When classifying point clouds, a large amount of time is devoted to the process of engineering a reliable set of features which are then passed to a classifier of choice. Generally, such features -usually derived from the 3Dcovariance matrix -are computed using the surrounding neighborhood of points. While these features capture local information, the process is usually time-consuming, and requires the application at multiple scales combined with contextual methods in order to adequately describe the diversity of objects within a scene. In this paper we present a 1D-fully convolutional network that consumes terrain-normalized points directly with the corresponding spectral data, if available, to generate point-wise labeling while implicitly learning contextual features in an end-to-end fashion. Our method uses only the 3D-coordinates and three corresponding spectral features for each point. Spectral features may either be extracted from 2D-georeferenced images, as shown here for Light Detection and Ranging (LiDAR) point clouds, or extracted directly for passive-derived point clouds, i.e. from muliple-view imagery. We train our network by splitting the data into square regions, and use a pooling layer that respects the permutation-invariance of the input points. Evaluated using the ISPRS 3D Semantic Labeling Contest, our method scored second place with an overall accuracy of 81.6%. We ranked third place with a mean F1-score of 63.32%, surpassing the F1-score of the method with highest accuracy by 1.69%. In addition to labeling 3D-point clouds, we also show that our method can be easily extended to 2D-semantic segmentation tasks, with promising initial results.

This paper focuses on comparing three basis-vector selection techniques as applied to target detection in hyperspectral imagery. The basis-vector selection methods tested were the singular value decomposition (SVD), pixel purity index (PPI), and a newly developed approach called the maximum distance (MaxD) method. Target spaces were created using an illumination invariant technique, while the background space was generated from AVIRIS hyperspectral imagery. All three selection techniques were applied (in various combinations) to target as well as background spaces so as to generate dimensionally-reduced subspaces. Both target and background subspaces were described by linear subspace models (i.e., structured models). Generated basis vectors were then implemented in a generalized likelihood ratio (GLR) detector. False alarm rates (FAR) were tabulated along with a new summary metric called the average false alarm rate (AFAR). Some additional summary metrics are also introduced. Impact of the number of basis vectors in the target and background subspaces on detector performance was also investigated. For the given AVIRIS data set, the MaxD method as applied to the background subspace outperformed the other two methods tested (SVD and PPI).

No abstract

No abstract

We investigate modifying convolutional neural network (CNN) architecture to facilitate aerial hyperspectral scene understanding and present a new hyperspectral dataset-AeroRITthat is large enough for CNN training. To date the majority of hyperspectral airborne have been confined to various subcategories of vegetation and roads and this scene introduces two new categories: buildings and cars. To the best of our knowledge, this is the first comprehensive large-scale hyperspectral scene with nearly seven million pixel annotations for identifying cars, roads, and buildings. We compare the performance of three popular architectures -SegNet, U-Net, and Res-U-Net, for scene understanding and object identification via the task of dense semantic segmentation to establish a benchmark for the scene. To further strengthen the network, we add squeeze and excitation blocks for better channel interactions and use self-supervised learning for better encoder initialization. Aerial hyperspectral image analysis has been restricted to small datasets with limited train/test splits capabilities and we believe that AeroRIT will help advance the research in the field with a more complex object distribution to perform well on. The full dataset, with flight lines in radiance and reflectance domain, is available for download at https://github.com/aneesh3108/AeroRIT. This dataset is the first step towards developing robust algorithms for hyperspectral airborne sensing that can robustly perform advanced tasks like vehicle tracking and occlusion handling.