Search

The paper describes an iterative extension to maximum a posteriori (MAP) supervised classification methods. A posteriori probabilities per class are used for classification as well as to obtain class area estimates. From these, an updated set of prior probabilities is calculated and used in the next iteration. The process converges to statistically correct area estimates. The iterative process can be combined effectively with a stratification of the image, which is made on the basis of additional map data. Moreover, it relies on the sample sets being representative. Therefore, the method is shown to be well applicable in combination with an existing GIS. The paper gives a description of the procedure and provides a mathematical foundation. An example is presented to distinguish residential, industrial, and greenhouse classes. A significant improvement of the classification was obtained. Index Terms - Bayes procedures, image classification, MAP estimation, remote sensing.

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The European FP7 project IQmulus yearly organizes several processing contests, where submissions are requested for novel algorithms for point cloud and other big geodata processing. This paper describes the set-up and execution of a contest having the purpose to evaluate state-of-the-art algorithms for Mobile Mapping System point clouds, in order to detect and identify (individual) trees. By the nature of MMS these are trees in the vicinity of the road network (rather than in forests). Therefore, part of the challenge is distinguishing between trees and other objects, such as buildings, street furniture, cars etc. Three submitted segmentation and classification algorithms are thus evaluated. [ABSTRACT FROM AUTHOR]

Topography affects the fraction of direct and diffuse radiation received on a pixel and changes the sun–target–sensor geometry, resulting in variations in the observed radiance. Retrieval of surface–atmosphere properties from top of atmosphere radiance may need to account for topographic effects. This study investigates how such effects can be taken into account for top of atmosphere radiance modeling. In this paper, a system for top of atmosphere radiance modeling over heterogeneous non-Lambertian rugged terrain through radiative transfer modeling is presented. The paper proposes an extension of "the four-stream radiative transfer theory" (Verhoef and Bach 2003, 2007 and 2012) mainly aimed at representing topography-induced contributions to the top of atmosphere radiance modeling. A detailed account for BRDF effects, adjacency effects and topography effects on the radiance modeling is given, in which sky-view factor and non-Lambertian reflected radiance from adjacent slopes are modeled precisely. The paper also provides a new formulation to derive the atmospheric coefficients from MODTRAN with only two model runs, to make it more computationally efficient and also avoiding the use of zero surface albedo as used in the four-stream radiative transfer theory. The modeling begins with four surface reflectance factors calculated by the Soil–Leaf–Canopy radiative transfer model SLC at the top of canopy and propagates them through the effects of the atmosphere, which is explained by six atmospheric coefficients, derived from MODTRAN radiative transfer code. The top of the atmosphere radiance is then convolved with the sensor characteristics to generate sensor-like radiance. Using a composite dataset, it has been shown that neglecting sky view factor and/or terrain reflected radiance can cause uncertainty in the forward TOA radiance modeling up to 5 (mW/m2•sr•nm). It has also been shown that this level of uncertainty can be translated into an over/underestimation of more than 0.5 in LAI (or 0.07 in fCover) in variable retrieval. [ABSTRACT FROM AUTHOR]

Delineation of aquatic plants and estimation of its surface extent are crucial to the efficient control of its proliferation, and this information can be derived accurately with fine resolution remote sensing products. However, small swath and low observation frequency associated with them may be prohibitive for application to large water bodies with rapid proliferation and dynamic floating aquatic plants. The information can be derived from products with large swath and high observation frequency, but with coarse resolution; and the quality of so derived information must be eventually assessed using finer resolution data. In this study, we evaluate two methods: Normalized Difference Vegetation Index (NDVI) slicing and maximum likelihood in terms of delineation; and two methods: Gutman and Ignatov's NDVI-based fractional cover retrieval and linear spectral unmixing in terms of area estimation of aquatic plants from 300 m Medium Resolution Imaging Spectrometer (MERIS) data, using as reference results obtained with 30 m Landsat-7 ETM+. Our results show for delineation, that maximum likelihood with an average classification accuracy of 80% is better than NDVI slicing at 75%, both methods showing larger errors over sparse vegetation. In area estimation, we found that Gutman and Ignatov's method and spectral unmixing produce almost the same root mean square (RMS) error of about 0.10, but the former shows larger errors of about 0.15 over sparse vegetation while the latter remains invariant. Where an end member spectral library is available, we recommend the spectral unmixing approach to estimate extent of vegetation with coarse resolution data, as its performance is relatively invariant to the fragmentation of aquatic vegetation cover. [ABSTRACT FROM AUTHOR]

Change detection on the basis of multi-temporal imagery may lead to false alarms when the image has changed, whereas the scene has not. Geometric image differerences in an unchanged scene may be due to relief displacement, caused by diferent camera positions. Radiometric differences may be caused by changes in illumimation and shadow between the images, caused by a different position of the sun. The effects may be predicted, and after that compensated, if a 3d model of the scene is available. The paper presents an integrated approach to prediction of and compensation for relief displacement, shading and shadow. [ABSTRACT FROM AUTHOR]

Copyright of Photogrammetric Record is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A method and algorithm for reconstructing the three-dimensional (3D) surface of stems based on terrestrial laser scanner data from standing trees is presented. Laser scanning delivers a dense cloud of points, and this raw point data are filtered for deriving a digital terrain model and subsequent fitting of a parametric stem model. The stem model is made up of a sequence of successive cylinders that overlap in space; each cylinder is parameterized by its orientation and radius. The model is estimated iteratively from a given starting point and by adding cylinder segments. Successive segments are added whenever criteria on deviation in orientation and radius relative to the previous cylinder and a fit statistic to the point data are met. The method has proven applicable when applied to a European beech tree and a wild cherry tree from dense forest stands. The use of the resulting 3D reconstruction of tree stems in respect to diameter in breast height and height of crown base calculation, as well as taper, sweep and lean assessment of standing trees, is described. Finally, desirable future improvements to the basic algorithm are discussed. [ABSTRACT FROM AUTHOR]

Objects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based on the results of plane segmentation is proposed in this paper. The plane segmentation algorithm includes two steps: Initial segmentation based on mean-shift and alpha-expansion-based energy minimization. According to the results of plane segmentation and fitting, the disparity is refined by filling missed matching regions and removing outliers. The experimental results showed that the proposed plane segmentation method could not only accurately fit the plane in the presence of noise but also approximate the surface by plane combination. After the proposed plane segmentation method was applied to the disparity refinement of remote sensing images, many missed matches were filled, and the elevation errors were reduced. This proved that the proposed algorithm was effective. For difficult evaluations resulting from significant variations in remote sensing images of different satellites, the edge matching rate and the edge matching map are proposed as new stereo matching evaluation and analysis tools. Experiment results showed that they were easy to use, intuitive, and effective. [ABSTRACT FROM AUTHOR]

Efficient building instance segmentation is necessary for many applications such as parallel reconstruction, management and analysis. However, most of the existing instance segmentation methods still suffer from low completeness, low correctness and low quality for building instance segmentation, which are especially obvious for complex building scenes. This paper proposes a novel unsupervised building instance segmentation (UBIS) method of airborne Light Detection and Ranging (LiDAR) point clouds for parallel reconstruction analysis, which combines a clustering algorithm and a novel model consistency evaluation method. The proposed method first divides building point clouds into building instances by the improved kd tree 2D shared nearest neighbor clustering algorithm (Ikd-2DSNN). Then, the geometric feature of the building instance is obtained using the model consistency evaluation method, which is used to determine whether the building instance is a single building instance or a multi-building instance. Finally, for multiple building instances, the improved kd tree 3D shared nearest neighbor clustering algorithm (Ikd-3DSNN) is used to divide multi-building instances again to improve the accuracy of building instance segmentation. Our experimental results demonstrate that the proposed UBIS method obtained good performances for various buildings in different scenes such as high-rise building, podium buildings and a residential area with detached houses. A comparative analysis confirms that the proposed UBIS method performed better than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) building models play an important role in digital cities and have numerous potential applications in environmental studies. In recent years, the photogrammetric point clouds obtained by aerial oblique images have become a major source of data for 3D building reconstruction. Aiming at reconstructing a 3D building model at Level of Detail (LoD) 2 and even LoD3 with preferred geometry accuracy and affordable computation expense, in this paper, we propose a novel method for the efficient reconstruction of building models from the photogrammetric point clouds which combines the rule-based and the hypothesis-based method using a two-stage topological recovery process. Given the point clouds of a single building, planar primitives and their corresponding boundaries are extracted and regularized to obtain abstracted building counters. In the first stage, we take advantage of the regularity and adjacency of the building counters to recover parts of the topological relationships between different primitives. Three constraints, namely pairwise constraint, triplet constraint, and nearby constraint, are utilized to form an initial reconstruction with candidate faces in ambiguous areas. In the second stage, the topologies in ambiguous areas are removed and reconstructed by solving an integer linear optimization problem based on the initial constraints while considering data fitting degree. Experiments using real datasets reveal that compared with state-of-the-art methods, the proposed method can efficiently reconstruct 3D building models in seconds with the geometry accuracy in decimeter level. [ABSTRACT FROM AUTHOR]

Many urban applications require building polygons as input. However, manual extraction from point cloud data is time- and labor-intensive. Hough transform is a well-known procedure to extract line features. Unfortunately, current Hough-based approaches lack flexibility to effectively extract outlines from arbitrary buildings. We found that available point order information is actually never used. Using ordered building edge points allows us to present a novel ordered points–aided Hough Transform (OHT) for extracting high quality building outlines from an airborne LiDAR point cloud. First, a Hough accumulator matrix is constructed based on a voting scheme in parametric line space (θ, r). The variance of angles in each column is used to determine dominant building directions. We propose a hierarchical filtering and clustering approach to obtain accurate line based on detected hotspots and ordered points. An Ordered Point List matrix consisting of ordered building edge points enables the detection of line segments of arbitrary direction, resulting in high-quality building roof polygons. We tested our method on three different datasets of different characteristics: one new dataset in Makassar, Indonesia, and two benchmark datasets in Vaihingen, Germany. To the best of our knowledge, our algorithm is the first Hough method that is highly adaptable since it works for buildings with edges of different lengths and arbitrary relative orientations. The results prove that our method delivers high completeness (between 90.1% and 96.4%) and correctness percentages (all over 96%). The positional accuracy of the building corners is between 0.2–0.57 m RMSE. The quality rate (89.6%) for the Vaihingen-B benchmark outperforms all existing state of the art methods. Other solutions for the challenging Vaihingen-A dataset are not yet available, while we achieve a quality score of 93.2%. Results with arbitrary directions are demonstrated on the complex buildings around the EYE museum in Amsterdam. [ABSTRACT FROM AUTHOR]