Topic Modelling for Object-Based Unsupervised Classification of VHR Panchromatic Satellite Images Based on Multiscale Image Segmentation

Abstract

Abstract:Image segmentation is a key prerequisite for object-based classification. However, it is often difficult, or even impossible, to determine a unique optimal segmentation scale due to the fact that various geo-objects, and even an identical geo-object, present at multiple scales in very high resolution (VHR) satellite images. To address this problem, this paper presents a novel unsupervised object-based classification for VHR panchromatic satellite images using multiple segmentations via the latent Dirichlet allocation (LDA) model. Firstly, multiple segmentation maps of the original satellite image are produced by means of a common multiscale segmentation technique. Then, the LDA model is utilized to learn the grayscale histogram distribution for each geo-object and the mixture distribution of geo-objects within each segment. Thirdly, the histogram distribution of each segment is compared with that of each geo-object using the Kullback-Leibler (KL) divergence measure, which is weighted with a constraint specified by the mixture distribution of geo-objects. Each segment is allocated a geo-object category label with the minimum KL divergence. Finally, the final classification map is achieved by integrating the multiple classification results at different scales. Extensive experimental evaluations are designed to compare the performance of our method with those of some state-of-the-art methods for three different types of images. The experimental results over three different types of VHR panchromatic satellite images demonstrate the proposed method is able to achieve scale-adaptive classification results, and improve the ability to differentiate the geo-objects with spectral overlap, such as water and grass, and water and shadow, in terms of both spatial consistency and semantic consistency.

Bidirectional Segmented Detection of Land Use Change Based on Object-Level Multivariate Time Series

“…For multiresolution segmentation, numerous studies have demonstrated the importance of the scale parameter. The scale parameter controls the dimension and size of segmented objects, which may directly affect subsequent results [47][48][49]. In numerous applied studies, land-cover extraction mainly relied on a trial-and-error approach, with segmentation scale parameters determined based on previous experience [50].…”

Improving Ecotope Segmentation by Combining Topographic and Spectral Data

“…Alternatively, Geographic Object-Based Image Analysis can be used to delineate spatial regions by grouping adjacent pixels into homogeneous areas according to the objectives of the study [23,24]. For biodiversity research, image segmentation has been used to automatically derive homogeneous vegetation units based on spectral [25] or a combination of spectral and structural (height) information [16,26].…”

Local-HDP: Interactive Open-Ended 3D Object Categorization in Real-Time Robotic Scenarios

“…We propose the Local Hierarchical Dirichlet Process (Local-HDP), an extension of the Hierarchical Dirichlet Process [11] method, which can incrementally learn new topics for each category of objects independently. In contrast to the notable recent works [8,12,13] using a predefined number of topics, Local-HDP is more flexible since it is a non-parametric Bayesian model that can autonomously determine the number of topics for each category at run-time. Figure 2 shows the processing layers of the proposed Local-HDP.…”