Proceedings of the 27th annual conference on Computer graphics and interactive techniques
A Theory of Shape by Space Carving
International Journal of Computer Vision - Special issue on Genomic Signal Processing
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene
International Journal of Computer Vision
The Visual Hull Concept for Silhouette-Based Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning to Locate an Object in 3D Space from a Sequence of Camera Images
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Polyhedral Visual Hulls for Real-Time Rendering
Proceedings of the 12th Eurographics Workshop on Rendering Techniques
3D reconstruction using labeled image regions
Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing
Geometric modeling for computer vision.
Geometric modeling for computer vision.
On Exploiting Occlusions in Multiple-view Geometry
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Counting People in Crowds with a Real-Time Network of Simple Image Sensors
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Methods for Volumetric Reconstruction of Visual Scenes
International Journal of Computer Vision
Learning Spatiotemporal T-Junctions for Occlusion Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Learning Spatiotemporal T-Junctions for Occlusion Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Ensuring Color Consistency across Multiple Cameras
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Fusion of Multi-View Silhouette Cues Using a Space Occupancy Grid
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Visual Hull Construction in the Presence of Partial Occlusion
3DPVT '06 Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)
Multicamera People Tracking with a Probabilistic Occupancy Map
IEEE Transactions on Pattern Analysis and Machine Intelligence
A bayesian approach to image-based visual hull reconstruction
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Carved visual hulls for image-based modeling
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Background updating for visual surveillance
ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Special Issue on Probabilistic Models for Image Understanding, Part II
International Journal of Computer Vision
A comparative study on multi-person tracking using overlapping cameras
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
| Hi-index | 0.00 |
In this paper, we present an algorithm to probabilistically estimate object shapes in a 3D dynamic scene using their silhouette information derived from multiple geometrically calibrated video camcorders. The scene is represented by a 3D volume. Every object in the scene is associated with a distinctive label to represent its existence at every voxel location. The label links together automatically-learned view-specific appearance models of the respective object, so as to avoid the photometric calibration of the cameras. Generative probabilistic sensor models can be derived by analyzing the dependencies between the sensor observations and object labels. Bayesian reasoning is then applied to achieve robust reconstruction against real-world environment challenges, such as lighting variations, changing background etc. Our main contribution is to explicitly model the visual occlusion process and show: (1) static objects (such as trees or lamp posts), as parts of the pre-learned background model, can be automatically recovered as a byproduct of the inference; (2) ambiguities due to inter-occlusion between multiple dynamic objects can be alleviated, and the final reconstruction quality is drastically improved. Several indoor and outdoor real-world datasets are evaluated to verify our framework.