Digital Aerial Images Research Articles

Vulnerability Analysis of the Urban Environments to Different Seismic Scenarios: Residential Buildings and Associated Population Distribution Modelling through Integrating Dasymetric Mapping Method and GIS

Residential buildings and associated population distribution modeling, is an integral part of analysis of the direct and indirect risks related to natural disasters, including earthquakes in urban environments. In this study, the distribution of residential population along with the distribution of residential buildings is estimated. The study offers a more comprehensive and accurate model for Iran in accordance with local conditions and with higher degree of details as available and accessible databases.Dasymetric mapping method as an alternative to a choropleth map is an efficient method for the spatial distribution of data benefitting from spatial information and statistical modeling. This research intends to integrate Dasymetric mapping method and GIS (Geographical Information System) to bring spatial, locational and statistical dataset together in order to analyze vulnerability of the exposed elements at risk in an urban context considering different seismic scenarios.In this study, statistical data at urban, block and parcel level as well as digital aerial and satellite images were compiled together. Building related features were extracted from remotely sensed images and integrated with the statistical information in order to generate spatially distributed dataset. This study develops a scenario-based seismic loss estimation model for residential building in city of Sari as a case study. The data was processed according to the following steps. At first, object extraction from satellite imagery was accomplished to acquire building boundaries within urban blocks. Then, the structural and demographic information were spatially distributed using Dasymetric mapping method. Next, ground motions map for different scenarios were generated for the entire metropolitan area. In the final step, the estimation of structural damage and loss of life were calculated for different scenarios. The results from this study indicate that, in comparison with Gridding method, Dasymetric mapping method would allow for a more realistic and careful assessment of seismic vulnerability of buildings at an urban scale due to more accurate classification and distribution of underlying data.

Flood Analysis Supported by Low‐cost Geometric Modelling

AbstractToday, it is increasingly clear that non‐stationarity hydrological and hydraulic variables and processes are occurring largely because of global warming. Accordingly, extreme hydrological events are becoming more common over time, and their effects are creating greater negative impacts on the environment (fluvial geomorphology and floodplains) and society (flood damage). Given this situation, the implementation of adaptation‐mitigation measures is vital, as well as an increased knowledge of the interaction between water and physical environments. In the binominal water‐terrain, having a reliable digital elevation model (DEM) is essential because of its important influence on fluvial modelling. However, this is frequently a technical‐economic problem. The aim of this paper is first to evaluate the compatibility between hydraulics and geometrics for fluvial applications and second to determine the quality of a novel DEM by robust estimators. This was obtained through the photogrammetric processing of digital aerial images acquired from a low‐cost camera mounted on an alternative aerial platform. Flood modelling and hydraulic parameters were obtained with the assistance of photogrammetric DEM (mesh size: 0.15 m, vertical accuracy: 0.102 ± 0.081 m, point density: ≈40 point/m2). Finally, our other goal is to develop a comparative analysis between light detection and ranging and digital photogrammetry on‐demand. This comparison revealed that flood modelling by photogrammetric DEM was considerably more detailed than that by light detection and ranging‐DEM, mainly because of higher point density and vertical accuracy. Consequently, flood analysis assisted by this novel geometric modelling approach qualifies as a reliable and competitive approach. Copyright © 2016 John Wiley & Sons, Ltd.

A NEW APPROACH FOR URBAN ROADS DETECTION USING LASER DATA AND AERIAL DIGITAL IMAGES

The automatic feature extraction from digital aerial images is not a trivial task mainly due to occlusion problems, shadows and different viewpoints. To obtain an improved feature extraction we used laser data, which have additional information such as height and material type of the surface. In this paper we performed the combination of digital image and laser data in order to improve the results of automatic extraction of urban roads. Initially, the urban roads were detected from the response of laser information; in the sequence we applied two different approaches to connect the disconnected road segments. The results were very promising, with sensitivity rate of 92%.

