CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts

We present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prio...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on pattern analysis and machine intelligence Ročník 34; číslo 7; s. 1312 - 1328
Hlavní autori:	Carreira, J., Sminchisescu, C.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Los Alamitos, CA IEEE 01.07.2012 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Algorithms Applied sciences Artificial intelligence Categories Computer science; control theory; systems Constraints Detectors Exact sciences and technology figure-ground segmentation Hypotheses Image color analysis Image edge detection Image segmentation Information retrieval. Graph learning Mathematical models Object recognition Object segmentation Pattern recognition. Digital image processing. Computational geometry Segmentation Shape Studies Theoretical computing Image recognition Stimulus Pipeline processor Image processing Grid Labelling learning Ground truth Modeling Relevance Image segmentation figure-ground segmentation Graph cut Object oriented Bottom up method Overlay Regularity Image classification
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	We present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge of the properties of individual object classes, by solving a sequence of Constrained Parametric Min-Cut problems (CPMC) on a regular image grid. In a subsequent step, we learn to rank the corresponding segments by training a continuous model to predict how likely they are to exhibit real-world regularities (expressed as putative overlap with ground truth) based on their mid-level region properties, then diversify the estimated overlap score using maximum marginal relevance measures. We show that this algorithm significantly outperforms the state of the art for low-level segmentation in the VOC 2009 and 2010 data sets. In our companion papers [1], [2], we show that the algorithm can be used, successfully, in a segmentation-based visual object category recognition pipeline. This architecture ranked first in the VOC2009 and VOC2010 image segmentation and labeling challenges.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23
ISSN:	0162-8828 1939-3539 2160-9292 1939-3539
DOI:	10.1109/TPAMI.2011.231