Saliency-Guided Object Candidates Based on Gestalt Principles

We present a new method for generating general object candidates for cluttered RGB-D scenes. Starting from an over-segmentation of the image, we build a graph representation and define an object candidate as a subgraph that has maximal internal similarity as well as minimal external similarity. These candidates are created by successively adding segments to a seed segment in a saliency-guided way. Finally, the resulting object candidates are ranked based on Gestalt principles. We show that the proposed algorithm clearly outperforms three other recent methods for object discovery on the challenging Kitchen dataset.

[1]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[2]  Santiago Manen,et al.  Prime Object Proposals with Randomized Prim's Algorithm , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  Simone Frintrop,et al.  VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search , 2006, Lecture Notes in Computer Science.

[4]  J. R. Pomerantz,et al.  A century of Gestalt psychology in visual perception: II. Conceptual and theoretical foundations. , 2012, Psychological bulletin.

[5]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[6]  Gert Kootstra,et al.  Fast and bottom-up object detection, segmentation, and evaluation using Gestalt principles , 2011, 2011 IEEE International Conference on Robotics and Automation.

[7]  Fei-Fei Li,et al.  Object discovery in 3D scenes via shape analysis , 2013, 2013 IEEE International Conference on Robotics and Automation.

[8]  S. Palmer,et al.  A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure-ground organization. , 2012, Psychological bulletin.

[9]  Thomas Deselaers,et al.  Measuring the Objectness of Image Windows , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Markus Vincze,et al.  Implementation of Gestalt principles for object segmentation , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[11]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.

[12]  Simone Frintrop,et al.  Sequence-level object candidates based on saliency for generic object recognition on mobile systems , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Simone Frintrop,et al.  Salient Pattern Detection Using W 2 on Multivariate Normal Distributions , 2012, DAGM/OAGM Symposium.

[14]  Walter Gerbino,et al.  Convexity and Symmetry in Figure-Ground Organization , 1976 .

[15]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[16]  Simone Frintrop,et al.  Traditional saliency reloaded: A good old model in new shape , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Simone Frintrop 6 Sensor Fusion , 2006 .

[18]  H. Pashler The Psychology of Attention , 1997 .

[19]  Armin B. Cremers,et al.  A Cognitive Approach for Object Discovery , 2014, 2014 22nd International Conference on Pattern Recognition.