A NEW APPROACH FOR URBAN ROADS DETECTION USING LASER DATA AND AERIAL DIGITAL IMAGES

The automatic feature extraction from digital aerial images is not a trivial task mainly due to occlusion problems, shadows and different viewpoints. To obtain an improved feature extraction we used laser data, which have additional information such as height and material type of the surface. In this paper we performed the combination of digital image and laser data in order to improve the results of automatic extraction of urban roads. Initially, the urban roads were detected from the response of laser information; in the sequence we applied two different approaches to connect the disconnected road segments. The results were very promising, with sensitivity rate of 92%.

MONITORING SEABIRDS AND MARINE MAMMALS BY GEOREFERENCED AERIAL PHOTOGRAPHY

Abstract. The assessment of anthropogenic impacts on the marine environment is challenged by the accessibility, accuracy and validity of biogeographical information. Offshore wind farm projects require large-scale ecological surveys before, during and after construction, in order to assess potential effects on the distribution and abundance of protected species. The robustness of site-specific population estimates depends largely on the extent and design of spatial coverage and the accuracy of the applied census technique. Standard environmental assessment studies in Germany have so far included aerial visual surveys to evaluate potential impacts of offshore wind farms on seabirds and marine mammals. However, low flight altitudes, necessary for the visual classification of species, disturb sensitive bird species and also hold significant safety risks for the observers. Thus, aerial surveys based on high-resolution digital imagery, which can be carried out at higher (safer) flight altitudes (beyond the rotor-swept zone of the wind turbines) have become a mandatory requirement, technically solving the problem of distant-related observation bias. A purpose-assembled imagery system including medium-format cameras in conjunction with a dedicated geo-positioning platform delivers series of orthogonal digital images that meet the current technical requirements of authorities for surveying marine wildlife at a comparatively low cost. At a flight altitude of 425 m, a focal length of 110 mm, implemented forward motion compensation (FMC) and exposure times ranging between 1/1600 and 1/1000 s, the twin-camera system generates high quality 16 bit RGB images with a ground sampling distance (GSD) of 2 cm and an image footprint of 155 x 410 m. The image files are readily transferrable to a GIS environment for further editing, taking overlapping image areas and areas affected by glare into account. The imagery can be routinely screened by the human eye guided by purpose-programmed software to distinguish biological from non-biological signals. Each detected seabird or marine mammal signal is identified to species level or assigned to a species group and automatically saved into a geo-database for subsequent quality assurance, geo-statistical analyses and data export to third-party users. The relative size of a detected object can be accurately measured which provides key information for species-identification. During the development and testing of this system until 2015, more than 40 surveys have produced around 500.000 digital aerial images, of which some were taken in specially protected areas (SPA) of the Baltic Sea and thus include a wide range of relevant species. Here, we present the technical principles of this comparatively new survey approach and discuss the key methodological challenges related to optimizing survey design and workflow in view of the pending regulatory requirements for effective environmental impact assessments.

