A Crossing Detector Based on the Structure Tensor

Abstract. A new crossing detector is presented which also permits orientation estimation of the underlying structures. The method relies on well established tools such as the structure tensor, the double angle mapping and descriptors for second order variations. The performance of our joint crossing detector and multi-orientation estimator is relatively independent of the angular separation of the underlying unimodal structures.

• Type: Conference
• Year: 2007
• Where: ACIVS
• Authors: Frank G. A. Faas, Lucas J. van Vliet
• Keywords: ACIVS 2007, Computer Vision, Crossing Detector, Double Angle Mapping, Joint Crossing Detector