Unsupervised feature selection (UFS) is a standard approach to reduce the dimensionality of hyperspectral images (HSIs). The main idea in UFS is to define a similarity metric, and select the features minimizing the metric to reduce the data redundancy. In this paper, we proposed a novel criterion for unsupervised dimensionality reduction based on the representation of spectral reflectance to capture dominant reflectance variations. Since capturing all the spectral information from an entire hyperspectral dataset is a time-consuming process, we proposed a heuristic algorithm named Greedy Search for Spectral Representation (GSSR). This algorithm divides the spectrum into spectral regions with less spectral variations and merges them. GSSR, similar to feature selection techniques, preserves the original data from being distorted or compromised by a transformation. We compared the GSSR algorithm with well-known existing algorithms in different experiments using various datasets. Comparison with the best approximation to represent single spectra as well as entire hyperspectral scene revealed that spectral representation is almost the same. The difference between the best spectral representation and the ones provided by GSSR is less than 0.01%; while on average, GSSR is about 660 times faster to represent single spectra and 37 times faster for a complete hyperspectral scene. Five well-known unsupervised dimensionality reduction methods were also implemented and used for comparison analysis. Based on the image classification accuracy over two hyperspectral datasets, the spectral features identified by the proposed criterion improved the classification accuracy as well.

@en

Natural and man-made disasters lead to challenging situations for the affected communities, where comprehensive and reliable information on the nature, extent, and the consequences of an event are required. Providing timely information, however, is particularly difficult following sudden disasters, such as those caused by earthquakes or industrial accidents. In those situations only partial, inaccurate or conflicting ground-based information is typically available, creating a well-recognized potential for satellite remote sensing to fill the gap. Despite continuous technical improvements, however, currently operational, non-classified, space-based sensors may not be able to provide timely data. In addition, even high spatial resolution satellites (< 1m) are limited in their capacity to reveal true 3D structural damage at a level of detail necessary for appropriate disaster response in urban areas. Uncalibrated oblique airborne imagery, both video and photography, is typically the first data type available after any given disaster in an urban setting, usually captured by law enforcement or news agencies. In this study we address the use of video data for systematic, quantitative, and near-real time damage assessment, using video and auxiliary data of an in-dustrial disaster in 2000 in Enschede, the Netherlands, and of Golcuk, Turkey, acquired after the 1999 Kocaeli (or Marmara) earthquake. We focus in particular on texture-based damage mapping based on both empirical and more generic, geometric indicators. Data-specific attributes included color indices and edge characteristics, while the data-independent approach included rotation invariant Local Binary Pattern and contrast operators (LBP/C). In an earlier step of the project, an interface was created to allow the near-real time processing of video streams, and, depending on positional information encoded with the data, their combination with auxiliary data such as maps or pre-disaster image data. Here we further investigated the potential of the available imagery for 3D reconstruction of the disaster area. Correspondences between consecutive video frames were established automatically by feature point tracking and used for the estimation of the coordinates of the terrain points as well as the camera parameters. Furthermore, we quantitatively assessed the quality of the reconstruction based on the data available. The ultimate goal of the project is to establish a versatile processing platform that supports extraction of such information as well as damage mapping, but also partial 3D reconstruction and integration of pre-event GIS and other auxiliary data.

@en

Various kinds of urban applications require true orthophotos. True orthophoto generation requires a DSM (Digital Surface Model) to project the photo orthogonally and minimize geometric distortion due to topographic variance. DSMs are often generated from airborne laser scan data. In urban scenes, DSM data may fail to deliver sharp and straight building roof edges. This will affect the quality of the resulting orthophotos. Therefore, it is necessary to incorporate good quality building outlines as breaklines during DSM interpolation. This study proposes a data-driven approach to construct building roof outlines from LiDAR point clouds by a workflow consisting of the following steps: given roof segments, roof boundary points are extracted using a concave hull algorithm. Straight edges may be difficult to find in complex roof configurations. Therefore, two ingredients are combined. First, RanSAC corner point preselection, and second, DBSCAN-based clustering of edge points. The method is demonstrated on an area of ±1.2 km² containing 42 buildings of different characteristics. A quality assessment shows that the proposed method is able to deliver 92% of building lines with acceptable geometric accuracy in comparison to a building line in the base map.

