A Subspace-Based Change Detection Method for Hyperspectral Images

Wu, Chen; Du, Bo; Zhang, Liangpei

doi:10.1109/jstars.2013.2241396

Cited by 116 publications

(62 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same preprocessing operations (i.e., uncalibrated and noisiest bands removal, bad stripes repairing, atmospheric correction, co-registration) has been done as in the previous dataset, thus 159 bands (i.e., 8-57, 82-119, 131-164, 182-184, and 187-220) out of the original 242 bands were used in the CD experiment. Land cover changes in this scenario mainly include the class transitions between crops, bare soil, variations in soil moisture, and water content of vegetation [36]. Figure 6a-c shows the false color composite of X1, X2 and three bands in XD images, respectively.…”

Section: Results On the Umatilla County Irrigated Agricultural Datasetmentioning

confidence: 99%

Band Selection-Based Dimensionality Reduction for Change Detection in Multi-Temporal Hyperspectral Images

Tong

Samat

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

This paper proposes to use band selection-based dimensionality reduction (BS-DR) technique in addressing a challenging multi-temporal hyperspectral images change detection (HSI-CD) problem. The aim of this work is to analyze and evaluate in detail the CD performance by selecting the most informative band subset from the original high-dimensional data space. In particular, for cases where ground reference data are available or unavailable, either supervised or unsupervised CD approaches are designed. The following sub-problems in HSI-CD are investigated, including: (1) the estimated number of multi-class changes; (2) the binary CD; (3) the multiple CD; (4) the estimated optimal number of selected bands; and (5) computational efficiency. The main contribution of this paper is to provide for the first time a thorough analysis of the impacts of band selection on the HSI-CD problem, thus to fix the gap in the state-of-the-art techniques either by simply utilizing the full dimensionality of the data or exploring a complex hierarchical change analysis. It is applicable to CD problems in multispectral or PolSAR images when the feature space is expanded for discriminant feature extraction. Two real multi-temporal hyperspectral Hyperion datasets are used to validate the proposed approaches. Quantitative and qualitative experimental results demonstrated that by selecting a subset of the most informative and distinct spectral bands, the proposed approaches offered better CD performance than the state-of-the-art techniques using original full bands, without losing the change representative and discriminable capabilities of a detector.

show abstract

Section: Results On the Umatilla County Irrigated Agricultural Datasetmentioning

confidence: 99%

Band Selection-Based Dimensionality Reduction for Change Detection in Multi-Temporal Hyperspectral Images

Tong

Samat

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The magnitude of the change vector (Euclidean distance of CVA or CVAED) and the spectral information divergence (SID) similarity measures are applied to detect the changed area [24,41]. Subspace-based change-detection (SCD) algorithms, that is, original SCD, adaptive SCD (ASCD), and local SCD (LSCD), are also employed [26]. ASCD and LSCD are applied to estimate the effects of varying sensor positions or misregistration between the multitemporal hyperspectral data.…”

Section: Change-detection Resultsmentioning

confidence: 99%

“…The change-detection results can be quantitatively evaluated by estimating the receiver operating characteristic (ROC) curve and by evaluating the binary change map using a thresholding technique. The ROC curve provides a graphical plot for the estimating the performance and selecting an optimal model from the class distribution [26,43,44]. The ROC curve is composed of the cumulative distribution function of the detection rate versus that of the false-alarm rate.…”

Section: Journal Of Sensorsmentioning

confidence: 99%

“…Júnior et al [25] used CVA based on distance (Euclidean distance and Mahalanobis distance) and similarity (spectral angle mapper, SAM, and spectral correlation mapper, SCM) measurements and concluded that CVA using the Euclidean distance and SAM is superior to other measures. Wu et al [26] developed a subspace-based algorithm using two types of information from Hyperion and from the Chinese HJ-1A satellite, proving that measurements based on the SAM are identical to the orthogonal subspace projection-(OSP-) based measurements. Based on this concept, the authors have proposed local and adaptive measures based on OSP to minimize registration errors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Unsupervised Algorithm for Change Detection in Hyperspectral Remote Sensing Data Using Synthetically Fused Images and Derivative Spectral Profiles

