Frank P. Ferrie's research while affiliated with McGill University and other places

Publications (122)

Article
Full-text available
A new non-stationary, high-order sequential simulation method is presented herein, aiming to accommodate complex curvilinear patterns when modelling non-Gaussian, spatially distributed and variant attributes of natural phenomena. The proposed approach employs spatial templates, training images and a set of sample data. At each step of a multi-grid...
Chapter
Full-text available
The Collaborative Advanced Robotics and Intelligent Systems (CARIS) laboratory at the University of British Columbia studies the development of robotic systems that are capable of autonomous human-robot interaction. This chapter will provide an overview of our laboratory’s activities and methodologies. We first discuss a recently-concluded multi-in...
Article
Finding the set of nearest neighbors for a query point of interest appears in a variety of algorithms for machine learning and pattern recognition. Examples include k nearest neighbor classification, information retrieval, case-based reasoning, manifold learning, and nonlinear dimensionality reduction. In this work, we propose a new approach for de...
Chapter
This paper presents a new high-order, nonstationary sequential simulation approach, aiming to deal with the typically complex, curvilinear structures and high-order spatial connectivity of the attributes of natural phenomena. Similar to multipoint methods, the proposed approach employs spatial templates and a group of training images (TI). A coarse...
Article
Collaboration between human workers and robotic assistants is seen as one way to increase both flexibility and efficiency in a production line environment. In this setup, human workers can be assigned tasks that require high perceptual ability, dexterity and judgement, supplemented by robotic assistants that can perform work of low (skill) value, s...
Article
We present a marker-less human motion capture system that uses multiple RGB-D cameras to estimate the 3D posture of multiple people online at interactive rates in an indoor workspace measuring approximately 5 m × 5 m × 2 m. An interesting aspect of this work is how we handle the self-contact problem. We propose a novel multi-view voting scheme (MVS...
Article
A key problem in mine planning is estimating the locations of underground ore bodies from a set of sparse core samples that span the area to be excavated. Data from each sample location are interpreted by a geologist and rendered as an image depicting the local ore distribution. The goal is to reconstruct these sparse samples into a dense image tha...
Article
We present a method to upsample low-resolution light detection and ranging (LiDAR) data using coregistered panoramic images collected in urban environments. The context is a mobile mapping vehicle equipped with a LiDAR scanner and spherical camera system, where the goal is to recover a three-dimensional model of the built environment. What makes th...
Article
We address the class masking problem in multiclass linear discriminant analysis (LDA). In the multiclass setting, LDA does not maximize each pairwise distance between classes, but rather maximizes the sum of all pairwise distances. This results in serious overlaps between classes that are close to each other in the input space, and degrades classif...
Article
We present an automatic mutual information (MI) registration method for mobile LiDAR and panoramas collected from a driving vehicle. The suitability of MI for registration of aerial LiDAR and aerial oblique images has been demonstrated under an assumption that minimization of joint entropy (JE) is a sufficient approximation of maximization of MI. W...
Conference Paper
Manifold learning algorithms rely on a neighbourhood graph to provide an estimate of the data's local topology. Unfortunately, current methods for estimating local topology assume local Euclidean geometry and locally uniform data density, which often leads to poor embeddings of the data. We address these shortcomings by proposing a framework that c...
Article
Manifold learning algorithms rely on a neighbourhood graph to provide an estimate of the data's local topology. Unfortunately, current methods for estimating local topology assume local Euclidean geometry and locally uniform data density, which often leads to poor data embeddings. We address these shortcomings by proposing a framework that combines...
Conference Paper
Multivariate Gaussian densities are pervasive in pattern recognition and machine learning. A central operation that appears in most of these areas is to measure the difference between two multivariate Gaussians. Unfortunately, traditional measures based on the Kullback-Leibler (KL) divergence and the Bhattacharyya distance do not satisfy all metric...
