The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We are developing a robotic measurement facility which makes it very easy to build “reality-based” models, i.e., computational models of existing, physical objects based on actual measurements. These include not only models of shape, but also reflectance, contact forces, and sound. Such realistic models are crucial in many applications, including telerobotics, virtual reality, computer-assisted medicine,...
We present a method for extracting foreground objectsfrom video and its application to content-aware video compression. Our method uses trimaps inferred from backgroundsubtraction to represent the foreground-background relationship. The appearance of foreground and background are modeled withRadial Basis Functions initialized from the background substractionstep. Finally, Graph Cuts are used to compute...
We describe the current state of ACME, the UBC Active Measurement facility, a telerobotic facility designed for building computational models of everyday physical objects. We show how ACME is being used to acquire models of contact texture (including friction and roughness), contact sounds, and contact deformation.
Correlation filters for long-term visual object tracking have recently seen great interest. Although they present competitive performance results, there is still a need for improving their tracking capabilities. In this paper, we present a fast scalable solution based on the Kernalized Correlation Filter (KCF) framework. We introduce an adjustable Gaussian window function and a keypoint-based model...
Semantic segmentation, or segmenting all the objects in an image is one of the core problems of computer vision. In order to achieve an object-level semantic segmentation, we propose to label image regions and to improve the segmentation result based on these labels. We build upon the recent super parsing approach, which is a nonparametric solution to the image labelling problem. We propose to initialize...
In this paper, we present a real-time approach for 3D object detection using a single, mobile and uncalibrated camera. We develop our algorithm using a feature-based method based on two novel naive Bayes classifiers for viewpoint and feature matching. Our algorithm exploits the specific structure of various binary descriptors in order to boost feature matching by conserving descriptor properties (e...
Most high dynamic range (HDR) imaging techniques generate HDR radiance maps from exposure bracketed low dynamic range (LDR) images captured with a stationary camera. We propose a novel general framework for spherical HDR imaging for image-based virtual environments from a moving camera. The framework is composed of three major stages: calibration and alignment, spherical stereo matching and HDR composition...
In this paper, we present a fast and robust haptic system for a FEM-based dissection simulation built on top of open source software packages. Our system integrates the extended finite element (XFEM) into these packages in order to model the deformation of a dissected body without introducing any topological changes to the underlying volumetric tetrahedral mesh. We develop a semi-progressive cutting...
The matching of oriented local image feature descriptors like SIFT, SURF or ORB often includes the refinement and filtering of matches based on the relative orientation of the features. This is important since the computational cost for subsequent tasks like camera pose estimation or object detection increases dramatically with the number of outliers. Simple 2D orientation descriptions are unsuitable...
Glucose sensors have improved and facilitated therapy for type 1 diabetes. However, they are still not capable to sense all physiological signals and to act in a closed-loop. Pancreatic β-cells have been shaped during evolution as biological sensors and offer the advantage to integrate all physiological signals in addition to glucose. Moreover, biosensors based on these cells may also serve for non-invasive...
We present an approach to robustly track the geometry of an object that deforms over time from a set of input point clouds captured from a single viewpoint. The deformations we consider are caused by applying forces to known locations on the object's surface. Our method combines the use of prior information on the geometry of the object modeled by a smooth template and the use of a linear finite element...
Exploration of 2-D images is a challenging problem in computer haptics and research has primarily been focused on the exploration of restricted types of images, e.g., maps or mathematical curves. In contrast, this paper describes the design and implementation of a system for the haptic exploration of general photographs. We transform the photograph to a set of contours which are then rendered as three-dimensional...
In this paper we present a time- and space-efficient multi-scale method for stereo reconstruction from high-resolution planar and omni directional images. We first present the stereo algorithm and then extend it to omni directional images using a novel spherical disparity formulation. Our multi-scale method is based on a novel application of distance transforms to the disparity space images (DSI)...
In this paper we present a framework for vision-based robot localization using natural planar landmarks. Specifically, we demonstrate our framework with planar targets using Fern classifiers that have been shown to be robust against illumination changes, perspective distortion, motion blur, and occlusions. We add stratified sampling in the image plane to increase robustness of the localization scheme...
We present a reconfigurable acquisition and wavelet-based detection circuit, NeuroBetaMed, for in vitro biological signals. It is implemented on a configurable digital integrated circuit (FPGA). We consider real-time computing as a hard specification and silicon area as a price to pay. It is designed for noisy signals like those recorded from in vitro cellular preparations, by extracellular electrodes...
When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstruct is the human face. In this paper we learn a statistical wavelet prior of the shape of the human face and use it to constrain stereo reconstruction within a Bayesian framework. We initialize our algorithm with a, typically...
This paper proposes a simple window-based range flow method which uses isometry of the observed surface as its primary matching constraint. The method uses feature points as anchoring references of the surface deformation. Given a set of matched features no other intensity information is used and hence the method can tolerate intensity changes over time. The range-flow equation is only required for...
Vibration feedback models are known to be effective to convey tactile characteristics in virtual environments and they can be rendered with existing haptic devices. In this paper we develop a novel texture model based on a spatial distribution of infinite-impulse-response filters which operate in the time domain. We match the impulse response of the filters to measured acceleration profiles obtained...
In this paper, we introduce a 3D scanning system consisting of a stereo camera combined with an inertial navigation system. We employ this system to explore the suitability of the standard 3D scanning pipeline when working with stereo range data of objects and architecture in an outdoor setting. Our range scanning system is very mobile without any mechanical actuators. We rely solely on the inertial...
In modern computer graphics, 3D scanning is common practise for the acquisition of the geometry of objects. However, in addition to geometric models, physical models of interaction behaviour are required for the realistic representation of objects in arbitrary environments. In this paper, we introduce a hand-held scanning approach for the acquisition of physical surface texture (roughness) of real-...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.