Perceptual Organization of Occluding Contours of Opaque Surfaces

Saund, Eric

doi:10.1006/cviu.1999.0789

Cited by 31 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Historically, more attention has been paid to segmentation, though some important studies of figure/ground exist, focusing on contour and junction structure [13,11,25,32] or specific cues [10] such as convexity [21] or lower-region [29]. Recent work has revived interest on figure/ground discrimination [24,16] and the related problem of depth ordering [15,26].…”

Section: Introductionmentioning

confidence: 99%

Simultaneous Segmentation and Figure/Ground Organization Using Angular Embedding

Maire

2010

Computer Vision – ECCV 2010

View full text Add to dashboard Cite

Abstract. Image segmentation and figure/ground organization are fundamental steps in visual perception. This paper introduces an algorithm that couples these tasks together in a single grouping framework driven by low-level image cues. By encoding both affinity and ordering preferences in a common representation and solving an Angular Embedding problem, we allow segmentation cues to influence figure/ground assignment and figure/ground cues to influence segmentation. Results are comparable to state-of-the-art automatic image segmentation systems, while additionally providing a global figure/ground ordering on regions.

show abstract

Section: Introductionmentioning

confidence: 99%

Simultaneous Segmentation and Figure/Ground Organization Using Angular Embedding

Maire

2010

Computer Vision – ECCV 2010

View full text Add to dashboard Cite

show abstract

“…Smooth continuation is an important factor that promotes figure-ground separation and optimal discovery of object-like components in the scene corresponding to structurally salient parts of the image. This factor has been interpreted in terms of minimum energy curves in the context of surface organization [4], generic positioning or non-accidental alignment [22], contour smoothness under occlusion of opaque surfaces [22], and low curvature between edgels [2].…”

Section: Related Past Workmentioning

confidence: 99%

“…At the highest level, interpreting image structure involves joining or severing contour fragments to determine figure-ground arrangements of structurally salient parts of the image [23]. Saund [22] conceptualizes events as 'non-accidental' when grouped configurations could be described with fewer relative parameters than in the generic ungrouped case. Each new package created by the grouping process requires fewer relative parameters for description than the original input set.…”

Section: Computational Theorymentioning

confidence: 99%

“…Applying MDL to figure-ground grouping makes explicit the tradeoff between how structured the image is to how complex (succinct) its description. In general, figure-ground organization schemes construct and regularize an objective function by penalizing any deviation from desired smoothness or genericity based on local evidence subject to constraints identified at the required level of abstraction [2] [8] [19] [22]. MDL is a better regularization metric than choices of ad hoc cost functions and more suitable to figure-ground problem because the trade off helps identify high-level structures in the image with simpler descriptions.…”

Section: Computational Theorymentioning

confidence: 99%

See 1 more Smart Citation

MDL based Structural Interpretation of Images under Partial Occlusion

Ramakrishnan

Forte²

2001

Procedings of the British Machine Vision Conference 2001

View full text Add to dashboard Cite

In this paper an information theoretic approach is provided for resolving border ambiguity under partial occlusion. The proposed framework allows structural interpretation of images prior to the application of domain specific knowledge. The central idea behind MDL based figure-ground grouping is merging those place-token candidates whose composed description length (whole) is better than sum of their individual description lengths (parts). The computational theory is illustrated by application to blocks-world images.

show abstract

“…Many possible spatial cues may contribute to figure perception from a single image, including convexity [25], junctions [27], and familiar configurations [26]). However, depth ordering from a single image may be subjective and prone to ambiguities, whereas motion gives a very powerful and usually unambiguous cue.…”

Section: Introductionmentioning

confidence: 99%

Motion Segmentation and Depth Ordering Using an Occlusion Detector

Feldman

Weinshall

2008

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-We present a novel method for motion segmentation and depth ordering from a video sequence in general motion. We first compute motion segmentation based on differential properties of the spatio-temporal domain, and scale-space integration. Given a motion boundary, we describe two algorithms to determine depth ordering from two-and three-frame sequences. A remarkable characteristic of our method is its ability compute depth ordering from only two frames. The segmentation and depth ordering algorithms are shown to give good results on 6 real sequences taken in general motion. We use synthetic data to show robustness to high levels of noise and illumination changes; we also include cases where no intensity edge exists at the location of the motion boundary, or when no parametric motion model can describe the data. Finally, we describe psychophysical experiments showing that people, like our algorithm, can compute depth ordering from only two frames, even when the boundary between the layers is not visible in a single frame.

show abstract

Perceptual Organization of Occluding Contours of Opaque Surfaces

Cited by 31 publications

References 23 publications

Simultaneous Segmentation and Figure/Ground Organization Using Angular Embedding

Simultaneous Segmentation and Figure/Ground Organization Using Angular Embedding

MDL based Structural Interpretation of Images under Partial Occlusion

Motion Segmentation and Depth Ordering Using an Occlusion Detector

Contact Info

Product

Resources

About