Article
Mobile lidar (light detection and ranging) data collection is a rapidly emerging technology in which multiple georeferenced sensors (e.g., laser scanners, cameras) are mounted on a moving vehicle to collect real world data. The photorealistic modeling of large-scale real world scenes such as urban environments has become increasingly interesting to...
Conference Paper
We present an automatic mutual information (MI) registration method for mobile LiDAR and panoramas collected from a driving vehicle. The suitability of MI for registration of aerial LiDAR and aerial oblique images has been demonstrated in [17], under an assumption that minimization of joint entropy (JE) is a sufficient approximation of maximization...
Article
Multivariate Gaussian densities are pervasive in pattern recognition and machine learning. A central operation that appears in most of these areas is to measure the difference between two multivariate Gaussians. Unfortunately, traditional measures based on the Kullback- Leibler (KL) divergence and the Bhattacharyya distance do not satisfy all metri...
Article
We present a novel method to upsample mobile LiDAR data using panoramic images collected in urban environments. Our method differs from existing methods in the following aspects: First, we consider point visibility with respect to a given viewpoint, and use only visible points for interpolation; second, we present a multi-resolution depth map based...
Article
One major challenge for traffic management systems is the inference of traffic flow in regions of the network for which there are little data. In this paper, Global-Positioning-System (GPS)-based vehicle locator data from a fleet of 40-60 roving ambulances are used to predict the most likely ambulance speeds in a network of 20 000 streets in the ci...
Conference Paper
Full-text available
Many unsupervised learning algorithms make use of kernels that rely on the Euclidean distance between two samples. However, the Euclidean distance is optimal for Gaussian distributed data. In this paper, we relax the global Gaussian assumption made by the Euclidean distance, and propose a locale Gaussian modelling for the immediate neighbourhood of...
Conference Paper
We present an automatic approach to window and façade detection from LiDAR (Light Detection And Ranging) data collected from a moving vehicle along streets in urban environments. The proposed method combines bottom-up with top-down strategies to extract façade planes from noisy LiDAR point clouds. The window detection is achieved through a two-step...
Chapter
Measuring the difference between two multivariate Gaussians is central to statistics and machine learning. Traditional measures based on the Bhattacharyya coefficient or the symmetric Kullback-Leibler divergence do not satisfy metric properties necessary for many algorithms. This paper proposes a metric for Gaussian densities. Similar to the Bhatta...
Conference Paper
Full-text available
Linear Discriminant Analysis (LDA) is a popular tool for multiclass discriminative dimensionality reduction. How- ever, LDA suffers from two major problems: (1) It only op- timizes the Bayes error for the case of unimodal Gaussian classes with equal covariances (assuming full rank matri- ces) and, (2) The multiclass extension maximizes the sum of p...
Article
A regularization-based approach to 3D reconstruction from multiple images is proposed. As one of the most widely used multiple-view 3D reconstruction algorithms, Space Carving can produce a Photo Hull of a scene, which is at best a coarse volumetric model. The two-view stereo algorithm, on the other hand, can generate a more accurate reconstruction...
Conference Paper
Full-text available
We present a bimodal information analysis system for automatic emotion recognition. Our approach is based on the analysis of video sequences which combines facial expressions observed visually with acoustic features to automatically recognize five universal emotion classes: anger, disgust, happiness, sadness and surprise. We address the challenges...
Conference Paper
Full-text available
Although our two eyes view the world from different perspectives, our brain can effortlessly associate items seen by one eye with those by the other - leading to the binocular depth sensation. We would like computers to make this match as well as humans, so that an intelligent system can perceive 3-D using binocular inputs from cameras. Current met...
Conference Paper
Full-text available
Accurate image correspondence is crucial for estimating multiple-view geometry. In this paper, we present a registration-based method for improving accuracy of the image correspondences. We apply the method to fundamental matrix estimation under practical situations where there are both erroneous matches (outliers) and small feature location errors...
