scholarly journals Evaluating Superpixels in Video: Metrics Beyond Figure-Ground Segmentation

2013 ◽  
Author(s):  
Peer Neubert ◽  
Peter Protzel
Keyword(s):  
Ground Segmentation

When figure-ground segmentation modulates brightness: The case of phantom illumination

2008 ◽  
Vol 129 (1) ◽  
pp. 166-174 ◽  
Author(s):  
Daniele Zavagno ◽  
Olga Daneyko
Keyword(s):  
Ground Segmentation

scholarly journals Feedback Enhances Feedforward Figure-Ground Segmentation by Changing Firing Mode

PLoS ONE ◽  
2011 ◽  
Vol 6 (6) ◽  
pp. e21641 ◽  
Author(s):  
Hans Supèr ◽  
August Romeo
Keyword(s):  
Ground Segmentation ◽  
Firing Mode

Urban Ground Segmentation Algorithm Based on Ray Slope Threshold

2019 ◽  
Vol 39 (9) ◽  
pp. 0928004
Author(s):  
李炯 Jiong Li ◽  
赵凯 Kai Zhao ◽  
白睿 Rui Bai ◽  
朱愿 Yuan Zhu ◽  
徐友春 Youchun Xu
Keyword(s):  
Segmentation Algorithm ◽  
Ground Segmentation

Sky/Ground Segmentation Using Different Approaches

2020 ◽  
Author(s):  
Arlete Teresinha Beuren ◽  
Alceu de Souza Britto ◽  
Jacques Facon
Keyword(s):  
Ground Segmentation

scholarly journals Detection of Symmetry and Repetition in One and Two Objects

2009 ◽  
Vol 56 (1) ◽  
pp. 5-17 ◽  
Author(s):  
Arno Koning ◽  
Johan Wagemans
Keyword(s):  
Three Dimensional ◽  
Intrinsic Property ◽  
Spatial Relations ◽  
Two Dimensional ◽  
Single Object ◽  
Ground Segmentation ◽  
Matching Strategy ◽  
The One

Symmetry is usually easier to detect within a single object than in two objects (one-object advantage), while the reverse is true for repetition (two-objects advantage). This interaction between regularity and number of objects could reflect an intrinsic property of encoding spatial relations within and across objects or it could reflect a matching strategy. To test this, regularities between two contours (belonging to a single object or two objects) had to be detected in two experiments. Projected three-dimensional (3-D) objects rotated in depth were used to disambiguate figure-ground segmentation and to make matching based on simple translations of the two-dimensional (2-D) contours unlikely. Experiment 1 showed the expected interaction between regularity and number of objects. Experiment 2 used two-objects displays only and prevented a matching strategy by also switching the positions of the two objects. Nevertheless, symmetry was never detected more easily than repetition in these two-objects displays. We conclude that structural coding, not matching strategies, underlies the one-object advantage for symmetry and the two-objects advantage for repetition.

Sign in / Sign up

Export Citation Format

Share Document