MONITORING SEABIRDS AND MARINE MAMMALS BY GEOREFERENCED AERIAL PHOTOGRAPHY

The assessment of anthropogenic impacts on the marine environment is challenged by the accessibility, accuracy and validity of biogeographical information. Offshore wind farm projects require large-scale ecological surveys before, during and after construction, in order to assess potential effects on the distribution and abundance of protected species. The robustness of site-specific population estimates depends largely on the extent and design of spatial coverage and the accuracy of the applied census technique. Standard environmental assessment studies in Germany have so far included aerial visual surveys to evaluate potential impacts of offshore wind farms on seabirds and marine mammals. However, low flight altitudes, necessary for the visual classification of species, disturb sensitive bird species and also hold significant safety risks for the observers. Thus, aerial surveys based on high-resolution digital imagery, which can be carried out at higher (safer) flight altitudes (beyond the rotor-swept zone of the wind turbines) have become a mandatory requirement, technically solving the problem of distant-related observation bias. A purpose-assembled imagery system including medium-format cameras in conjunction with a dedicated geo-positioning platform delivers series of orthogonal digital images that meet the current technical requirements of authorities for surveying marine wildlife at a comparatively low cost. At a flight altitude of 425 m, a focal length of 110 mm, implemented forward motion compensation (FMC) and exposure times ranging between 1/1600 and 1/1000 s, the twin-camera system generates high quality 16 bit RGB images with a ground sampling distance (GSD) of 2 cm and an image footprint of 155 x 410 m. The image files are readily transferrable to a GIS environment for further editing, taking overlapping image areas and areas affected by glare into account. The imagery can be routinely screened by the human eye guided by purpose-programmed software to distinguish biological from non-biological signals. Each detected seabird or marine mammal signal is identified to species level or assigned to a species group and automatically saved into a geo-database for subsequent quality assurance, geo-statistical analyses and data export to third-party users. The relative size of a detected object can be accurately measured which provides key information for species-identification. During the development and testing of this system until 2015, more than 40 surveys have produced around 500.000 digital aerial images, of which some were taken in specially protected areas (SPA) of the Baltic Sea and thus include a wide range of relevant species. Here, we present the technical principles of this comparatively new survey approach and discuss the key methodological challenges related to optimizing survey design and workflow in view of the pending regulatory requirements for effective environmental impact assessments.

Automatic 3D Coordinate Extraction from High Resolution Digital Aerial Images

Image matching has been widely used in various fields such as digital photogrammetry, remote sensing, image processing and computer vision. In this study, the speeded up robust feature extraction algorithm for automatic point extraction was applied to a pair of high resolution digital aerial stereo images. In contrast to other studies, the universal transverse mercator coordinates of randomly selected test points were computed automatically with the proposed approach and compared with the same points that were manually measured. As a result, the mean square differences for the UTM coordinates’ in the X, Y and Z axes were calculated as ±0.043, 0.030 and 0.153 m, respectively. It is proved that the proposed algorithm is successful in matching remotely sensed high-resolution images acquired with digital cameras. Moreover, the automatization of the basic tasks in image matching and the 3D coordinate acquisition were also achieved by the algorithm.

시각적 기법에 의한 DMC/UlatraCamXp/ADS80 디지털 항공영상의 공간해상도 특성 분석

시각적 기법에 의한 DMC/UlatraCamXp/ADS80 디지털 항공영상의 공간해상도 특성 분석

Efficiency and Detection Accuracy Using Print and Digital Stereo Aerial Photography for Remotely Mapping Vernal Pools in New England Landscapes

Aerial imagery has been used to identify potential vernal pools (PVPs) using stereo photographic prints. Stereoplotter photogrammetry now allows digital aerial images to be viewed in stereo (3-Dimensional) to enhance remote sensing capabilities. We used both print and digital imagery to map PVPs in 10 towns in Maine, USA. We used field verification of 771 PVPs to explore efficiency and accuracy of the two methodologies and to determine effects of pool size and land cover on accuracy. We compared known pool locations with National Wetland Inventory (NWI) data. The stereoplotter was more efficient and easier to use than prints. In the towns where print imagery was used, 77.4 % of surveyed PVPs were confirmed as compared to 60.8 % of PVPs surveyed in the towns with digital photography. The higher commission errors using the digital method were likely due to enhanced ability to detect smaller features. Omission errors were common using both print and digital methods. Only 43 % of confirmed vernal pools were located in areas mapped by NWI, suggesting that NWI information does not improve detection accuracy. Aerial photo interpretation continues to be effective for PVP identification in our region and is improved with the use of digital stereoplotters.

