In the latter application, we impose an additional inter-sequences inclusion constraint by adding directed infinite links between pixels of dependent image structures.

show abstract

Section: Introductionmentioning

confidence: 99%

Enforcing Monotonous Shape Growth or Shrinkage in Video Segmentation

Tarabalka¹,

Charpiat²,

Brucker³

et al. 2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

show abstract

“…Instead of replacing pixel colors, one could group pixels initially by their proximity to modes. In the case of images, one could then efficiently calculate a hierarchical segmentation by successively merging different clusters based on a similarity threshold, following the method of Paris and Durand [31] and similar to Grundmann et al [21] and Arbelaez [3]. A complete discussion and evaluation of hierarchical image segmentation is outside the scope of this work, although we demonstrate the usefulness of the permutohedral lattice as a first stage in a hierarchical clustering algorithm.…”

Section: Mean Shift Filteringmentioning

confidence: 99%

Lattice-Based High-Dimensional Gaussian Filtering and the Permutohedral Lattice

2012

View full text Add to dashboard Cite

High-dimensional Gaussian filtering is a popular technique in image processing, geometry processing and computer graphics for smoothing data while preserving important features. For instance, the bilateral filter, cross bilateral filter and non-local means filter fall under the broad umbrella of high-dimensional Gaussian filters. Recent algorithmic advances therein have demonstrated that by relying on a sampled representation of the underlying space, one can obtain speed-ups of orders of magnitude over the naïve approach. The simplest such sampled representation is a lattice, and it has been used successfully in the bilateral grid and the permutohedral lattice algorithms. In this paper, we analyze these lattice-based algorithms, developing a general theory of lattice-based high-dimensional Gaussian filtering. We consider the set of criteria for an optimal lattice for filtering, as it offers a good tradeoff of quality for computational efficiency, and evaluate the existing lattices under the criteria. In particular, we give a rigorous exposition of the properties of the permutohedral lattice and argue that it is the optimal lattice for Gaussian filtering. Lastly, we explore further uses of the permutohedral-lattice-based Gaussian filtering framework, showing that it can be easily adapted to perform mean shift filtering and yield improvement over the traditional approach based on a Cartesian grid.

show abstract

“…Some of the other methods make use of the superpixels. They connect them spatially and temporally to generate temporally consistent object regions [15,4,19,11]. This approach is often used in an unsupervised setting, which usually leads to severe over-segmentation.…”

Section: Related Workmentioning

confidence: 99%

Hierarchy of Localized Random Forests for Video Annotation

Nagaraja

Ochs

Liu

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We address the problem of annotating a video sequence with partial supervision. Given the pixel-wise annotations in the first frame, we aim to propagate these labels ideally throughout the whole video. While some labels can be propagated using optical flow, disocclusion and unreliable flow in some areas require additional cues. To this end, we propose to train localized classifiers on the annotated frame. In contrast to a global classifier, localized classifiers allow to distinguish colors that appear in both the foreground and the background but at very different locations. We design a multi-scale hierarchy of localized random forests, which collectively takes a decision. Cues from optical flow and the classifier are combined in a variational framework. The approach can deal with multiple objects in a video. We present qualitative and quantitative results on the Berkeley Motion Segmentation Dataset.

show abstract

Efficient hierarchical graph-based video segmentation

Cited by 601 publications

References 25 publications

Enforcing Monotonous Shape Growth or Shrinkage in Video Segmentation

Enforcing Monotonous Shape Growth or Shrinkage in Video Segmentation

Lattice-Based High-Dimensional Gaussian Filtering and the Permutohedral Lattice

Hierarchy of Localized Random Forests for Video Annotation

Contact Info

Product

Resources

About