@en

There has been a steady increase in applications that rely on crowdsensing to gather data for analysis purposes. Crowdsensing enables the use of dynamic sensors to collect data on static objects of interest. However, using dynamic sensors in this way causes a problem. The focus of the collected data is on the position of the sensor, not on the object of interest. This results in difficulties in tracking the object of interest in terms of what part of the data from the dynamic sensor describes the object of interest. To shift the focus from the dynamic sensors to a static object, the virtual sensor is introduced. A virtual sensor enables the grouping of data from different dynamic sensors into a single virtual sensor based on measurement positions. The data from the multiple dynamic sensors can be analyzed to provide information per virtual sensor. The data structure of a visual sensor is close to the SensorThings API data structure, which can be expanded to support virtual sensors by adding an additional entity.@en

In VHR(very high resolution) aerial images, shadows indicating height information are valuable for validating or detecting changes on an existing 3D city model. In the paper, we propose a novel and full automatic approach for shadow detection from VHR images. Instead of automatic thresholding, the supervised machine learning approach is expected with better performance on shadow detection, but it requires to obtain training samples manually. The shadow image reconstructed from an existing 3D city model can provide free training samples with large variety. However, as the 3D model is often not accuracy, incomplete and outdated, a small portion of training samples are mislabeled. The erosion morphology is provided to remove boundary pixels which have high mislabeling possibility from the reconstructed image. Moreover, the quadratic discriminant analysis (QDA) which is resistant to the mislabeling is chosen. Further, two feature domains, RGB and ratio of the hue over the intensity, are analyzed to have complementary effects on better detecting different objects. Finally, a decision fusion approach is proposed to combine the results wisely from preliminary classifications from two feature domains. The fuzzy membership is a confidence measurement and determines the way of making decision, in the meanwhile the memberships are weighted by an entropy measurements to indicate their certainties. The experimental results on two cities in the Netherlands demonstrate that the proposed approach outperforms the two separate classifiers and two stacked-vector fusion approaches.@en

LiDAR data acquisition is recognized as one of the fastest solutions to provide basis data for large-scale topographical base maps worldwide. Automatic LiDAR processing is believed one possible scheme to accelerate the large-scale topographic base map provision by the Geospatial Information Agency in Indonesia. As a progressive advanced technology, Geographic Information System (GIS) open possibilities to deal with geospatial data automatic processing and analyses. Considering further needs of spatial data sharing and integration, the one stop processing of LiDAR data in a GIS environment is considered a powerful and efficient approach for the base map provision. The quality of the automated topographic base map is assessed and analysed based on its completeness, correctness, quality, and the confusion matrix.

@en

Hyperspectral images may be applied to classify objects in a scene. The redundancy in hyperspectral data implies that fewer spectral features might be sufficient for discriminating the objects captured in a scene. The availability of labeled classes of several areas in a scene paves the way for a supervised dimensionality reduction, i.e., using a discrimination measure between the classes in a scene to select spectral features. We show that averaging adjacent spectral channels and using wider spectral regions yield a better class separability than the selection of individual channels from the original hyperspectral dataset. We used a method named spectral region splitting (SRS), which creates a new feature space by averaging neighboring channels. In addition to the common benefits of channel selection methods, the algorithm constructs wider spectral regions when it is useful. Using different class separability measures over various datasets resulted in a better discrimination between the classes than the best-selected channels using the same measure. The reason is that the wider spectral regions led to a reduction in intraclass distances and an improvement in class discrimination. The overall classification accuracy of two hyperspectral scenes gave an increase of about two-percent when using the spectral regions determined by applying SRS. @en

One of the main steps in hyperspectral image classification is the selection of bands that provide the best separability among classes. It is usually understood that the selected bands for classification must contain a large amount of information, and the correlation among selected bands should be small to avoid redundancy. At the same time for optimal classification, class separability should be at maximum value. The question arises whether the most informative spectral regions are really the same as the most discriminant ones for a given set of classes. Answering the question, we developed a new method named Spectral Region Splitting (SRS) to identify interesting spectral regions. This article concludes that the optimal informative and the optimal separable spectral regions are not identical. Furthermore, the cause of the difference is proven theoretically.

