Recognizing corners by fitting parametric models
International Journal of Computer Vision
Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
Junctions: Detection, Classification, and Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Uncertainty Propagation and the Matching of Junctions as Feature Groupings
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing: Concepts, Algorithms, and Scientific Applications
Digital Image Processing: Concepts, Algorithms, and Scientific Applications
Neural mechanisms for the robust representation of junctions
Neural Computation
Statistical Analysis of Local 3D Structure in 2D Images
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Continuous dimensionality characterization of image structures
Image and Vision Computing
Bayesian Classification of Image Structures
SCIA '09 Proceedings of the 16th Scandinavian Conference on Image Analysis
A Probabilistic Framework for 3D Visual Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Comparison of Point and Line Features and Their Combination for Rigid Body Motion Estimation
Statistical and Geometrical Approaches to Visual Motion Analysis
Hi-index | 0.00 |
This article describes a novel junction descriptor that encodes junctions' semantic information in terms incoming lines' orientations, both in 2D and 3D. A Kalman filter process is used to reduce the effect of local noise on the descriptor's error and to track the features. The improvement gained by our algorithm is demonstrated quantitatively on synthetic scenes and qualitatively on real scenes.