Probabilistic Spatial Context Models for Scene Content Understanding
نویسندگان
چکیده
Scene content understanding facilitates a large number of applications, ranging from content-based image retrieval to other multimedia applications. Material detection refers to the problem of identifying key semantic material types (such as sky, grass, foliage, water, and snow in images. In this paper, we present a holistic approach to determining scene content, based on a set of individual material detection algorithms, as well as probabilistic spatial context models. A major limitation of individual material detectors is the significant number of misclassifications that occur because of the similarities in color and texture characteristics of various material types. We have developed a spatial context-aware material detection system that reduces misclassification by constraining the beliefs to conform to the probabilistic spatial context models. Experimental results show that the accuracy of materials detection is improved by 13% using the spatial context models over the individual material detectors themselves.
منابع مشابه
Inferring Context through Scene Understanding
In this work we propose the application of scene understanding methods using probabilistic graphs to the problem of learning and representing computational context. Many machine learning methods treat their input space as a ’bag of features’; that is, inference is accomplished by taking some global aggregation which may be engineered or learned. A limitation of this approach is that many models...
متن کاملContext-Based Probabilistic Scene Interpretation
In high-level scene interpretation, it is useful to exploit the evolving probabilistic context for stepwise interpretation decisions. We present a new approach based on a general probabilistic framework and beam search for exploring alternative interpretations. As probabilistic scene models, we propose Bayesian Compositional Hierarchies (BCHs) which provide object-centered representations of co...
متن کاملProbabilistic Retrieval with a Visual Grammar
We describe a system for content-based retrieval and classification of multispectral images. Our system models images on pixel, region and scene levels. To reduce the gap between low-level features and highlevel user semantics, and to support complex query scenarios that consist of many regions with different feature characteristics, we propose a probabilistic visual grammar that includes autom...
متن کاملInferring Naval Tactical Context through Scene Understanding
In this work we explore the application of scene understanding methods to the problem of learning and representing computational context. Modern machine learning models often treat their input space as a statistical ’bag of features’; that is, inference is accomplished by taking a weighted (possibly non-linear) aggregation of features which may be engineered or learned. A representational limit...
متن کاملScene Semantic Understanding Based on the Spatial Context Relations of Multiple Objects
As a result of the large semantic gap between the low-level features and the high-level semantics, scene understanding is a challenging task for high satellite resolution images. To achieve scene understanding, we need to know the contents of the scene. However, most of the existing scene classification methods, such as the bag-of-visual-words model (BoVW), feature coding, topic models, and neu...
متن کامل