TY - JOUR
T1 - Toward parts-based scene understanding with pixel-support parts-sparse pictorial structures
AU - Corso, Jason J.
PY - 2013
Y1 - 2013
N2 - Scene understanding remains a significant challenge in the computer vision community. The visual psychophysics literature has demonstrated the importance of interdependence among parts of the scene. Yet, the majority of methods in scene understanding remain local. Pictorial structures have arisen as a fundamental parts-based model for some vision problems, such as articulated object detection. However, the form of classical pictorial structures limits their applicability for global problems, such as semantic pixel labeling. In this paper, we propose an extension of the pictorial structures approach, called pixel-support parts-sparse pictorial structures, or PS3, to overcome this limitation. Our model extends the classical form in two ways: first, it defines parts directly based on pixel-support rather than in a parametric form, and second, it specifies a space of plausible parts-based scene models and permits one to be used for inference on any given image. PS3 makes strides toward unifying object-level and pixel-level modeling of scene elements. In this paper, we implement the first half of our model and rely upon external knowledge to provide an initial graph structure for a given image. Our experimental results on benchmark datasets demonstrate the capability of this new parts-based view of scene modeling.
AB - Scene understanding remains a significant challenge in the computer vision community. The visual psychophysics literature has demonstrated the importance of interdependence among parts of the scene. Yet, the majority of methods in scene understanding remain local. Pictorial structures have arisen as a fundamental parts-based model for some vision problems, such as articulated object detection. However, the form of classical pictorial structures limits their applicability for global problems, such as semantic pixel labeling. In this paper, we propose an extension of the pictorial structures approach, called pixel-support parts-sparse pictorial structures, or PS3, to overcome this limitation. Our model extends the classical form in two ways: first, it defines parts directly based on pixel-support rather than in a parametric form, and second, it specifies a space of plausible parts-based scene models and permits one to be used for inference on any given image. PS3 makes strides toward unifying object-level and pixel-level modeling of scene elements. In this paper, we implement the first half of our model and rely upon external knowledge to provide an initial graph structure for a given image. Our experimental results on benchmark datasets demonstrate the capability of this new parts-based view of scene modeling.
KW - Image segmentation
KW - Object recognition
KW - Pictorial structures
KW - Scene understanding
KW - Stochastic optimization
UR - http://www.scopus.com/inward/record.url?scp=84875931258&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84875931258&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2012.04.004
DO - 10.1016/j.patrec.2012.04.004
M3 - Article
AN - SCOPUS:84875931258
SN - 0167-8655
VL - 34
SP - 762
EP - 769
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
IS - 7
ER -