SUSAN—A New Approach to Low Level Image Processing
International Journal of Computer Vision
Determining 3D Structure and Motion of Man-made Objects from Image Corners
SSIAI '02 Proceedings of the Fifth IEEE Southwest Symposium on Image Analysis and Interpretation
Aerial tracking of elongated objects in rural environments
Machine Vision and Applications
| Hi-index | 0.00 |
This paper presents a perceptual organization basedmethod for the representation and extraction of junctionstructures of edge segments from digital images. PerceptualJunctions (PJs) are higher-level view invariant feature entities,which are made up by intersected generic edge tokensincluding both linear and non-linear segments. The class oflow-order PJs (LPJs) is the junctions defined by two connectedsegments, and detected directly by an edge trackingand partitioning algorithm. The class of high-order PJs(HPJs) is the junctions made up by more than two segmentswhich are extended from LPJs by grouping additional segmentsfrom different edge traces. The method is robust sinceit mainly uses qualitative perceptual features. The computationis efficient because it is mainly involved in symbolicreasoning. The experimental results are provided.