No abstract

Deep convolutional neural networks (DCNNs) have been used to achieve state-of-the-art performance on many computer vision tasks (e.g., object recognition, object detection, semantic segmentation) thanks to a large repository of annotated image data. Large labeled datasets for other sensor modalities, e.g., multispectral imagery (MSI), are not available due to the large cost and manpower required. In this paper, we adapt state-of-the-art DCNN frameworks in computer vision for semantic segmentation for MSI imagery. To overcome label scarcity for MSI data, we substitute real MSI for generated synthetic MSI in order to initialize a DCNN framework. We evaluate our network initialization scheme on the new RIT-18 dataset that we present in this paper. This dataset contains very-high resolution MSI collected by an unmanned aircraft system. The models initialized with synthetic imagery were less prone to over-fitting and provide a state-of-the-art baseline for future work.

Abstract-A fast, completely automated method to create 3D watertight building models from airborne LiDAR point clouds is presented. The proposed method analyzes the scene content and produces multi-layer rooftops with complex boundaries and vertical walls that connect rooftops to the ground. A graph cuts based method is used to segment vegetative areas from the rest of scene content. The ground terrain and building rooftop patches are then extracted utilizing our technique, the hierarchical Euclidean clustering. Our method adopts a "divide-and-conquer" strategy. Once potential points on rooftops are segmented from terrain and vegetative areas, the whole scene is divided into individual pendent processing units which represent potential building footprints. For each individual building region, significant features on the rooftop are further detected using a specifically designed region growing algorithm with smoothness constraint. Boundaries for all of these features are refined in order to produce strict description. After this refinement, mesh models could be generated using an existing robust dual contouring method.

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.

No abstract