Clive Fraser

• University of Melbourne

Existing camera localisation methods for indoor augmented and mixed reality (AR/MR) are almost exclusively image based. The main issue with image-based methods is that they do not scale well and, as a consequence, AR/MR applications are mostly limited to small-scale room experiences. To tackle the challenge of large-scale indoor AR/MR localisation,...

The application of mixed reality visualisation in construction engineering requires accurate placement and retrieval of virtual models within the real world, which depends on the localisation accuracy. However, it is hard to understand what this means practically from localisation accuracy alone. For example, when we superimpose a Building Informat...

This paper presents a platform for multilayered documentation of cultural heritage, inspired by the current lack of a heritage BIM approach capable of creating models with both high geometric accuracy and high semantic richness. The platform is developed in the Unity game engine. It comprises several integrated and interconnected layers or datasets...

This paper reviews the existing heritage building modelling approaches, both parametric and reality-based, with the focus being upon geometric accuracy and semantic richness of the generated models. Our review identifies that there is currently no approach that offers both and that there is always a trade-off between visual fidelity and parametric...

A major challenge in the application of state-of-the-art deep learning methods to the classification of mobile lidar data is the lack of sufficient training samples for different object categories. The transfer learning technique based on pre-trained networks, which is widely used in deep learning for image classification, is not directly applicabl...

Automated building detection has been an active topic in photogrammetry and computer vision. One of the challenges is to effectively separate buildings from trees using aerial imagery and Lidar data. In cases where an adopted building detection technique cannot distinguish between these two classes of objects, the presence of trees in the scene can...

Commission VI, WG VI/4 ABSTRACT: The classification of mobile Lidar data is challenged by the complexity of objects in the point clouds and the limited number of available training samples. Incomplete shape, noise points and uneven point density make the extraction of features from point clouds relatively arduous. Additionally, the difference in po...

Fine scale land cover classification of urban environments is important for a variety of applications. LiDAR data has been increasingly used, separately or in conjunction with other remote sensing data, for providing land cover classification due to its high geometric accuracy as well as its additional radiometric information. An important issue in...

The development of robust and accurate filtering approaches for automated extraction of digital terrain models (DTMs) from airborne Light Detection and Ranging (LiDAR) data continues to be a challenge. The problem is due to the nature of LiDAR point clouds, the complexity of scene components, and the intrinsic structure of the terrain itself. This...

In this paper, a novel approach to ego-motion estimation is proposed based on visual and inertial sensors, named Omnidirectional Visual-Inertial Odometry (OVIO). The proposed approach combines omnidirectional visual features with inertial measurements within the Multi-State Constraint Kalman Filter (MSCKF). In contrast by perspective cameras, the p...

This letter presents a novel approach to automated extraction of roof planes from airborne light detection and ranging data based on spectral clustering of straight-line segments. The straight-line segments are derived from laser scan lines, and 3-D line geometry analysis is employed to identify coplanar line segments so as to avoid skew lines in p...

Nowadays, lidar is widely used in cultural heritage documentation, urban modeling, and driverless car technology for its fast and accurate 3D scanning ability. However, full exploitation of the potential of point cloud data for efficient and automatic object recognition remains elusive. Recently, feature-based methods have become very popular in ob...

Automatic registration of multisensor data, for example, imagery and Light Detection And Ranging (LiDAR), is a basic step in data fusion in the field of geospatial information processing. Mutual information (MI) has recently attracted research attention as a statistical similarity measure for intensity-based registration of multisensor images in th...

Full-waveform lidar data provides supplementary radiometric as well as more accurate geometric target information, when compared to discrete return systems. In this research, a wide range of classes in an urban scene; including trees, medium vegetation, low vegetation (grass), water bodies, pitched roofs, flat roofs, asphalt, vehicles, power lines,...

Full-waveform lidar systems capture the complete backscattered signal from the interaction of the laser beam with targets located within the laser footprint. The resulting data have advantages over discrete return lidar, including higher accuracy of the range measurements and the possibility of retrieving additional returns from weak and overlappin...

Urban green spaces, particularly urban trees, play a key role in enhancing the liveability of cities. The availability of accurate and up-to-date maps of tree canopy cover is important for sustainable development of urban green spaces. LiDAR point clouds are widely used for the mapping of buildings and trees, and several LiDAR point cloud classific...

Urban green spaces, particularly urban trees, play a key role in enhancing the liveability of cities. The availability of accurate and up-to-date maps of tree canopy cover is important for sustainable development of urban green spaces. LiDAR point clouds are widely used for the mapping of buildings and trees, and several LiDAR point cloud classific...

