Results 1 - 10
of
10
Spatio-Temporal Shape from Silhouette using Four-Dimensional Delaunay Meshing
, 2007
"... We propose a novel method for computing a fourdimensional (4D) representation of the spatio-temporal visual hull of a dynamic scene, based on an extension of a recent provably correct Delaunay meshing algorithm. By considering time as an additional dimension, our approach exploits seamlessly the tim ..."
Abstract
-
Cited by 26 (3 self)
- Add to MetaCart
We propose a novel method for computing a fourdimensional (4D) representation of the spatio-temporal visual hull of a dynamic scene, based on an extension of a recent provably correct Delaunay meshing algorithm. By considering time as an additional dimension, our approach exploits seamlessly the time coherence between different frames to produce a compact and high-quality 4D mesh representation of the visual hull. The 3D visual hull at a given time instant is easily obtained by intersecting this 4D mesh with a temporal plane, thus enabling interpolation of objects’ shape between consecutive frames. In addition, our approach offers easy and extensive control over the size and quality of the output mesh as well as over its associated reprojection error. Our numerical experiments demonstrate the effectiveness and flexibility of our approach for generating compact, high-quality, time-coherent visual hull representations from real silhouette image data.
Efficient visual hull computation for realtime 3D reconstruction using CUDA
- IN: PROCEEDINGS OF THE 2008 CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS
, 2008
"... In this paper we present two efficient GPU-based visual hull computation algorithms. We compare them in terms of performance using image sets of varying size and different voxel resolutions. In addition, we present a real-time 3D reconstruction system which uses the proposed GPU-based reconstruction ..."
Abstract
-
Cited by 24 (3 self)
- Add to MetaCart
In this paper we present two efficient GPU-based visual hull computation algorithms. We compare them in terms of performance using image sets of varying size and different voxel resolutions. In addition, we present a real-time 3D reconstruction system which uses the proposed GPU-based reconstruction method to achieve real-time performance (30 fps) using 16 cameras and 4 PCs.
3D occlusion inference from silhouette cues
- In CVPR
, 2007
"... We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views. While well studied and robust in controlled environments, silhouette-based reconstruction of dynamic objects fails in ge ..."
Abstract
-
Cited by 23 (3 self)
- Add to MetaCart
(Show Context)
We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views. While well studied and robust in controlled environments, silhouette-based reconstruction of dynamic objects fails in general environments where uncontrolled occlusions are commonplace, due to inherent silhouette corruption by occluders. We show that occluders in the interaction space of dynamic objects can be detected and their 3D shape fully recovered as a byproduct of shape-from-silhouette analysis. We provide a Bayesian sensor fusion formulation to process all occlusion cues occurring in a multi-view sequence. Results show that the shape of static occluders can be robustly recovered from pure dynamic object motion, and that this information can be used for online self-correction and consolidation of dynamic object shape reconstruction. 1.
Free-form Object Reconstruction from Silhouettes, Occluding Edges and Texture Edges: A Unified and Robust Operator based on Duality
, 2007
"... In this paper, the duality in differential form is developed between a 3D primal surface and its dual manifold formed by the surface’s tangent planes, i.e., each tangent plane of the primal surface is represented as a four-dimensional vector which constitutes a point on the dual manifold. The iterat ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
(Show Context)
In this paper, the duality in differential form is developed between a 3D primal surface and its dual manifold formed by the surface’s tangent planes, i.e., each tangent plane of the primal surface is represented as a four-dimensional vector which constitutes a point on the dual manifold. The iterated dual theorem shows that each tangent plane of the dual manifold corresponds to a point on the original 3D surface, i.e., the “dual ” of the “dual ” goes back to the “primal”. This theorem can be directly used to reconstruct 3D surface from image edges by estimating the dual manifold from these edges. In this paper we further develop the work in our original conference papers resulting in the robust differential dual operator. We argue that the operator makes good use of the information available in the image data, by using both points of intensity discontinuity and their edge directions; we provide a simple physical interpretation of what the abstract algorithm is actually estimating and why it makes sense in terms of estimation accuracy; our algorithm operates on all edges in the images, including silhouette edges, self occlusion edges, and texture edges, without distinguishing their types (thus resulting in improved accuracy and handling locally concave surface estimation if texture edges are present); the algorithm automatically handles various degeneracies; and the algorithm incorporates new methodologies for
Recovery and Reasoning About Occlusions in 3D Using Few Cameras with Applications to 3D Tracking
"... Abstract In this work we propose algorithms to learn the locations of static occlusions and reason about both static and dynamic occlusion scenarios in multi-camera scenes for 3D surveillance (e.g., reconstruction, tracking). We will show that this leads to a computer system which is able to more ef ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Abstract In this work we propose algorithms to learn the locations of static occlusions and reason about both static and dynamic occlusion scenarios in multi-camera scenes for 3D surveillance (e.g., reconstruction, tracking). We will show that this leads to a computer system which is able to more effectively track (follow) objects in video when they are obstructed from some of the views. Because of the nature of the application area, our algorithm will be under the constraints of using few cameras (no more than 3) that are configured wide-baseline. Our algorithm consists of a learning phase, where a 3D probabilistic model of occlusions is estimated per-voxel, per-view over time via an iterative framework. In this framework, at each frame the visual hull of each foreground object (person) is computed via a Markov Random Field that integrates the occlusion model. The model is then updated at each frame using this solution, providing an iterative process that can accurately estimate the occlusion model over time and overcome the few-camera constraint. We demonstrate the application of such a model to a number of areas, including visual hull reconstruction, the reconstruction of the occluding structures themselves, and 3D tracking.
