Segment-Based Clustering of Hyperspectral Images Using Tree-Based Data Partitioning Structures

Abstract

Hyperspectral image classification has been increasingly used in the field of remote sensing. In this study, a new clustering framework for large-scale hyperspectral image (HSI) classification is proposed. The proposed four-step classification scheme explores how to effectively use the global spectral information and local spatial structure of hyperspectral data for HSI classification. Initially, multidimensional Watershed is used for pre-segmentation. Region-based hierarchical hyperspectral image segmentation is based on the construction of Binary partition trees (BPT). Each segmented region is modeled while using first-order parametric modelling, which is then followed by a region merging stage using HSI regional spectral properties in order to obtain a BPT representation. The tree is then pruned to obtain a more compact representation. In addition, principal component analysis (PCA) is utilized for HSI feature extraction, so that the extracted features are further incorporated into the BPT. Finally, an efficient variant of k-means clustering algorithm, called filtering algorithm, is deployed on the created BPT structure, producing the final cluster map. The proposed method is tested over eight publicly available hyperspectral scenes with ground truth data and it is further compared with other clustering frameworks. The extensive experimental analysis demonstrates the efficacy of the proposed method.

Hyperspectral imaging – a short review of methods and applications

“…The steps of segmentation and clustering are the most dynamically developed operations, very often based on artificial intelligence (AI). Especially the combination and iterative approach to segmentation (often referred to as the re-representation of an image as a set of 𝑛 one-band images instead of one 𝑛-band image) and clustering (which clusters similar pixels into regions classified as one type of object) are the subject of many interesting solutions, such as tree-based data partitioning structures [41]. This is due to the fact that after logically-determined first steps of hyperspectral image processing, segmentation and clustering are more challenging and knowledge or an application-dependent process is applied.…”

DCCaps-UNet: A U-Shaped Hyperspectral Semantic Segmentation Model Based on the Depthwise Separable and Conditional Convolution Capsule Network

“…However, the complex data structure and high information redundancy of hyperspectral images make this task challenging. Although the operation of traditional image segmentation [15][16][17][18][19][20][21] is relatively simple, it is difficult to obtain satisfactory performance because it mostly relies on handmade features. Therefore, it is of great research significance to establish an efficient semantic segmentation model for hyperspectral images.…”

Editorial Paper for the Special Issue “Algorithms in Hyperspectral Data Analysis”

“…In their work, Ismail et al [1] have dealt with hyperspectral image classification, which has been increasingly used in the field of remote sensing. This work proposes a new clustering framework for large-scale hyperspectral image (HSI) classification.…”