Das aktuelle Vegetationshöhenmodell der Schweiz: spezifische Anwendungen im Waldbereich

Current model of canopy heights in Switzerland: specific applications in forestry A national vegetation height model was calculated for Switzerland for the first time last year using digital aerial images. The ADS80 stereo aerial images, which were routinely gathered by the Swiss Federal Office of Topography (swisstopo), contain information about the height of vegetation in forests. We used the stereo aerial images to first calculate a digital surface model (DSM) with a very high spatial resolution (1 × 1 m). The DSM was then normalized to obtain the actual vegetation heights using a digital terrain model (DTM) based on laser data with the buildings masked out, and to produce a vegetation height model (VHM). Such a model could be calculated in the framework of the Swiss National Forest Inventory (NFI) with consistent methods and a very high level of detail. For covering the whole of Switzerland, we used summer aerial images from the years 2007 to 2012. The VHM reached almost nationwide coverage (98% of the country's surface area). Some areas, such as steep mountainsides or very bright glaciers, were problematic for calculating the model, and appear in it as gaps. Vegetation height information collected with this method is most useful for analyzing entire forest stands, but the data do not have a high enough spatial resolution for single-tree-based analyses. The VHM can be applied in a wide variety of ways. Here, we describe three of these: 1) generating forest masks, 2) extracting forest canopy gaps, and 3) detecting changes in the stocking of a forested area.

A Robust Digital Watermarking Algorithm for Copyright Protection of Aerial Photogrammetric Images

AbstractCurrent research on digital watermarking for the copyright protection of digital multimedia data has led to fairly advanced techniques with fruitful results. However, there remains a lack of research on digital watermarking for geospatial data, which is very costly to produce but is of great importance and with wide application. In this study an analysis and discussion of digital watermarking is carried out for digital aerial photogrammetric images. Focusing on the requirements for the main applications of such images, a feature‐based digital watermarking algorithm is proposed. Testing and analysis of the robustness of the watermark is performed to achieve the goal of copyright protection, even after image processing and geometric transformation have been undertaken on the watermarked image. Furthermore, the image quality is (almost) preserved to avoid detrimental effects on subsequent applications. The experimental results prove that the proposed watermarking method has a certain degree of robustness and can resist most types of image‐processing and geometric attacks, while maintaining the data quality of the aerial images.

Quality assessment of high density digital surface model over different land cover classes

Background and Purpose: Recent research on generation of digital surface models (DSMs) using image matching methods revealed a great potential of DSM application in forestry, especially in forest inventory. However, research dealing with DSM generation from digital aerial images are still lacking in Croatia. Therefore, the main objective of this study was to present the workflow for generating high density DSM from colour infrared (CIR) digital stereo aerial images using area-based image matching algorithm. Materials and Methods: The high density DSM was generated from colour infrared digital aerial stereo images using Dense DTM algorithm of PHOTOMOD software - an area-based image matching algorithm which operates on the principle of cross-correlation approach. To evaluate the quality of the generated DSM, an agreement assessment with manual stereo measurements was conducted over three different land cover classes (forests, shrubs, grasslands) using the same images as for DSM generation. Results: The good vertical agreement between the generated DSM and stereo measurement was achieved for all three land cover classes present at the research area. The highest vertical agreement was obtained for the grassland land cover class (RMSE=0.36), slightly lower for forest (RMSE=0.62), whereas the lowest vertical agreement was obtained for shrub land cover class (RMSE=0.83). Conclusions: The results of this research are very promising and suggest that the high density DSM generated from digital aerial stereo images and by using the proposed methodology has the potential to be used in forestry, primarily in forest inventory. Therefore, further research should be focused on generation of CHM by subtracting available DTM from the high density DSM and on the examination of its potential for deriving various forest attributes.