Along with providing high-resolution 3D topography data, airborne LiDAR is being increasingly employed for land cover classification in urban environments. The laser ranging approach potentially overcomes difficulties associated with classification of satellite imagery. When compared to discrete return systems, full-waveform LiDAR data provides sup...

This paper proposes an accurate multi-view stereo method for image-based 3D reconstruction that features robustness in the presence of occlusions. The new method offers improvements in dealing with two fundamental image matching problems. The first concerns the selection of the support window model, while the second centers upon accurate visibility...

Building data are one of the important data types in a topographic database. Building change detection after a period of time is necessary for many applications, such as identification of informal settlements. Based on the detected changes, the database has to be updated to ensure its usefulness. This paper proposes an improved building detection t...

Geometric and radiometric attributes of targets are provided by full-waveform LiDAR data. However, the accuracy of such information depends largely on the adopted data processing method. In this study, the emphasis is on the retrieval of the temporal target cross-section by regularization methods, with the subsequent extraction of the backscatterin...

Recently developed automatic dense image matching algorithms are now being implemented for DSM/DTM production, with their pixel-level surface generation capability offering the prospect of partially alleviating the need for manual and semi-automatic stereoscopic measurements. In this paper, five commercial/public software packages for 3D surface ge...

Some performance evaluation systems for building extraction techniques are manual in the sense that only visual results are provided or human judgment is employed. Many evaluation systems that employ one or more thresholds to ascertain whether an extracted building or roof plane is correct are subjective and cannot be applied in general. There are...

The 27 papers in this special issue were originally presented at the IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013), held July 21-26 in Melbourne, Australia.

This paper presents a new method for segmentation of LIDAR point cloud data for automatic building extraction. Using the ground height from a DEM (Digital Elevation Model), the non-ground points (mainly buildings and trees) are separated from the ground points. Points on walls are removed from the set of non-ground points by applying the following...

Accurate co-registration of multi-sensor data is a primary step in data integration for photogrammetric and remote sensing applications. A proven intensity-based registration approach is Mutual Information (MI). However the effectiveness of MI for automated registration of multi-sensor remote sensing data can be impacted to the point of failure by...

This paper presents an automated approach to the extraction of building footprints from airborne LiDAR data based on energy minimization. Automated 3D building reconstruction in complex urban scenes has been a long-standing challenge in photogrammetry and computer vision. Building footprints constitute a fundamental component of a 3D building model...

Accurate waveform restoration, from the received noisy waveform, is of great interest to the full-waveform LiDAR community. As a result of this, important attributes could be estimated precisely which are valuable in describing and differentiating LiDAR targets. Assumptions behind prominent methods like the Gaussian decomposition do not hold due to...

Automatic extraction of building roofs from remote sensing data is important for many applications, including 3D city modeling. This paper proposes a new method for automatic segmentation of raw LIDAR (light detection and ranging) data. Using the ground height from a DEM (digital elevation model), the raw LIDAR points are separated into two groups....

The development of robust and accurate methods for automatic registration of optical imagery and 3D LiDAR data continues to be a challenge for a variety of applications in photogrammetry, computer vision and remote sensing. This paper proposes a new approach for the registration of optical imagery with LiDAR data based on the theory of Mutual Infor...

Automatic registration of multi-sensor data is a basic step in data fusion for photogrammetric and remote sensing applications. The effectiveness of intensity-based methods such as Mutual Information (MI) for automated registration of multi-sensor image has been previously reported for medical and remote sensing applications. In this paper, a new m...

Accurate range determination and retrieval of the cross section are two important issues in the processing of full-waveform LiDAR data, especially between closely located targets. The dependency of the received waveform on the emitted pulse can be removed through deconvolution and consequently comparisons between waveforms recorded by different sen...

The lack of noise reduction methods resistant to waveform distortion can hamper correct and accurate decomposition in the processing of full-waveform LiDAR data. This paper evaluates a time-domain method for smoothing and reducing the noise level in such data. The Savitzky-Golay (S-G) approach approximates and smooths data by taking advantage of fi...

Planar structures are essential components of the urban landscape and automated extraction planar structure from LiDAR data is a fundamental step in solving complex mapping tasks such as building recognition and urban modelling. This paper presents a new and effective method for planar structure extraction from airborne LiDAR data based on spectral...

This paper presents a new segmentation technique for LIDAR point cloud data for automatic extraction of building roof planes. Using the ground height from a DEM (Digital Elevation Model), the raw LIDAR points are separated into two groups: ground and nonground points. The ground points are used to generate a "building mask" in which the black areas...