Conference Paper
A technique to automatically detect anomalies in data from mobile terrestrial LIDAR systems is proposed. Terrapoint's TITAN system uses multiple LIDAR scanners mounted on a vehicle, which scan the same object at different times as the system moves past. By automatically finding anomalies in these scans a human operator can be alerted that editing o...
Conference Paper
Full-text available
To learn a metric for query-based operations, we combine the concept underlying manifold learning algorithms and the minimum volume ellipsoid metric in a unified algorithm to find the nearest neighbouring points on the manifold on which the query point is lying. Extensive experiments on standard benchmark data sets in the context of classification...
Article
TITAN® is a mobile terrestrial multi-LiDAR system. It uses GPS and an Inertial Measurement Unit (IMU) to determine its position and attitude. By using four LiDARs, the TITAN system has overlapping coverage. When the GPS signal is lost, the position error increases exponentially with the duration of the interruption. Drift in the position data manif...
Conference Paper
We first investigate the combined effect of data complexity, curse of dimensionality and the definition of the Euclidean distance on the distance measure between points. Then, based on the concepts un- derlying manifold learning algorithms and the minimum volume ellipsoid metric, we design an algorithm that learns a local metric on the lower dimens...
Conference Paper
A major challenge for traffic management systems is the inference of traffic flow in regions of the network for which there is little data. In this paper, GPS-based vehicle locator data from a fleet of 40-60 roving ambulances are used to estimate traffic congestion along a network of 20,000 streets in the city of Ottawa, Canada. Essentially, the ro...
Conference Paper
This paper presents a new method for reconstructing rectilinear buildings from single images under the assumption of flat terrain. An intuition of the method is that, given an image composed of rectilinear buildings, the 3D buildings can be geometrically reconstructed by using the image only. The recovery algorithm is formulated in terms of two obj...
Conference Paper
A technique to improve the positional accuracy of mobile ground-based LIDAR systems is proposed. Terrapointpsilas TITAN(TM) system scans the same objects at different times, so by aligning scans, any drift over time can be estimated. This paper describes a simple way of tessellating the scanned data into segments based on the vehiclepsilas path. Pr...
Article
It is well known that vanishing point based analysis requires images with strong perspective effects due to wide angle lenses, close objects, and often oblique viewing angles. Aerial imagery, however, normally present weak perspective effects because of long-range shootings. In this paper, we present a model-based method for reconstructing rectilin...
Conference Paper
We are interested in learning an adaptive local metric on a lower dimensional manifold for query-based operations. We combine the concept underlying manifold learning algo- rithms and the minimum volume ellipsoid metric to find the nearest neighbouring points to a query point on the man- ifold on which the query point is lying. Extensive experi- me...
Conference Paper
Full-text available
This paper presents a novel method for detection of image interest regions called Structure Guided Salient Regions (SGSR). Following the information theoretic route to saliency detection, we extend Kadir et al.'s Salient Region detector by exploiting image structure information. The detected SGSRs are highly distinct and very selective. For planar...
Conference Paper
Full-text available
We propose an unsupervised "local learning" algorithm for learning a metric in the input space. Geometrically, for a given query point, the algorithm finds the minimum volume ellipsoid (MVE) cover-ing its neighborhood which characterizes the correlations and variances of its neighborhood variables. Algebraically, the algorithm maximizes the determi...
Conference Paper
This paper explores the possibility of assessing the adequacy of a training database to be used in a learning-based super-resolution process. The Mean Euclidean Distance (MED) function is obtained by averaging the distance between each input patch and its closest candidate in the training database, for a series of blurring kernels used to construct...
Article
A novel procedure is presented to construct image-domain filters (receptive fields) that directly recover local motion and shape parameters. These receptive fields are derived from training on image deformations that best discriminate between different shape and motion parameters. Beginning with the construction of 1-D receptive fields that detect...
