What Is a Good Image Segment? A Unified Approach to Segment Extraction

Bagon, Shai; Boiman, Oren; Irani, Michal

doi:10.1007/978-3-540-88693-8_3

Cited by 84 publications

(99 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of these approaches minimize a binary pairwise energy function (Boykov and Jolly, 2001) whose unary potentials are determined by appearance models estimated based on user input on the test image. Bagon et al (Bagon et al, 2008) proposed an algorithm that generates figure-ground segmentations by maximizing a selfsimilarity criterion around a user selected image point. While the method of (Küttel and Ferrari, 2012) is also based on minimizing an energy function of the same form as interactive segmentation, it is fully automatic.…”

Section: Related Workmentioning

confidence: 99%

Superpixel Cut for Figure-Ground Image Segmentation

Yang¹,

Rosenhahn²

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Figure-ground image segmentation has been a challenging problem in computer vision. Apart from the difficulties in establishing an effective framework to divide the image pixels into meaningful groups, the notions of figure and ground often need to be properly defined by providing either user inputs or object models. In this paper, we propose a novel graph-based segmentation framework, called superpixel cut. The key idea is to formulate foreground segmentation as finding a subset of superpixels that partitions a graph over superpixels. The problem is formulated as Min-Cut. Therefore, we propose a novel cost function that simultaneously minimizes the inter-class similarity while maximizing the intra-class similarity. This cost function is optimized using parametric programming. After a small learning step, our approach is fully automatic and fully bottom-up, which requires no high-level knowledge such as shape priors and scene content. It recovers coherent components of images, providing a set of multiscale hypotheses for high-level reasoning. We evaluate our proposed framework by comparing it to other generic figure-ground segmentation approaches. Our method achieves improved performance on state-of-the-art benchmark databases.

show abstract

Section: Related Workmentioning

confidence: 99%

Superpixel Cut for Figure-Ground Image Segmentation

Yang¹,

Rosenhahn²

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Different approaches have been proposed, such as scribbling in the image [2,34], framing the object of interest with a rectangle [3,35], or just indicating object positions with single points [36,37]. Scribbling allows you to directly build appearance models from the scribbled areas.…”

Section: Initialization and Interactionmentioning

confidence: 99%

Detecting, segmenting and tracking unknown objects using multi-label MRF inference

Björkman

Bergström

Kragić

2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

This article presents a unified framework for detecting, segmenting and tracking unknown objects in everyday scenes, allowing for inspection of object hypotheses during interaction over time. A heterogeneous scene representation is proposed, with background regions modeled as a combinations of planar surfaces and uniform clutter, and foreground objects as 3D ellipsoids. Recent energy minimization methods based on loopy belief propagation, tree-reweighted message passing and graph cuts are studied for the purpose of multi-object segmentation and benchmarked in terms of segmentation quality, as well as computational speed and how easily methods can be adapted for parallel processing. One conclusion is that the choice of energy minimization method is less important than the way scenes are modeled. Proximities are more valuable for segmentation than similarity in colors, while the benefit of 3D information is limited. It is also shown through practical experiments that, with implementations on GPUs, multiobject segmentation and tracking using state-of-art MRF inference methods is feasible, despite the computational costs typically associated with such methods.

show abstract

“…At a conceptual level, our ideas relate to the work of Bagon et al [1] on interactive figure-ground segmentation. In that work, the authors suggest that good segments are self-similar, i.e.…”

Section: Background and Related Workmentioning

confidence: 99%

“…see [1,29]). In other words, our model is based on the observation that similar appearance of disjoint image regions suggests similar semantic meaning for pairs of corresponding pixels in the regions.…”

Section: Introductionmentioning

confidence: 99%