Automatic registration of multi-sensor data is a basic step in data fusion applications. Mutual information (MI) has been widely used in medical and remote sensing image registration. In this paper, an effective histogram binning technique is proposed to improve the robustness of image registration using MI and Normalized MI (NMI). Increasing the b...

Automatic 3D extraction of building roofs from remotely sensed data is important for many applications including city modelling. This paper proposes a new method for automatic 3D roof extraction through an effective integration of LIDAR (Light Detection And Ranging) data and multispectral orthoimagery. Using the ground height from a DEM (Digital El...

Automatic co-registration is a basic step in multi-sensor data fusion for remote sensing applications. The effectiveness of Mutual Information (MI) as a similarity measure for multisensor image registration has previously been reported for medical and remote sensing applications. In this paper, a new intensity-based approach built on local MI princ...

Automatic 3D extraction of building roofs from remotely sensed data is important for many applications including city modeling. This paper proposes a new method for automatic 3D roof extraction through an effective integration of LIDAR (Light Detection And Ranging) data and multispectral orthoimagery. Using the ground height from a DEM (Digital Ele...

Although a large number of building roof reconstruction techniques from the remotely sensed data have been proposed, there is a serious lack in standard and automatic evaluation system. The manual evaluation systems are based on human judgment and so may be biased. Moreover, the application of such an evaluation system on a large data set requires...

Separation of buildings from trees is a major challenge in automatic building detection. In residential and hilly areas, buildings are often surrounded by dense vegetation. This paper presents a three-step method for effective separation of buildings from trees. Firstly, height and width thresholds are applied to LIDAR data for removing small bushe...

Automated close-range photogrammetric network orientation has been traditionally performed with the use of coded targets in the object space to allow for initial point correspondence determination and subsequent network orientation. Feature-based matching (FBM) techniques have recently offered an alternative procedure for point correspondence calcu...

The performance of automatic building detection techniques can be significantly impeded due to the presence of same-height objects, for example, trees. Consequently, if a building detection technique cannot distinguish between trees and buildings, both its false positive and false negative rates rise significantly. This paper presents an improved a...

Automatic camera calibration using self-calibration with the aid of coded targets is now very much the norm in close-range photogrammetry. This is irrespective of whether the cameras to be calibrated are high-end metric, or the digital SLRs and consumer-grade models that are increasingly being employed for image-based 3D measurement. Automation has...

The registration process forms an important step in the integration of Digital Elevation Models (DEMs) of differing accuracy and resolution. Registration effectively constitutes a surface-to-surface matching in which horizontal and vertical offsets between the two DEMs are determined and corrected. This paper evaluates five approaches for DEM regis...

The provision of high-quality ground control points (GCPs) is a prerequisite for 1-pixel level georeferencing of high-resolution satellite imagery (HRSI), irrespective of whether the GCPs are used to remove biases in RPCs or to support physical sensor orientation models. This is especially so in remote regions where the benefits to orthoimage gener...

Automatic image registration is a basic step in multi-sensor data integration in remote sensing and photogrammetric operations such as data fusion. The effectiveness of intensity-based methods for automated multi-sensor image registration, such as Mutual Information (MI) and the Correlation Ratio (CR), have previously been demonstrated for medical...

This paper discusses the evolution of algorithms and procedures for network orientation that have accompanied the transition of close-range photogrammetry from a film-based to a digital image-based measurement process suited to partial or full automation. A brief mathematical background to orientation models derived via perspective projection and p...

Automated 3D building model generation continues to attract research interests in photogrammetry and computer vision. Airborne Light Detection and Ranging (LIDAR) data with increasing point density and accuracy has been recognized as a valuable source for automated 3D building reconstruction. While considerable achievements have been made in roof e...

Automatic image registration is a basic step in multi-sensor data integration in remote sensing and photogrammetric applications such as data fusion. The effectiveness of Mutual Information (MI) as a technique for automated multi-sensor image registration has previously been demonstrated for medical and remote sensing applications. In this paper, a...

The Australian Geographic Reference Image (AGRI) is a national satellite image mosaic that covers the vast Australian continent. Formed from 9560 ALOS PRISM images, AGRI provides a spatially correct reference image at 2.5 m resolution, with 1-pixel accuracy. The production of AGRI was made feasible by the development and implementation of a long-st...

To exploit full metric quality of optical satellite imagery, precise georeferencing is necessary. A number of sensor orientation models designed to exploit the full metric potential of images have been developed over the past decades. In particular, generic models attract more interest as they take full account of the physical imaging process by ad...

