Advances in wide-area hyperspectral image simulation

Ientilucci, Emmett J.; Brown, Scott

doi:10.1117/12.488706

Cited by 74 publications

(30 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One possibility to overcome this, for the purpose of comparing various classifiers, is to use synthetic hyperspectral imagery where each pixel is labeled. This is becoming a realistic choice through rigorous simulation work [85,86]. We want to stress, however, the need for research that can yield new, innovative measures of performance for accuracy evaluation of class maps obtained from real data, for which it is not possible to obtain the requisite number of test samples.…”

Section: Discussionmentioning

confidence: 99%

Classification of hyperspectral imagery with neural networks: comparison to conventional tools

Merényi

Farrand

Taranik

et al. 2014

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Efficient exploitation of hyperspectral imagery is of great importance in remote sensing. Artificial intelligence approaches have been receiving favorable reviews for classification of hyperspectral data because the complexity of such data challenges the limitations of many conventional methods. Artificial neural networks (ANNs) were shown to outperform traditional classifiers in many situations. However, studies that use the full spectral dimensionality of hyperspectral images to classify a large number of surface covers are scarce if non-existent. We advocate the need for methods that can handle the full dimensionality and a large number of classes to retain the discovery potential and the ability to discriminate classes with subtle spectral differences. We demonstrate that such a method exists in the family of ANNs. We compare the maximum likelihood, Mahalonobis distance, minimum distance, spectral angle mapper, and a hybrid ANN classifier for real hyperspectral AVIRIS data, using the full spectral resolution to map 23 cover types and using a small training set. Rigorous evaluation of the classification accuracies shows that the ANN outperforms the other methods and achieves ≈90% accuracy on test data.

show abstract

Section: Discussionmentioning

confidence: 99%

Classification of hyperspectral imagery with neural networks: comparison to conventional tools

Merényi

Farrand

Taranik

et al. 2014

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…MODTRAN [39] is incorporated to simulate realistic atmospheric behavior from user-provided atmospheric and weather information. Incorporating all of this information, the software employs thermal and radiometric models along with a ray tracer to compute radiance fluxes at specific points [40]. The approach is used to generate realistic remote sensing images.…”

Section: Experimental Data Descriptionmentioning

confidence: 99%

Using Physically-Modeled Synthetic Data to Assess Hyperspectral Unmixing Approaches

Stites¹,

Gunther

Moon

et al. 2013

Remote Sensing

View full text Add to dashboard Cite

This paper considers an experimental approach for assessing algorithms used to exploit remotely sensed data. The approach employs synthetic images that are generated using physical models to make them more realistic while still providing ground truth data for quantitative evaluation. This approach complements the common approach of using real data and/or simple model-generated data. To demonstrate the value of such an approach, the behavior of the FastICA algorithm as a hyperspectral unmixing technique is evaluated using such data. This exploration leads to a number of useful insights such as: (1) the need to retain more dimensions than indicated by eigenvalue analysis to obtain near-optimal results; (2) conditions in which orthogonalization of unmixing vectors is detrimental to the exploitation results; and (3) a means for improving FastICA unmixing results by recognizing and compensating for materials that have been split into multiple abundance maps.

show abstract

“…In this section we present clustering of a hypersectral urban image, which was synthetically generated through the rigorous DIRSIG modeling procedure at the Rochester Institute of Technology. 18,19 Owing to its simulated nature, this image has ground truth for every pixel, allowing objective evaluation of analysis results on the 1-pixel scale. The characteristics of this data set are close to that of a low-altitude AVIRIS image: it comprises 400 x 400 pixels in 210 image bands in the 0.38 to 2.4 µm visible-near-infrared spectral window, with a spatial resolution of 2 m/pixel.…”

Section: Discoveries In An Urban Hyperspectral Imagementioning

confidence: 99%

“…The hyperspectral image was generated by the DIRSIG procedure at the Rochester Institute of Technology. 18,19 The scene covers an area of 800 x 800 square meters (2 meters/pixel spatial resolution). Besides the obvious vegetation (trees and grass), the approximately 70 different surface cover types contained in this image include a large number of various roof materials, pavings, and several types of car paints.…”

Section: Discoveries In An Urban Hyperspectral Imagementioning

confidence: 99%

Intelligent information extraction to aid science decision making in autonomous space exploration

2008

View full text Add to dashboard Cite

Effective scientific exploration of remote targets such as solar system objects increasingly calls for autonomous data analysis and decision making on-board. Today, robots in space missions are programmed to traverse from one location to another without regard to what they might be passing by. By not processing data as they travel, they can miss important discoveries, or will need to travel back if scientists on Earth find the data warrant backtracking. This is a suboptimal use of resources even on relatively close targets such as the Moon or Mars. The farther mankind ventures into space, the longer the delay in communication, due to which interesting findings from data sent back to Earth are made too late to command a (roving, floating, or orbiting) robot to further examine a given location. However, autonomous commanding of robots in scientific exploration can only be as reliable as the scientific information extracted from the data that is collected and provided for decision making. In this paper, we focus on the discovery scenario, where information extraction is accomplished with unsupervised clustering. For high-dimensional data with complicated structure, detailed segmentation that identifies all significant groups and discovers the small, surprising anomalies in the data, is a challenging task at which conventional algorithms often fail. We approach the problem with precision manifold learning using self-organizing neural maps with non-standard features developed in the course of our research. We demonstrate the effectiveness and robustness of this approach on multi-spectral imagery from the Mars Exploration Rovers Pancam, and on synthetic hyperspectral imagery.

show abstract

Advances in wide-area hyperspectral image simulation

Cited by 74 publications

References 5 publications

Classification of hyperspectral imagery with neural networks: comparison to conventional tools

Classification of hyperspectral imagery with neural networks: comparison to conventional tools

Using Physically-Modeled Synthetic Data to Assess Hyperspectral Unmixing Approaches

Intelligent information extraction to aid science decision making in autonomous space exploration

Contact Info

Product

Resources

About