Quality assessment of high density digital surface model over different land cover classes

Background and Purpose: Recent research on generation of digital surface models (DSMs) using image matching methods revealed a great potential of DSM application in forestry, especially in forest inventory. However, research dealing with DSM generation from digital aerial images are still lacking in Croatia. Therefore, the main objective of this study was to present the workflow for generating high density DSM from colour infrared (CIR) digital stereo aerial images using area-based image matching algorithm. Materials and Methods: The high density DSM was generated from colour infrared digital aerial stereo images using Dense DTM algorithm of PHOTOMOD software - an area-based image matching algorithm which operates on the principle of cross-correlation approach. To evaluate the quality of the generated DSM, an agreement assessment with manual stereo measurements was conducted over three different land cover classes (forests, shrubs, grasslands) using the same images as for DSM generation. Results: The good vertical agreement between the generated DSM and stereo measurement was achieved for all three land cover classes present at the research area. The highest vertical agreement was obtained for the grassland land cover class (RMSE=0.36), slightly lower for forest (RMSE=0.62), whereas the lowest vertical agreement was obtained for shrub land cover class (RMSE=0.83). Conclusions: The results of this research are very promising and suggest that the high density DSM generated from digital aerial stereo images and by using the proposed methodology has the potential to be used in forestry, primarily in forest inventory. Therefore, further research should be focused on generation of CHM by subtracting available DTM from the high density DSM and on the examination of its potential for deriving various forest attributes.

Improved seagrass mapping using linear spectral unmixing of aerial photographs

Mapping of seagrass is challenging, particularly in areas where seagrass cover ranges from extensive, continuous meadows to aggregations of patchy mounds often no more than a meter across. Manual delineation of seagrass habitat polygons through visual photointerpretation of high resolution aerial imagery remains the most widely adopted approach for mapping seagrass extent but polygons often include unvegetated gaps. Although mapped polygon data exist for many estuaries, these are likely insufficient to accurately characterize spatial pattern or estimate area actually occupied by seagrass. We evaluated whether a linear spectral unmixing (LSU) classifier applied to manually-delineated seagrass polygons clipped from digital aerial images could improve mapping of seagrass in North Carolina. Representative seagrass endmembers were chosen directly from images and used to unmix image-clipped polygons, resulting in fraction planes (maps) of the proportion of seagrass present in each image pixel.Thresholding was used to generate seagrass maps for each pixel proportion from 0 (no thresholding, all pixel proportions included) to 1 (only pixels having 100% seagrass) in 0.1 increments. The optimal pixel proportion for identifying seagrass was assessed using Euclidean distance calculated from Receiver Operating Characteristic (ROC) curves and overall thematic accuracy calculated from confusion matrices. We assessed overall classifier performance using Kappa statistics and Area Under the (ROC) Curve (AUC). We compared seagrass area calculated from each threshold map to the total area of the corresponding manually-delineated polygon. LSU effectively classified seagrass and performed better than a random classification as indicated by high values for both Kappa statistics (0.72–98) and AUC (0.80–0.99). The LSU classifier effectively distinguished between seagrass and bare substrate resulting in fine-scale seagrass maps with overall thematic accuracies that exceeded our expected accuracy target of 85% (range: 86.3–99.0%) and were comparable to those reported from previous seagrass mapping studies utilizing aerial image spectral data. The pixel proportion producing seagrass maps with highest accuracy varied among sites (range: 0 to 0.5). The optimal pixel proportion determined from Euclidean distance varied among sites (range: 0.2 to 0.6) and differed from those having highest accuracy. Importantly, the classifier identified small patches of seagrass, resulting in seagrass area estimates that were 2–94% lower than the area of the corresponding habitat polygon. We conclude that where seagrass polygon data exist, LSU can be used together with photointerpretation to generate spatially resolved maps suitable for analysis of seagrass spatial configuration and provide improved estimates of actual seagrass acreage.