Automatic 3D reconstruction of building roofs from remotely sensed data is important for many applications including city modeling. This paper proposes a new method for automatic 3D roof reconstruction through an effective integration of LIDAR data and multispectral imagery. Using the ground height from a DEM, the raw LIDAR points are separated int...

The success of automatic building detection techniques lies in the effective separation of buildings from trees. This paper presents an improved automatic building detection technique that achieves more effective separation of buildings from trees. Firstly, it uses cues such as height to remove objects of low height such as bushes, and width to exc...

Effective separation of buildings from trees is a major challenge in image-based automatic building detection. This paper presents a three-step method for effective separation of buildings from trees using aerial imagery and lidar data. First, it uses cues such as height to remove objects of low height such as bushes, and width to exclude trees wit...

The registration process forms an important step in the integration of Digital Elevation Models (DEMs) of resolution. DEM registration invariably involves what is effectively an 'image matching' process utilising similarity number of prospective image matching approaches, Mutual Information (MI) offers potential for application to has proven to be...

Corner detectors have many applications in computer vision and image identification and retrieval. Contour-based corner detectors directly or indirectly estimate a significance measure (e.g., curvature) on the points of a planar curve, and select the curvature extrema points as corners. While an extensive number of contour-based corner detectors ha...

Around 1200 AD, a number of remarkable rock churches were constructed in Lalibela, a town in northern Ethiopia. One construction manner stands apart in its uniqueness. This is the rock-hewn monolithic church, which while imitating a built-up structure is actually cut in one piece from the rock and separated from it by an all-around trench. The best...

Commission V, WG V/2 and V/4 ABSTRACT: This paper discusses image-based modelling and the generation of textured 3D object models. The main focus of the presentation is upon a low-cost, easy-to-use photogrammetric system which can handle hidden object parts and model curves in object space. The concept includes the following stages: first, measurem...

Much of the mobile mapping activity in Australia has been applied to the mapping of railways. Over the last decade the process has evolved from one narrowly focused upon establishing the position of track centrelines to one which includes the position and geometry of the track, imagery and detailed attributes of all trackside features. This broader...

High-resolution satellite imagery (HRSI) is being increasingly employed for large-scale topographic mapping, and especially for geodatabase updating. As the spatial resolution of HRSI sensors increases, so the potential georeferencing accuracy also improves. However, accuracy is not a function of spatial resolution alone, as it is also dependent up...

This paper will discuss strategies for trinocular image rectification and matching for linear object tracking. It is well known that a pair of stereo images generates two epipolar images. Three overlapped images can yield six epipolar images in situations where any two are required to be rectified for the purpose of image matching. In this case, th...

Automatic D reconstruction of building roofs from remotely sensed data is important for many applications including automatic city modeling. This paper proposes a new method for automatic roof reconstruction using LIDAR (Light Detection And Ranging) data and multispectral imagery. Using the ground height from a DEM (Digital Elevation Model), the ra...

One of the practical impediments to the adoption of long focal length lenses in close range photogrammetry is the difficulty in network exterior orientation and self-calibration that can be encountered with the collinearity equation model when the camera field of view is smaller than around 10°. This paper reports on an investigation that examined...

This paper reports on the application of a generic physical sensor orientation model for evaluation of the georeferencing performance of 2 m resolution imagery from the Thailand Earth Observation System (THEOS) satellite. Within the generic sensor orientation model, orbit and attitude data are employed to describe the satellite trajectory, which is...

An automatic building detection technique using LIDAR data and multispectral imagery has been proposed. Two masks are obtained from the LIDAR data: a 'primary building mask' and a 'secondary building mask'. The primary building mask indicates the void areas where the laser does not reach below a certain height threshold. The secondary building mask...

The main obstacle to achieving high precision in georeferencing from high-resolution satellite imagery (HRSI) remains the need for provision of good quality ground control points (GCPs), whether the GCPs are used to remove biases in RPC triangulation or to support physical sensor orientation models. The provision of GCPs can be very costly and is o...

Effective separation of buildings from trees is a major challenge in automatic building detection from aerial imagery and Lidar data. In cases where an adopted building detection technique cannot distinguish between these two classes of objects, the presence of trees in the scene can increase the rates of both false positives and false negatives in...

Contour-based corner detectors directly or indirectly estimate a significance measure (e.g. curvature) on the points of a planar curve and select the curvature extrema points as corners. While an extensive number of contour-based corner detectors have been proposed over the last four decades, there is no comparative study of recently proposed promi...

