Multi-Probe Based Artificial DNA Encoding and Matching Classifier for Hyperspectral Remote Sensing Imagery

Abstract

Abstract:In recent years, a novel matching classification strategy inspired by the artificial deoxyribonucleic acid (DNA) technology has been proposed for hyperspectral remote sensing imagery. Such a method can describe brightness and shape information of a spectrum by encoding the spectral curve into a DNA strand, providing a more comprehensive way for spectral similarity comparison. However, it suffers from two problems: data volume is amplified when all of the bands participate in the encoding procedure and full-band comparison degrades the importance of bands carrying key information. In this paper, a new multi-probe based artificial DNA encoding and matching (MADEM) method is proposed. In this method, spectral signatures are first transformed into DNA code words with a spectral feature encoding operation. After that, multiple probes for interesting classes are extracted to represent the specific fragments of DNA strands. During the course of spectral matching, the different probes are compared to obtain the similarity of different types of land covers. By computing the absolute vector distance (AVD) between different probes of an unclassified spectrum and the typical DNA code words from the database, the class property of each pixel is set as the minimum distance class. The main benefit of this strategy is that the risk of redundant bands can be deeply reduced and critical spectral discrepancies can be enlarged. Two hyperspectral image datasets were tested. Comparing with the other classification methods, the overall accuracy can be improved from 1.22% to 10.09% and 1.19% to 15.87%, respectively. Furthermore, the kappa coefficient can be improved from 2.05% to 15.29% and 1.35% to 19.59%, respectively. This demonstrated that the proposed algorithm outperformed other traditional classification methods.

Monitoring Marine Oil Spills in Hyperspectral and Multispectral Remote Sensing Data by the Spectral Gene Extraction (SGE) Method

“…Inspired by pattern recognition technologies and spectral encoding methods [13,14], a spectral gene extraction (SGE) method based on the spectral DNA encoding method was proposed for detecting oil spills in this research. It was validated that the spectral DNA encoding method could describe spectral information distinctively [15,16]. Based on this, the SGE method was proposed to mine the population genetic characteristics of oil slicks.…”

“…In addition, the spectral genes extracted by the LIS strategy were distributed in both sides of the spectral brightness information part and the spectral shape information part of the spectral DNA chains. However, the LID strategy obtained fewer spectral genes than the LIS strategy, especially for seawater (16) and sheens (14). This might be because the spectral gene extraction criteria of the LID strategy were more demanding than the LIS strategy.…”

Enhanced Spectral–Spatial Residual Attention Network for Hyperspectral Image Classification

“…In HSIC, problems such as high imbalance between the number of samples of categories and few known labels for some of the features are very common [58]. The small number of training samples of HSI limits the learning ability of deep learning-based models, which makes it difficult to extract the typical features and affects the classification accuracy.…”