Data Assimilation in Forest Inventory: First Empirical Results

Data assimilation techniques were used to estimate forest stand data in 2011 by sequentially combining remote sensing based estimates of forest variables with predictions from growth models. Estimates of stand data, based on canopy height models obtained from image matching of digital aerial images at six different time-points between 2003 and 2011, served as input to the data assimilation. The assimilation routines were built on the extended Kalman filter. The study was conducted in hemi-boreal forest at the Remningstorp test site in southern Sweden (lat. 13°37′ N; long. 58°28′ E). The assimilation results were compared with two other methods used in practice for estimation of forest variables: the first was to use only the most recent estimate obtained from remotely sensed data (2011) and the second was to forecast the first estimate (2003) to the endpoint (2011). All three approaches were validated using nine 40 m radius validation plots, which were carefully measured in the field. The results showed that the data assimilation approach provided better results than the two alternative methods. Data assimilation of remote sensing time series has been used previously for calibrating forest ecosystem models, but, to our knowledge, this is the first study with real data where data assimilation has been used for estimating forest inventory data. The study constitutes a starting point for the development of a framework useful for sequentially utilizing all types of remote sensing data in order to provide precise and up-to-date estimates of forest stand parameters.

COMPARISON OF DIFFERENT VEGETATION INDICES FOR VERY HIGH-RESOLUTION IMAGES, SPECIFIC CASE ULTRACAM-D IMAGERY

Abstract. Today digital aerial images acquired with UltraCam sensor are known to be a valuable resource for producing high resolution information of land covers. In this research, different methods for extracting vegetation from semi-urban and agricultural regions were studied and their results were compared in terms of overall accuracy and Kappa statistic. To do this, several vegetation indices were first tested on three image datasets with different object-based classifications in terms of presence or absence of sample data, defining other features and also more classes. The effects of all these cases were evaluated on final results. After it, pixel-based classification was performed on each dataset and their accuracies were compared to optimum object-based classification. The importance of this research is to test different indices in several cases (about 75 cases) and to find the quantitative and qualitative effects of increasing or decreasing auxiliary data. This way, researchers who intent to work with such high resolution data are given an insight on the whole procedure of detecting vegetation species as one of the outstanding and common features from such images. Results showed that DVI index can better detect vegetation regions in test images. Also, the object-based classification with average 93.6% overall accuracy and 86.5% Kappa was more suitable for extracting vegetation rather than the pixel-based classification with average 81.2% overall accuracy and 59.7% Kappa.

Application of Technical Measures and Software in Constructing Photorealistic 3D Models of Historical Building Using Ground-Based and Aerial (UAV) Digital Images

Abstract Preparing digital documentation of historical buildings is a form of protecting cultural heritage. Recently there have been several intensive studies using non-metric digital images to construct realistic 3D models of historical buildings. Increasingly often, non-metric digital images are obtained with unmanned aerial vehicles (UAV). Technologies and methods of UAV flights are quite different from traditional photogrammetric approaches. The lack of technical guidelines for using drones inhibits the process of implementing new methods of data acquisition. This paper presents the results of experiments in the use of digital images in the construction of photo-realistic 3D model of a historical building (Raphaelsohns’ Sawmill in Olsztyn). The aim of the study at the first stage was to determine the meteorological and technical conditions for the acquisition of aerial and ground-based photographs. At the next stage, the technology of 3D modelling was developed using only ground-based or only aerial non-metric digital images. At the last stage of the study, an experiment was conducted to assess the possibility of 3D modelling with the comprehensive use of aerial (UAV) and ground-based digital photographs in terms of their labour intensity and precision of development. Data integration and automatic photo-realistic 3D construction of the models was done with Pix4Dmapper and Agisoft PhotoScan software Analyses have shown that when certain parameters established in an experiment are kept, the process of developing the stock-taking documentation for a historical building moves from the standards of analogue to digital technology with considerably reduced cost.

