Image Mining Using Directional Spatial Constraints

Abstract

Abstract-Spatial information plays a fundamental role in building high-level content models for supporting analysts' interpretations and automating geospatial intelligence. We describe a framework for modeling directional spatial relationships among objects and using this information for contextual classification and retrieval. The proposed model first identifies image areas that have a high degree of satisfaction of a spatial relation with respect to several reference objects. Then, this information is incorporated into the Bayesian decision rule as spatial priors for contextual classification. The model also supports dynamic queries by using directional relationships as spatial constraints to enable object detection based on the properties of individual objects as well as their spatial relationships to other objects. Comparative experiments using high-resolution satellite imagery illustrate the flexibility and effectiveness of the proposed framework in image mining with significant improvements in both classification and retrieval performance.

An Object-Based Image Analysis Approach for Detecting Penguin Guano in very High Spatial Resolution Satellite Images

“…Image semantics are context sensitive, which means that semantics are not an intrinsic property captured during the image acquisition process but rather an emergent property of the interactions of human perception and the image content [77][78][79][80]. GEOBIA's Achilles' heel-the semantic gap (lack of explicit link)-impedes repeatability, transferability, and interoperability of classification workflows.…”

Scalable Bag of Subpaths Kernel for Learning on Hierarchical Image Representations and Multi-Source Remote Sensing Data Classification

“…For instance, in [8], the authors propose to model topological relations between segmented objects, e.g., roads and moving vehicles, and construct rule-sets for classifying objects and refining classification results. In [9,10], spatial relationships among objects are also used for defining rule-sets. Although designing the knowledge-based rule-set is straightforward to integrate context features into classification, it often requires human involvement and interpretation, which is subjective and hard to adapt to new locations and datasets.…”

“…In the GEOBIA framework, the most common way to take into account such features is through constructing rules for classifying objects and refining classification results [4,[8][9][10]. However, such a knowledge-based subjective rule-set designing strategy is highly reliant on human involvement and interpretation, which makes it difficult to be adapted to new locations and datasets and makes the processing of data in large remote sensing archives practically impossible.…”

Genetic Optimization for Associative Semantic Ranking Models of Satellite Images by Land Cover

“…Recent research in the geospatial area provided a variety of in-depth solutions [7][8][9][10][11][12][13][14][15][16][17][18], to represent the complex, often overlapping geospatial knowledge and to assist image analysts in generating necessary domain specific metadata. The research in [7] describes a framework for modeling and image retrieval using directional spatial relationships among objects.…”

“…The research in [7] describes a framework for modeling and image retrieval using directional spatial relationships among objects. Content-based image retrieval (CBIR) methods were applied to ranking satellite images using possibilistic associations between low-level features and semantics of interest [8].…”