Using Pixel-Based and Object-Based Methods to Classify Urban Hyperspectral Features

Abstract

Object-based image analysis methods have been developed recently. They have since become a very active research topic in the remote sensing community. This is mainly because the researchers have begun to study the spatial structures within the data. In contrast, pixel-based methods only use the spectral content of data. To evaluate the applicability of object-based image analysis methods for land-cover information extraction from hyperspectral data, a comprehensive comparative analysis was performed. In this study, six supervised classification methods were selected from pixel-based category, including the maximum likelihood (ML), fisher linear likelihood (FLL), support vector machine (SVM), binary encoding (BE), spectral angle mapper (SAM) and spectral information divergence (SID). The classifiers were conducted on several features extracted from original spectral bands in order to avoid the problem of the Hughes phenomenon, and obtain a sufficient number of training samples. Three supervised and four unsupervised feature extraction methods were used. Pixel based classification was conducted in the first step of the proposed algorithm. The effective feature number (EFN) was then obtained. Image objects were thereafter created using the fractal net evolution approach (FNEA), the segmentation method implemented in eCognition software. Several experiments have been carried out to find the best segmentation parameters. The classification accuracy of these objects was compared with the accuracy of the pixel-based methods. In these experiments, the Pavia University Campus hyperspectral dataset was used. This dataset was collected by the ROSIS sensor over an urban area in Italy. The results reveal that when using any combination of feature extraction and classification methods, the performance of object-based methods was better than pixel-based ones. Furthermore the statistical analysis of results shows that on average, there is almost an 8 percent improvement in classification accuracy when we use the object-based methods.

Lithological classification by PCA-QPSO-LSSVM method with thermal infrared hyper-spectral data

“…After analysis of the measured spectrum and JHU spectrum library, the TASI emissivity data in the study were divided into 27 types of lithological units (the corresponding sequence number). These are andesite (1), dolomite marble (2), marble (3), two-mica quartzite (4), monzonitic granite ( 5), monzodiorite (6), biotite plagioclase granulite (7), granite porphyry ( 8), granodiorite porphyry (9), granodiorite (10), limestone (11), diabase (12), pyroxenite (13), gabbro diorite (14), moyite (15), plauenite (16), sericite felsic slate (17), sub-rhyolite (18), diorite-porphyrite (19), diorite (20), serpentine (21), aposandstone (22), plagiogranite (23), basalt (24), dacite (25), mica slate (26), and felsic rock (27). The 50 samples were selected randomly for each type of lithology, of which 40 samples were used as training samples and 10 samples were used as test samples to carry out the lithological classification experiments in the study area.…”

“…A relatively complete method system has been formed 22 – 29 A series of studies have shown that hyperspectral remote sensing data can distinguish the undistinguishable substances in multispectral remote sensing data due to its rich spectral information, which can help obtain accurate classification results. Zhang and Li 30 proposed the determining reference spectra method based on SAM for lithological mapping with EO-1 hyperion hyperspectral data.…”

Object-Oriented Multi-Scale Segmentation and Multi-Feature Fusion-Based Method for Identifying Typical Fruit Trees in Arid Regions Using Sentinel-1/2 Satellite Images

“…The pixel-based classi cation method often results in "salt and pepper noise," which affects classi cation accuracy [19]. In contrast, the object-oriented(OO) classi cation method considers factors such as pixel context, object scale, and spatial consistency, effectively handling salt and pepper noise in images and improving classi cation robustness.…”

Comparing the effectiveness of hyperspectral imaging and Raman spectroscopy: a case study on Armenian manuscripts

“…The techniques are included in the software as standard as they have been used for the analysis of remote sensing data (SFF [73][74][75], SAM [76][77][78], BE [79][80][81]). For the analysis of heritage based hyperspectral data only SAM appears to have been used previously [42,82,83].…”