Traffic islands are important features of mapped road networks in topographic databases. The modelling of these, however, is generally not explicit in most approaches to road extraction from aerial imagery. Traffic islands can be considered as elements of road junctions and in this paper an active contour-based approach is proposed for their automa...

This paper presents an automatic building detection technique using LIDAR data and multispectral imagery. Two masks are obtained from the LIDAR data: a ‘primary building mask’ and a ‘secondary building mask’. The primary building mask indicates the void areas where the laser does not reach below a certain height threshold. The secondary building ma...

Although automated object surface reconstruction via feature-based matching is commonly employed in both stereoscopic close range and topographic photogrammetry, it has rarely been used in conjunction with multi-image, convergent photogrammetric networks. A prerequisite for feature-based matching of distinct points is the application of interest op...

Precise georeferencing is one of the prerequisites for orthoimage generation from high-resolution satellite imagery. This requires the availability of a small number of GCPs that have to be visible in each scene. In this paper, it is shown how the number of GCPs required for the precise georeferencing of Advanced Land Observation Satellite (ALOS) i...

Three important stages within automated 3D object reconstruction via multi-image convergent photogrammetry are image pre-processing, interest point detection for feature-based matching and triangular mesh generation. This paper investigates approaches to each of these. The Wallis filter is initially examined as a candidate image pre-processor to en...

This paper presents an automatic system for the detection of buildings from LIDAR data and multispectral imagery, which employs a threshold-free evaluation system that does not involve any thresholds based on human choice. Two binary masks are obtained from the LIDAR data: a 'primary building mask' and a 'secondary building mask'. Line segments are...

Within topographic databases, traffic islands constitute important features of mapped road networks. However, they are generally not explicitly modelled in most approaches to road extraction from aerial imagery. Traffic islands can be considered as elements of road junctions and in this paper an active contour-based approach for their automatic ext...

This paper develops an improved approach to digital surface model (DSM) generation from high‐resolution satellite imagery (HRSI). The approach centres upon an image matching strategy that integrates feature point, grid point and edge matching algorithms within a coarse‐to‐fine hierarchical process. The starting point is a knowledge of precise senso...

Abstract This work looks at the automation of the reconstruction of buildings using a handheld consumer grade video camera. We discuss our progress to date which includes: deinterlacing the video footage, automated selection of non-blurred key frames, registration of key frames using a Fast Fourier Transformation technique and tracking of points an...

In remote developing countries, such as Bhutan, it is common for existing maps to be either out-of-date or to not exist. Featuring forest covered peaks and broad valleys with a 2000 m elevation range, the rugged mountainous and largely inaccessible landscape is not well suited to traditional topographic surveying and mapping. It does, however, prov...

Full automation in close-range photogrammetric measurement has long been a practical reality. However, constraints apply to the process such that automated 3D measurement is generally confined to targeted points in an environment of controlled illumination. The ready availability of consumer-grade digital cameras has made photogrammetric measuremen...

The previously proposed contour-based multi-scale corner detector based on the chord-to-point distance accumulation (CPDA) technique has proved its superior robustness over many other single- and multi-scale detectors. However, the original CPDA detector is computationally expensive since it calculates the CPDA discrete curvature on each point of t...

The options available for orientation of satellite imagery in cases requiring optimal metric precision are generally rational functions, where the RPCs are provided by the image supplier, or a rigorous physical model. In either case, it is ground control that facilitates pixel-level georeferencing via a compensation for systematic errors in the sen...

GeoEye-1 was launched in September 2008, and after some five months of commissioning commenced commercial operations in February, 2009. With its 0.41m panchromatic and 1.65m multispectral resolution, GeoEye-1 represents a further step along the way to higher resolution capabilities for remote sensing satellites. Given experiences with precise geore...

Road roundabouts, as a class of road junctions, are generally not explicitly modelled in existing road extraction approaches. This paper presents a new approach for the automatic extraction of roundabouts from aerial imagery through the use of prior knowledge from an existing topographic database. The proposed snake-based approach makes use of zipl...

A new generic pushbroom sensor model for high-resolution satellite images in which the orbit and attitudes are modelled by splines is presented. Direct observations for the satellite orbits and attitudes provided in imagery metadata files are used to determine the parameters of these splines. As such observations are contaminated by systematic erro...

Network orientation is a fundamental step in image-based 3D measurement. This paper aims to offer insights into network orientation by considering developments in analytical close-range photogrammetry during its evolution from a film-based to digital image-based measurement technology suited to full process automation. A brief mathematical backgrou...