A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Camera Calibration with Distortion Models and Accuracy Evaluation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Reconstructing Polyhedral Models of Architectural Scenes from Photographs
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
3D Model Acquisition from Extended Image Sequences
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
3-D Scene Data Recovery using Omnidirectional Multibaseline Stereo
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
A scene analysis system for the generation of 3-D models
NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
Registration and integration of textured 3-D data
NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
Interactive person path analysis in reconstructed public buildings
Proceedings of the 25th Spring Conference on Computer Graphics
| Hi-index | 0.00 |
This paper describes a system which integrates laser range data and video data to construct textured 3D models of building interiors. The system has been implemented in a prototype known as the AEST (Autonomous Environmental Sensor for Telepresence) - an autonomous mobile platform carrying a scanning laser range finder and video camera. The AEST is intended to fully automate the creation of models from building interiors by navigating automatically between positions at which range data and video images are captured. Embedded software performs several functions, including triangulation of the range data and registration of video texture, registration and integration of data acquired from different capture points, and optimal selection of these capture points. This paper concentrates on the triangulation algorithm of the system, which is a hybrid approach combining geometric surface extraction and a robust triangulation. It produces accurate geometric information and at the same time, a photo-realistic triangular mesh. This is important for graphical and visualisation applications such as virtual studios, virtualised reality for content-related applications (e.g., CD-ROMs), social tele-presence, architecture and others.