A Fast Search System for Remote Sensing Imagery Based on Bag of Visual Words and Latent Dirichlet Allocation

Karmakar, Chandrabali; Datcu, Mihai

doi:10.1109/igarss39084.2020.9324359

Cited by 2 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With these assumptions, LDA maps the documents to the topics through assigning the words of the document to the topics in a Dirichlet distribution. Particularly, LDA assumes that each document is a distribution of topics and each topic is a distribution of words in Dirichlet distribution [14], [16], [22].…”

Section: B Latent Dirichlet Allocation (Lda)modelmentioning

confidence: 99%

“…A word in text can be the equivalent of a visual word (i.e., from BOVW model) in the image, which itself corresponds to a segment or a window of pixels. Additionally, a text document can be analogous to the image [16], [22].…”

Section: B Latent Dirichlet Allocation (Lda)modelmentioning

confidence: 99%

“…The simple features such as mean and standard deviation for the LDA-image representation are used in the maximum-likelihood method to classify the large unseen satellite images. Furthermore, Karmakar and Datcu [22] utilized BOVW and LDA models for representing EO images in word-and topic-level and applied text-based search algorithms for fast semantic search in EO images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Earth Observation Semantic Data Mining: Latent Dirichlet Allocation-Based Approach

Asiyabi

Datcu

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Recent advances in remote sensing technology have provided (very) high spatial resolution Earth Observation (EO) data with abundant latent semantic information. Conventional data processing algorithms are not capable of extracting the latent semantic information form these data and harness their full potential. As a result, semantic information discovery methods, based on data mining techniques, such as Latent Dirichlet Allocation (LDA) and Bag of Visual Words (BOVW) models, can discover the latent information. Despite their crucial rule, there are only a few studies in the field of semantic data mining for remote sensing applications. This study is focused on this shortage. Three different scenarios are used to evaluate the semantic information discovery in various remote sensing applications, including both optical and Synthetic Aperture Radar (SAR) data with different spatial resolutions. In the first scenario, semantic discovery method correlated the semantic perception of the user and machine to correct and enhance the user defined Ground Truth (GT) map in very high-resolution RGB data. The potential of the semantic discovery is evaluated for wildfire affected area detection in Sentinel-2 data in the second scenario. Finally, in the third scenario, the semantic discovery method is utilized to detect the misclassifications as well as the patches with ambiguous or multiple semantic labels in a Sentinel-1 SAR patch-based benchmark dataset, to enhance the robustness and accuracy of the annotation in the dataset. Our results in these three scenarios demonstrated the capability of the data mining-based semantic information discovery methods for various remote sensing applications.

show abstract

Section: B Latent Dirichlet Allocation (Lda)modelmentioning

confidence: 99%

Section: B Latent Dirichlet Allocation (Lda)modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation