ID: 58732
Title: Sensitivity of spectral reflectance values to different burn and vegetation ratios: A multi-scale approach applied in a fire affected area.
Author: Magdalini Pleniou, Nikos Koutsias.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 199-210 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Spectral properties, Sub-pixel, Burned surfaces, ASTER, IKONOS
Abstract: The aim of our study was to explore the spectral properties of fire-scorched (burned) and non fire-scorched (vegetation) areas, as well as areas with different burn/vegetation ratios, using a multisource multiresolution satellite data set. A case study was undertaken following a very destructive wildfire that occurred in Parnitha, Greece, July 2007, for which we acquired satellite images from LANDSAT, ASTER, and IKONOS. Additionally, we created spatially degraded satellite data over a range of coarser resolutions using resampling techniques. The panchromatic (1 m) and multispectral component (4 m) of IKONOS were merged using the Gram-Schmidt spectral sharpening method. This very high resolution imagery served as the basis to estimate the cover percentage of burned areas, bare land and vegetation at pixel level, by applying the maximum likelihood classification algorithm. Finally, multiple linear regression models were fit to estimate each land-cover fraction as a function of surface reflectance values of the original and the spatially degraded satellite images.
The main findings of our research were: (a) the Near Infrared (NIR) and Short-wave Infrared (SWIR) are the most important channels to estimate the percentage of burned area, whereas the NIR and red channels are most important to estimate the percentage of vegetation in fire affected areas; (b) when the bi-spectral space consists only of NIR and SWIR, then the NIR ground reflectance value plays a more significant role in estimating the percent of vegetation; and (c) semi-burned areas comprising 45-55% burned area and 45-55% vegetation are spectrally closer to burned areas in the NIR channel, whereas those areas are spectrally closer to vegetation in the SWIR channel. These findings, at least partially, are attributed to the fact that: (i) completely burned pixels present low variance in the NIR and high variance in the SWIR, whereas the opposite is observed in completely vegetated areas where higher variance is observed in the NIR and lower variance in the SWIR, and (ii) bare land modifies the spectral signal of burned areas more than the spectral signal of vegetated areas in the NIR, while the opposite is observed in SWIR region of the spectrum where the bare land modifies the spectral signal of vegetation more than the burned area because the bare land and the vegetation are spectrallly more similar in the NIR, and the bare land and burned areas are spectrally more similar in the SWIR.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58731
Title: A laser scanning-based method for fast estimation of seismic-induced building deformations.
Author: Arianna Pesci, Giordano Teza, Elena Bonali, Giuseppe Casula, Enzo Boschi.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 185-198 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Architechture, Change detection, Laser scanning, Model, Performance.
Abstract: Monitoring damaged buildings in an area where an earthquake has occurred requires the use of techniques which provide rapid and safe meaurements even in emergency conditions. In particular, remote sensing techniques like terrestrail laser scanning (TLS) can satisfy these requirements, since they produce very dense point clouds in little time and also allow an accurate geometric modelling of observed buildings. Nevertheless, strong constraints on TLS data acquisition geometry, such as acquisition distance and incidence angles, typically characterize an area in seismic emergency conditions. In order to correctly interpret the data, it is necessary to estimate errors affecting TLS measurements in these critical conditions. A reliable estimation can be achieved by means of experiments and numerical simulations aimed at quantifying a realistic noise level, with emphasis on reduction of artifacts due to data acquisitiion, registration and modelling. This paper proposes a data analysis strategy in which TLS based morphological maps computed as point-to-primitive differences are created. The method can easily used for accurate surveying in emergency conditions. In order to demonstrate the proposed method in very diverse situations, it was applied to rapidly detect deformation traces in the San Giacomo Roncole Campanile(Modena), the Asinelli tower (Bologna) and the Cantalovo Church (Verona), three buildings damaged by the Mw 5.9 Emilia Romagna 2012 earthquake (Italy).
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58730
Title: Automatic fuzzy object-based analysis of VHSR images for urban objects extraction.
Author: Imane Sebari, Dong-Chen He
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 171-184 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Automatic object extraction, Object Based Image Analysis (OBIA), Fuzzy rule base, VHSR satellite images, Urban areas.
Abstract: We present an automatic approach for object extraction from very high spatial resolution (VHSR) satellite images based on Object-Based Image Analysis (OBIA). The proposed solution requires no input data other than the studied image. Not input parameters are required. First, an automatic non-parametric co-operative segmentation technique is applied to create object primitives. A fuzzy rule base is developed based on the human knowledge used for image interpretation. The rules integrate spectral, textural, geometric and contextual object properties. The classes of interest are: tree, lawn, bare soil and water for natural classes; building, road, parking lot for man made classes. The fuzzy logic is integrated in out approach in order to manage the complexity of the studied subject, to reason with imprecise knowledge and to give information on the precision and certainity of the extracted objects. The proposed approach was applied to extracts of Ikonos images of Sherbrooke city (Canada). An overall total extraction accuracy of 80% was observed. The correctness rates obtained for building road and parking lot classes are of 81%, 75% and 60% respectively.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58729
Title: Hybrid conventional and Persistent Scatterer SAR interferometry for land subsidence monitoring in the Tehran Basin, Iran.
Author: Maryam Dehghani, Mohammad Javad Valadan Zoej, Andrew Hooper, Ramon F Hanssen. Iman Entezam, Sassan Saatchi
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 157-170 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Tehran basin, Subsidence, High-rate deformation, InSAR, Persistent scatterer, ENVISAT ASAR
Abstract: Excessive groundwater extraction has caused land subsidence in a large rural area located southwest of Tehran, Iran. We used radar images to estimate the temporal and spatial variation in the magnitude of the subsidence. Due to the large perpendicular baselines and rapid temporal decorrelation of the available data, the application of conventional synthetic aperture radar interferometry (InSAR) to monitor the deformation was not possible. Instead, we applied a recently developed Persistent Scatterer InSAR (PSI) method but found that displacements were underestimated in some areas due to high deformation rates that cause temporal aliasing of the signal. We therefore developed a method that combines conventional InSAR and PSI to estimate the high deformation rates in the southwestern Tehran Basin. We used rates estimated from conventional small temporal baseline interferograms to reduce the likelihood of aliasing and then applied PSI to the residual phase. The method was applied to descending and ascending ENVISAT ASAR images spanning from 2003 to 2009. Mean line-of-sight velocities obtained from both orientations that were further decomposed into horizontal and vertical deformation components were highly compatible with each other, indicating the high performance of the applied method. The mean precision of the estimated vertical component is 2.5 mm/yr. We validated our results using measurements from a continuous GPS station located in one of the subsiding areas. The results also compare favourably with levelling data acquired over a different time interval. Finally, we compared the estimated displacements to hydraulic head variations and geologic profiles at several piezometric wells. We found that the geology is the most important factor controlling the subsidence rate in the southwestern Tehran Basin, regardless of the water level decline.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58728
Title: Estimating single-tree branch of Norway spruce by airborne laser scanning
Author: Marius Hauglin, Janka Dibdiakova, Terje Gobakken, Erik Nasset.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 147-156 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Forestry, LIDAR, Inventory, Estimation, Accuracy.
Abstract: The use of forest biomass for bioenergy purposes, directly or through refinement processes, has increased in the last decade. One example of such use is the utilization of logging residues. Branch biomass constitutes typically a considerable part of the logging residues, and should be quantified and included in future forest inventories. Airborne laser scanning (ALS) is widely used when collecting data for forest inventories, and even methods to derive information at the single-tree level has been described. Procedures for estimation of single-tree branch biomass of Norway spruce using features derived from ALS data are proposed in the present study. As field reference data the dry weight branch biomass of 50 trees were obtained through destructive sampling. Variables were further derived from the ALS echoes from each tree, including crown volume calculated from an interpolated crown surface constructed with a radial basis function. Spatial information derived from the pulse vectors were also incorporated when calculating the crown volume. Regression models with branch biomass as response variable were fit to the data, and the prediction accuracy assessed through a cross-validation procedure. Random forest regression models were compared to stepwise and simple linear least squares models. In the present study branch biomass equations based on field measurements. An improved prediction accuracy was observed when incorporating information from the laser pulse vectors into the calculation of the crown volume variable, and a linear model with the crown volume as a single predictor gave the best overall results with a root mean square error of 35% in the validation.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58727
Title: Direct stereo radargrammetric processing using massively parallel processing.
Author: Timo Balz, Lu Zhang, Mingsheng Liao.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 137-146 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: High resolution, SAR, Radagrammetry, DSM, Correlation
Abstract: Synthetic Aperture Radar (SAR) offers many ways to reconstruct digital surface models (DSMs). The two most commonly used methods are SAR interferometry (InSAR) and stereo radargrammetry. Stereo radargrammetry is a very stable and reliable process and is far less affected by temporal decorrelation compared with InSAR. It is therefore often used for DSM generatiion in heavilly vegetated areas. However, stereo radargrammetry often produces rather noisy DSMs, sometimes containing large outliers. In this manuscript, we present a new approach for stereo radargrammetric processing, where the homologus points between the images are found by geocoding large amount of points. This offers a very flexible approach. allowing the simultaneous processing of multiple images and of cross-heading image pairs. Our approach relies on a good initial geocoding accuracy of the data and on very fast processing using a massive parallel implementation. The approach is demonstrated using TerraSAR-X images from Mount Song, China, and from Trento, Italy.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58726
Title: Geometric calibration of a terrestrial laser scanner with local additional parameters: An automatic strategy.
Author: D. Garcia-San-Miguel, J L Lerma.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 122-136 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Calibration, Automation, Adjustment, Laser scanning, Parameters, Geometric.
Abstract: Terrestrial laser scanning systems are steadily increasing in many fields of engineering, geoscience and architechture namely for fast data acquistion, 3-D modelling and mapping. Similarly to other precision instruments, these systems provide measursements with implicit systematic errors. Systematic errors are physically corrected by manufacturers before delivery and sporadically afterwards. The approach presented herein tackles the raw observables acquired by a laser scanner with additional parameters, a set of geometric calibration parameters that model the systematic error of the instrument to achieve the most accurate point cloud outputs, implroving eventual workflow owing to less filtering, better registration and best 3D modelling. This paper presents a fully automatic strategy calibrate geometrically terrestrial laser scanning datasets. The strategy is tested with multiple scans taken by a FARO FOCUS 3D, a phase-based terrestrial laser scanner. A calibration with local parameters for datasets is undertaken to improve the raw observables and a weighted mathematical index is proposed to select the most significant set of additional parameters. The improvements achieved are exposed, highlighting the necessity of correcting the terrestrial laser scanner before handling multiple datas ets.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58725
Title: Field-based sub-boundary ectraction from remote sensing imagery using perceptual grouping
Author: Mustafa Turker, Emre Hamit Kok.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 106-121 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Field-based, Boundary detection, Perceptual-grouping, Agriculture, SPOT imagery.
Abstract: This study presents an approach for the automatic extraction of dynamic sub-boundaries within existing agricultural fields from remote sensing imagery using perceptual grouping. We define sub-boundaries as boundaries, where a chang in crop type takes a place withtin fixed geometry of an agricultural field. To perforn field-based processing and analysis operations, the field boundary data and the satellite are integrated. The edge pixels are detected using Canny edge detector. The edge pixels are then analysed to find the connected edge chains and from these chains the line segments are detected using the graph based vectorization method. The spurious line segments is employed for detecting sub-boundaries and constructing sub-fields within the fixed geometry of agricultural fields. Our strategy for perceptual grouping involves the Gestalt laws of proximity, continuation, symmetry and closure. The processing and analysis operations are carried out on field-by-field basis. For each field, the geometries of sub-boundaries are integrated with the fixed geometry of the field. The experimental validation of the approach was carried out on the SPOT4 multispectral (XS) and SPOT5 XS images that cover an agricultural area located in the north-western section of Turkey. The overall matching percentages between the reference data and tha automatically extracted sub-boundaries were computed to be 82.6% and 76.2% for the SPOT5 and SPOT4 images respectively. The higher matching percentage of the SPOT5 image is due to the fact that some of the boundaries present in the SPOT5 image were not detected in the coarser resolution SPOT4 image. For the SPOT5 image, of the total 292 fields processed, 177 showed a total agreement between the detected segments and the reference dat. For SPOT4 image, 154 fields showed a total agreement between the detected segments and the reference data.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58724
Title: Reconstructing satellite images to quantify spatially explicit land surface change caused by fires and succession: A demonstration in the Yukon River Basin of interior Alaska.
Author: Shengli Huang, Suming Jin, Devendra Dahal, Xuexia Chen, Claudia Young, Heping Liu, Shuguang Liu.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 94-105 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Alaska, Fire, Land Surface, Landsat, Image reconstruction, NDVI.
Abstract: Land surface change caused by fires and succession is confounded by many site-specific factors and requires futher study. The objective of this study was to reveal the spatially explicit land surface change by minimizing the confounding factors of wheather variability, seasonal offset, topography, land cover and drainage. In a pilot study of the Yukon River Basin of interior Alaska, we retrieved Normalized Difference Vegetation Index (NDVI), albedo, and land surface temperature (LST) from a postfire landsat image acquired on August 5th, 2004. With a Landsat reference image acquired on June 26th, 1986, we reconstructed NDVI, albedo, and LST of 1987-2004 fire scars for August 5th 2004, assuming that these fires had not occurred. The difference between actual postfire and assuming-no-fire scenarios depicted the fires and succession impact. Our results demonstrated the following: (1) NDVI showed an immediate decrease after burning but gradually recovered to prefire levels in the following years, in which burn severity might play an important role during this process; (2) Albedo showed an immediate decrease after burning but then recovered and became higher than prefire levels; and (3) Most fires caused surface warming, but cooler surfaces did exist; time-since-fire affected the prefire and postfire LST differences but no absolute trends could be found. Our approach provided spatially explicit land surface change rather than average condition, enabling a better understanding of fires and succession impact on ecological consequences at the pixel level.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58723
Title: Semi-automated extraction and delineation of 3D roads of street scene from mobile laser scanning point clouds.
Author: Bisheng Yang, Lina Fang, Jonathan Li.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 80-93 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Mobile Laser scanning, Curb detection, 3D road extraction, Scanning lines, Moving windows filtering.
Abstract: Accurate 3D road information is important for applicatiion such as road maintenance and virtual 3D modelling. Mobile laser scanning (MLS) is an efficient technique for capturing dense point clouds that can be used to construct detailed road models for large areas. This paper presents a method for extracting and delineating roads from large-scale MLS point clouds. The proposed method partitions MLS point clouds into a set of consecutive "scanning lines", which each consists of a road cross section. A moving window operator is used to filter out non-ground points line by line, and curb points are detected based on curb patterns. The detected curb points are tracked and redefined so that they are globally consistent and locally similar. To evaluate the validity of the proposed method, experiments were conducted using two types of street-scene point clouds captured by Optech ' s Lynx Mobile Mapper System. The completeness, correctness and quality of the extracted roads are over 94.42%, 91.13%, and 91.3%, respectively which proves the proposed method is a promising solution for extracting 3D roads from MLS point clouds.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58722
Title: Generalization of 3D building texture using image compression and multiple representation data structure
Author: Bo Mao, Yifang Ban.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 68-79 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Three-dimensional builiding model, Texture compression, Multi-resolution Image, Multiple representation data structures, Dynamic visualization.
Abstract: Textures are an essential part of 3D building models and often consume large portions of data volume, thus making visualization difficult. Therefore, we propose a multi-resolution texture generalization methods to compress the textures of 3D building models for dynamic visualization at different scales. It consists of two steps: image compression and text coloring. In the first step, texture images are compressed using wavelet transformation in both the horizontal and the vertical direction. In the second step, a Texture Tree is created to store building texture color for dynamic visualization from different distances. To generate a TextureTree, texture images are iteratively segmented by horizontal and vertical dividing zones, until each section is basically in the same color. Then the texture of each section is represented by their main color and the TextureTree is created based on the color difference between the adjacent sections. In dynamic visualization, the suitable compressed texture images or the TextureTree nodes are selected to generate 3D scenes based on the angle and the distance between the view-point and the building surface. The experimental results indicate that wavelet based image compression and the proposed TextureTree can effectively represent the visual features of the textured buildings with much less data.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58721
Title: Use of shadows for detection of earthquake-induced collapsed buildings in high-resolution satellite imagery
Author: Xiaohua Tong, Xiaofei Lin, Tiantian Feng, Huan Xie, Shijie Liu, Zhonghua Hong, Peng Chen.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 53-67 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Hybrid appraoch, Shadow analysis, Building collapse detection, High-resolustion satellite image, Earthquake-induced damage assessment. Accuracy.
Abstract: In this paper, we present a hybrid shadow analysis approach that integrates the model and property-based methods for detecting collapsed buildings after an earthquake using high resolution satellite imagery. The framework proposed approach has four main steps. (1) The three-dimensional (3D) building model is established according to its footprint and height data stored in a geographical information system. (2) The theoretical shadow area of the building at the time that the post-seismic image was acquired is calculated. And the polygon of the ground shadow area of the building, which is called the theoretical ground shadow polygon, is extracted. (3) The theoretical ground shadow polygon is overlaid with the casting shadow area of the building, which is called the actual shadow area in the post-seismic satellite image, and the mean value of the digital number values of the post-seismic image pixels within the polygon of the theoretical shadow area is calculated. (4) The calculated mean value is compared with predefined thresholds, which are determined by the training pixels collected from the different types of shadows. On this basis, the shadows of totally collapsed, partially collapsed and uncollapsed buildings can be distinguished. A comprehensive experiment for Dujiangyan city, one of the urban areas most severely damaged in May 2008 Wenchuan Earthquake, was conducted, and the experimental results showed the superiority of the proposed approach to the other existing ones.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58720
Title: Spatiotemporal dynamic of surface water bodies using Landsat time-series data from 1999 to 2011
Author: Mirela G Tulbure, Mark Broich.
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 44-52 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Optical remote sensing, Surface water body detection, Large area wetland inventory, Swan Coastal Plain, Western Australia, Long term trends.
Abstract: Detailed information on the spatiotemporal dynamic in surface water bodies is important for quantifying the effects of a drying climate, increased water abstraction and rapid urbanization on wetlands. The Swan Coastal Plain (SCP) with over 1500 wetlands is a global biodiversity hotspot located in the south west of Western Australia, where more than 70% of the wetlands have been lost since European settlement. SCP is located in an area affected by recent climate change that also experiences rapid urban development and ground water abstraction. Landsat TM and ETM+ imagery from 1999 to 2011 has been used to automatically derive a spatially and temporally explicit time-series of surface water body extent on the SCP. A mapping method based on the Landsat data and a decision tree classification algorithm is described. Two generic classifiers were derived for the Landsat 5 and Landsat 7 data. Several landscape metrics were computed to summarize the intra and interannual patterns of surface water dynamic. Top of the atmosphere (TOA) reflectance of bands 4 and 3 were explanatory variables most important for mapping surface water bodies. Accuracy assessment yielded an overall classification accuracy of 96%, with 89% producer ' s accuracy and 93% user ' s accuracy of surface water bodies. The number, mean size, and total area of water bodies showed high seasonal variability with highest numbers in witner and lowest numbers in summer. The number of water bodies in winter increased until 2005 after which a decline can be noted. The lowest numbers occurred in 2010 which coincided with one of the years with the lowest rainfall in the area. Understanding the spatiotemporal dynamic of surface water bodies on the SCP constitutes the basis for understanding the effect of rainfall, water abstraction and urban development on water bodies in a spatially explicit way.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58719
Title: A generative statistical approach to automatic 3D building roof reconstruction from laser scanning data.
Author: Hai Huang, Claus Brenner, Monika Sester
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 29-43 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Building, LIDAR, point cloud, Urban, Extraction, Reconstruction, Three-dimensional
Abstract: This paper presents a generative statistical approach to automatic 3D building roof construction from airborne laser scanning point clouds. In previous works, bottom-up methods, e.g, points clustering, plane detection, and contour extraction, are widely used. Due to the data artefacts caused by tree clutter, reflection from windows, water features, etc., the bottom-up reconstruction in urban areas may suffer from a number of incomplete or irregular roof parts. Manually given geometric constraints are usually needed to ensure plausible results. In this work we propose an automatic process with emphasis on top-down approaches. The input point cloud is firstly pre-segmented into subzones containing a limited number of buildings to reduce the computational complexity for large urban scenes. For the building extraction and reconstruction in the subzones we propose a pure top-down statistical scheme, in which the bottom-up efforts or additional data like building footprints are no more required. Based on a predefined primitive library we conduct a generative modeling to reconstruct roof models that fit the data, Primitives are assembled into an entire roof with given rules of combination and merging. Overlaps of primitives are allowed in the assembly. The selection of roof primitives, as well as the sampling of their parameters, is driven by a variant of Markov Chain Monte Carlo technique with specified jump mechanism. Experiments are performed on data-sets of different building types (from simple houses, high-rise buildings to combined building groups) and resolutions. The results show robustness despite the data artefacts mentioned above and plausibility in reconstruction.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None
ID: 58718
Title: Commertial tree species discrimination using airborne AISA Eagle hyperspectral imagery and partial least squares discriminant analysis (PLS-DA) in KwaZulu-Natal, South Africa
Author: Kabir Yunus Peerbhay, Onisimo Mutanga, Riyad Ismail .......................................................................
Editor: Derek Lichti
Year: 2013
Publisher: Elsevier B. V.
Source: Centre for Ecological Sciences
Reference: ISPRS Journal of Photogrammetry & Remote Sensing Vol. 79, pp. 19-28 (2013)
Subject: ISPRS Journal of Photogrammetry & Remote Sensing
Keywords: Commercial forest species, Partial least squares discriminant analysis (PLS-DA), Variable importance in projection (VIP)
Abstract: Discriminating commercial tree species using hyperspectral remote sensing techniques is critical in monitoring the spatial distributions and compositions of commercial forests. However, issues related to data dimensionality and multicolinearity limit the successful application of the technology. The aim of this stufy was to examine the utility of the partial least squares discriminant analysis (PLS-DA) technique in accurately classifying six exotic commercial forest species (Eucalyptus grandis, Eucalyptus nitens, Euculyptus smithii, Pinus patula, Pinus ellioti and Acacia mearnsii) using airborne AISA Eagle hyperspectral imagery (393-900 nm). Additionally, the variable importance in the projection (VIP) method was used to identify subsets of bands that could successfully discriminate the forest species. Results indicated that the PLS-DA model that used all the AISA Eagle bands (n=230) produced an overall accuracy of 80.61% and a kappa value of 0.77, with user ' s and producer ' s accuracies ranging from 50% and 100%. In comparison, incorporating the optimal subset of VIP selected wavebands (n=78) in the PLS-DA model resulted in an improved overall accuracy of 88.78% and a kappa value of 0.87, with user ' s and producer ' s accuracies ranging from 70% to 100%. Bands located predominantly within the visible region of the electromagnetic spectrum (393-723 nm) showed the most capability in terms of discriminating between the six commercial forest species. Overall, the research has demonstrated the potential of using PLS-DA for reducing the dimensionality of hyperspectral datasets as well as determining the optimal subset of bands to produce the highest classification accuracies.
Location: TE 12 New Biology Building
Literature cited 1: None
Literature cited 2: None