Optical Aerial Images Change Detection Based on a Color Local Dissimilarity Map and k-Means ClusteringShow others and affiliations
2022 (English)In: IEEE Geoscience and Remote Sensing Letters, ISSN 1545-598X, E-ISSN 1558-0571, Vol. 19, article id 6517705Article in journal (Refereed) Published
Abstract [en]
Considering the unavailability of labeled data sets in remote sensing change detection, this letter presents a novel and low complexity unsupervised change detection method based on the combination of similarity and dissimilarity measures: mutual information (MI), disjoint information (DI), and local dissimilarity map (LDM). MI and DI are calculated on sliding windows with a step of 1 pixel for each pair of channels of both images. The resulting scalar values, weighted by q and m coefficients, are multiplied by the values of the center pixels of the windows weighted by p to remove the textures on images. The changes are detected using, respectively, the grayscale LDM and color LDM. A sliding window is then used on the color LDM and each pixel is characterized by a two-parameter Weibull distribution. Binarized change maps can be obtained by using a k-means clustering on the model parameters. Experiments on optical aerial image data set show that the proposed method produces comparable, even better results, to the state-of-the-art methods in terms of recall, precision, and F-measure.
Place, publisher, year, edition, pages
IEEE, 2022. Vol. 19, article id 6517705
Keywords [en]
Disjoint information (DI), k-means clustering, local dissimilarity map (LDM), mutual information (MI), Weibull distribution, Antennas, Change detection, Decoding, Feature extraction, Maximum likelihood, Optical remote sensing, Pixels,
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:hj:diva-60430DOI: 10.1109/LGRS.2022.3216952ISI: 000880645100010Scopus ID: 2-s2.0-85141477985OAI: oai:DiVA.org:hj-60430DiVA, id: diva2:1758973
2023-05-242023-05-242023-05-24Bibliographically approved