Interactive learning and probabilistic retrieval in remote sensing image archives

Schröder, Michael; Rehrauer, H.; Seidel, K.; Datcu, Mihai

doi:10.1109/36.868886

Cited by 107 publications

(50 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(An alternative is to use a parametric distribution assumption, e.g., Gaussian, for each individual continuous feature but these parametric assumptions do not always hold.) Schröder et al [19] used similar classifiers to retrieve images from remote sensing archives by approximating the probabilities of images belonging to different classes using pixel level probabilities. In the following, we describe learning of the models for p(x i |w j ) using the positive training examples for the j'th class label.…”

Section: Pixel Classificationmentioning

confidence: 99%

Spatial Techniques for Image Classification

Aksoy¹

2006

Signal and Image Processing for Remote Sensing

View full text Add to dashboard Cite

The constant increase in the amount and resolution of remotely sensed imagery necessitates development of intelligent systems for automatic processing and classification. We describe a Bayesian framework that uses spatial information for classification of high-resolution images. First, spectral and textural features are extracted for each pixel. Then, these features are quantized and are used to train Bayesian classifiers with discrete non-parametric density models. Next, an iterative split-and-merge algorithm is used to convert the pixel level classification maps into contiguous regions. Then, the resulting regions are modeled using the statistical summaries of their spectral, textural and shape properties, and are used with Bayesian classifiers to compute the final classification maps. Experiments with three ground truth data sets show the effectiveness of the proposed approach over traditional techniques that do not make strong use of region-based spatial information.

show abstract

Section: Pixel Classificationmentioning

confidence: 99%

Spatial Techniques for Image Classification

Aksoy¹

2006

Signal and Image Processing for Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The semantic modeling detailed in this section was previously presented in [18]. The learning framework presents similarities with the one adopted by Schroder et al [5].…”

Section: User-specific Semantic Labeling By Interactive Learningmentioning

confidence: 99%

“…Examples of these image models are Gibbs-Markov random field models for textural features or the intensities of the multi-spectral images for spectral features [5]. Of course, for the latter, no sophisticated modeling is involved.…”

Section: A Feature Extractionmentioning

confidence: 99%

Trajectory of Dynamic Clusters in Image Time-Series

Héas¹,

Irit²,

Dlr³

et al. 2004

Analysis of Multi-Temporal Remote Sensing Images

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use a Bayesian label training algorithm with naive Bayes models 35 to perform fusion of multispectral data, DEM data and the extracted features. The Bayesian framework provides a probabilistic link between low-level image feature attributes and high-level user defined semantic structure labels.…”

Section: Structural Relationshipsmentioning

confidence: 99%

Scene Modeling and Image Mining With a Visual Grammar

Aksoy¹,

Koperski²,

Marchisio³

2003

Frontiers of Remote Sensing Information Processing

View full text Add to dashboard Cite

Automatic content extraction, classification and content-based retrieval are highly desired goals in intelligent remote sensing databases. Pixel level processing has been the common choice for both academic and commercial systems. We extend the modeling of remotely sensed imagery to three levels: Pixel level, region level and scene level. Pixel level features are generated using unsupervised clustering of spectral values, texture features and ancillary data like digital elevation models. Region level features include shape information and statistics of pixel level feature values. Scene level features include statistics and spatial relationships of regions. This chapter describes our work on developing a probabilistic visual grammar to reduce the gap between low-level features and high-level user semantics, and to support complex query scenarios that consist of many regions with different feature characteristics. The visual grammar includes automatic identification of region prototypes and modeling of their spatial relationships. The system learns the prototype regions in an image collection using unsupervised clustering. Spatial relationships are represented by fuzzy membership functions. The system automatically selects significant relationships from training data and builds visual grammar models which can also be updated using user relevance feedback. A Bayesian framework is used to automatically classify scenes based on these models. We demonstrate our system with query scenarios that cannot be expressed by traditional region or scene level approaches but where the visual grammar provides accurate classifications and effective retrieval.

show abstract

Interactive learning and probabilistic retrieval in remote sensing image archives

Cited by 107 publications

References 20 publications

Spatial Techniques for Image Classification

Spatial Techniques for Image Classification

Trajectory of Dynamic Clusters in Image Time-Series

Scene Modeling and Image Mining With a Visual Grammar

Contact Info

Product

Resources

About