Добірка наукової літератури з теми "Possibilistic supervised classificatio"

This paper presents a unique Possibilistic c-Means with constraints (PCM-S) with Adaptive Possibilistic Local Information c-Means (ADPLICM) in a supervised way by incorporating local information through local spatial constraints and local similarity measures in Possibilistic c-Means Algorithm. PCM-S with ADPLICM overcome the limitations of the known Possibilistic c-Means (PCM) and Possibilistic c-Means with constraints (PCM-S) algorithms. The major contribution of proposed algorithm to ensure the noise resistance in the presence of random salt & pepper noise. The effectiveness of proposed algorithm has been analysed on random “salt and pepper” noise added on original dataset and Root Mean Square Error (RMSE) has been calculated between original dataset and noisy dataset. It has been observed that PCM-S with ADPLICM is effective in minimizing noise during supervised classification by introducing local convolution.

Fuzzy c-means (FCM) and possibilistic c-means (PCM) are two commonly used fuzzy clustering algorithms for extracting land use land cover (LULC) information from satellite images. However, these algorithms use only spectral or grey-level information of pixels for clustering and ignore their spatial correlation. Different variants of the FCM algorithm have emerged recently that utilize local spatial information in addition to spectral information for clustering. Such algorithms are seen to generate clustering outputs that are more enhanced than the classical spectral-based FCM algorithm. Nonetheless, the scope of integrating spatial contextual information with the conventional PCM algorithm, which has several advantages over the FCM algorithm for supervised classification, has not been explored much. This study proposed integrating local spatial information with the PCM algorithm using simpler but proven approaches from available FCM-based local spatial information algorithms. The three new PCM-based local spatial information algorithms: Possibilistic c-means with spatial constraints (PCM-S), possibilistic local information c-means (PLICM), and adaptive possibilistic local information c-means (ADPLICM) algorithms, were developed corresponding to the available fuzzy c-means with spatial constraints (FCM-S), fuzzy local information c-means (FLICM), and adaptive fuzzy local information c-means (ADFLICM) algorithms. Experiments were conducted to analyze and compare the FCM and PCM classifier variants for supervised LULC classifications in soft (fuzzy) mode. The quantitative assessment of the soft classification results from fuzzy error matrix (FERM) and root mean square error (RMSE) suggested that the new PCM-based local spatial information classifiers produced higher accuracies than the PCM, FCM, or its local spatial variants, in the presence of untrained classes and noise. The promising results from PCM-based local spatial information classifiers suggest that the PCM algorithm, which is known to be naturally robust to noise, when integrated with local spatial information, has the potential to result in more efficient classifiers capable of better handling ambiguities caused by spectral confusions in landscapes.

This paper deals with (both supervised and unsupervised) classification of multispectral Sentinel-2 images, utilizing the abundance representation of the pixels of interest. The latter pixel representation uncovers the hidden structured regions that are not often available in the reference maps. Additionally, it encourages class distinctions and bolsters accuracy. The adopted methodology, which has been successfully applied to hyperpsectral data, involves two main stages: (I) the determination of the pixel’s abundance representation; and (II) the employment of a classification algorithm applied to the abundance representations. More specifically, stage (I) incorporates two key processes, namely (a) endmember extraction, utilizing spectrally homogeneous regions of interest (ROIs); and (b) spectral unmixing, which hinges upon the endmember selection. The adopted spectral unmixing process assumes the linear mixing model (LMM), where each pixel is expressed as a linear combination of the endmembers. The pixel’s abundance vector is estimated via a variational Bayes algorithm that is based on a suitably defined hierarchical Bayesian model. The resulting abundance vectors are then fed to stage (II), where two off-the-shelf supervised classification approaches (namely nearest neighbor (NN) classification and support vector machines (SVM)), as well as an unsupervised classification process (namely the online adaptive possibilistic c-means (OAPCM) clustering algorithm), are adopted. Experiments are performed on a Sentinel-2 image acquired for a specific region of the Northern Pindos National Park in north-western Greece containing water, vegetation and bare soil areas. The experimental results demonstrate that the ad-hoc classification approaches utilizing abundance representations of the pixels outperform those utilizing the spectral signatures of the pixels in terms of accuracy.

Dans ce travail, nous proposons un système de recalage géométrique possibiliste qui fusionne les connaissances sémantiques et les connaissances au niveau du gris des images à recaler. Les méthodes de recalage géométrique existantes se reposent sur une analyse des connaissances au niveau des capteurs lors de la détection des primitives ainsi que lors de la mise en correspondance. L'évaluation des résultats de ces méthodes de recalage géométrique présente des limites au niveau de la perfection de la précision causées par le nombre important de faux amers. L’idée principale de notre approche proposée est de transformer les deux images à recaler en un ensemble de projections issues des images originales (source et cible). Cet ensemble est composé des images nommées « cartes de possibilité », dont chaque carte comporte un seul contenu et présente une distribution possibiliste d’une classe sémantique des deux images originales. Le système de recalage géométrique basé sur la théorie de possibilités proposé présente deux contextes : un contexte supervisé et un contexte non supervisé. Pour le premier cas de figure nous proposons une méthode de classification supervisée basée sur la théorie des possibilités utilisant les modèles d'apprentissage. Pour le contexte non supervisé, nous proposons une méthode de clustering possibiliste utilisant la méthode FCM-multicentroide. Les deux méthodes proposées fournissent en résultat les ensembles de classes sémantiques des deux images à recaler. Nous créons par la suite, les bases de connaissances pour le système de recalage possibiliste proposé. Nous avons amélioré la qualité du recalage géométrique existant en termes de perfection de précision, de diminution du nombre de faux amers et d'optimisation de la complexité temporelle
In this work, we propose a possibilistic geometric registration system that merges the semantic knowledge and the gray level knowledge of the images to be registered. The existing geometric registration methods are based on an analysis of the knowledge at the level of the sensors during the detection of the primitives as well as during the matching. The evaluation of the results of these geometric registration methods has limits in terms of the perfection of the precision caused by the large number of outliers. The main idea of our proposed approach is to transform the two images to be registered into a set of projections from the original images (source and target). This set is composed of images called “possibility maps”, each map of which has a single content and presents a possibilistic distribution of a semantic class of the two original images. The proposed geometric registration system based on the possibility theory presents two contexts: a supervised context and an unsupervised context. For the first case, we propose a supervised classification method based on the theory of possibilities using learning models. For the unsupervised context, we propose a possibilistic clustering method using the FCM-multicentroid method. The two proposed methods provide as a result the sets of semantic classes of the two images to be registered. We then create the knowledge bases for the proposed possibilistic registration system. We have improved the quality of the existing geometric registration in terms of precision perfection, reductionin the number of false landmarks and optimization of time complexity