Conference Paper
This paper addresses the problem of super-resolving a single image and recovering the characteristics of the sensor using a learning-based approach. In particular, the point spread function (PSF) of the camera is sought by minimizing the mean Euclidean distance function between patches from the input frame and from degraded versions of high-resolut...
Conference Paper
Full-text available
A regularization-based approach to 3-D reconstruction from multiple images is proposed. As one of the most widely used multiple-view 3-D reconstruction algorithms, Space Carving can produce a photo hull of a scene, which is at best a coarse volumetric model. The two-view stereo algorithm, on the other hand, can generate a more accurate reconstructi...
Conference Paper
This paper presents comparisons of two learning-based super-resolution algorithms as well as standard interpolation methods. To allow quality assessment of results, a comparison of a variety of image quality measures is also performed. Results show that a MRF-based super-resolution algorithm improves a previously interpolated image. The estimated d...
Conference Paper
An attentive vision system is proposed that estimates traffic motion parameters from MPEG-2 compressed video recorded using an un-calibrated camera mounted on a pan-tilt unit. Compressed domain information from a stream of MPEG-2 video is used to estimate a traffic motion field and infer the 2D frame location of the traffic lanes. With these visual...
Chapter
Image-guided surgery (IGS) is a technique for localizing anatomical structures on the basis of volumetric image data and for determining the optimal surgical path to reach these structures, by the means of a localization device, or probe, whose position is tracked over time. The usefulness of this technology hinges on the accuracy of the transforma...
Conference Paper
The paper presents a 2 frame structure-from-motion algo- rithm that operates by mapping local changes (image deformations) into estimates of time-to-collision (TTC). For constant velocity motion of the camera in a stationary scene, time-to-collision amounts to coarse depth data - useful for navigation and qualitative scene understanding. The the- o...
Conference Paper
A procedure for generating steerable kernels corresponding to general image mappings for arbitrary image tesselations was discussed. By treating each pixel as a Voronoi cell, correspondence matrix theory predicts the optimal real-valued spectral decomposition of possible irregular image region for a range of deformation. The same analysis and metho...
Article
Full-text available
Neptec Design Group has developed the Laser Camera System (LCS), a 3D autosynchronized laser scanner based on a principle originating from the National Research Council of Canada. In imaging mode, the LCS raster scans objects and captures reflections from their surface features. In centroid acquisition mode, the LCS determines the position of discr...
Article
This paper presents a literature survey of automatic 3D surface registration techniques emphasizing the mathematical and algorithmic underpinnings of the subject. The relevance of surface registration to medical imaging is that there is much useful anatomical information in the form of collected surface points which originate from complimentary mod...
Conference Paper
Full-text available
This paper presents a novel method for surface recovery from discrete 3D point data sets. In order to produce improved reconstruction results, the algorithm presented in this paper combines the advantages of a parametric approach to model local surface structure, with the generality and the topological adaptability of a geometric flow approach. Thi...
Article
Image-guided surgery (IGS) is a technique for localizing anatomical structures on the basis of volumetric image data and for determining the optimal surgical path to reach these structures, by the means of a localization device, or probe, whose position is tracked over time. The usefulness of this technology hinges on the accuracy of the transforma...
Conference Paper
A novel procedure is presented to construct image-domain filters (receptive fields) that directly recover local motion and shape parameters. These receptive fields are derived from training on image deformations that best discriminate between different shape and motion parameters. Beginning with the construction of 1D receptive fields that detect l...
Article
This paper presents a novel image-based approach for updating the geometry of 3D models. The technique can cope with large-scale models, using a single imaging sensor to which an arbitrary motion is applied. Current approaches usually do not fully take advantage of strong prior information, often available in the form of an initial model. The appro...
Conference Paper
Full-text available
This paper describes the design and implementation of an active surface reconstruction algorithm for two-frame image sequences using passive imaging. A novel strategy based on the statistical grouping of image gradient features is used. It is shown that the gradient of the intensity in an image can successfully be used to drive the direction of the...
