Spectral image complexity estimated through local convex hull volume

Messinger, David W.; Ziemann, Amanda; Schlamm, Ariel; Basener, Bill

doi:10.1109/whispers.2010.5594869

Cited by 20 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the dimensionality for each image was estimated by using the Gram Matrix method. 12 For SHARE 2010, 12 dimensions were considered and for SHARE 2012, 7 dimensions.α was set to 0.11 based on the experiment of estimation of α presented in a previous work. 6 The σ parameter in (1) for the spectral weighted matrix was adaptively computed using a self-tuning method 13 that considers the local spreading of the data and that has been previously tested and used.…”

Section: Resultsmentioning

confidence: 99%

Schroedinger eigenmaps with knowledge propagation for target detection

Dorado-Munoz

Messinger

2016

SPIE Proceedings

View full text Add to dashboard Cite

The applicability of Laplacian Eigenmaps (LE) and Schroedinger Eigenmaps (SE) has been widely shown in the processing of hyperspectral imagery. Specifically, we have previously shown that SE has a promising performance in spectral target detection. SE, unlike LE, could include prior information or labeled data points into a barrier potential term that steers the transformation in certain directions making the labeled points and the similar points pulled toward the origin in the new space. We have also noticed that the barrier potentials generated from a few labeled points may affect in a brittle manner the dimensionality in the Schroedinger space and in turn, the target detection performance. In this paper, we show that the number of SE used in the detection could be increased without affecting the detection performance by adding spatial and spectral constraints on the individual labeled points and propagating this knowledge to nearby points through a modified Schroedinger matrix. We apply our algorithm to hyperspectral data sets with several target panels and different complexity in order to have a wide framework of assessment.

show abstract

Section: Resultsmentioning

confidence: 99%

Schroedinger eigenmaps with knowledge propagation for target detection

Dorado-Munoz

Messinger

2016

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…Therefore, we only used the dataset covering the cars in our experiments. Clearly, the majority of the scene is qualitatively complex [56] and is difficult for target detection. Fig.…”

Section: Hydice Dataset Experimentsmentioning

confidence: 99%

Target Detection Based on Random Forest Metric Learning

Dong

Zhang

2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

113

View full text Add to dashboard Cite

Target detection is aimed at detecting and identifying target pixels based on specific spectral signatures, and is of great interest in hyperspectral image (HSI) processing. Target detection can be considered as essentially a binary classification. Random forests have been effectively applied to the classification of HSI data. However, random forests need a huge amount of labeled data to achieve a good performance, which can be difficult to obtain in target detection. In this paper, we propose an efficient metric learning detector based on random forests, named the random forest metric learning (RFML) algorithm, which combines semimultiple metrics with random forests to better separate the desired targets and background. The experimental results demonstrate that the proposed method outperforms both the state-of-the-art target detection algorithms and the other classical metric learning methods.Index Terms-Hyperspectral image (HSI), metric learning, random forests, target detection.

show abstract

“…The "complexity" of a region in a spectral image is assumed to be related to the number, and spectral diversity, of the materials in that region. 9 More complex regions of the image are assumed to: 1) contain a relatively larger number of materials, and 2) contain materials that are relatively more spectrally diverse…”

Section: Spectral Complexity Measurementioning

confidence: 99%

Metrics of spectral image complexity with application to large area search

et al. 2012

View full text Add to dashboard Cite

Spectral image complexity is an ill-defined term that has been addressed previously in terms of dimensionality, multivariate normality, and other approaches. Here, we apply the concept of the linear mixture model to the question of spectral image complexity at spatially local scales. Essentially, the "complexity" of an image region is related to the volume of a convex set enclosing the data in the spectral space. The volume is estimated as a function of increasing dimensionality (through the use of a set of endmembers describing the data cloud) using the Gram Matrix approach. It is hypothesized that more complex regions of the image are composed of multiple, diverse materials and will thus occupy a larger volume in the hyperspace. The ultimate application here is large area image search without a priori information regarding the target signature. Instead, image cues will be provided based on local, relative estimates of the image complexity. The technique used to estimate the spectral image complexity is described and results are shown for representative image chips and a large area flightline of reflective hyperspectral imagery. The extension to the problem of large area search will then be described and results are shown for a 4-band multispectral image.

show abstract

Spectral image complexity estimated through local convex hull volume

Cited by 20 publications

References 6 publications

Schroedinger eigenmaps with knowledge propagation for target detection

Schroedinger eigenmaps with knowledge propagation for target detection

Target Detection Based on Random Forest Metric Learning

Metrics of spectral image complexity with application to large area search

Contact Info

Product

Resources

About