Data reduction techniques are becoming increasingly important in modern data analysis problems{especially in fields involving big data. Although not quite on the same scale as high velocity and volume big data problems, remote sensing analysis on hyperspectral imagery (HSI) can suffer from the increase in dimensionality provided by this sensing modality. Common hyperspectral sensors divide the sensed optical bandwidth into as many as 270 different channels. Depending on the specific bandwidth and application, some channels may be unusable due to water absorption, while others may provide little-to-no discriminative information when considering their impact on algorithm performance. With this in mind, there are several techniques devised to subsample the original number of bands to a more manageable size allowing for increased algorithm performance both in classification accuracy and computation time. Herein, we propose a neural network-based band selection technique that seeks to generalize existing autoencoder-based methods and experiment with tracking input contributions throughout the network. We explore the ability to perform task-specific band selection by applying this method to a general multilayer perceptron architecture. We apply our proposed band selection methodology to a novel HSI dataset captured by the U.S. Army ERDC and compare performance to alternative band selection algorithms.
Synthetic imagery generation is not a new topic; however, it has reemerged as a major focus in recent years. This is in part due to the success achieved by modern machine learning methodologies, in particular, deep learning. One reason these technologies have succeeded is due to the wealth of available training data. A majority of the available data are of generic objects or scenes. However, there are numerous applications in which data are neither readily available nor easily obtained in large quantities. In such scenarios, synthetic imagery is an appealing choice to address this shortcoming. While still faster than the performance of data collections, physics- based models tend to have computational complexity and require extensive computational time. This work seeks to investigate the use of reduced-order modeling (ROM) of relevant objects identified by a maximally stable extremal region (MSER) detector from the entropy image of simple ideal high-fidelity, physics-based synthetic images. Specifically, this work will utilize MSERs to identify pertinent objects to be placed within the simple scene via ROM to produce a more complex scene. This approach has the benefit of rapidly increasing both the complexity of simple, ideal, high-fidelity, physics-based scenes and the amount of synthetic imagery generated via random or statistically-based placement of the objects throughout the scene.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.