Article
In this paper we propose a paradigm called the interactive visual dialog (IVD) as a means of facilitating a system's ability to recognize objects presented to it by a human. The presentation centers around a supermarket checkout scenario in which an operator presents an item to be tallied to a stationary television camera. An active vision approach...
Article
This paper presents an enhancement to current image-based rendering methods. It suggests thatmotionconsistencycanbeusedinarealtime dynamic rendering system to increase computational efficiency up to one order of magnitude. Parameterization of the image warping function with respect to the viewer's motion can be used to provide an efficient method f...
Article
Synthetic vision systems render artificial images of the world based on a database and position/attitude information of the aircraft. Due to both its static nature and inherent modelling errors, the database introduces anomalies in the synthetic imagery. Since it reflects at best a nominal state of the environment, it often requires updating via on...
Article
In aviation, synthetic vision systems produce artificial views of the world to support navigation and situational awareness in poor visibility conditions. Synthetic images of local terrain are rendered from a database and registered through the aircraft navigation system. Because the database reflects, at best, a nominal state of the environment, i...
Article
This paper describes an algorithm for recognizing known objects in an unstructured environment (e.g. landmarks) from measurements acquired with a single monochrome television camera mounted on a mobile observer. The approach is based on the concept of an entropy map, which is used to guide the mobile observer along an optimal trajectory that minimi...
Article
Full-text available
This paper introduces an object recognition strategy based on the following premises: i) an object can be identified on the basis of the optical flow it induces on a stationary observer, and ii) a basis for recognition can be built on the appearance of flow corresponding to local curvilinear motion. Unlike other approaches that seek to recognize pa...
Article
In this paper, we introduce a method for sequentially accumulating evidence as it pertains to an active observer seeking to identify an object in a known environment. We develop a probabilistic framework, based on a generalized inverse theory, where assertions are represented by conditional probability density functions. This leads to a sequential...
Conference Paper
Full-text available
A road sign (RS) recognition system poses a real challenge for machine vision. It must recognize a wide variety of RSs under considerable variations in illumination and imaging geometry-all in real-time. Such a system is presented, with emphasis on the system architecture and specific model-based techniques used in the different processing steps. C...
Article
This paper introduces an information-based methodology for view selection that actively exploits prior knowledge about the objects to be found in a scene. The methodology is used to implement an active recognition strategy which effectively puts prior constraints from the object database into the gaze control (planning) loop. Theoretical results ar...
Article
The hand-eye problem consists in determining the relative pose between two coordinate frames fixed to the same rigid body from measurements of the poses attained by these two frames, as the body moves. In robotics this problem arises when two frames are attached to the end-effector (EE), one of these at the gripper, the other to a sensor such as a...
Article
This paper presents a literature survey of automatic 3D surface registration techniques emphasizing the mathematical and algorithmic underpinnings of the subject. The relevance of surface registration to medical imaging is that there is much useful anatomical information in the form of collected surface points which originate from complimentary mod...
Article
The primary intent of this work is to present a method for sequentially associating three-dimensional surface measurements acquired by an autonomous exploration agent with models that describe those surfaces. Traditional multiple-viewpoint registration approaches are concerned only with finding the transformation that maps data points to a chosen g...
Article
An autonomous approach for learning the colors of specific objects assumed to have known body spectral reflectances is developed for daylight illumination conditions. The main issue is to be able to find these objects autonomously in a set of training images captured under a wide variety of daylight illumination conditions, and to extract their col...
Conference Paper
The problem of estimating and tracking the pose of a 3D object is a well-established problem in machine vision with important applications in terrestrial and space robotics. The paper describes how 3D range data, available from a new generation of real time laser rangefinding systems, can be used to solve the pose determination problem. The approac...
Conference Paper
Full-text available
In this paper, we show how entropy maps can be used to guide an active observer along an optimal trajectory, by which the identity and pose of objects in the world can be inferred with confidence, while minimizing the amount of data that must be gathered. Specifically we consider the case of active object recognition where entropy maps are used to...