Real-Time 3D Reconstruction for Occlusion-aware Interactions in Mixed Reality
"... Abstract. In this paper, we present a system for performing real-time occlusion-aware interactions in a mixed reality environment. Our system consists of 16 ceiling-mounted cameras observing an interaction space of size 3.70 m x 3.20 m x 2.20 m. We reconstruct the shape of all objects inside the int ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. In this paper, we present a system for performing real-time occlusion-aware interactions in a mixed reality environment. Our system consists of 16 ceiling-mounted cameras observing an interaction space of size 3.70 m x 3.20 m x 2.20 m. We reconstruct the shape of all objects inside the interaction space using a visual hull method at a frame rate of 30 Hz. Due to the interactive speed of the system, the users can act naturally in the interaction space. In addition, since we reconstruct the shape of every object, the users can use their entire body to interact with the virtual objects. This is a significant advantage over marker-based tracking systems, which require a prior setup and tedious calibration steps for every user who wants to use the system. With our system anybody can just enter the interaction space and start interacting naturally. We illustrate the usefulness of our system through two sample applications. The first application is a real-life version of the well known game Pong. With our system, the player can use his whole body as the pad. The second application is concerned with video compositing. It allows a user to integrate himself as well as virtual objects into a prerecorded sequence while correctly handling occlusions. 1
Detecting behavioral zones in local and global camera views
- MACHINE VISION AND APPLICATIONS
, 2012
"... We present a complete end-to-end framework to detect and exploit entry and exit regions in video using behavioral models of object trajectories. Using easily collected “weak ” tracking data (short and frequently broken tracks) as input, we construct a set of entity tracks to provide more reliable e ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
We present a complete end-to-end framework to detect and exploit entry and exit regions in video using behavioral models of object trajectories. Using easily collected “weak ” tracking data (short and frequently broken tracks) as input, we construct a set of entity tracks to provide more reliable entry and exit observations. These observations are then clustered to produce a set of potential entry and exit regions within the scene, and a behavior-based reliability metric is used to score each region and select the final zones. We also present an extension of our fixed-view approach to detect entry and exit regions within the entire viewspace of a pan–tilt–zoom camera. We additionally provide methods employing the regions to learn scene occlusions and causal relationships from entry–exit pairs along with exploitation algorithms (e.g., anomaly detection). Qualitative and quantitative experiments are presented using multiple outdoor surveillance cameras and demonstrate the reliability and usefulness of our approach.
A Safe Fault Tolerant Multi-View Approach for Vision-Based Protective Devices
"... We present a new approach that realizes an imagebased fault tolerant distance computation for a multi-view camera system which conservatively approximates the shortest distance between unknown objects and 3D volumes. Our method addresses the industrial application of vision-based protective devices ..."
Abstract
- Add to MetaCart
(Show Context)
We present a new approach that realizes an imagebased fault tolerant distance computation for a multi-view camera system which conservatively approximates the shortest distance between unknown objects and 3D volumes. Our method addresses the industrial application of vision-based protective devices which are used to detect intrusions of humans into areas of dangerous machinery, in order to prevent injuries. This requires hardware redundancy for compensation of hardware failures without loss of functionality and safety. By taking sensor failures during the fusion process of distances from different cameras into account, this is realized implicitly, with the benefit of no additional hardware cost. In particular we employ multiple camera perspectives for safe and non-conservative occlusion handling of obstacles and formulate general system assumptions which are also appropriate for other applications like multi-view reconstruction methods. 1. Keyords Safety, vision-based protective devices (VBPDs), fault tolerance, redundancy, replication, distance calculation, occlusion handling, occlusion masks, protection zone, multi-view reconstruction, human-robot cooperation 2.
Author manuscript, published in "IEEE Computer Vision and Pattern Recognition (2010)" Probabilistic 3D Occupancy Flow with Latent Silhouette Cues
"... ..."
(Show Context)
3D Tracking of Mouse Locomotion Using Shape-From-Silhouette Techniques
"... Abstract — Locomotion is commonly used as a method for evaluating the effectiveness of interventions and treatments for recovery of function after spinal cord injury in rodent models. However, most conventional approaches to assess recovery rely on a series of semi-quantitative visual inspections. I ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract — Locomotion is commonly used as a method for evaluating the effectiveness of interventions and treatments for recovery of function after spinal cord injury in rodent models. However, most conventional approaches to assess recovery rely on a series of semi-quantitative visual inspections. In the present study, we propose a volume intersection approach to obtain 3D information about the position of the center of volume and locomotion speed from multiview video cameras. The addition of quantitative measures can be used to improve precision and repeatability within and across testing sites, and further assist researchers in behavioral evaluations of locomotion.