@en

The integration of computer vision and photogrammetry to generate three-dimensional (3D) information from images has contributed to a wider use of point clouds, for mapping purposes. Large-scale topographic map production requires 3D data with high precision and accuracy to represent the real conditions of the earth surface. Apart from LiDAR point clouds, the image-based matching is also believed to have the ability to generate reliable and detailed point clouds from multiple-view images. In order to examine and analyze possible fusion of LiDAR and image-based matching for large-scale detailed mapping purposes, point clouds are generated by Semi Global Matching (SGM) and by Structure from Motion (SfM). In order to conduct comprehensive and fair comparison, this study uses aerial photos and LiDAR data that were acquired at the same time. Qualitative and quantitative assessments have been applied to evaluate LiDAR and image-matching point clouds data in terms of visualization, geometric accuracy, and classification result. The comparison results conclude that LiDAR is the best data for large-scale mapping.

@en

The paper presents a very straightforward and effective algorithm to convert a space partitioning, made up of polyhedral objects, into a 3D block of voxels, which is fully occupied, i.e. in which every voxel has a value. In addition to walls, floors, etc. there are 'air' voxels, which in turn may be distinguished as indoor and outdoor air. The method is a 3D extension of a 2D polygon-to-raster conversion algorithm. The input of the algorithm is a set of non-overlapping, closed polyhedra, which can be nested or touching. The air volume is not necessarily represented explicitly as a polyhedron (it can be treated as 'background', leading to the 'default' voxel value). The approach consists of two stages, the first being object (boundary) based, the second scan-line based. In addition to planar faces, other primitives, such as ellipsoids, can be accommodated in the first stage without affecting the second.@en

The paper presents a new algorithm to reconstruct elongated objects defined by cross sections and trajectories in gridded threedimensional models represented as voxels. Examples of such objects are the elements of underground infrastructure in urban environments, such as pipes, conduits and tunnels. Starting from a basic methodology, which is based on distance transformations, the algorithm is extended in three ways on the basis of Voronoi datasets being produced alongside@en

(Semi)- Automatic facade reconstruction from terrestrial LiDAR point clouds is often affected by both quality of point cloud itself and imperfectness of object recognition algorithms. In this paper, we employ regularities, which exist on façades, to mitigate these problems. For example, doors, windows and balconies often have orthogonal and parallel boundaries. Many windows are constructed with the same shape. They may be arranged at the same lines and distance intervals, so do different windows. By identifying regularities among objects with relatively poor quality, these can be applied to calibrate the objects and improve their quality. The paper focuses on the regularities among the windows, which is the majority of objects on the wall. Regularities are classified into three categories: Within an individual window, among similar windows and among different windows. Nine cases are specified as a reference for exploration. A hierarchical clustering method is employed to identify and apply regularities in a feature space, where regularities can be identified from clusters. To find the corresponding features in the nine cases of regularities, two phases are distinguished for similar and different windows. In the first phase, ICP (iterative closest points) is used to identify groups of similar windows. The registered points and a number of transformation matrices are used to identify and apply regularities among similar windows. In the second phase, features are extracted from the boundaries of the different windows. When applying regularities by relocating windows, the connections, called chains, established among the similar windows in the first phase are preserved. To test the performance of the algorithms, two datasets from terrestrial LiDAR point clouds are used. Both show good effects on the reconstructed model, while still matching with original point cloud, preventing over or under-regularization.

@en

@en