Imagens de Alta Resolução Espacial de Veículos Aéreos Não Tripulados (VANT) no Planejamento do Uso e Ocupação do Solo

The creation, improving and use of remote sensing techniques focused on suborbital images are increasing, as they present several advantages in geographical and ecological analysis, producing high spatial resolution data. The aim of this work was to test the supervised and unspervised classification techniques in aerial digital images with high spatial resolution obtained by Unmanned Aerial Vehicle (UAV), using the softwares SPRING and ArcGis. The aerial images have spatial resolution in approximately 10 cm, covering around 45% of the floor area. They were obtained in June, 2011, and overlies a stretch of the headwaters of the Sao Lourenco river in Campo Verde, Mato Grosso. Th aerial photographs were georeferenced and then the classification tests were performed, which presented better results the ones by region. At this stage, about 100 segmentation tests were performed with distinguished similarity parameters and areas, until finding a routine that would fit better to the study area. The classification that better delimited the different features present in the images was the supervised by region, whose segmentation had 20 pixels of similarity and 200 of area. To prove statistically the efficiency of classification, a cluster test was performed and the validation was done through Kappa index and overall accuracy. The presented results along with the use of UAVs are great tools and liable to use in several areas, including environmental expertising routines and recovery of degraded areas monitoring, under the Brazilian Forest Code.

A new feature selection from lidar data and digital aerial images acquired for an urban/c environment using an ANFIS-based classification and a fuzzy rough set method

In this article, a new fuzzy rough set (FRS) method was proposed for extracting rules from an adaptive neuro-fuzzy inference system (ANFIS)-based classification procedure in order to select the optimum features. The proposed methodology was used to classify lidar data and digital aerial images acquired for an urban environment to detect four classes, including trees, buildings, roads, and natural grounds. In this regard, 16 potentially primary features were produced for classification using the lidar data and the digital aerial images. The training and checking inputs of the proposed ANFIS were collected from the generated features for further training and evaluation processes. Also, the fuzzy c-mean clustering algorithm was used to initialize the fuzzy inference system of the proposed ANFIS-based classification method. By considering all states of fuzzy rules for each training input, the fuzzy rule with the maximum firing value was selected. Accordingly, these fuzzy rules were used as the inputs of the Rough Set Theory. Accordingly, the optimum features were acquired by the basic minimal covering algorithm as the rule induction method. To validate our proposed methodology, the procedure of classification was repeated by the achieved optimum features. The results showed that the classification using the optimum features has reached better overall accuracy than those achieved by using the 16 potentially primary features. Also, comparing the results of our proposed methodology with the other well-known genetic-algorithm-based feature selection methods indicated the significance of the proposed FRS method to select optimum features with high accuracy in a short running time.

A Comparative Study of Adaptive Neuro-Fuzzy Inference Systems in Object Detection of Complex City Scenes Using Digital Aerial Images and LiDAR Data

As adaptive neuro-fuzzy inference systems (ANFISs) have shown a high capability in solving various complicated problems, their usage have been increased so far. ANFISs are able to deal with large amounts of data with linear or nonlinear relations. In this paper, an ANFIS-based methodology was proposed in order to detect objects in complex city scenes using digital aerial images and LiDAR data. In this regard, four features were generated and normalized as ANFIS inputs including Green band, normalized difference vegetation index (NDVI), and normalized digital surface model (nDSM) using two different algorithms via morphological operations. Two types of objects were detected including buildings and trees. The proposed ANFIS used three different algorithms to build its fuzzy inference system structure including grid partition, subtractive clustering, and fuzzy c-means clustering. The results were evaluated on three different test areas provided by the fourth working group of the third commission (WG III/4) of international society of photogrammetry and remote sensing (ISPRS), over Vaihingen in Germany, known as Areas 1, 2, and 3. The achieved results were compared with each other, as well as with ISPRS WG III/4 participants’ results, by considering Completeness, Correctness, Quality, and RMS indices per-area and per-object levels. The achieved results demonstrated the capability of the proposed ANFIS in detecting buildings and trees in complex city scenes in comparison with other methods. In building detection, the proposed ANFIS-based methods achieved Completeness of 100 % in all three test areas for buildings larger than 50 m2. Also in both tree detection and building detection, the proposed ANFIS-based methods achieved Completeness and Correctness values larger than 90 %, by considering objects larger than 50 m2.