Conference Paper
Describes a system for automatically digitizing the surfaces of a completely unknown object to a prescribed sampling density. Unlike many available commercial systems (e.g. Cyberware), our system analyzes actively the data and computes sensor trajectories to achieve complete surface coverage taking into account the limitations of the sensor/manipul...
Article
. This paper describes a new framework for parametric shape recognition based on a probabilistic model of inverse theory first introduced by Tarantola. The key result is a method for generating classifiers in the form of conditional probability densities for recognizing an unknown from a set of reference models. Our procedure is automatic. Off-line...
Article
This paper introduces a novel model-based technique to determine the pose of complex, noncooperatrice 3-D objects from laser rangefinder images. Geometrical models of object parts are probabilistically matched against a model database, and various sources of uncertainty are carried through the process, yielding local, point-by-point estimates of po...
Article
this paper is a set of algorithms for reconstructing surfaces obtained from overlapping range images in a common frame of reference. Surfaces are assumed to be piecewise-smooth but not necessarily rigid. Motion parameters, rotations and translations that describe correspondence between views, are recovered locally under the assumption that the curv...
Article
Full-text available
In this paper we introduce a method for distinguishing between informative and uninformative viewpoints as they pertain to an active observer seeking to identify an object in a known environment. The method is based on a generalized inverse theory using a probabilistic framework where assertions are represented by conditional probability density fu...
Conference Paper
We propose a the use of a consistent Bayesian methodology for the analysis of the uncertainty associated with a pose estimation procedure. A novel model-based technique to estimate the pose of rigid 3D objects from laser range finder images is studied, and various sources of uncertainty are carried through the process using a Bayesian MAP treatment...
Conference Paper
This paper addresses the question of how to integrate local and global information-the goal being a stable mechanism to partition parametric data into meaningful classes without injecting a priori information about the data. To do this we introduce a novel framework to represent both local and global information and their interactions. Where both t...
Article
Many strategies in computer vision assume the existence of general purpose models that can be used to characterize a scene or environment at various levels of abstraction. The usual assumptions are that a selected model is competent to describe a particular attribute and that the parameters of this model can be estimated by interpreting the input d...
Conference Paper
Many relaxation based smoothing methods used in surface reconstruction algorithms filter out the effect of noise in image data, but result in the elimination of important discontinuity information as well. In this paper the inter-pixel interaction during relaxation is shown to be equivalent to a multiple measurement fusion problem which can be solv...
Conference Paper
This paper describes an extension to a class of surface reconstruction algorithms based on the minimization of variation of curvature, the so-called curvature consistency framework. It deals explicitly with the problem of localizing surface discontinuities, which was one of the shortcomings of the original work. Inter-pixel interactions during the...
Article
Passively accepting measurements of the world is not enough, as the data we obtain is always incomplete, and the inferences made from it uncertain to a degree which is often unacceptable. If we are to build machines that operate autonomously, they will always be faced with this dilemma, and can only be successful if they play a much more active rol...
Conference Paper
Many relaxation based smoothing methods used in surface reconstruction algorithms filter out the effect of noise in image data, but result in the elimination of important discontinuity information as well. In this paper the inter-pixel interaction during relaxation is shown to be equivalent to a multiple measurement fusion problem which can be solv...
Conference Paper
This paper introduces a monocular optical flow algorithm that has been shown to perform well at nearly real-time frame rates (4 FPS on a 100 MHz SGI Indy workstation), using natural image sequences. The system is completely bottom-up, using pixel region-matching techniques. A coordinated gradient descent method is broken down into two stages: pixel...
Conference Paper
Scene ambiguity, due to noisy measurements and uncertain object models, can be quantified and actively used by an autonomous agent to efficiently gather new data and improve its information about the environment. In this work an information-based utility measure is used to derive from a learned classification of shape models an efficient data colle...