IEEE Transactions on Pattern Analysis and Machine Intelligence
Determining motion from 3D line segment matches: a comparative study
Image and Vision Computing
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
Efficient algorithms for line and curve segment intersection using restricted predicates
SCG '99 Proceedings of the fifteenth annual symposium on Computational geometry
Automatic Extraction of Generic House Roofs from High Resolution Aerial Imagery
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Automatic Modeling and 3D Reconstruction of Urban House Roofs from High Resolution Aerial Imagery
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Automatic line matching across views
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Automatic Pose Estimation of Complex 3D Building Models
WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
Interactive 3D Building Modeling Using a Hierarchical Representation
HLK '03 Proceedings of the First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis
Algorithms for Matching 3D Line Sets
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image and Vision Computing
A survey of visibility for walkthrough applications
IEEE Transactions on Visualization and Computer Graphics
Hi-index | 0.00 |
We present an algorithm to modelling the test scene for intelligent robot. In intelligent robotics, to develop compact and reliable vision system components for navigation or human computer interaction is essential. As our approach, we develop the line-based modelling and recognition algorithm based on 3D features from stereo camera images. The basic concept is build real plane features from 3D stereo images from mobile robot to navigate or for human computer interaction in the living room environment. The procedure is, first, given 3D line segments, we set up reference plane using principle component analysis (PCA) for each line pair. Then, we measure the normal distance and line orientation for the remains of 3D segments to the reference plane and define coplanarity. And we initiate visibility test to prune out ambiguous planes from reference planes. After we finish visibility test, we patching these reference planes and define them as real plane candidates using plane sweep algorithm. And finally, try to find model objects from the test scene using iterative closest point (ICP). During the implementation, we also use 3D map information for exact localization. We apply this algorithm to the real images and the result found useful to identify door at the wall.