et al. 2017

View full text Add to dashboard Cite

Multitemporal hyperspectral remote sensing data have the potential to detect altered areas on the earth's surface. However, dissimilar radiometric and geometric properties between the multitemporal data due to the acquisition time or position of the sensors should be resolved to enable hyperspectral imagery for detecting changes in natural and human-impacted areas. In addition, data noise in the hyperspectral imagery spectrum decreases the change-detection accuracy when general change-detection algorithms are applied to hyperspectral images. To address these problems, we present an unsupervised change-detection algorithm based on statistical analyses of spectral profiles; the profiles are generated from a synthetic image fusion method for multitemporal hyperspectral images. This method aims to minimize the noise between the spectra corresponding to the locations of identical positions by increasing the change-detection rate and decreasing the false-alarm rate without reducing the dimensionality of the original hyperspectral data. Using a quantitative comparison of an actual dataset acquired by airborne hyperspectral sensors, we demonstrate that the proposed method provides superb change-detection results relative to the state-of-the-art unsupervised change-detection algorithms.

show abstract

“…It illustrates that the joint classification with both LiDAR data and high resolution image can obtain a better performance than each independent classification, while the proposed method can get an obvious improvement because it involves object-based postclassification fusion. Table 3 shows the false alarm rate (FAR) [56] and omission rate (OR) of each class for the proposed method and the comparative methods. It can be observed that high resolution image cannot determine the building and soil accurately, while LiDAR data also get a bad performance in classifying soil and pavement.…”

Section: Object-based Post-classification Fusionmentioning

confidence: 99%

An Improved Method for Impervious Surface Mapping Incorporating Lidar Data and High-Resolution Imagery at Different Acquisition Times

Luo¹,

Wang²,

Wu³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Impervious surface mapping with high-resolution remote sensing imagery has attracted increasing interest as it can provide detailed information for urban structure and distribution. Previous studies have suggested that the combination of LiDAR data and high-resolution imagery for impervious surface mapping performs better than using only high-resolution imagery. However, due to the high cost of the acquisition of LiDAR data, it is difficult to obtain the multisensor remote sensing data acquired at the same acquisition time for impervious surface mapping. Consequently, real landscape changes between multi-sensor remote sensing data at different acquisition times would lead to the error of misclassification in impervious surface mapping. This issue has mostly been neglected in previous works. Furthermore, the observation differences generated from multi-sensor data, including the problems of misregistration, missing data in LiDAR data, and shadow in high-resolution images would also challenge the final mapping result in the fusion of LiDAR data and high-resolution images. In order to conquer these problems, we propose an improved impervious surface mapping method incorporating both LiDAR data and highresolution imagery at different acquisition times in consideration of real landscape changes and observation differences. In the proposed method, a multi-sensor change detection by supervised multivariate alteration detection is employed to obtain changed areas and misregistration areas. The no-data areas in the LiDAR data and the shadow areas in the high-resolution imagery are extracted by independent classification yielded by its corresponding single sensor data. Finally, an objectbased post-classification fusion is proposed to take advantage of independent classification results with single-sensor data and the joint classification result with stacked multi-sensor data. Experiments covering the study site in Buffalo, NY, USA demonstrate that our method can accurately detect landscape changes and obviously improve the performance of impervious surface mapping.

show abstract

A Subspace-Based Change Detection Method for Hyperspectral Images

Cited by 116 publications

References 68 publications

Band Selection-Based Dimensionality Reduction for Change Detection in Multi-Temporal Hyperspectral Images

Band Selection-Based Dimensionality Reduction for Change Detection in Multi-Temporal Hyperspectral Images

An Unsupervised Algorithm for Change Detection in Hyperspectral Remote Sensing Data Using Synthetically Fused Images and Derivative Spectral Profiles

An Improved Method for Impervious Surface Mapping Incorporating Lidar Data and High-Resolution Imagery at Different Acquisition Times

Contact Info

Product

Resources

About