Some issues in the classification of DAIS hyperspectral data

Pal, Mahesh; Mather, Paul M.

doi:10.1080/01431160500185227

Cited by 104 publications

(63 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The primary advantage of the SVM method is that it requires no assumptions in terms of the distribution of the data and can achieve a good result with relatively limited training sample data [5,67]. In addition, the SVM method is not sensitive to high data dimensionality [11,41,71], and is especially suited to classify data with high dimensionality and multiple sources [9,67]. In general, previous studies have shown that the SVM is more accurate than the MLC method, e.g., [66,72].…”

Section: Classification Methodsmentioning

confidence: 99%

Fusion of Airborne Discrete-Return LiDAR and Hyperspectral Data for Land Cover Classification

Luo

Wang

et al. 2015

Remote Sensing

View full text Add to dashboard Cite

Accurate land cover classification information is a critical variable for many applications. This study presents a method to classify land cover using the fusion data of airborne discrete return LiDAR (Light Detection and Ranging) and CASI (Compact Airborne Spectrographic Imager) hyperspectral data. Four LiDAR-derived images (DTM, DSM, nDSM, and intensity) and CASI data (48 bands) with 1 m spatial resolution were spatially resampled to 2, 4, 8, 10, 20 and 30 m resolutions using the nearest neighbor resampling method. These data were thereafter fused using the layer stacking and principal components analysis (PCA) methods. Land cover was classified by commonly used supervised classifications in remote sensing images, i.e., the support vector machine (SVM) and maximum likelihood (MLC) classifiers. Each classifier was applied to four types of datasets (at seven different spatial resolutions): (1) the layer stacking fusion data; (2) the PCA fusion data; (3) the LiDAR data alone; and (4) the CASI data alone. In this study, the land cover category was classified into seven classes, i.e., buildings, road, water bodies, forests, grassland, cropland and barren land. A total of 56 classification results were produced, and the classification accuracies were assessed and compared. The results show that the classification accuracies produced from two fused datasets were higher than that of the single LiDAR and CASI data at all seven spatial resolutions. Moreover, we find that the layer stacking method produced higher overall classification accuracies than the PCA fusion method using both the SVM and MLC classifiers. The highest classification accuracy obtained (OA = 97.8%, kappa = 0.964) using the SVM classifier on the layer stacking fusion data at 1 m spatial resolution. Compared with the best classification results of the CASI and LiDAR data alone, the overall classification accuracies improved by 9.1% and 19.6%, respectively. Our findings also demonstrated that the SVM classifier generally performed better than the MLC when classifying multisource data; however, none of the classifiers consistently produced higher accuracies at all spatial resolutions.

show abstract

Section: Classification Methodsmentioning

confidence: 99%

Fusion of Airborne Discrete-Return LiDAR and Hyperspectral Data for Land Cover Classification

Luo

Wang

et al. 2015

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Besides the performance of the chosen analyses methods, it was found that studies' results were affected by several differing factors, e.g., land use and land cover types assessed, the quality of the training data and availability of the input imagery, e.g., [56,99,100], as well as the topography and other geographical properties of the study areas. Moreover, accuracy assessments depended heavily on the chosen validation data; while some studies used field data, others were based on visual interpretation of high-resolution images, e.g., provided by Google Earth or IKONOS.…”

Section: Integration Step Number Of Studies Study Idsmentioning

confidence: 99%

“…Studies exploring continuous land properties mainly looked at forest properties (e.g., biomass (e.g., ID 51,53,59,99), forest stand height (e.g., ID 109); 24 of 37 studies). Fewer studies used continuous properties to describe crop lands (e.g., yields (e.g., ID 27), leaf area index (e.g., ID 6, 38); 9 of 37 studies) and grasslands (e.g., biomass (e.g., ID 65); 7 of 37 studies) R1.2.…”

Section: Overview Of the Characteristics Of Land Use Or Cover Studiedmentioning

confidence: 99%

A Review of the Application of Optical and Radar Remote Sensing Data Fusion to Land Use Mapping and Monitoring

et al. 2016

View full text Add to dashboard Cite

Abstract:The wealth of complementary data available from remote sensing missions can hugely aid efforts towards accurately determining land use and quantifying subtle changes in land use management or intensity. This study reviewed 112 studies on fusing optical and radar data, which offer unique spectral and structural information, for land cover and use assessments. Contrary to our expectations, only 50 studies specifically addressed land use, and five assessed land use changes, while the majority addressed land cover. The advantages of fusion for land use analysis were assessed in 32 studies, and a large majority (28 studies) concluded that fusion improved results compared to using single data sources. Study sites were small, frequently 300-3000 km 2 or individual plots, with a lack of comparison of results and accuracies across sites. Although a variety of fusion techniques were used, pre-classification fusion followed by pixel-level inputs in traditional classification algorithms (e.g., Gaussian maximum likelihood classification) was common, but often without a concrete rationale on the applicability of the method to the land use theme being studied. Progress in this field of research requires the development of robust techniques of fusion to map the intricacies of land uses and changes therein and systematic procedures to assess the benefits of fusion over larger spatial scales.

show abstract

“…Inappropriate training samples were indeed identified as the main source of errors in many classification processes [12]. For instance, Foody and Arora [13] showed that the choice of training samples had a significant effect on the classification results, whereas changing the classifier model (the number of layers in a neural network) was not significant.…”

Section: Introductionmentioning

confidence: 99%

Automated Training Sample Extraction for Global Land Cover Mapping

et al. 2014

View full text Add to dashboard Cite

Land cover is one of the essential climate variables of the ESA Climate Change Initiative (CCI). In this context, the Land Cover CCI (LC CCI) project aims at building global land cover maps suitable for climate modeling based on Earth observation by satellite sensors. The challenge is to generate a set of successive maps that are both accurate and consistent over time. To do so, operational methods for the automated classification of optical images are investigated. The proposed approach consists of a locally trained classification using an automated selection of training samples from existing, but outdated land cover information. Combinations of local extraction (based on spatial criteria) and self-cleaning of training samples (based on spectral criteria) are quantitatively assessed. Two large study areas, one in Eurasia and the other in South America, are considered. The proposed morphological cleaning of the training samples leads to higher accuracies than the statistical outlier removal in the spectral domain. An optimal neighborhood has been identified for the local sample extraction. The results are coherent for the two test areas, showing an improvement of the overall accuracy compared with the original reference datasets and a significant reduction of macroscopic errors. More importantly, the proposed method partly controls the reliability of existing land cover maps as sources of training samples for supervised classification.Remote Sens. 2014, 6 3966

show abstract

Some issues in the classification of DAIS hyperspectral data

Cited by 104 publications

References 29 publications

Fusion of Airborne Discrete-Return LiDAR and Hyperspectral Data for Land Cover Classification

Fusion of Airborne Discrete-Return LiDAR and Hyperspectral Data for Land Cover Classification

A Review of the Application of Optical and Radar Remote Sensing Data Fusion to Land Use Mapping and Monitoring

Automated Training Sample Extraction for Global Land Cover Mapping

Contact Info

Product

Resources

About