Local abundance regularization for hyperspectral sparse unmixing

Rizkinia, Mia; Okuda, Masahiro

doi:10.1109/apsipa.2016.7820684

Cited by 8 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the local abundance of mixed pixels has a high correlation, Rizkinia et al. [16] adopted the method of minimizing the kernel norm of the local neighborhood matrix to model the correlation.…”

Section: Introductionmentioning

confidence: 99%

Analysis and optimization method of influencing factors for three-dimensional target mixed pixels under zero meteorological view distance

Wang,

LIU,

CHEN

et al. 2023

Preprint

View full text Add to dashboard Cite

Mixed pixels widely exist in the obtained hyper-spectral data,which directly affects the accuracy of optical remote sensing imaging simulation. Aiming at the three-dimensional target under zero meteorological view distance, this paper comprehensively considers the effects of directional reflection characteristics, geometric shadows and background radiation on the generation of mixed pixels.It proposes a method of modeling mixed pixels by taking each surface of a three-dimensional target as an end element component and using the weight coefficient of the distance between the end element groups to the view center. Through designing experiments to simulate different influence conditions such as directional reflection, geometric shadow and background radiation, this paper verifies the influence of the radiation value of the mixed pixels of the three-dimensional target produced by different mixing conditions in the single-pixel field of view. The experimental results show that directional reflection characteristics, geometric occlusion shadows and background radiation have significant effects on the generation of mixed pixels for the three-dimensional targets. The improved mixed pixel modeling method proposed in this paper considering the influence of multiple factors has an average error of less than 10% in modeling accuracy of three-dimensional targets, which is significantly better than traditional linear modeling methods. It can be seen that the research results of this paper have good reference significance for the research of the three-dimensional target mixed pixel radiation model.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis and optimization method of influencing factors for three-dimensional target mixed pixels under zero meteorological view distance

Wang,

LIU,

CHEN

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A hyperspectral image (HSI) is an image cube that consists of hundreds of spatial images of a particular space with different spectral information. It has better spectral information than a multispectral image because of its large number of narrow spectral bands [1]. Its rich information opens the possibility to differentiate several objects of interest based on their spectral signatures.…”

Section: Introductionmentioning

confidence: 99%

A Hyperspectral Anomaly Detection Algorithm Based on Morphological Profile and Attribute Filter with Band Selection and Automatic Determination of Maximum Area

2020

Self Cite

View full text Add to dashboard Cite

Anomaly detection is one of the most challenging topics in hyperspectral imaging due to the high spectral resolution of the images and the lack of spatial and spectral information about the anomaly. In this paper, a novel hyperspectral anomaly detection method called morphological profile and attribute filter (MPAF) algorithm is proposed. Aiming to increase the detection accuracy and reduce computing time, it consists of three steps. First, select a band containing rich information for anomaly detection using a novel band selection algorithm based on entropy and histogram counts. Second, remove the background of the selected band with morphological profile. Third, filter the false anomalous pixels with attribute filter. A novel algorithm is also proposed in this paper to define the maximum area of anomalous objects. Experiments were run on real hyperspectral datasets to evaluate the performance, and analysis was also conducted to verify the contribution of each step of MPAF. The results show that the performance of MPAF yields competitive results in terms of average area under the curve (AUC) for receiver operating characteristic (ROC), precision-recall, and computing time, i.e., 0.9916, 0.7055, and 0.25 seconds, respectively. Compared with four other anomaly detection algorithms, MPAF yielded the highest average AUC for ROC and precision-recall in eight out of thirteen and nine out of thirteen datasets, respectively. Further analysis also proved that each step of MPAF has its effectiveness in the detection performance.

show abstract

“…The remote sensing technology based on the hypersepctral imaging is now a powerful observation technique for investigating ground materials. In addition, the use of the spectral information improves capability in image processing techniques like classification and target detection and realizes many practical applications such as environmental monitoring and food analysis [1]- [6]. In the applications, the reflectance information is more preferable than radiance acquired by image sensors, since colored illumination and shadows often degrade the performance of image processing, and thus it is important to develop reflectance estimation algorithms.…”

Section: Introductionmentioning

confidence: 99%

Computationally Efficient Reflectance Estimation for Hyperspectral Images

Okabe

Okuda

2017

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

The Retinex theory assumes that large intensity changes correspond to reflectance edges, while smoothly-varying regions are due to shading. Some algorithms based on the theory adopt simple thresholding schemes and achieve adequate results for reflectance estimation. In this paper, we present a practical reflectance estimation technique for hyperspectral images. Our method is realized simply by thresholding singular values of a matrix calculated from scaled pixel values. In the method, we estimate the reflectance image by measuring spectral similarity between two adjacent pixels. We demonstrate that our thresholding scheme effectively estimates the reflectance and outperforms the Retinex-based thresholding. In particular, our methods can precisely distinguish edges caused by reflectance change and shadows.

show abstract

Local abundance regularization for hyperspectral sparse unmixing

Cited by 8 publications

References 22 publications

Analysis and optimization method of influencing factors for three-dimensional target mixed pixels under zero meteorological view distance

Analysis and optimization method of influencing factors for three-dimensional target mixed pixels under zero meteorological view distance

A Hyperspectral Anomaly Detection Algorithm Based on Morphological Profile and Attribute Filter with Band Selection and Automatic Determination of Maximum Area

Computationally Efficient Reflectance Estimation for Hyperspectral Images

Contact Info

Product

Resources

About